{ "cells": [ { "attachments": {}, "cell_type": "markdown", "id": "81e0620e", "metadata": {}, "source": [ "Last updated: 15 Feb 2023\n", "\n", "# 👋 PyCaret Regression Tutorial\n", "\n", "PyCaret is an open-source, low-code machine learning library in Python that automates machine learning workflows. It is an end-to-end machine learning and model management tool that exponentially speeds up the experiment cycle and makes you more productive.\n", "\n", "Compared with the other open-source machine learning libraries, PyCaret is an alternate low-code library that can be used to replace hundreds of lines of code with a few lines only. This makes experiments exponentially fast and efficient. PyCaret is essentially a Python wrapper around several machine learning libraries and frameworks, such as scikit-learn, XGBoost, LightGBM, CatBoost, spaCy, Optuna, Hyperopt, Ray, and a few more.\n", "\n", "The design and simplicity of PyCaret are inspired by the emerging role of citizen data scientists, a term first used by Gartner. Citizen Data Scientists are power users who can perform both simple and moderately sophisticated analytical tasks that would previously have required more technical expertise.\n" ] }, { "attachments": {}, "cell_type": "markdown", "id": "8116e19d", "metadata": {}, "source": [ "# 💻 Installation\n", "\n", "PyCaret is tested and supported on the following 64-bit systems:\n", "- Python 3.7 – 3.10\n", "- Python 3.9 for Ubuntu only\n", "- Ubuntu 16.04 or later\n", "- Windows 7 or later\n", "\n", "You can install PyCaret with Python's pip package manager:\n", "\n", "`pip install pycaret`\n", "\n", "PyCaret's default installation will not install all the extra dependencies automatically. For that you will have to install the full version:\n", "\n", "`pip install pycaret[full]`\n", "\n", "or depending on your use-case you may install one of the following variant:\n", "\n", "- `pip install pycaret[analysis]`\n", "- `pip install pycaret[models]`\n", "- `pip install pycaret[tuner]`\n", "- `pip install pycaret[mlops]`\n", "- `pip install pycaret[parallel]`\n", "- `pip install pycaret[test]`" ] }, { "cell_type": "code", "execution_count": 1, "id": "d7142a33", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "'3.4.0'" ] }, "execution_count": 1, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# check installed version (must be >3.0)\n", "import pycaret\n", "pycaret.__version__" ] }, { "attachments": {}, "cell_type": "markdown", "id": "fb66e98d", "metadata": {}, "source": [ "# 🚀 Quick start" ] }, { "attachments": {}, "cell_type": "markdown", "id": "00347d44", "metadata": {}, "source": [ "PyCaret's Regression Module is a supervised machine learning module that is used for estimating the relationships between a dependent variable (often called the outcome variable, or target) and one or more independent variables (often called features, predictors, or covariates). \n", "\n", "The objective of regression is to predict continuous values such as predicting sales amount, predicting quantity, predicting temperature, etc. Regression module provides several pre-processing features to preprocess the data for modeling through the setup function. \n", "\n", "PyCaret's regression module has many preprocessing capabilities and it coems with over 25 ready-to-use algorithms and several plots to analyze the performance of trained models. \n", "\n", "A typical workflow in PyCaret Regression module consist of the following 5 steps in this order:\n", "\n", "### **Setup** ➡️ **Compare Models** ➡️ **Analyze Model** ➡️ **Prediction** ➡️ **Save Model** \n", "
" ] }, { "cell_type": "code", "execution_count": 2, "id": "1b09f8df", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
agesexbmichildrensmokerregioncharges
019female27.9000yessouthwest16884.92400
118male33.7701nosoutheast1725.55230
228male33.0003nosoutheast4449.46200
333male22.7050nonorthwest21984.47061
432male28.8800nonorthwest3866.85520
\n", "
" ], "text/plain": [ " age sex bmi children smoker region charges\n", "0 19 female 27.900 0 yes southwest 16884.92400\n", "1 18 male 33.770 1 no southeast 1725.55230\n", "2 28 male 33.000 3 no southeast 4449.46200\n", "3 33 male 22.705 0 no northwest 21984.47061\n", "4 32 male 28.880 0 no northwest 3866.85520" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "### load sample dataset from pycaret dataset module\n", "from pycaret.datasets import get_data\n", "data = get_data('insurance')" ] }, { "attachments": {}, "cell_type": "markdown", "id": "c00f6a4a", "metadata": {}, "source": [ "## Setup\n", "The `setup` function initializes the training environment and creates the transformation pipeline. Setup function must be called before executing any other function in PyCaret. It only has two required parameters i.e. `data` and `target`. All the other parameters are optional." ] }, { "cell_type": "code", "execution_count": 3, "id": "97f2c6c6", "metadata": {}, "outputs": [ { "data": { "text/html": [ "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
 DescriptionValue
0Session id123
1Targetcharges
2Target typeRegression
3Original data shape(1338, 7)
4Transformed data shape(1338, 10)
5Transformed train set shape(936, 10)
6Transformed test set shape(402, 10)
7Numeric features3
8Categorical features3
9PreprocessTrue
10Imputation typesimple
11Numeric imputationmean
12Categorical imputationmode
13Maximum one-hot encoding25
14Encoding methodNone
15Fold GeneratorKFold
16Fold Number10
17CPU Jobs-1
18Use GPUFalse
19Log ExperimentFalse
20Experiment Namereg-default-name
21USIae31
\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "# import pycaret regression and init setup\n", "from pycaret.regression import *\n", "s = setup(data, target = 'charges', session_id = 123)" ] }, { "attachments": {}, "cell_type": "markdown", "id": "3c583864", "metadata": {}, "source": [ "Once the setup has been successfully executed it shows the information grid containing experiment level information. \n", "\n", "- **Session id:** A pseudo-random number distributed as a seed in all functions for later reproducibility. If no `session_id` is passed, a random number is automatically generated that is distributed to all functions.
\n", "
\n", "- **Target type:** Binary, Multiclass, or Regression. The Target type is automatically detected.
\n", "
\n", "- **Original data shape:** Shape of the original data prior to any transformations.
\n", "
\n", "- **Transformed train set shape :** Shape of transformed train set
\n", "
\n", "- **Transformed test set shape :** Shape of transformed test set
\n", "
\n", "- **Numeric features :** The number of features considered as numerical.
\n", "
\n", "- **Categorical features :** The number of features considered as categorical.
" ] }, { "attachments": {}, "cell_type": "markdown", "id": "ada19398", "metadata": {}, "source": [ "PyCaret has two set of API's that you can work with. (1) Functional (as seen above) and (2) Object Oriented API.\n", "\n", "With Object Oriented API instead of executing functions directly you will import a class and execute methods of class." ] }, { "cell_type": "code", "execution_count": 4, "id": "32ee91c9", "metadata": {}, "outputs": [], "source": [ "# import RegressionExperiment and init the class\n", "from pycaret.regression import RegressionExperiment\n", "exp = RegressionExperiment()" ] }, { "cell_type": "code", "execution_count": 5, "id": "3ead9fb5", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "pycaret.regression.oop.RegressionExperiment" ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# check the type of exp\n", "type(exp)" ] }, { "cell_type": "code", "execution_count": 6, "id": "f05b8590", "metadata": {}, "outputs": [ { "data": { "text/html": [ "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
 DescriptionValue
0Session id123
1Targetcharges
2Target typeRegression
3Original data shape(1338, 7)
4Transformed data shape(1338, 10)
5Transformed train set shape(936, 10)
6Transformed test set shape(402, 10)
7Numeric features3
8Categorical features3
9PreprocessTrue
10Imputation typesimple
11Numeric imputationmean
12Categorical imputationmode
13Maximum one-hot encoding25
14Encoding methodNone
15Fold GeneratorKFold
16Fold Number10
17CPU Jobs-1
18Use GPUFalse
19Log ExperimentFalse
20Experiment Namereg-default-name
21USIbd35
\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/plain": [ "" ] }, "execution_count": 6, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# init setup on exp\n", "exp.setup(data, target = 'charges', session_id = 123)" ] }, { "attachments": {}, "cell_type": "markdown", "id": "77213120", "metadata": {}, "source": [ "You can use any of the two method i.e. Functional or OOP and even switch back and forth between two set of API's. The choice of method will not impact the results and has been tested for consistency.\n", "___" ] }, { "attachments": {}, "cell_type": "markdown", "id": "f98dd435", "metadata": {}, "source": [ "## Compare Models\n", "\n", "The `compare_models` function trains and evaluates the performance of all the estimators available in the model library using cross-validation. The output of this function is a scoring grid with average cross-validated scores. Metrics evaluated during CV can be accessed using the `get_metrics` function. Custom metrics can be added or removed using `add_metric` and `remove_metric` function." ] }, { "cell_type": "code", "execution_count": 7, "id": "65a19df4", "metadata": {}, "outputs": [ { "data": { "text/html": [], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
 ModelMAEMSERMSER2RMSLEMAPETT (Sec)
dummyDummy Regressor9192.5418148516792.800012132.4733-0.01751.01541.56370.0180
ompOrthogonal Matching Pursuit9191.5663148619037.969812135.9667-0.01801.01611.56660.0180
brBayesian Ridge9195.0295148681348.631612138.8558-0.01861.01601.56580.0180
enElastic Net9196.7784148894953.535612147.0012-0.01991.01681.56810.0200
ridgeRidge Regression9235.6876149670276.944112178.3613-0.02531.01901.57390.0190
lrLinear Regression9236.1261149679639.233212178.7361-0.02541.01911.57390.6940
lassoLasso Regression9235.7161149673862.089112178.5032-0.02541.01901.57390.5100
llarLasso Least Angle Regression9235.7159149673869.001912178.5035-0.02541.01901.57390.0210
larLeast Angle Regression9238.2397149729647.308412180.8215-0.02581.01921.57420.0190
huberHuber Regressor8474.0147160777637.902112587.5340-0.08820.94231.11470.0230
gbrGradient Boosting Regressor9556.0643160386898.551512611.0717-0.10251.02941.57160.0310
rfRandom Forest Regressor9802.7309165922683.328112842.1702-0.14851.05601.67320.0640
catboostCatBoost Regressor9717.0421170370219.025013007.0063-0.17711.07271.57280.3980
parPassive Aggressive Regressor9094.4214174284567.936813124.4802-0.19271.00671.14930.0180
knnK Neighbors Regressor9864.8764176171865.600013242.3901-0.22641.05241.57930.0230
lightgbmLight Gradient Boosting Machine10221.1599183056885.451313480.6561-0.26181.11381.64500.0680
adaAdaBoost Regressor11574.3105178727210.497113354.9808-0.26441.17902.33150.0230
etExtra Trees Regressor10097.1329188470162.602713672.0375-0.30131.07671.64540.0520
dtDecision Tree Regressor12288.8204294260077.154817077.4897-1.03161.31281.90080.0210
\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "# compare baseline models\n", "best = compare_models()" ] }, { "cell_type": "code", "execution_count": 8, "id": "87477aa4", "metadata": {}, "outputs": [], "source": [ "# compare models using OOP\n", "# exp.compare_models()" ] }, { "cell_type": "code", "execution_count": 9, "id": "ab899495", "metadata": {}, "outputs": [ { "data": { "text/html": [], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
 MAEMSERMSER2RMSLEMAPE
Fold      
010580.4866200400795.357114156.2988-0.19701.07711.6220
19597.2934166289041.663412895.31080.03310.96381.2589
28359.1849108388921.876110411.0000-0.37231.07611.7702
39185.3919145699845.286112070.6191-0.21661.10581.8201
48885.4717159037060.018712610.9897-0.18280.97901.1912
59026.4221172610960.027313138.1490-0.11040.96551.1727
610506.8232194762125.964313955.7202-0.32521.26711.7585
711022.5806199678725.102414130.7723-0.09801.07961.6111
810570.1831189707801.827013773.4455-0.22531.13181.7836
99436.5835167126913.127412927.7575-0.07651.08081.7395
Mean9717.0421170370219.025013007.0063-0.17711.07271.5728
Std847.906927093682.41471089.95700.11380.08640.2480
\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "best = create_model('catboost') #choose catboost to avoid plot errors with some models" ] }, { "attachments": {}, "cell_type": "markdown", "id": "340de1e2", "metadata": {}, "source": [ "Notice that the output between functional and OOP API is consistent. Rest of the functions in this notebook will only be shown using functional API only. \n", "\n", "___" ] }, { "attachments": {}, "cell_type": "markdown", "id": "6a77ec0c", "metadata": {}, "source": [ "## Analyze Model" ] }, { "attachments": {}, "cell_type": "markdown", "id": "595ea108", "metadata": {}, "source": [ "The `plot_model` function is used to analyze the performance of a trained model on the test set. It may require re-training the model in certain cases." ] }, { "cell_type": "code", "execution_count": 10, "id": "0ec7fad6", "metadata": {}, "outputs": [ { "data": { "text/html": [], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "# plot residuals\n", "plot_model(best, plot = 'residuals')" ] }, { "cell_type": "code", "execution_count": 11, "id": "9fc4b9b1", "metadata": {}, "outputs": [ { "data": { "text/html": [], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "# plot error\n", "plot_model(best, plot = 'error')" ] }, { "cell_type": "code", "execution_count": 12, "id": "bbc790e4", "metadata": {}, "outputs": [ { "data": { "text/html": [], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "# plot feature importance\n", "plot_model(best, plot = 'feature')" ] }, { "cell_type": "code", "execution_count": 13, "id": "da718984", "metadata": {}, "outputs": [], "source": [ "# check docstring to see available plots \n", "# help(plot_model)" ] }, { "attachments": {}, "cell_type": "markdown", "id": "6bd66179", "metadata": {}, "source": [ "An alternate to `plot_model` function is `evaluate_model`. It can only be used in Notebook since it uses `ipywidget`." ] }, { "cell_type": "code", "execution_count": 14, "id": "c75f07a8", "metadata": {}, "outputs": [ { "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "b8a62b655b6346dabb18b9c8b5db3e4a", "version_major": 2, "version_minor": 0 }, "text/plain": [ "interactive(children=(ToggleButtons(description='Plot Type:', icons=('',), options=(('Pipeline Plot', 'pipelin…" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "evaluate_model(best)" ] }, { "attachments": {}, "cell_type": "markdown", "id": "ab3d2f1e", "metadata": {}, "source": [ "___" ] }, { "attachments": {}, "cell_type": "markdown", "id": "954cbeff", "metadata": {}, "source": [ "## Prediction\n", "The `predict_model` function returns `prediction_label` as new column to the input dataframe. When data is `None` (default), it uses the test set (created during the setup function) for scoring." ] }, { "cell_type": "code", "execution_count": 15, "id": "87c1a007", "metadata": {}, "outputs": [ { "data": { "text/html": [ "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
 ModelMAEMSERMSER2RMSLEMAPE
0CatBoost Regressor9955.3140169148685.396513005.7174-0.18401.04401.5586
\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "# predict on test set\n", "holdout_pred = predict_model(best)" ] }, { "cell_type": "code", "execution_count": 16, "id": "5c01ac77", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
agesexbmichildrensmokerregionchargesprediction_label
65049female42.6800002nosoutheast9800.88867213504.425282
31932male37.3349991nonortheast4667.60742216114.309577
31427female31.4000000yessouthwest34838.87109413424.087493
15035male24.1299991nonorthwest5125.21582022955.805214
33660male25.7400000nosoutheast12142.5781256919.557906
\n", "
" ], "text/plain": [ " age sex bmi children smoker region charges \\\n", "650 49 female 42.680000 2 no southeast 9800.888672 \n", "319 32 male 37.334999 1 no northeast 4667.607422 \n", "314 27 female 31.400000 0 yes southwest 34838.871094 \n", "150 35 male 24.129999 1 no northwest 5125.215820 \n", "336 60 male 25.740000 0 no southeast 12142.578125 \n", "\n", " prediction_label \n", "650 13504.425282 \n", "319 16114.309577 \n", "314 13424.087493 \n", "150 22955.805214 \n", "336 6919.557906 " ] }, "execution_count": 16, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# show predictions df\n", "holdout_pred.head()" ] }, { "attachments": {}, "cell_type": "markdown", "id": "d4baf825", "metadata": {}, "source": [ "The same function works for predicting the labels on unseen dataset. Let's create a copy of original data and drop the `charges`. We can then use the new data frame without labels for scoring." ] }, { "cell_type": "code", "execution_count": 17, "id": "fb1cb86d", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
agesexbmichildrensmokerregion
019female27.9000yessouthwest
118male33.7701nosoutheast
228male33.0003nosoutheast
333male22.7050nonorthwest
432male28.8800nonorthwest
\n", "
" ], "text/plain": [ " age sex bmi children smoker region\n", "0 19 female 27.900 0 yes southwest\n", "1 18 male 33.770 1 no southeast\n", "2 28 male 33.000 3 no southeast\n", "3 33 male 22.705 0 no northwest\n", "4 32 male 28.880 0 no northwest" ] }, "execution_count": 17, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# copy data and drop charges\n", "\n", "new_data = data.copy()\n", "new_data.drop('charges', axis=1, inplace=True)\n", "new_data.head()" ] }, { "cell_type": "code", "execution_count": 18, "id": "c5803df9", "metadata": {}, "outputs": [ { "data": { "text/html": [], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
agesexbmichildrensmokerregionprediction_label
019female27.9000000yessouthwest5499.082074
118male33.7700001nosoutheast20929.778672
228male33.0000003nosoutheast10090.377502
333male22.7050000nonorthwest19514.314701
432male28.8799990nonorthwest22811.056640
\n", "
" ], "text/plain": [ " age sex bmi children smoker region prediction_label\n", "0 19 female 27.900000 0 yes southwest 5499.082074\n", "1 18 male 33.770000 1 no southeast 20929.778672\n", "2 28 male 33.000000 3 no southeast 10090.377502\n", "3 33 male 22.705000 0 no northwest 19514.314701\n", "4 32 male 28.879999 0 no northwest 22811.056640" ] }, "execution_count": 18, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# predict model on new_data\n", "predictions = predict_model(best, data = new_data)\n", "predictions.head()" ] }, { "attachments": {}, "cell_type": "markdown", "id": "3950252d", "metadata": {}, "source": [ "___" ] }, { "attachments": {}, "cell_type": "markdown", "id": "e4384735", "metadata": {}, "source": [ "## Save Model" ] }, { "attachments": {}, "cell_type": "markdown", "id": "cd63f053", "metadata": {}, "source": [ "Finally, you can save the entire pipeline on disk for later use, using pycaret's `save_model` function." ] }, { "cell_type": "code", "execution_count": 19, "id": "4181de41", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Transformation Pipeline and Model Successfully Saved\n" ] }, { "data": { "text/plain": [ "(Pipeline(memory=Memory(location=None),\n", " steps=[('numerical_imputer',\n", " TransformerWrapper(include=['age', 'bmi', 'children'],\n", " transformer=SimpleImputer())),\n", " ('categorical_imputer',\n", " TransformerWrapper(include=['sex', 'smoker', 'region'],\n", " transformer=SimpleImputer(strategy='most_frequent'))),\n", " ('ordinal_encoding',\n", " TransformerWrapper(include=['sex', 'smoker'],\n", " transfor...\n", " 'data_type': dtype('O'),\n", " 'mapping': female 0\n", " male 1\n", " NaN -1\n", " dtype: int64},\n", " {'col': 'smoker',\n", " 'data_type': dtype('O'),\n", " 'mapping': no 0\n", " yes 1\n", " NaN -1\n", " dtype: int64}]))),\n", " ('onehot_encoding',\n", " TransformerWrapper(include=['region'],\n", " transformer=OneHotEncoder(cols=['region'],\n", " handle_missing='return_nan',\n", " use_cat_names=True))),\n", " ('trained_model',\n", " )]),\n", " 'my_first_pipeline.pkl')" ] }, "execution_count": 19, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# save pipeline\n", "save_model(best, 'my_first_pipeline')" ] }, { "cell_type": "code", "execution_count": 20, "id": "40ed5152", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Transformation Pipeline and Model Successfully Loaded\n" ] }, { "data": { "text/html": [ "
Pipeline(memory=FastMemory(location=C:\\Users\\celes\\AppData\\Local\\Temp\\joblib),\n",
       "         steps=[('numerical_imputer',\n",
       "                 TransformerWrapper(include=['age', 'bmi', 'children'],\n",
       "                                    transformer=SimpleImputer())),\n",
       "                ('categorical_imputer',\n",
       "                 TransformerWrapper(include=['sex', 'smoker', 'region'],\n",
       "                                    transformer=SimpleImputer(strategy='most_frequent'))),\n",
       "                ('ordinal_encoding',\n",
       "                 TransformerW...\n",
       "                                                                         'data_type': dtype('O'),\n",
       "                                                                         'mapping': female    0\n",
       "male      1\n",
       "NaN      -1\n",
       "dtype: int64},\n",
       "                                                                        {'col': 'smoker',\n",
       "                                                                         'data_type': dtype('O'),\n",
       "                                                                         'mapping': no     0\n",
       "yes    1\n",
       "NaN   -1\n",
       "dtype: int64}]))),\n",
       "                ('onehot_encoding',\n",
       "                 TransformerWrapper(include=['region'],\n",
       "                                    transformer=OneHotEncoder(cols=['region'],\n",
       "                                                              handle_missing='return_nan',\n",
       "                                                              use_cat_names=True))),\n",
       "                ('trained_model',\n",
       "                 <catboost.core.CatBoostRegressor object at 0x000001939B57CF90>)])
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
" ], "text/plain": [ "Pipeline(memory=FastMemory(location=C:\\Users\\celes\\AppData\\Local\\Temp\\joblib),\n", " steps=[('numerical_imputer',\n", " TransformerWrapper(include=['age', 'bmi', 'children'],\n", " transformer=SimpleImputer())),\n", " ('categorical_imputer',\n", " TransformerWrapper(include=['sex', 'smoker', 'region'],\n", " transformer=SimpleImputer(strategy='most_frequent'))),\n", " ('ordinal_encoding',\n", " TransformerW...\n", " 'data_type': dtype('O'),\n", " 'mapping': female 0\n", "male 1\n", "NaN -1\n", "dtype: int64},\n", " {'col': 'smoker',\n", " 'data_type': dtype('O'),\n", " 'mapping': no 0\n", "yes 1\n", "NaN -1\n", "dtype: int64}]))),\n", " ('onehot_encoding',\n", " TransformerWrapper(include=['region'],\n", " transformer=OneHotEncoder(cols=['region'],\n", " handle_missing='return_nan',\n", " use_cat_names=True))),\n", " ('trained_model',\n", " )])" ] }, "execution_count": 20, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# load pipeline\n", "loaded_best_pipeline = load_model('my_first_pipeline')\n", "loaded_best_pipeline" ] }, { "attachments": {}, "cell_type": "markdown", "id": "b2c7d62e", "metadata": {}, "source": [ "# 👇 Detailed function-by-function overview" ] }, { "attachments": {}, "cell_type": "markdown", "id": "e05937f5", "metadata": {}, "source": [ "## ✅ Setup\n", "The `setup` function initializes the experiment in PyCaret and creates the transformation pipeline based on all the parameters passed in the function. Setup function must be called before executing any other function. It takes two required parameters: `data` and `target`. All the other parameters are optional and are used for configuring data preprocessing pipeline." ] }, { "cell_type": "code", "execution_count": 21, "id": "24e503be", "metadata": {}, "outputs": [ { "data": { "text/html": [ "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
 DescriptionValue
0Session id123
1Targetcharges
2Target typeRegression
3Original data shape(1338, 7)
4Transformed data shape(1338, 10)
5Transformed train set shape(936, 10)
6Transformed test set shape(402, 10)
7Numeric features3
8Categorical features3
9PreprocessTrue
10Imputation typesimple
11Numeric imputationmean
12Categorical imputationmode
13Maximum one-hot encoding25
14Encoding methodNone
15Fold GeneratorKFold
16Fold Number10
17CPU Jobs-1
18Use GPUFalse
19Log ExperimentFalse
20Experiment Namereg-default-name
21USIde1c
\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "s = setup(data, target = 'charges', session_id = 123)" ] }, { "attachments": {}, "cell_type": "markdown", "id": "924d198b", "metadata": {}, "source": [ "To access all the variables created by the setup function such as transformed dataset, random_state, etc. you can use `get_config` method." ] }, { "cell_type": "code", "execution_count": 22, "id": "76128b08", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "{'USI',\n", " 'X',\n", " 'X_test',\n", " 'X_test_transformed',\n", " 'X_train',\n", " 'X_train_transformed',\n", " 'X_transformed',\n", " '_available_plots',\n", " '_ml_usecase',\n", " 'data',\n", " 'dataset',\n", " 'dataset_transformed',\n", " 'exp_id',\n", " 'exp_name_log',\n", " 'fold_generator',\n", " 'fold_groups_param',\n", " 'fold_shuffle_param',\n", " 'gpu_n_jobs_param',\n", " 'gpu_param',\n", " 'html_param',\n", " 'idx',\n", " 'is_multiclass',\n", " 'log_plots_param',\n", " 'logging_param',\n", " 'memory',\n", " 'n_jobs_param',\n", " 'pipeline',\n", " 'seed',\n", " 'target_param',\n", " 'test',\n", " 'test_transformed',\n", " 'train',\n", " 'train_transformed',\n", " 'transform_target_param',\n", " 'variable_and_property_keys',\n", " 'variables',\n", " 'y',\n", " 'y_test',\n", " 'y_test_transformed',\n", " 'y_train',\n", " 'y_train_transformed',\n", " 'y_transformed'}" ] }, "execution_count": 22, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# check all available config\n", "get_config()" ] }, { "cell_type": "code", "execution_count": 23, "id": "dbc43292", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
agesexbmichildrensmokerregion_southwestregion_southeastregion_northwestregion_northeast
019.00.027.9000000.01.01.00.00.00.0
118.01.033.7700001.00.00.01.00.00.0
228.01.033.0000003.00.00.01.00.00.0
333.01.022.7050000.00.00.00.01.00.0
432.01.028.8799990.00.00.00.01.00.0
..............................
132952.01.038.5999982.00.01.00.00.00.0
133057.00.025.7400002.00.00.01.00.00.0
133123.00.033.4000020.00.01.00.00.00.0
133418.00.031.9200000.00.00.00.00.01.0
133518.00.036.8499980.00.00.01.00.00.0
\n", "

936 rows × 9 columns

\n", "
" ], "text/plain": [ " age sex bmi children smoker region_southwest \\\n", "0 19.0 0.0 27.900000 0.0 1.0 1.0 \n", "1 18.0 1.0 33.770000 1.0 0.0 0.0 \n", "2 28.0 1.0 33.000000 3.0 0.0 0.0 \n", "3 33.0 1.0 22.705000 0.0 0.0 0.0 \n", "4 32.0 1.0 28.879999 0.0 0.0 0.0 \n", "... ... ... ... ... ... ... \n", "1329 52.0 1.0 38.599998 2.0 0.0 1.0 \n", "1330 57.0 0.0 25.740000 2.0 0.0 0.0 \n", "1331 23.0 0.0 33.400002 0.0 0.0 1.0 \n", "1334 18.0 0.0 31.920000 0.0 0.0 0.0 \n", "1335 18.0 0.0 36.849998 0.0 0.0 0.0 \n", "\n", " region_southeast region_northwest region_northeast \n", "0 0.0 0.0 0.0 \n", "1 1.0 0.0 0.0 \n", "2 1.0 0.0 0.0 \n", "3 0.0 1.0 0.0 \n", "4 0.0 1.0 0.0 \n", "... ... ... ... \n", "1329 0.0 0.0 0.0 \n", "1330 1.0 0.0 0.0 \n", "1331 0.0 0.0 0.0 \n", "1334 0.0 0.0 1.0 \n", "1335 1.0 0.0 0.0 \n", "\n", "[936 rows x 9 columns]" ] }, "execution_count": 23, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# lets access X_train_transformed\n", "get_config('X_train_transformed')" ] }, { "cell_type": "code", "execution_count": 24, "id": "ef9cd061", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "The current seed is: 123\n", "The new seed is: 786\n" ] } ], "source": [ "# another example: let's access seed\n", "print(\"The current seed is: {}\".format(get_config('seed')))\n", "\n", "# now lets change it using set_config\n", "set_config('seed', 786)\n", "print(\"The new seed is: {}\".format(get_config('seed')))" ] }, { "attachments": {}, "cell_type": "markdown", "id": "7afbe41d", "metadata": {}, "source": [ "All the preprocessing configurations and experiment settings/parameters are passed into the `setup` function. To see all available parameters, check the docstring:" ] }, { "cell_type": "code", "execution_count": 25, "id": "2885a14f", "metadata": {}, "outputs": [], "source": [ "# help(setup)" ] }, { "cell_type": "code", "execution_count": 26, "id": "34ae0fce", "metadata": {}, "outputs": [ { "data": { "text/html": [ "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
 DescriptionValue
0Session id123
1Targetcharges
2Target typeRegression
3Original data shape(1338, 7)
4Transformed data shape(1338, 10)
5Transformed train set shape(936, 10)
6Transformed test set shape(402, 10)
7Numeric features3
8Categorical features3
9PreprocessTrue
10Imputation typesimple
11Numeric imputationmean
12Categorical imputationmode
13Maximum one-hot encoding25
14Encoding methodNone
15NormalizeTrue
16Normalize methodminmax
17Fold GeneratorKFold
18Fold Number10
19CPU Jobs-1
20Use GPUFalse
21Log ExperimentFalse
22Experiment Namereg-default-name
23USIbf84
\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "# init setup with normalize = True\n", "s = setup(data, target = 'charges', session_id = 123,\n", " normalize = True, normalize_method = 'minmax')" ] }, { "cell_type": "code", "execution_count": 27, "id": "04204ae7", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 27, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "# lets check the X_train_transformed to see effect of params passed\n", "get_config('X_train_transformed')['age'].hist()" ] }, { "attachments": {}, "cell_type": "markdown", "id": "d28a3e4e", "metadata": {}, "source": [ "Notice that all the values are between 0 and 1 - that is because we passed `normalize=True` in the `setup` function. If you don't remember how it compares to actual data, no problem - we can also access non-transformed values using `get_config` and then compare. See below and notice the range of values on x-axis and compare it with histogram above." ] }, { "cell_type": "code", "execution_count": 28, "id": "68cc1c63", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 28, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "get_config('X_train')['age'].hist()" ] }, { "attachments": {}, "cell_type": "markdown", "id": "b3776fbf", "metadata": {}, "source": [ "___" ] }, { "attachments": {}, "cell_type": "markdown", "id": "36b8b803", "metadata": {}, "source": [ "## ✅ Compare Models\n", "The `compare_models` function trains and evaluates the performance of all estimators available in the model library using cross-validation. The output of this function is a scoring grid with average cross-validated scores. Metrics evaluated during CV can be accessed using the `get_metrics` function. Custom metrics can be added or removed using `add_metric` and `remove_metric` function." ] }, { "cell_type": "code", "execution_count": 29, "id": "a3350418", "metadata": {}, "outputs": [ { "data": { "text/html": [], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
 ModelMAEMSERMSER2RMSLEMAPETT (Sec)
brBayesian Ridge9196.7962148504418.059712131.8559-0.01741.01571.56500.0220
dummyDummy Regressor9192.5418148516792.800012132.4733-0.01751.01541.56370.0210
enElastic Net9199.7686148549726.950512133.8720-0.01771.01591.56600.0200
ompOrthogonal Matching Pursuit9221.5250149344322.908912165.8760-0.02311.01801.57110.0240
ridgeRidge Regression9235.7964149651033.920112177.5983-0.02521.01901.57390.0190
lassoLasso Regression9235.6445149665146.042012178.1566-0.02531.01901.57380.0230
llarLasso Least Angle Regression9235.6430149665174.688912178.1577-0.02531.01901.57380.0220
larLeast Angle Regression9236.1261149679639.233212178.7361-0.02541.01911.57390.0190
lrLinear Regression9257.7067150002684.863612194.0574-0.02871.02091.58070.0180
huberHuber Regressor8473.8513160759513.641912586.8693-0.08810.94231.11480.0250
gbrGradient Boosting Regressor9558.8409160438196.140712613.1824-0.10281.02981.57310.0330
parPassive Aggressive Regressor8478.7556164627419.014012737.8812-0.11420.93941.05750.0220
rfRandom Forest Regressor9810.1061165973929.240612844.8475-0.14931.05621.67420.0600
catboostCatBoost Regressor9717.1261170370340.488513007.0106-0.17711.07271.57280.3450
knnK Neighbors Regressor10035.7207179988374.400013373.4167-0.24961.07911.64980.0250
lightgbmLight Gradient Boosting Machine10218.7242182737357.175613468.9454-0.25971.13051.64650.0900
adaAdaBoost Regressor11630.4633179599299.512713386.4600-0.26921.18272.34970.0230
etExtra Trees Regressor10097.1329188470162.602713672.0375-0.30131.07671.64540.0510
dtDecision Tree Regressor12227.1646292357681.067417021.6224-1.01961.30991.89070.0230
\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "best = compare_models()" ] }, { "attachments": {}, "cell_type": "markdown", "id": "cd18dcf6", "metadata": {}, "source": [ "`compare_models` by default uses all the estimators in model library (all except models with `Turbo=False`) . To see all available models you can use the function `models()`" ] }, { "cell_type": "code", "execution_count": 30, "id": "432e93d7", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
NameReferenceTurbo
ID
lrLinear Regressionsklearn.linear_model._base.LinearRegressionTrue
lassoLasso Regressionsklearn.linear_model._coordinate_descent.LassoTrue
ridgeRidge Regressionsklearn.linear_model._ridge.RidgeTrue
enElastic Netsklearn.linear_model._coordinate_descent.Elast...True
larLeast Angle Regressionsklearn.linear_model._least_angle.LarsTrue
llarLasso Least Angle Regressionsklearn.linear_model._least_angle.LassoLarsTrue
ompOrthogonal Matching Pursuitsklearn.linear_model._omp.OrthogonalMatchingPu...True
brBayesian Ridgesklearn.linear_model._bayes.BayesianRidgeTrue
ardAutomatic Relevance Determinationsklearn.linear_model._bayes.ARDRegressionFalse
parPassive Aggressive Regressorsklearn.linear_model._passive_aggressive.Passi...True
ransacRandom Sample Consensussklearn.linear_model._ransac.RANSACRegressorFalse
trTheilSen Regressorsklearn.linear_model._theil_sen.TheilSenRegressorFalse
huberHuber Regressorsklearn.linear_model._huber.HuberRegressorTrue
krKernel Ridgesklearn.kernel_ridge.KernelRidgeFalse
svmSupport Vector Regressionsklearn.svm._classes.SVRFalse
knnK Neighbors Regressorsklearn.neighbors._regression.KNeighborsRegressorTrue
dtDecision Tree Regressorsklearn.tree._classes.DecisionTreeRegressorTrue
rfRandom Forest Regressorsklearn.ensemble._forest.RandomForestRegressorTrue
etExtra Trees Regressorsklearn.ensemble._forest.ExtraTreesRegressorTrue
adaAdaBoost Regressorsklearn.ensemble._weight_boosting.AdaBoostRegr...True
gbrGradient Boosting Regressorsklearn.ensemble._gb.GradientBoostingRegressorTrue
mlpMLP Regressorsklearn.neural_network._multilayer_perceptron....False
lightgbmLight Gradient Boosting Machinelightgbm.sklearn.LGBMRegressorTrue
catboostCatBoost Regressorcatboost.core.CatBoostRegressorTrue
dummyDummy Regressorsklearn.dummy.DummyRegressorTrue
\n", "
" ], "text/plain": [ " Name \\\n", "ID \n", "lr Linear Regression \n", "lasso Lasso Regression \n", "ridge Ridge Regression \n", "en Elastic Net \n", "lar Least Angle Regression \n", "llar Lasso Least Angle Regression \n", "omp Orthogonal Matching Pursuit \n", "br Bayesian Ridge \n", "ard Automatic Relevance Determination \n", "par Passive Aggressive Regressor \n", "ransac Random Sample Consensus \n", "tr TheilSen Regressor \n", "huber Huber Regressor \n", "kr Kernel Ridge \n", "svm Support Vector Regression \n", "knn K Neighbors Regressor \n", "dt Decision Tree Regressor \n", "rf Random Forest Regressor \n", "et Extra Trees Regressor \n", "ada AdaBoost Regressor \n", "gbr Gradient Boosting Regressor \n", "mlp MLP Regressor \n", "lightgbm Light Gradient Boosting Machine \n", "catboost CatBoost Regressor \n", "dummy Dummy Regressor \n", "\n", " Reference Turbo \n", "ID \n", "lr sklearn.linear_model._base.LinearRegression True \n", "lasso sklearn.linear_model._coordinate_descent.Lasso True \n", "ridge sklearn.linear_model._ridge.Ridge True \n", "en sklearn.linear_model._coordinate_descent.Elast... True \n", "lar sklearn.linear_model._least_angle.Lars True \n", "llar sklearn.linear_model._least_angle.LassoLars True \n", "omp sklearn.linear_model._omp.OrthogonalMatchingPu... True \n", "br sklearn.linear_model._bayes.BayesianRidge True \n", "ard sklearn.linear_model._bayes.ARDRegression False \n", "par sklearn.linear_model._passive_aggressive.Passi... True \n", "ransac sklearn.linear_model._ransac.RANSACRegressor False \n", "tr sklearn.linear_model._theil_sen.TheilSenRegressor False \n", "huber sklearn.linear_model._huber.HuberRegressor True \n", "kr sklearn.kernel_ridge.KernelRidge False \n", "svm sklearn.svm._classes.SVR False \n", "knn sklearn.neighbors._regression.KNeighborsRegressor True \n", "dt sklearn.tree._classes.DecisionTreeRegressor True \n", "rf sklearn.ensemble._forest.RandomForestRegressor True \n", "et sklearn.ensemble._forest.ExtraTreesRegressor True \n", "ada sklearn.ensemble._weight_boosting.AdaBoostRegr... True \n", "gbr sklearn.ensemble._gb.GradientBoostingRegressor True \n", "mlp sklearn.neural_network._multilayer_perceptron.... False \n", "lightgbm lightgbm.sklearn.LGBMRegressor True \n", "catboost catboost.core.CatBoostRegressor True \n", "dummy sklearn.dummy.DummyRegressor True " ] }, "execution_count": 30, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# check available models\n", "models()" ] }, { "attachments": {}, "cell_type": "markdown", "id": "f588f54b", "metadata": {}, "source": [ "You can use the `include` and `exclude` parameter in the `compare_models` to train only select model or exclude specific models from training by passing the model id's in `exclude` parameter." ] }, { "cell_type": "code", "execution_count": 31, "id": "f2a7e578", "metadata": {}, "outputs": [ { "ename": "ValueError", "evalue": "Estimator xgboost Not Available. Please see docstring for list of available estimators.", "output_type": "error", "traceback": [ "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m", "\u001b[1;31mValueError\u001b[0m Traceback (most recent call last)", "Cell \u001b[1;32mIn[31], line 1\u001b[0m\n\u001b[1;32m----> 1\u001b[0m compare_tree_models \u001b[38;5;241m=\u001b[39m \u001b[43mcompare_models\u001b[49m\u001b[43m(\u001b[49m\u001b[43minclude\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m \u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43mdt\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43mrf\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43met\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43mgbr\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43mxgboost\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43mlightgbm\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43mcatboost\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m)\u001b[49m\n", "File \u001b[1;32mc:\\Users\\celes\\pycaret\\.venv\\Lib\\site-packages\\pycaret\\utils\\generic.py:964\u001b[0m, in \u001b[0;36mcheck_if_global_is_not_none..decorator..wrapper\u001b[1;34m(*args, **kwargs)\u001b[0m\n\u001b[0;32m 962\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m globals_d[name] \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[0;32m 963\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(message)\n\u001b[1;32m--> 964\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfunc\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n", "File \u001b[1;32mc:\\Users\\celes\\pycaret\\.venv\\Lib\\site-packages\\pycaret\\regression\\functional.py:805\u001b[0m, in \u001b[0;36mcompare_models\u001b[1;34m(include, exclude, fold, round, cross_validation, sort, n_select, budget_time, turbo, errors, fit_kwargs, groups, experiment_custom_tags, engine, verbose, parallel)\u001b[0m\n\u001b[0;32m 670\u001b[0m \u001b[38;5;129m@check_if_global_is_not_none\u001b[39m(\u001b[38;5;28mglobals\u001b[39m(), _CURRENT_EXPERIMENT_DECORATOR_DICT)\n\u001b[0;32m 671\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mcompare_models\u001b[39m(\n\u001b[0;32m 672\u001b[0m include: Optional[List[Union[\u001b[38;5;28mstr\u001b[39m, Any]]] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[1;32m (...)\u001b[0m\n\u001b[0;32m 687\u001b[0m parallel: Optional[ParallelBackend] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[0;32m 688\u001b[0m ):\n\u001b[0;32m 689\u001b[0m \u001b[38;5;250m \u001b[39m\u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[0;32m 690\u001b[0m \u001b[38;5;124;03m This function trains and evaluates performance of all estimators available in the\u001b[39;00m\n\u001b[0;32m 691\u001b[0m \u001b[38;5;124;03m model library using cross validation. The output of this function is a score grid\u001b[39;00m\n\u001b[1;32m (...)\u001b[0m\n\u001b[0;32m 803\u001b[0m \n\u001b[0;32m 804\u001b[0m \u001b[38;5;124;03m \"\"\"\u001b[39;00m\n\u001b[1;32m--> 805\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43m_CURRENT_EXPERIMENT\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcompare_models\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m 806\u001b[0m \u001b[43m \u001b[49m\u001b[43minclude\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43minclude\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 807\u001b[0m \u001b[43m \u001b[49m\u001b[43mexclude\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mexclude\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 808\u001b[0m \u001b[43m \u001b[49m\u001b[43mfold\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mfold\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 809\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;28;43mround\u001b[39;49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mround\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[0;32m 810\u001b[0m \u001b[43m \u001b[49m\u001b[43mcross_validation\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcross_validation\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 811\u001b[0m \u001b[43m \u001b[49m\u001b[43msort\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43msort\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 812\u001b[0m \u001b[43m \u001b[49m\u001b[43mn_select\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mn_select\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 813\u001b[0m \u001b[43m \u001b[49m\u001b[43mbudget_time\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mbudget_time\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 814\u001b[0m \u001b[43m \u001b[49m\u001b[43mturbo\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mturbo\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 815\u001b[0m \u001b[43m \u001b[49m\u001b[43merrors\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43merrors\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 816\u001b[0m \u001b[43m \u001b[49m\u001b[43mfit_kwargs\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mfit_kwargs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 817\u001b[0m \u001b[43m \u001b[49m\u001b[43mgroups\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mgroups\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 818\u001b[0m \u001b[43m \u001b[49m\u001b[43mexperiment_custom_tags\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mexperiment_custom_tags\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 819\u001b[0m \u001b[43m \u001b[49m\u001b[43mengine\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mengine\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 820\u001b[0m \u001b[43m \u001b[49m\u001b[43mverbose\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mverbose\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 821\u001b[0m \u001b[43m \u001b[49m\u001b[43mparallel\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mparallel\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 822\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n", "File \u001b[1;32mc:\\Users\\celes\\pycaret\\.venv\\Lib\\site-packages\\pycaret\\regression\\oop.py:1122\u001b[0m, in \u001b[0;36mRegressionExperiment.compare_models\u001b[1;34m(self, include, exclude, fold, round, cross_validation, sort, n_select, budget_time, turbo, errors, fit_kwargs, groups, experiment_custom_tags, engine, verbose, parallel)\u001b[0m\n\u001b[0;32m 1119\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_set_engine(estimator\u001b[38;5;241m=\u001b[39mestimator, engine\u001b[38;5;241m=\u001b[39meng, severity\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124merror\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m 1121\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m-> 1122\u001b[0m return_values \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43msuper\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcompare_models\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m 1123\u001b[0m \u001b[43m \u001b[49m\u001b[43minclude\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43minclude\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 1124\u001b[0m \u001b[43m \u001b[49m\u001b[43mexclude\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mexclude\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 1125\u001b[0m \u001b[43m \u001b[49m\u001b[43mfold\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mfold\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 1126\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;28;43mround\u001b[39;49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mround\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[0;32m 1127\u001b[0m \u001b[43m \u001b[49m\u001b[43mcross_validation\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcross_validation\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 1128\u001b[0m \u001b[43m \u001b[49m\u001b[43msort\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43msort\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 1129\u001b[0m \u001b[43m \u001b[49m\u001b[43mn_select\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mn_select\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 1130\u001b[0m \u001b[43m \u001b[49m\u001b[43mbudget_time\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mbudget_time\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 1131\u001b[0m \u001b[43m \u001b[49m\u001b[43mturbo\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mturbo\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 1132\u001b[0m \u001b[43m \u001b[49m\u001b[43merrors\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43merrors\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 1133\u001b[0m \u001b[43m \u001b[49m\u001b[43mfit_kwargs\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mfit_kwargs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 1134\u001b[0m \u001b[43m \u001b[49m\u001b[43mgroups\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mgroups\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 1135\u001b[0m \u001b[43m \u001b[49m\u001b[43mexperiment_custom_tags\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mexperiment_custom_tags\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 1136\u001b[0m \u001b[43m \u001b[49m\u001b[43mverbose\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mverbose\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 1137\u001b[0m \u001b[43m \u001b[49m\u001b[43mparallel\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mparallel\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 1138\u001b[0m \u001b[43m \u001b[49m\u001b[43mcaller_params\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcaller_params\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 1139\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m 1141\u001b[0m \u001b[38;5;28;01mfinally\u001b[39;00m:\n\u001b[0;32m 1142\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m engine \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[0;32m 1143\u001b[0m \u001b[38;5;66;03m# Reset the models back to the default engines\u001b[39;00m\n", "File \u001b[1;32mc:\\Users\\celes\\pycaret\\.venv\\Lib\\site-packages\\pycaret\\internal\\pycaret_experiment\\supervised_experiment.py:557\u001b[0m, in \u001b[0;36m_SupervisedExperiment.compare_models\u001b[1;34m(self, include, exclude, fold, round, cross_validation, sort, n_select, budget_time, turbo, errors, fit_kwargs, groups, experiment_custom_tags, probability_threshold, verbose, parallel, caller_params)\u001b[0m\n\u001b[0;32m 555\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(i, \u001b[38;5;28mstr\u001b[39m):\n\u001b[0;32m 556\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m i \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m available_estimators:\n\u001b[1;32m--> 557\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\n\u001b[0;32m 558\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mEstimator \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mi\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m Not Available. Please see docstring for list of available estimators.\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m 559\u001b[0m )\n\u001b[0;32m 560\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28mhasattr\u001b[39m(i, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mfit\u001b[39m\u001b[38;5;124m\"\u001b[39m):\n\u001b[0;32m 561\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\n\u001b[0;32m 562\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mEstimator \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mi\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m does not have the required fit() method.\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m 563\u001b[0m )\n", "\u001b[1;31mValueError\u001b[0m: Estimator xgboost Not Available. Please see docstring for list of available estimators." ] } ], "source": [ "compare_tree_models = compare_models(include = ['dt', 'rf', 'et', 'gbr', 'xgboost', 'lightgbm', 'catboost'])" ] }, { "cell_type": "code", "execution_count": null, "id": "c15a467e", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
GradientBoostingRegressor(random_state=123)
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
" ], "text/plain": [ "GradientBoostingRegressor(random_state=123)" ] }, "execution_count": 31, "metadata": {}, "output_type": "execute_result" } ], "source": [ "compare_tree_models" ] }, { "attachments": {}, "cell_type": "markdown", "id": "af9ae6cd", "metadata": {}, "source": [ "The function above has return trained model object as an output. The scoring grid is only displayed and not returned. If you need access to the scoring grid you can use `pull` function to access the dataframe." ] }, { "cell_type": "code", "execution_count": null, "id": "fc529e25", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
ModelMAEMSERMSER2RMSLEMAPETT (Sec)
gbrGradient Boosting Regressor2701.91352.354862e+074832.92910.83200.44470.31370.064
rfRandom Forest Regressor2772.91952.540979e+075028.19730.81730.46870.32980.075
catboostCatBoost Regressor2899.48252.576275e+075057.57780.81630.48150.35220.046
lightgbmLight Gradient Boosting Machine3001.88842.554732e+075044.57670.81470.54450.37840.048
etExtra Trees Regressor2833.36242.842784e+075305.65160.79910.48770.33630.076
xgboostExtreme Gradient Boosting3439.88923.282651e+075711.73350.76260.62210.44650.042
dtDecision Tree Regressor3399.14024.810020e+076915.29840.64760.56290.40520.041
\n", "
" ], "text/plain": [ " Model MAE MSE RMSE \\\n", "gbr Gradient Boosting Regressor 2701.9135 2.354862e+07 4832.9291 \n", "rf Random Forest Regressor 2772.9195 2.540979e+07 5028.1973 \n", "catboost CatBoost Regressor 2899.4825 2.576275e+07 5057.5778 \n", "lightgbm Light Gradient Boosting Machine 3001.8884 2.554732e+07 5044.5767 \n", "et Extra Trees Regressor 2833.3624 2.842784e+07 5305.6516 \n", "xgboost Extreme Gradient Boosting 3439.8892 3.282651e+07 5711.7335 \n", "dt Decision Tree Regressor 3399.1402 4.810020e+07 6915.2984 \n", "\n", " R2 RMSLE MAPE TT (Sec) \n", "gbr 0.8320 0.4447 0.3137 0.064 \n", "rf 0.8173 0.4687 0.3298 0.075 \n", "catboost 0.8163 0.4815 0.3522 0.046 \n", "lightgbm 0.8147 0.5445 0.3784 0.048 \n", "et 0.7991 0.4877 0.3363 0.076 \n", "xgboost 0.7626 0.6221 0.4465 0.042 \n", "dt 0.6476 0.5629 0.4052 0.041 " ] }, "execution_count": 32, "metadata": {}, "output_type": "execute_result" } ], "source": [ "compare_tree_models_results = pull()\n", "compare_tree_models_results" ] }, { "attachments": {}, "cell_type": "markdown", "id": "05a72fc2", "metadata": {}, "source": [ "By default `compare_models` return the single best performing model based on the metric defined in the `sort` parameter. Let's change our code to return 3 top models based on `MAE`." ] }, { "cell_type": "code", "execution_count": null, "id": "1066dd07", "metadata": {}, "outputs": [ { "data": { "text/html": [], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
 ModelMAEMSERMSER2RMSLEMAPETT (Sec)
gbrGradient Boosting Regressor2701.913523548622.15984832.92910.83200.44470.31370.0640
rfRandom Forest Regressor2772.919525409792.96925028.19730.81730.46870.32980.0800
etExtra Trees Regressor2833.362428427844.24125305.65160.79910.48770.33630.0800
catboostCatBoost Regressor2899.482525762752.20965057.57780.81630.48150.35220.0420
lightgbmLight Gradient Boosting Machine3001.888425547324.58135044.57670.81470.54450.37840.0500
dtDecision Tree Regressor3399.140248100203.38476915.29840.64760.56290.40520.0430
xgboostExtreme Gradient Boosting3439.889232826514.40005711.73350.76260.62210.44650.0530
huberHuber Regressor3461.732749057640.56136981.85760.65280.48150.21880.0490
parPassive Aggressive Regressor3536.173348501878.13636940.19670.65660.47850.21540.0480
knnK Neighbors Regressor3778.458238143971.20006165.04630.72770.50270.36900.0470
adaAdaBoost Regressor4175.591628401799.05795321.70060.79760.62630.71440.0470
ridgeRidge Regression4296.064238392999.78496176.61600.73080.57100.43970.0420
llarLasso Least Angle Regression4298.603838369142.08496174.94240.73090.57860.44240.0450
brBayesian Ridge4300.628638387539.90696176.41920.73070.58810.44190.0480
lassoLasso Regression4302.246938386534.55536176.44630.73060.59130.44300.0430
larLeast Angle Regression4303.555938388058.45786176.59200.73060.59490.44330.0420
lrLinear Regression4312.618638452749.80076182.47960.72980.62850.44600.0430
ompOrthogonal Matching Pursuit5754.776957503207.72337566.70860.59970.74180.89900.0460
enElastic Net7571.4598104738034.470710182.32910.28460.89541.28880.0450
dummyDummy Regressor9192.5418148516792.800012132.4733-0.01751.01541.56370.0400
\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "", "version_major": 2, "version_minor": 0 }, "text/plain": [ "Processing: 0%| | 0/87 [00:00\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
NameReferenceTurbo
ID
lrLinear Regressionsklearn.linear_model._base.LinearRegressionTrue
lassoLasso Regressionsklearn.linear_model._coordinate_descent.LassoTrue
ridgeRidge Regressionsklearn.linear_model._ridge.RidgeTrue
enElastic Netsklearn.linear_model._coordinate_descent.Elast...True
larLeast Angle Regressionsklearn.linear_model._least_angle.LarsTrue
llarLasso Least Angle Regressionsklearn.linear_model._least_angle.LassoLarsTrue
ompOrthogonal Matching Pursuitsklearn.linear_model._omp.OrthogonalMatchingPu...True
brBayesian Ridgesklearn.linear_model._bayes.BayesianRidgeTrue
ardAutomatic Relevance Determinationsklearn.linear_model._bayes.ARDRegressionFalse
parPassive Aggressive Regressorsklearn.linear_model._passive_aggressive.Passi...True
ransacRandom Sample Consensussklearn.linear_model._ransac.RANSACRegressorFalse
trTheilSen Regressorsklearn.linear_model._theil_sen.TheilSenRegressorFalse
huberHuber Regressorsklearn.linear_model._huber.HuberRegressorTrue
krKernel Ridgesklearn.kernel_ridge.KernelRidgeFalse
svmSupport Vector Regressionsklearn.svm._classes.SVRFalse
knnK Neighbors Regressorsklearn.neighbors._regression.KNeighborsRegressorTrue
dtDecision Tree Regressorsklearn.tree._classes.DecisionTreeRegressorTrue
rfRandom Forest Regressorsklearn.ensemble._forest.RandomForestRegressorTrue
etExtra Trees Regressorsklearn.ensemble._forest.ExtraTreesRegressorTrue
adaAdaBoost Regressorsklearn.ensemble._weight_boosting.AdaBoostRegr...True
gbrGradient Boosting Regressorsklearn.ensemble._gb.GradientBoostingRegressorTrue
mlpMLP Regressorsklearn.neural_network._multilayer_perceptron....False
xgboostExtreme Gradient Boostingxgboost.sklearn.XGBRegressorTrue
lightgbmLight Gradient Boosting Machinelightgbm.sklearn.LGBMRegressorTrue
catboostCatBoost Regressorcatboost.core.CatBoostRegressorTrue
dummyDummy Regressorsklearn.dummy.DummyRegressorTrue
\n", "" ], "text/plain": [ " Name \\\n", "ID \n", "lr Linear Regression \n", "lasso Lasso Regression \n", "ridge Ridge Regression \n", "en Elastic Net \n", "lar Least Angle Regression \n", "llar Lasso Least Angle Regression \n", "omp Orthogonal Matching Pursuit \n", "br Bayesian Ridge \n", "ard Automatic Relevance Determination \n", "par Passive Aggressive Regressor \n", "ransac Random Sample Consensus \n", "tr TheilSen Regressor \n", "huber Huber Regressor \n", "kr Kernel Ridge \n", "svm Support Vector Regression \n", "knn K Neighbors Regressor \n", "dt Decision Tree Regressor \n", "rf Random Forest Regressor \n", "et Extra Trees Regressor \n", "ada AdaBoost Regressor \n", "gbr Gradient Boosting Regressor \n", "mlp MLP Regressor \n", "xgboost Extreme Gradient Boosting \n", "lightgbm Light Gradient Boosting Machine \n", "catboost CatBoost Regressor \n", "dummy Dummy Regressor \n", "\n", " Reference Turbo \n", "ID \n", "lr sklearn.linear_model._base.LinearRegression True \n", "lasso sklearn.linear_model._coordinate_descent.Lasso True \n", "ridge sklearn.linear_model._ridge.Ridge True \n", "en sklearn.linear_model._coordinate_descent.Elast... True \n", "lar sklearn.linear_model._least_angle.Lars True \n", "llar sklearn.linear_model._least_angle.LassoLars True \n", "omp sklearn.linear_model._omp.OrthogonalMatchingPu... True \n", "br sklearn.linear_model._bayes.BayesianRidge True \n", "ard sklearn.linear_model._bayes.ARDRegression False \n", "par sklearn.linear_model._passive_aggressive.Passi... True \n", "ransac sklearn.linear_model._ransac.RANSACRegressor False \n", "tr sklearn.linear_model._theil_sen.TheilSenRegressor False \n", "huber sklearn.linear_model._huber.HuberRegressor True \n", "kr sklearn.kernel_ridge.KernelRidge False \n", "svm sklearn.svm._classes.SVR False \n", "knn sklearn.neighbors._regression.KNeighborsRegressor True \n", "dt sklearn.tree._classes.DecisionTreeRegressor True \n", "rf sklearn.ensemble._forest.RandomForestRegressor True \n", "et sklearn.ensemble._forest.ExtraTreesRegressor True \n", "ada sklearn.ensemble._weight_boosting.AdaBoostRegr... True \n", "gbr sklearn.ensemble._gb.GradientBoostingRegressor True \n", "mlp sklearn.neural_network._multilayer_perceptron.... False \n", "xgboost xgboost.sklearn.XGBRegressor True \n", "lightgbm lightgbm.sklearn.LGBMRegressor True \n", "catboost catboost.core.CatBoostRegressor True \n", "dummy sklearn.dummy.DummyRegressor True " ] }, "execution_count": 40, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# check all the available models\n", "models()" ] }, { "cell_type": "code", "execution_count": null, "id": "16641cab", "metadata": {}, "outputs": [ { "data": { "text/html": [], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
 MAEMSERMSER2RMSLEMAPE
Fold      
04221.766233767244.16065810.95900.79830.48640.4323
14529.890243625181.52686604.93610.74630.55430.4301
23958.466032631291.90875712.38060.58681.02400.4630
33725.888726679679.25705165.23760.77720.49790.5219
44437.120443552381.43416599.42280.67610.57310.3768
54115.634035844995.00795987.06900.76940.53810.4131
64098.086839631320.05986295.34110.73030.57450.4266
74850.105846175035.29976795.22150.74610.57060.3959
84621.061640681916.37376378.23770.73720.70320.5225
94568.166141938452.97866475.99050.72990.76260.4780
Mean4312.618638452749.80076182.47960.72980.62850.4460
Std327.84125763256.3224479.26600.05690.15500.0470
\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "", "version_major": 2, "version_minor": 0 }, "text/plain": [ "Processing: 0%| | 0/4 [00:00\n" ] }, { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
MAEMSERMSER2RMSLEMAPE
Fold
04221.76623.376724e+075810.95900.79830.48640.4323
14529.89024.362518e+076604.93610.74630.55430.4301
23958.46603.263129e+075712.38060.58681.02400.4630
33725.88872.667968e+075165.23760.77720.49790.5219
44437.12044.355238e+076599.42280.67610.57310.3768
54115.63403.584500e+075987.06900.76940.53810.4131
64098.08683.963132e+076295.34110.73030.57450.4266
74850.10584.617504e+076795.22150.74610.57060.3959
84621.06164.068192e+076378.23770.73720.70320.5225
94568.16614.193845e+076475.99050.72990.76260.4780
Mean4312.61863.845275e+076182.47960.72980.62850.4460
Std327.84125.763256e+06479.26600.05690.15500.0470
\n", "
" ], "text/plain": [ " MAE MSE RMSE R2 RMSLE MAPE\n", "Fold \n", "0 4221.7662 3.376724e+07 5810.9590 0.7983 0.4864 0.4323\n", "1 4529.8902 4.362518e+07 6604.9361 0.7463 0.5543 0.4301\n", "2 3958.4660 3.263129e+07 5712.3806 0.5868 1.0240 0.4630\n", "3 3725.8887 2.667968e+07 5165.2376 0.7772 0.4979 0.5219\n", "4 4437.1204 4.355238e+07 6599.4228 0.6761 0.5731 0.3768\n", "5 4115.6340 3.584500e+07 5987.0690 0.7694 0.5381 0.4131\n", "6 4098.0868 3.963132e+07 6295.3411 0.7303 0.5745 0.4266\n", "7 4850.1058 4.617504e+07 6795.2215 0.7461 0.5706 0.3959\n", "8 4621.0616 4.068192e+07 6378.2377 0.7372 0.7032 0.5225\n", "9 4568.1661 4.193845e+07 6475.9905 0.7299 0.7626 0.4780\n", "Mean 4312.6186 3.845275e+07 6182.4796 0.7298 0.6285 0.4460\n", "Std 327.8412 5.763256e+06 479.2660 0.0569 0.1550 0.0470" ] }, "execution_count": 42, "metadata": {}, "output_type": "execute_result" } ], "source": [ "lr_results = pull()\n", "print(type(lr_results))\n", "lr_results" ] }, { "cell_type": "code", "execution_count": null, "id": "148a74c4", "metadata": {}, "outputs": [ { "data": { "text/html": [], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
 MAEMSERMSER2RMSLEMAPE
Fold      
04170.753735338831.93465944.64730.74820.65620.4578
14285.897039763353.69036305.81900.71760.54060.4443
24511.418940766553.91706384.86910.74920.61600.4383
Mean4322.689938622913.18066211.77850.73830.60430.4468
Std141.48852358035.1845191.62730.01470.04790.0082
\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "", "version_major": 2, "version_minor": 0 }, "text/plain": [ "Processing: 0%| | 0/4 [00:00" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
 MAEMSERMSER2RMSLEMAPE
Fold      
04222.961633775764.34325811.69200.79830.48790.4328
14522.581943620030.51926604.54620.74640.54730.4216
23853.037831981107.96025655.18420.59510.71080.4398
33707.770526513348.57605149.11140.77860.48910.5164
44484.212243828444.10006620.30540.67400.57610.3847
54113.622235882341.98105990.18710.76920.54640.4130
64098.086839631320.05986295.34110.73030.57450.4266
74833.774745739275.71726763.08180.74850.58870.3967
84621.061640681916.37376378.23770.73720.70320.5225
94578.449942227034.94766498.23320.72800.72520.4793
Mean4303.555938388058.45786176.59200.73060.59490.4433
Std343.63245849500.5628487.61600.05530.08380.0451
\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "", "version_major": 2, "version_minor": 0 }, "text/plain": [ "Processing: 0%| | 0/4 [00:00#sk-container-id-4 {color: black;background-color: white;}#sk-container-id-4 pre{padding: 0;}#sk-container-id-4 div.sk-toggleable {background-color: white;}#sk-container-id-4 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-4 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-4 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-4 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-4 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-4 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-4 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-4 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-4 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-4 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-4 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-4 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-4 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-4 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-4 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-4 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-4 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-4 div.sk-item {position: relative;z-index: 1;}#sk-container-id-4 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-4 div.sk-item::before, #sk-container-id-4 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-4 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-4 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-4 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-4 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-4 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-4 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-4 div.sk-label-container {text-align: center;}#sk-container-id-4 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-4 div.sk-text-repr-fallback {display: none;}
LinearRegression(fit_intercept=False, n_jobs=-1)
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
" ], "text/plain": [ "LinearRegression(fit_intercept=False, n_jobs=-1)" ] }, "execution_count": 44, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# train linear regression with specific model parameters\n", "create_model('lr', fit_intercept = False)" ] }, { "cell_type": "code", "execution_count": null, "id": "b85af29b", "metadata": {}, "outputs": [ { "data": { "text/html": [], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
  MAEMSERMSER2RMSLEMAPE
SplitFold      
CV-Train04267.426738159913.78206177.37110.73840.57500.4421
14234.852537077265.72166089.11040.74490.74740.4442
24416.245338462804.37336201.83880.75180.69810.4727
34389.041138983678.60376243.69110.74170.56970.4495
44212.717337111422.37676091.91450.75200.68240.4295
54288.564337909700.16196157.08540.74260.58800.4443
64271.990937519682.35136125.33120.74690.54970.4331
74164.172036878048.64176072.72990.74400.58180.4213
84234.146037404224.47846115.89930.74620.58960.4291
94230.412737247244.06246103.05200.74720.55900.4312
CV-Val04221.766233767244.16065810.95900.79830.48640.4323
14529.890243625181.52686604.93610.74630.55430.4301
23958.466032631291.90875712.38060.58681.02400.4630
33725.888726679679.25705165.23760.77720.49790.5219
44437.120443552381.43416599.42280.67610.57310.3768
54115.634035844995.00795987.06900.76940.53810.4131
64098.086839631320.05986295.34110.73030.57450.4266
74850.105846175035.29976795.22150.74610.57060.3959
84621.061640681916.37376378.23770.73720.70320.5225
94568.166141938452.97866475.99050.72990.76260.4780
CV-TrainMean4270.956937675398.45536137.80240.74560.61410.4397
Std73.8061649149.824252.73000.00400.06520.0138
CV-ValMean4312.618638452749.80076182.47960.72980.62850.4460
Std327.84125763256.3224479.26600.05690.15500.0470
Trainnan4200.467737762351.23756145.10790.74510.67390.4178
\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "", "version_major": 2, "version_minor": 0 }, "text/plain": [ "Processing: 0%| | 0/4 [00:00#sk-container-id-5 {color: black;background-color: white;}#sk-container-id-5 pre{padding: 0;}#sk-container-id-5 div.sk-toggleable {background-color: white;}#sk-container-id-5 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-5 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-5 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-5 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-5 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-5 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-5 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-5 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-5 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-5 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-5 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-5 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-5 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-5 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-5 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-5 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-5 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-5 div.sk-item {position: relative;z-index: 1;}#sk-container-id-5 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-5 div.sk-item::before, #sk-container-id-5 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-5 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-5 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-5 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-5 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-5 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-5 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-5 div.sk-label-container {text-align: center;}#sk-container-id-5 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-5 div.sk-text-repr-fallback {display: none;}
LinearRegression(n_jobs=-1)
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
" ], "text/plain": [ "LinearRegression(n_jobs=-1)" ] }, "execution_count": 45, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# train lr and return train score as well alongwith CV\n", "create_model('lr', return_train_score=True)" ] }, { "attachments": {}, "cell_type": "markdown", "id": "08634e9e", "metadata": {}, "source": [ "Some other parameters that you might find very useful in `create_model` are:\n", "\n", "- cross_validation\n", "- engine\n", "- fit_kwargs\n", "- groups\n", "\n", "You can check the docstring of the function for more info." ] }, { "cell_type": "code", "execution_count": null, "id": "3fb32c74", "metadata": {}, "outputs": [], "source": [ "# help(create_model)" ] }, { "attachments": {}, "cell_type": "markdown", "id": "d5378836", "metadata": {}, "source": [ "## ✅ Tune Model\n", "\n", "The `tune_model` function tunes the hyperparameters of the model. The output of this function is a scoring grid with cross-validated scores by fold. The best model is selected based on the metric defined in optimize parameter. Metrics evaluated during cross-validation can be accessed using the `get_metrics` function. Custom metrics can be added or removed using `add_metric` and `remove_metric` function." ] }, { "cell_type": "code", "execution_count": null, "id": "402597f2", "metadata": {}, "outputs": [ { "data": { "text/html": [], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
 MAEMSERMSER2RMSLEMAPE
Fold      
03244.617345002914.99786708.42120.73120.58840.4883
13106.261145435728.75366740.60300.73580.53890.3271
23646.266254445682.26277378.73180.31070.64750.4752
33267.925045463401.77496742.65540.62040.57510.4339
44344.747065261429.30138078.45460.51460.72610.6008
53497.928142984919.02546556.28850.72350.46140.3208
63596.263753600704.72987321.25020.63530.52840.4126
72804.749337461859.85416120.60940.79400.47370.1787
83080.180142102090.88466488.61240.72810.51680.4537
93402.464149243302.26257017.35720.68280.57250.3613
Mean3399.140248100203.38476915.29840.64760.56290.4052
Std398.21857518631.1992528.06420.13480.07540.1094
\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "", "version_major": 2, "version_minor": 0 }, "text/plain": [ "Processing: 0%| | 0/4 [00:00" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
 MAEMSERMSER2RMSLEMAPE
Fold      
01745.000818073621.25344251.30820.89200.34080.1390
12380.267133969297.49785828.31860.80250.48030.1491
22005.548123477540.52754845.36280.70270.47420.1604
31986.941922156779.86364707.09890.81500.37310.1550
42255.079728517151.43845340.14530.78790.48320.1465
51961.781020794913.66074560.14400.86620.36530.1287
61649.955920053618.60904478.12670.86350.33150.1164
72049.206626281892.46735126.58680.85550.46530.1298
81991.859923667668.43914864.94280.84710.38650.1452
92159.099426013111.35805100.30500.83240.42420.1459
Mean2018.474024300559.51154910.23390.82650.41240.1416
Std205.73614392006.1282436.07620.05110.05700.0126
\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "", "version_major": 2, "version_minor": 0 }, "text/plain": [ "Processing: 0%| | 0/7 [00:00#sk-container-id-6 {color: black;background-color: white;}#sk-container-id-6 pre{padding: 0;}#sk-container-id-6 div.sk-toggleable {background-color: white;}#sk-container-id-6 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-6 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-6 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-6 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-6 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-6 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-6 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-6 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-6 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-6 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-6 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-6 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-6 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-6 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-6 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-6 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-6 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-6 div.sk-item {position: relative;z-index: 1;}#sk-container-id-6 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-6 div.sk-item::before, #sk-container-id-6 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-6 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-6 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-6 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-6 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-6 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-6 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-6 div.sk-label-container {text-align: center;}#sk-container-id-6 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-6 div.sk-text-repr-fallback {display: none;}
DecisionTreeRegressor(random_state=123)
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
" ], "text/plain": [ "DecisionTreeRegressor(random_state=123)" ] }, "execution_count": 48, "metadata": {}, "output_type": "execute_result" } ], "source": [ "dt" ] }, { "cell_type": "code", "execution_count": null, "id": "31e050ff", "metadata": {}, "outputs": [ { "data": { "text/html": [], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
 MAEMSERMSER2RMSLEMAPE
Fold      
02862.168920651854.54404544.43120.87670.42910.3378
12985.548529278808.67365410.98960.82980.44710.3012
22843.367323854320.12384884.08850.69800.49000.3620
32868.125820204282.71994494.91740.83130.45970.4100
43153.215026237222.14325122.22820.80490.48010.3419
52735.182817885888.82924229.17120.88490.38060.2917
62606.728620086199.55534481.76300.86330.41240.3367
72831.025824114233.91384910.62460.86740.46640.3333
82663.457419629791.04904430.55200.87320.42880.3656
92788.250524885036.60724988.49040.83970.47710.3403
Mean2833.707122682763.81594749.72560.83690.44710.3421
Std148.16003372742.1687350.52880.05220.03260.0315
\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "", "version_major": 2, "version_minor": 0 }, "text/plain": [ "Processing: 0%| | 0/7 [00:00" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
 MAEMSERMSER2RMSLEMAPE
Fold      
01745.000818073621.25344251.30820.89200.34080.1390
12380.267133969297.49785828.31860.80250.48030.1491
22005.548123477540.52754845.36280.70270.47420.1604
31986.941922156779.86364707.09890.81500.37310.1550
42255.079728517151.43845340.14530.78790.48320.1465
51961.781020794913.66074560.14400.86620.36530.1287
61649.955920053618.60904478.12670.86350.33150.1164
72049.206626281892.46735126.58680.85550.46530.1298
81991.859923667668.43914864.94280.84710.38650.1452
92159.099426013111.35805100.30500.83240.42420.1459
Mean2018.474024300559.51154910.23390.82650.41240.1416
Std205.73614392006.1282436.07620.05110.05700.0126
\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "", "version_major": 2, "version_minor": 0 }, "text/plain": [ "Processing: 0%| | 0/7 [00:00#sk-container-id-7 {color: black;background-color: white;}#sk-container-id-7 pre{padding: 0;}#sk-container-id-7 div.sk-toggleable {background-color: white;}#sk-container-id-7 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-7 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-7 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-7 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-7 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-7 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-7 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-7 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-7 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-7 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-7 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-7 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-7 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-7 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-7 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-7 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-7 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-7 div.sk-item {position: relative;z-index: 1;}#sk-container-id-7 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-7 div.sk-item::before, #sk-container-id-7 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-7 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-7 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-7 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-7 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-7 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-7 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-7 div.sk-label-container {text-align: center;}#sk-container-id-7 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-7 div.sk-text-repr-fallback {display: none;}
DecisionTreeRegressor(criterion='absolute_error', max_depth=6, max_features=1.0,\n",
       "                      min_impurity_decrease=0.002, min_samples_leaf=5,\n",
       "                      min_samples_split=5, random_state=123)
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
" ], "text/plain": [ "DecisionTreeRegressor(criterion='absolute_error', max_depth=6, max_features=1.0,\n", " min_impurity_decrease=0.002, min_samples_leaf=5,\n", " min_samples_split=5, random_state=123)" ] }, "execution_count": 51, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# model object\n", "tuned_dt" ] }, { "cell_type": "code", "execution_count": null, "id": "7d5e49ca", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
RandomizedSearchCV(cv=KFold(n_splits=10, random_state=None, shuffle=False),\n",
       "                   estimator=Pipeline(memory=FastMemory(location=C:\\Users\\owner\\AppData\\Local\\Temp\\joblib),\n",
       "                                      steps=[('numerical_imputer',\n",
       "                                              TransformerWrapper(include=['age',\n",
       "                                                                          'bmi',\n",
       "                                                                          'children'],\n",
       "                                                                 transformer=SimpleImputer())),\n",
       "                                             ('categorical_imputer',\n",
       "                                              TransformerWrapper(include=['sex',\n",
       "                                                                          'smoker',\n",
       "                                                                          'region'],\n",
       "                                                                 tra...\n",
       "                                                                        7, 8, 9,\n",
       "                                                                        10, 11,\n",
       "                                                                        12, 13,\n",
       "                                                                        14, 15,\n",
       "                                                                        16],\n",
       "                                        'actual_estimator__max_features': [1.0,\n",
       "                                                                           'sqrt',\n",
       "                                                                           'log2'],\n",
       "                                        'actual_estimator__min_impurity_decrease': [0,\n",
       "                                                                                    0.0001,\n",
       "                                                                                    0.001,\n",
       "                                                                                    0.01,\n",
       "                                                                                    0.0002,\n",
       "                                                                                    0.002,\n",
       "                                                                                    0.02,\n",
       "                                                                                    0.0005,\n",
       "                                                                                    0.005,\n",
       "                                                                                    0.05,\n",
       "                                                                                    0.1,\n",
       "                                                                                    0.2,\n",
       "                                                                                    0.3,\n",
       "                                                                                    0.4,\n",
       "                                                                                    0.5],\n",
       "                                        'actual_estimator__min_samples_leaf': [2,\n",
       "                                                                               3,\n",
       "                                                                               4,\n",
       "                                                                               5,\n",
       "                                                                               6],\n",
       "                                        'actual_estimator__min_samples_split': [2,\n",
       "                                                                                5,\n",
       "                                                                                7,\n",
       "                                                                                9,\n",
       "                                                                                10]},\n",
       "                   random_state=123, refit=False, scoring='r2', verbose=1)
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
" ], "text/plain": [ "RandomizedSearchCV(cv=KFold(n_splits=10, random_state=None, shuffle=False),\n", " estimator=Pipeline(memory=FastMemory(location=C:\\Users\\owner\\AppData\\Local\\Temp\\joblib),\n", " steps=[('numerical_imputer',\n", " TransformerWrapper(include=['age',\n", " 'bmi',\n", " 'children'],\n", " transformer=SimpleImputer())),\n", " ('categorical_imputer',\n", " TransformerWrapper(include=['sex',\n", " 'smoker',\n", " 'region'],\n", " tra...\n", " 7, 8, 9,\n", " 10, 11,\n", " 12, 13,\n", " 14, 15,\n", " 16],\n", " 'actual_estimator__max_features': [1.0,\n", " 'sqrt',\n", " 'log2'],\n", " 'actual_estimator__min_impurity_decrease': [0,\n", " 0.0001,\n", " 0.001,\n", " 0.01,\n", " 0.0002,\n", " 0.002,\n", " 0.02,\n", " 0.0005,\n", " 0.005,\n", " 0.05,\n", " 0.1,\n", " 0.2,\n", " 0.3,\n", " 0.4,\n", " 0.5],\n", " 'actual_estimator__min_samples_leaf': [2,\n", " 3,\n", " 4,\n", " 5,\n", " 6],\n", " 'actual_estimator__min_samples_split': [2,\n", " 5,\n", " 7,\n", " 9,\n", " 10]},\n", " random_state=123, refit=False, scoring='r2', verbose=1)" ] }, "execution_count": 52, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# tuner object\n", "tuner" ] }, { "attachments": {}, "cell_type": "markdown", "id": "0a33c70b", "metadata": {}, "source": [ "The default search algorithm is `RandomizedSearchCV` from `sklearn`. This can be changed by using `search_library` and `search_algorithm` parameter." ] }, { "cell_type": "code", "execution_count": null, "id": "31e33547", "metadata": {}, "outputs": [ { "data": { "text/html": [], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
 MAEMSERMSER2RMSLEMAPE
Fold      
01780.470818661626.90654319.91050.88850.34920.1282
12378.832634060507.02145836.13800.80200.44050.1317
21914.887623340496.96884831.20040.70450.49000.1479
31965.266122365357.22184729.20260.81330.37070.1321
42391.038730760382.67175546.20430.77120.53730.1991
51906.352820367865.53424513.07720.86900.31840.1080
61729.714321351600.25754620.77920.85470.33870.1147
72039.061426615466.73255159.01800.85360.46890.1314
81927.496622598678.12824753.80670.85400.36630.1316
92195.401027341573.06675228.91700.82390.44430.1612
Mean2022.852224746355.45094953.82540.82350.41240.1386
Std217.86124616581.4311453.83860.05160.06980.0246
\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "", "version_major": 2, "version_minor": 0 }, "text/plain": [ "Processing: 0%| | 0/7 [00:00" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
 MAEMSERMSER2RMSLEMAPE
Fold      
02591.897023266281.45744823.51340.86100.46370.2976
12863.601730202461.81495495.67660.82440.48820.3053
22736.538024936511.93284993.64720.68430.51480.3293
32945.262627479881.32645242.12560.77050.51640.4187
43075.199030901342.43175558.89760.77020.56700.3906
52866.819825117097.44945011.69610.83840.37110.2607
62568.954522780849.68594772.92880.84500.37300.2717
72639.409126044331.10735103.36470.85680.47100.2506
82364.634319889092.44254459.71890.87150.41080.3040
92820.223131860942.57165644.54980.79480.46050.2805
Mean2747.253926247879.22205110.61190.81170.46360.3109
Std198.48993670176.0781359.89650.05470.06030.0521
\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "", "version_major": 2, "version_minor": 0 }, "text/plain": [ "Processing: 0%| | 0/6 [00:00#sk-container-id-9 {color: black;background-color: white;}#sk-container-id-9 pre{padding: 0;}#sk-container-id-9 div.sk-toggleable {background-color: white;}#sk-container-id-9 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-9 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-9 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-9 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-9 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-9 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-9 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-9 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-9 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-9 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-9 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-9 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-9 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-9 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-9 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-9 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-9 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-9 div.sk-item {position: relative;z-index: 1;}#sk-container-id-9 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-9 div.sk-item::before, #sk-container-id-9 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-9 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-9 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-9 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-9 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-9 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-9 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-9 div.sk-label-container {text-align: center;}#sk-container-id-9 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-9 div.sk-text-repr-fallback {display: none;}
BaggingRegressor(base_estimator=DecisionTreeRegressor(random_state=123),\n",
       "                 random_state=123)
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
" ], "text/plain": [ "BaggingRegressor(base_estimator=DecisionTreeRegressor(random_state=123),\n", " random_state=123)" ] }, "execution_count": 55, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# ensemble with bagging\n", "ensemble_model(dt, method = 'Bagging')" ] }, { "cell_type": "code", "execution_count": null, "id": "79279394", "metadata": {}, "outputs": [ { "data": { "text/html": [], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
 MAEMSERMSER2RMSLEMAPE
Fold      
02054.766926692081.42485166.43800.84060.41310.1936
11991.329127836623.83705276.04240.83810.39330.1198
22577.520234350249.68205860.90860.56510.57480.3238
32408.344930508533.28425523.45300.74530.51720.3788
42564.692331138720.30125580.20790.76840.56780.3023
53145.562639513518.59506285.97790.74580.44810.2825
62069.453527352438.44435229.95590.81390.34120.1427
72125.269526494689.44755147.29920.85430.44030.1571
82053.831621762810.23564665.06270.85940.33070.1743
92440.676129911998.00445469.18620.80730.49880.2361
Mean2343.144729556166.32565420.45320.78380.45250.2311
Std342.73424602124.0816418.15480.08330.08190.0827
\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "", "version_major": 2, "version_minor": 0 }, "text/plain": [ "Processing: 0%| | 0/6 [00:00#sk-container-id-10 {color: black;background-color: white;}#sk-container-id-10 pre{padding: 0;}#sk-container-id-10 div.sk-toggleable {background-color: white;}#sk-container-id-10 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-10 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-10 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-10 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-10 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-10 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-10 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-10 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-10 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-10 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-10 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-10 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-10 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-10 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-10 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-10 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-10 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-10 div.sk-item {position: relative;z-index: 1;}#sk-container-id-10 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-10 div.sk-item::before, #sk-container-id-10 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-10 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-10 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-10 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-10 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-10 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-10 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-10 div.sk-label-container {text-align: center;}#sk-container-id-10 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-10 div.sk-text-repr-fallback {display: none;}
AdaBoostRegressor(base_estimator=DecisionTreeRegressor(random_state=123),\n",
       "                  n_estimators=10, random_state=123)
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
" ], "text/plain": [ "AdaBoostRegressor(base_estimator=DecisionTreeRegressor(random_state=123),\n", " n_estimators=10, random_state=123)" ] }, "execution_count": 56, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# ensemble with boosting\n", "ensemble_model(dt, method = 'Boosting')" ] }, { "attachments": {}, "cell_type": "markdown", "id": "d0fa1ce2", "metadata": {}, "source": [ "Some other parameters that you might find very useful in `ensemble_model` are:\n", "\n", "- choose_better\n", "- n_estimators\n", "- groups\n", "- fit_kwargs\n", "- return_train_score\n", "\n", "You can check the docstring of the function for more info." ] }, { "cell_type": "code", "execution_count": null, "id": "78130ed1", "metadata": {}, "outputs": [], "source": [ "# help(ensemble_model)" ] }, { "attachments": {}, "cell_type": "markdown", "id": "ea8a9a4e", "metadata": {}, "source": [ "## ✅ Blend Models" ] }, { "attachments": {}, "cell_type": "markdown", "id": "2ede29c4", "metadata": {}, "source": [ "The `blend_models` function trains a `VotingRegressor` for select models passed in the `estimator_list` parameter. The output of this function is a scoring grid with CV scores by fold. Metrics evaluated during CV can be accessed using the `get_metrics` function. Custom metrics can be added or removed using `add_metric` and `remove_metric` function." ] }, { "cell_type": "code", "execution_count": null, "id": "61a7a1c5", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "[GradientBoostingRegressor(random_state=123),\n", " RandomForestRegressor(n_jobs=-1, random_state=123),\n", " ExtraTreesRegressor(n_jobs=-1, random_state=123)]" ] }, "execution_count": 62, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# top 3 models based on mae\n", "best_mae_models_top3" ] }, { "cell_type": "code", "execution_count": null, "id": "04f65f2f", "metadata": {}, "outputs": [ { "data": { "text/html": [], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
 MAEMSERMSER2RMSLEMAPE
Fold      
02720.893422050841.61034695.83240.86830.46370.3425
12865.401830821460.92795551.70790.82080.45350.2800
22581.606722252661.30194717.27270.71830.54630.3794
32810.233321734211.35644661.99650.81850.48640.3873
43070.010330740150.24645544.38010.77140.54690.3679
52854.709722065332.31364697.37500.85810.37710.2778
62450.823820209907.99114495.54310.86250.37400.2901
72595.249123563676.73644854.24320.87040.39970.2334
82262.947718038706.99754247.19990.88350.38460.2937
92947.544128438703.16745332.79510.81680.51250.3660
Mean2715.942023991565.26494879.83460.82890.45450.3218
Std231.86604212892.9107422.82350.04910.06470.0504
\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "", "version_major": 2, "version_minor": 0 }, "text/plain": [ "Processing: 0%| | 0/6 [00:00#sk-container-id-11 {color: black;background-color: white;}#sk-container-id-11 pre{padding: 0;}#sk-container-id-11 div.sk-toggleable {background-color: white;}#sk-container-id-11 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-11 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-11 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-11 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-11 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-11 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-11 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-11 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-11 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-11 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-11 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-11 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-11 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-11 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-11 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-11 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-11 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-11 div.sk-item {position: relative;z-index: 1;}#sk-container-id-11 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-11 div.sk-item::before, #sk-container-id-11 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-11 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-11 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-11 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-11 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-11 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-11 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-11 div.sk-label-container {text-align: center;}#sk-container-id-11 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-11 div.sk-text-repr-fallback {display: none;}
VotingRegressor(estimators=[('Gradient Boosting Regressor',\n",
       "                             GradientBoostingRegressor(random_state=123)),\n",
       "                            ('Random Forest Regressor',\n",
       "                             RandomForestRegressor(n_jobs=-1,\n",
       "                                                   random_state=123)),\n",
       "                            ('Extra Trees Regressor',\n",
       "                             ExtraTreesRegressor(n_jobs=-1, random_state=123))],\n",
       "                n_jobs=-1)
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
" ], "text/plain": [ "VotingRegressor(estimators=[('Gradient Boosting Regressor',\n", " GradientBoostingRegressor(random_state=123)),\n", " ('Random Forest Regressor',\n", " RandomForestRegressor(n_jobs=-1,\n", " random_state=123)),\n", " ('Extra Trees Regressor',\n", " ExtraTreesRegressor(n_jobs=-1, random_state=123))],\n", " n_jobs=-1)" ] }, "execution_count": 59, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# blend top 3 models\n", "blend_models(best_mae_models_top3)" ] }, { "attachments": {}, "cell_type": "markdown", "id": "9e788c9c", "metadata": {}, "source": [ "Some other parameters that you might find very useful in `blend_models` are:\n", "\n", "- choose_better\n", "- weights\n", "- optimize\n", "- fit_kwargs\n", "- return_train_score\n", "\n", "You can check the docstring of the function for more info." ] }, { "cell_type": "code", "execution_count": null, "id": "99b549a6", "metadata": {}, "outputs": [], "source": [ "# help(blend_models)" ] }, { "attachments": {}, "cell_type": "markdown", "id": "e76969b0", "metadata": {}, "source": [ "## ✅ Stack Models" ] }, { "attachments": {}, "cell_type": "markdown", "id": "55909804", "metadata": {}, "source": [ "The `stack_models` function trains a meta-model over select estimators passed in the estimator_list parameter. The output of this function is a scoring grid with CV scores by fold. Metrics evaluated during CV can be accessed using the `get_metrics` function. Custom metrics can be added or removed using `add_metric` and `remove_metric` function." ] }, { "cell_type": "code", "execution_count": null, "id": "201c681e", "metadata": {}, "outputs": [ { "data": { "text/html": [], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
 MAEMSERMSER2RMSLEMAPE
Fold      
02609.688419941923.01914465.63800.88090.43880.3216
12980.408331017277.78545569.31570.81970.47510.2922
22546.149422498470.10824743.25520.71510.49240.2973
32847.566221076820.86844590.94990.82400.47270.3775
42921.537728163259.16695306.90670.79050.52150.3215
52677.530619787391.31404448.30210.87270.39980.2686
62369.611820267877.62704501.98600.86210.33400.2382
72693.070324841785.80674984.15350.86340.43400.2560
82229.684017762684.40814214.58000.88530.37650.2832
93001.638727582761.21655251.92930.82230.51550.3513
Mean2687.688523294025.13204807.70160.83360.44600.3007
Std245.29304159112.4380424.29950.04940.05820.0408
\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "", "version_major": 2, "version_minor": 0 }, "text/plain": [ "Processing: 0%| | 0/6 [00:00#sk-container-id-13 {color: black;background-color: white;}#sk-container-id-13 pre{padding: 0;}#sk-container-id-13 div.sk-toggleable {background-color: white;}#sk-container-id-13 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-13 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-13 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-13 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-13 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-13 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-13 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-13 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-13 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-13 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-13 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-13 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-13 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-13 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-13 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-13 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-13 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-13 div.sk-item {position: relative;z-index: 1;}#sk-container-id-13 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-13 div.sk-item::before, #sk-container-id-13 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-13 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-13 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-13 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-13 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-13 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-13 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-13 div.sk-label-container {text-align: center;}#sk-container-id-13 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-13 div.sk-text-repr-fallback {display: none;}
StackingRegressor(cv=5,\n",
       "                  estimators=[('Gradient Boosting Regressor',\n",
       "                               GradientBoostingRegressor(random_state=123)),\n",
       "                              ('Random Forest Regressor',\n",
       "                               RandomForestRegressor(n_jobs=-1,\n",
       "                                                     random_state=123)),\n",
       "                              ('Extra Trees Regressor',\n",
       "                               ExtraTreesRegressor(n_jobs=-1,\n",
       "                                                   random_state=123))],\n",
       "                  final_estimator=LinearRegression(n_jobs=-1), n_jobs=-1,\n",
       "                  passthrough=True)
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
" ], "text/plain": [ "StackingRegressor(cv=5,\n", " estimators=[('Gradient Boosting Regressor',\n", " GradientBoostingRegressor(random_state=123)),\n", " ('Random Forest Regressor',\n", " RandomForestRegressor(n_jobs=-1,\n", " random_state=123)),\n", " ('Extra Trees Regressor',\n", " ExtraTreesRegressor(n_jobs=-1,\n", " random_state=123))],\n", " final_estimator=LinearRegression(n_jobs=-1), n_jobs=-1,\n", " passthrough=True)" ] }, "execution_count": 67, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# stack models\n", "stack_models(best_mae_models_top3)" ] }, { "attachments": {}, "cell_type": "markdown", "id": "af78cda8", "metadata": {}, "source": [ "Some other parameters that you might find very useful in `stack_models` are:\n", "\n", "- choose_better\n", "- meta_model\n", "- restack\n", "- optimize\n", "- return_train_score\n", "\n", "You can check the docstring of the function for more info." ] }, { "cell_type": "code", "execution_count": null, "id": "3305e597", "metadata": {}, "outputs": [], "source": [ "# help(stack_models)" ] }, { "attachments": {}, "cell_type": "markdown", "id": "279a3127", "metadata": {}, "source": [ "## ✅ Plot Model" ] }, { "attachments": {}, "cell_type": "markdown", "id": "862bd3e9", "metadata": {}, "source": [ "The `plot_model` function analyzes the performance of a trained model on the hold-out set. It may require re-training the model in certain cases." ] }, { "cell_type": "code", "execution_count": null, "id": "9c8da9b4", "metadata": {}, "outputs": [ { "data": { "text/html": [], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "# plot residuals\n", "plot_model(best, plot = 'residuals')" ] }, { "cell_type": "code", "execution_count": null, "id": "952b6f24", "metadata": {}, "outputs": [ { "data": { "text/html": [], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "# to control the scale of plot\n", "plot_model(best, plot = 'residuals', scale = 2)" ] }, { "cell_type": "code", "execution_count": null, "id": "293e4d15", "metadata": {}, "outputs": [ { "data": { "text/html": [], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/plain": [ "'Residuals.png'" ] }, "execution_count": 71, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# to save the plot\n", "plot_model(best, plot = 'residuals', save=True)" ] }, { "attachments": {}, "cell_type": "markdown", "id": "2fef279d", "metadata": {}, "source": [ "Some other parameters that you might find very useful in `plot_model` are:\n", "\n", "- fit_kwargs\n", "- plot_kwargs\n", "- groups\n", "- display_format\n", "\n", "You can check the docstring of the function for more info." ] }, { "cell_type": "code", "execution_count": null, "id": "54b09b8e", "metadata": {}, "outputs": [], "source": [ "# help(plot_model)" ] }, { "attachments": {}, "cell_type": "markdown", "id": "b724ca46", "metadata": {}, "source": [ "## ✅ Interpret Model" ] }, { "attachments": {}, "cell_type": "markdown", "id": "52f8fb33", "metadata": {}, "source": [ "The `interpret_model` function analyzes the predictions generated from a trained model. Most plots in this function are implemented based on the SHAP (Shapley Additive exPlanations). For more info on this, please see https://shap.readthedocs.io/en/latest/" ] }, { "cell_type": "code", "execution_count": null, "id": "6b6891b7", "metadata": {}, "outputs": [ { "data": { "text/html": [], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
 MAEMSERMSER2RMSLEMAPE
Fold      
02896.496423611929.40134859.21080.85900.59930.3808
13075.941930047230.74865481.53540.82530.46220.3295
23096.018527757739.18785268.56140.64860.61590.4550
33347.314426993115.82475195.49000.77460.81060.5509
43263.766029391206.78435421.36580.78140.56280.3846
52922.537221672554.75964655.37910.86060.41700.2881
62733.807121012815.38654583.97380.85700.39910.3139
72865.579625843408.71325083.64130.85790.50270.2995
82715.568021671018.59294655.21410.86000.52330.4192
93101.854727472226.41395241.39550.82300.55210.3621
Mean3001.888425547324.58135044.57670.81470.54450.3784
Std200.51633164504.0885315.54780.06350.11210.0765
\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "", "version_major": 2, "version_minor": 0 }, "text/plain": [ "Processing: 0%| | 0/4 [00:00" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "# interpret summary model\n", "interpret_model(lightgbm, plot = 'summary')" ] }, { "cell_type": "code", "execution_count": null, "id": "824bafdc", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "\n", "
\n", "
\n", " Visualization omitted, Javascript library not loaded!
\n", " Have you run `initjs()` in this notebook? If this notebook was from another\n", " user you must also trust this notebook (File -> Trust notebook). If you are viewing\n", " this notebook on github the Javascript has been stripped for security. If you are using\n", " JupyterLab this error is because a JupyterLab extension has not yet been written.\n", "
\n", " " ], "text/plain": [ "" ] }, "execution_count": 75, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# reason plot for test set observation 1\n", "interpret_model(lightgbm, plot = 'reason', observation = 1)" ] }, { "attachments": {}, "cell_type": "markdown", "id": "ca7ce2b4", "metadata": {}, "source": [ "Some other parameters that you might find very useful in `interpret_model` are:\n", "\n", "- plot\n", "- feature\n", "- use_train_data\n", "- X_new_sample\n", "- y_new_sample\n", "- save\n", "\n", "You can check the docstring of the function for more info." ] }, { "cell_type": "code", "execution_count": null, "id": "42595030", "metadata": {}, "outputs": [], "source": [ "# help(interpret_model)" ] }, { "attachments": {}, "cell_type": "markdown", "id": "9f57d0c8", "metadata": {}, "source": [ "## ✅ Get Leaderboard" ] }, { "attachments": {}, "cell_type": "markdown", "id": "ec63b67a", "metadata": {}, "source": [ "This function returns the leaderboard of all models trained in the current setup." ] }, { "cell_type": "code", "execution_count": null, "id": "307a6e3c", "metadata": {}, "outputs": [ { "data": { "text/html": [], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "", "version_major": 2, "version_minor": 0 }, "text/plain": [ "Processing: 0%| | 0/67 [00:00\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
Model NameModelMAEMSERMSER2RMSLEMAPE
Index
0Linear Regression(TransformerWrapper(include=['age', 'bmi', 'ch...4312.61863.845275e+076182.47960.72980.62850.4460
1Lasso Regression(TransformerWrapper(include=['age', 'bmi', 'ch...4302.24693.838653e+076176.44630.73060.59130.4430
2Ridge Regression(TransformerWrapper(include=['age', 'bmi', 'ch...4296.06423.839300e+076176.61600.73080.57100.4397
3Elastic Net(TransformerWrapper(include=['age', 'bmi', 'ch...7571.45981.047380e+0810182.32910.28460.89541.2888
4Least Angle Regression(TransformerWrapper(include=['age', 'bmi', 'ch...4303.55593.838806e+076176.59200.73060.59490.4433
...........................
61Decision Tree Regressor(TransformerWrapper(include=['age', 'bmi', 'ch...2343.14472.955617e+075420.45320.78380.45250.2311
62Voting Regressor(TransformerWrapper(include=['age', 'bmi', 'ch...2715.94202.399157e+074879.83460.82890.45450.3218
63Stacking Regressor(TransformerWrapper(include=['age', 'bmi', 'ch...2687.68852.329403e+074807.70160.83360.44600.3007
64Stacking Regressor(TransformerWrapper(include=['age', 'bmi', 'ch...2687.68852.329403e+074807.70160.83360.44600.3007
65Light Gradient Boosting Machine(TransformerWrapper(include=['age', 'bmi', 'ch...3001.88842.554732e+075044.57670.81470.54450.3784
\n", "

66 rows × 8 columns

\n", "" ], "text/plain": [ " Model Name \\\n", "Index \n", "0 Linear Regression \n", "1 Lasso Regression \n", "2 Ridge Regression \n", "3 Elastic Net \n", "4 Least Angle Regression \n", "... ... \n", "61 Decision Tree Regressor \n", "62 Voting Regressor \n", "63 Stacking Regressor \n", "64 Stacking Regressor \n", "65 Light Gradient Boosting Machine \n", "\n", " Model MAE \\\n", "Index \n", "0 (TransformerWrapper(include=['age', 'bmi', 'ch... 4312.6186 \n", "1 (TransformerWrapper(include=['age', 'bmi', 'ch... 4302.2469 \n", "2 (TransformerWrapper(include=['age', 'bmi', 'ch... 4296.0642 \n", "3 (TransformerWrapper(include=['age', 'bmi', 'ch... 7571.4598 \n", "4 (TransformerWrapper(include=['age', 'bmi', 'ch... 4303.5559 \n", "... ... ... \n", "61 (TransformerWrapper(include=['age', 'bmi', 'ch... 2343.1447 \n", "62 (TransformerWrapper(include=['age', 'bmi', 'ch... 2715.9420 \n", "63 (TransformerWrapper(include=['age', 'bmi', 'ch... 2687.6885 \n", "64 (TransformerWrapper(include=['age', 'bmi', 'ch... 2687.6885 \n", "65 (TransformerWrapper(include=['age', 'bmi', 'ch... 3001.8884 \n", "\n", " MSE RMSE R2 RMSLE MAPE \n", "Index \n", "0 3.845275e+07 6182.4796 0.7298 0.6285 0.4460 \n", "1 3.838653e+07 6176.4463 0.7306 0.5913 0.4430 \n", "2 3.839300e+07 6176.6160 0.7308 0.5710 0.4397 \n", "3 1.047380e+08 10182.3291 0.2846 0.8954 1.2888 \n", "4 3.838806e+07 6176.5920 0.7306 0.5949 0.4433 \n", "... ... ... ... ... ... \n", "61 2.955617e+07 5420.4532 0.7838 0.4525 0.2311 \n", "62 2.399157e+07 4879.8346 0.8289 0.4545 0.3218 \n", "63 2.329403e+07 4807.7016 0.8336 0.4460 0.3007 \n", "64 2.329403e+07 4807.7016 0.8336 0.4460 0.3007 \n", "65 2.554732e+07 5044.5767 0.8147 0.5445 0.3784 \n", "\n", "[66 rows x 8 columns]" ] }, "execution_count": 77, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# get leaderboard\n", "lb = get_leaderboard()\n", "lb" ] }, { "cell_type": "code", "execution_count": null, "id": "f8a8b060", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
Pipeline(memory=FastMemory(location=C:\\Users\\owner\\AppData\\Local\\Temp\\joblib),\n",
       "         steps=[('numerical_imputer',\n",
       "                 TransformerWrapper(include=['age', 'bmi', 'children'],\n",
       "                                    transformer=SimpleImputer())),\n",
       "                ('categorical_imputer',\n",
       "                 TransformerWrapper(include=['sex', 'smoker', 'region'],\n",
       "                                    transformer=SimpleImputer(strategy='most_frequent'))),\n",
       "                ('ordinal_encoding',\n",
       "                 TransformerW...\n",
       "                                                                         'mapping': {nan: -1,\n",
       "                                                                                     'female': 0,\n",
       "                                                                                     'male': 1}},\n",
       "                                                                        {'col': 'smoker',\n",
       "                                                                         'mapping': {nan: -1,\n",
       "                                                                                     'no': 0,\n",
       "                                                                                     'yes': 1}}]))),\n",
       "                ('onehot_encoding',\n",
       "                 TransformerWrapper(include=['region'],\n",
       "                                    transformer=OneHotEncoder(cols=['region'],\n",
       "                                                              handle_missing='return_nan',\n",
       "                                                              use_cat_names=True))),\n",
       "                ('normalize', TransformerWrapper(transformer=MinMaxScaler())),\n",
       "                ['trained_model', LinearRegression(n_jobs=-1)]])
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
" ], "text/plain": [ "Pipeline(memory=FastMemory(location=C:\\Users\\owner\\AppData\\Local\\Temp\\joblib),\n", " steps=[('numerical_imputer',\n", " TransformerWrapper(include=['age', 'bmi', 'children'],\n", " transformer=SimpleImputer())),\n", " ('categorical_imputer',\n", " TransformerWrapper(include=['sex', 'smoker', 'region'],\n", " transformer=SimpleImputer(strategy='most_frequent'))),\n", " ('ordinal_encoding',\n", " TransformerW...\n", " 'mapping': {nan: -1,\n", " 'female': 0,\n", " 'male': 1}},\n", " {'col': 'smoker',\n", " 'mapping': {nan: -1,\n", " 'no': 0,\n", " 'yes': 1}}]))),\n", " ('onehot_encoding',\n", " TransformerWrapper(include=['region'],\n", " transformer=OneHotEncoder(cols=['region'],\n", " handle_missing='return_nan',\n", " use_cat_names=True))),\n", " ('normalize', TransformerWrapper(transformer=MinMaxScaler())),\n", " ['trained_model', LinearRegression(n_jobs=-1)]])" ] }, "execution_count": 78, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# select the best model based on MAE\n", "lb.sort_values(by='MAE', ascending=True)['Model'].iloc[0]" ] }, { "attachments": {}, "cell_type": "markdown", "id": "9ecf0bfa", "metadata": {}, "source": [ "Some other parameters that you might find very useful in `get_leaderboard` are:\n", "\n", "- finalize_models\n", "- fit_kwargs\n", "- model_only\n", "- groups\n", "\n", "You can check the docstring of the function for more info." ] }, { "cell_type": "code", "execution_count": null, "id": "dc76f0a5", "metadata": {}, "outputs": [], "source": [ "# help(get_leaderboard)" ] }, { "attachments": {}, "cell_type": "markdown", "id": "94669c72", "metadata": {}, "source": [ "## ✅ AutoML\n", "This function returns the best model out of all trained models in the current setup based on the optimize parameter. Metrics evaluated can be accessed using the `get_metrics` function." ] }, { "cell_type": "code", "execution_count": null, "id": "01532054", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
DecisionTreeRegressor(max_depth=4, random_state=123)
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
" ], "text/plain": [ "DecisionTreeRegressor(max_depth=4, random_state=123)" ] }, "execution_count": 80, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# find best model based on CV metrics\n", "automl()" ] }, { "attachments": {}, "cell_type": "markdown", "id": "726b2986", "metadata": {}, "source": [ "## ✅ Dashboard\n", "The dashboard function generates the interactive dashboard for a trained model. The dashboard is implemented using `ExplainerDashboard`. For more information check out [Explainer Dashboard.](explainerdashboard.readthedocs.io)" ] }, { "cell_type": "code", "execution_count": null, "id": "ca75507d", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Generating self.shap_explainer = shap.TreeExplainer(model)\n", "Building ExplainerDashboard..\n", "The explainer object has no decision_trees property. so setting decision_trees=False...\n", "Warning: calculating shap interaction values can be slow! Pass shap_interaction=False to remove interactions tab.\n", "Generating layout...\n", "Calculating shap values...\n", "Calculating predictions...\n", "Calculating residuals...\n", "Calculating absolute residuals...\n", "Calculating shap interaction values...\n", "Reminder: TreeShap computational complexity is O(TLD^2), where T is the number of trees, L is the maximum number of leaves in any tree and D the maximal depth of any tree. So reducing these will speed up the calculation.\n", "Calculating dependencies...\n", "Calculating importances...\n", "Reminder: you can store the explainer (including calculated dependencies) with explainer.dump('explainer.joblib') and reload with e.g. ClassifierExplainer.from_file('explainer.joblib')\n", "Registering callbacks...\n", "Starting ExplainerDashboard inline (terminate it with ExplainerDashboard.terminate(8050))\n" ] }, { "data": { "text/html": [ "\n", " \n", " " ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "# dashboard function\n", "dashboard(dt, display_format ='inline')" ] }, { "attachments": {}, "cell_type": "markdown", "id": "58fd3e5a", "metadata": {}, "source": [ "## ✅Create App\n", "This function creates a basic gradio app for inference." ] }, { "cell_type": "code", "execution_count": null, "id": "5cf989d3", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Running on local URL: http://127.0.0.1:7860\n", "\n", "To create a public link, set `share=True` in `launch()`.\n" ] }, { "data": { "text/html": [ "
" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/plain": [] }, "execution_count": 84, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# create gradio app\n", "create_app(best)" ] }, { "attachments": {}, "cell_type": "markdown", "id": "a2d8e21d", "metadata": {}, "source": [ "## ✅ Create API\n", "This function takes an input model and creates a POST API for inference." ] }, { "cell_type": "code", "execution_count": null, "id": "978413c9", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "API successfully created. This function only creates a POST API, it doesn't run it automatically. To run your API, please run this command --> !python my_first_api.py\n" ] } ], "source": [ "# create api\n", "create_api(best, api_name = 'my_first_api')" ] }, { "cell_type": "code", "execution_count": null, "id": "68e539aa", "metadata": {}, "outputs": [], "source": [ "# !python my_first_api.py" ] }, { "cell_type": "code", "execution_count": null, "id": "a3de3327", "metadata": {}, "outputs": [], "source": [ "# check out the .py file created with this magic command\n", "# %load my_first_api.py" ] }, { "attachments": {}, "cell_type": "markdown", "id": "1023f7df", "metadata": {}, "source": [ "## ✅ Create Docker\n", "This function creates a `Dockerfile` and `requirements.txt` for productionalizing API end-point." ] }, { "cell_type": "code", "execution_count": null, "id": "452ced14", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Writing requirements.txt\n", "Writing Dockerfile\n", "Dockerfile and requirements.txt successfully created.\n", " To build image you have to run --> !docker image build -f \"Dockerfile\" -t IMAGE_NAME:IMAGE_TAG .\n", " \n" ] } ], "source": [ "create_docker('my_first_api')" ] }, { "cell_type": "code", "execution_count": null, "id": "301e1fa5", "metadata": {}, "outputs": [], "source": [ "# check out the DockerFile file created with this magic command\n", "# %load DockerFile" ] }, { "cell_type": "code", "execution_count": null, "id": "ca1e9ef7", "metadata": {}, "outputs": [], "source": [ "# check out the requirements file created with this magic command\n", "# %load requirements.txt" ] }, { "attachments": {}, "cell_type": "markdown", "id": "e27c212b", "metadata": {}, "source": [ "## ✅ Finalize Model\n", "This function trains a given model on the entire dataset including the hold-out set." ] }, { "cell_type": "code", "execution_count": null, "id": "65225684", "metadata": {}, "outputs": [], "source": [ "final_best = finalize_model(best)" ] }, { "cell_type": "code", "execution_count": null, "id": "80d17fec", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
Pipeline(memory=FastMemory(location=C:\\Users\\owner\\AppData\\Local\\Temp\\joblib),\n",
       "         steps=[('numerical_imputer',\n",
       "                 TransformerWrapper(include=['age', 'bmi', 'children'],\n",
       "                                    transformer=SimpleImputer())),\n",
       "                ('categorical_imputer',\n",
       "                 TransformerWrapper(include=['sex', 'smoker', 'region'],\n",
       "                                    transformer=SimpleImputer(strategy='most_frequent'))),\n",
       "                ('ordinal_encoding',\n",
       "                 TransformerW...\n",
       "                                                                                     'female': 0,\n",
       "                                                                                     'male': 1}},\n",
       "                                                                        {'col': 'smoker',\n",
       "                                                                         'mapping': {nan: -1,\n",
       "                                                                                     'no': 0,\n",
       "                                                                                     'yes': 1}}]))),\n",
       "                ('onehot_encoding',\n",
       "                 TransformerWrapper(include=['region'],\n",
       "                                    transformer=OneHotEncoder(cols=['region'],\n",
       "                                                              handle_missing='return_nan',\n",
       "                                                              use_cat_names=True))),\n",
       "                ('normalize', TransformerWrapper(transformer=MinMaxScaler())),\n",
       "                ('actual_estimator',\n",
       "                 GradientBoostingRegressor(random_state=123))])
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
" ], "text/plain": [ "Pipeline(memory=FastMemory(location=C:\\Users\\owner\\AppData\\Local\\Temp\\joblib),\n", " steps=[('numerical_imputer',\n", " TransformerWrapper(include=['age', 'bmi', 'children'],\n", " transformer=SimpleImputer())),\n", " ('categorical_imputer',\n", " TransformerWrapper(include=['sex', 'smoker', 'region'],\n", " transformer=SimpleImputer(strategy='most_frequent'))),\n", " ('ordinal_encoding',\n", " TransformerW...\n", " 'female': 0,\n", " 'male': 1}},\n", " {'col': 'smoker',\n", " 'mapping': {nan: -1,\n", " 'no': 0,\n", " 'yes': 1}}]))),\n", " ('onehot_encoding',\n", " TransformerWrapper(include=['region'],\n", " transformer=OneHotEncoder(cols=['region'],\n", " handle_missing='return_nan',\n", " use_cat_names=True))),\n", " ('normalize', TransformerWrapper(transformer=MinMaxScaler())),\n", " ('actual_estimator',\n", " GradientBoostingRegressor(random_state=123))])" ] }, "execution_count": 92, "metadata": {}, "output_type": "execute_result" } ], "source": [ "final_best" ] }, { "attachments": {}, "cell_type": "markdown", "id": "b4693f88", "metadata": {}, "source": [ "## ✅ Convert Model\n", "This function transpiles the trained machine learning model's decision function in different programming languages such as Python, C, Java, Go, C#, etc. It is very useful if you want to deploy models into environments where you can't install your normal Python stack to support model inference." ] }, { "cell_type": "code", "execution_count": null, "id": "dbe0e9fe", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "public class Model {\n", " public static double score(double[] input) {\n", " double var0;\n", " if (input[4] <= 0.5) {\n", " if (input[0] <= 0.554347813129425) {\n", " if (input[3] <= 0.10000000149011612) {\n", " if (input[0] <= 0.31521739065647125) {\n", " if (input[0] <= 0.09782608598470688) {\n", " if (input[2] <= 0.39116452634334564) {\n", " if (input[0] <= 0.0326086962595582) {\n", " if (input[1] <= 0.5) {\n", " if (input[5] <= 0.5) {\n", " if (input[8] <= 0.5) {\n", " if (input[0] <= 0.010869565419852734) {\n", " if (input[2] <= 0.19418424367904663) {\n", " var0 = 1607.5101318359375;\n", " } else {\n", " var0 = 1615.7667236328125;\n", " }\n", " } else {\n", " if (input[2] <= 0.16314832866191864) {\n", " if (input[2] <= 0.07786941900849342) {\n", " if (input[2] <= 0.03872498869895935) {\n", " var0 = 1727.7850341796875;\n", " } else {\n", " var0 = 1728.89697265625;\n", " }\n", " } else {\n", " var0 = 1731.677001953125;\n", " }\n", " } else {\n", " if (input[2] <= 0.2791835367679596) {\n", " var0 = 1737.3759765625;\n", " } else {\n", " var0 = 1743.2139892578125;\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[2] <= 0.2709352597594261) {\n", " var0 = 2117.3388671875;\n", " } else {\n", " var0 = 2128.43115234375;\n", " }\n", " }\n", " } else {\n", " if (input[2] <= 0.2749195843935013) {\n", " var0 = 2196.47314453125;\n", " } else {\n", " if (input[2] <= 0.34530963003635406) {\n", " var0 = 2200.830810546875;\n", " } else {\n", " if (input[2] <= 0.3745281547307968) {\n", " var0 = 2203.471923828125;\n", " } else {\n", " var0 = 2203.73583984375;\n", " }\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[6] <= 0.5) {\n", " if (input[7] <= 0.5) {\n", " if (input[8] <= 0.5) {\n", " if (input[2] <= 0.28421637415885925) {\n", " if (input[2] <= 0.21781067550182343) {\n", " if (input[2] <= 0.1846078261733055) {\n", " if (input[2] <= 0.1739829108119011) {\n", " var0 = 1704.568115234375;\n", " } else {\n", " var0 = 1704.7001953125;\n", " }\n", " } else {\n", " var0 = 1705.62451171875;\n", " }\n", " } else {\n", " var0 = 1708.0013427734375;\n", " }\n", " } else {\n", " var0 = 1712.22705078125;\n", " }\n", " } else {\n", " if (input[2] <= 0.19788897037506104) {\n", " if (input[2] <= 0.07835869677364826) {\n", " var0 = 1621.3402099609375;\n", " } else {\n", " if (input[2] <= 0.15007686614990234) {\n", " var0 = 1627.282470703125;\n", " } else {\n", " var0 = 1628.470947265625;\n", " }\n", " }\n", " } else {\n", " if (input[2] <= 0.3466377407312393) {\n", " if (input[2] <= 0.27624770253896713) {\n", " if (input[2] <= 0.23906050622463226) {\n", " var0 = 1632.0362548828125;\n", " } else {\n", " var0 = 1632.564453125;\n", " }\n", " } else {\n", " var0 = 1635.733642578125;\n", " }\n", " } else {\n", " var0 = 1639.5631103515625;\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[2] <= 0.2756884768605232) {\n", " var0 = 1121.8739013671875;\n", " } else {\n", " var0 = 1131.506591796875;\n", " }\n", " }\n", " } else {\n", " if (input[2] <= 0.205088771879673) {\n", " if (input[2] <= 0.09045151993632317) {\n", " var0 = 1241.56494140625;\n", " } else {\n", " if (input[2] <= 0.10303367301821709) {\n", " var0 = 1242.260009765625;\n", " } else {\n", " var0 = 1242.8160400390625;\n", " }\n", " }\n", " } else {\n", " if (input[2] <= 0.35607434809207916) {\n", " if (input[2] <= 0.3169299513101578) {\n", " var0 = 1252.406982421875;\n", " } else {\n", " var0 = 1253.93603515625;\n", " }\n", " } else {\n", " var0 = 1256.2989501953125;\n", " }\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[2] <= 0.19362502545118332) {\n", " if (input[8] <= 0.5) {\n", " var0 = 2731.912109375;\n", " } else {\n", " var0 = 2527.818603515625;\n", " }\n", " } else {\n", " if (input[2] <= 0.3713127076625824) {\n", " if (input[1] <= 0.5) {\n", " if (input[2] <= 0.3487347811460495) {\n", " if (input[0] <= 0.0652173925191164) {\n", " var0 = 2257.475341796875;\n", " } else {\n", " if (input[2] <= 0.24842720478773117) {\n", " var0 = 2150.468994140625;\n", " } else {\n", " if (input[6] <= 0.5) {\n", " if (input[2] <= 0.3248986005783081) {\n", " var0 = 2155.681396484375;\n", " } else {\n", " var0 = 2156.751708984375;\n", " }\n", " } else {\n", " var0 = 2154.361083984375;\n", " }\n", " }\n", " }\n", " } else {\n", " var0 = 1875.343994140625;\n", " }\n", " } else {\n", " if (input[7] <= 0.5) {\n", " if (input[2] <= 0.3386690616607666) {\n", " if (input[2] <= 0.3240597993135452) {\n", " if (input[2] <= 0.3028099983930588) {\n", " if (input[5] <= 0.5) {\n", " var0 = 2045.685302734375;\n", " } else {\n", " if (input[2] <= 0.2762477248907089) {\n", " var0 = 2102.2646484375;\n", " } else {\n", " var0 = 2104.11328125;\n", " }\n", " }\n", " } else {\n", " var0 = 1967.022705078125;\n", " }\n", " } else {\n", " var0 = 2250.835205078125;\n", " }\n", " } else {\n", " var0 = 1906.3582763671875;\n", " }\n", " } else {\n", " var0 = 1664.9996337890625;\n", " }\n", " }\n", " } else {\n", " var0 = 2459.72021484375;\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[2] <= 0.3982944041490555) {\n", " var0 = 16586.498046875;\n", " } else {\n", " if (input[0] <= 0.0326086962595582) {\n", " if (input[6] <= 0.5) {\n", " if (input[2] <= 0.6337200701236725) {\n", " if (input[2] <= 0.5986298620700836) {\n", " if (input[2] <= 0.4802180528640747) {\n", " if (input[2] <= 0.4670068174600601) {\n", " if (input[5] <= 0.5) {\n", " var0 = 1622.1884765625;\n", " } else {\n", " if (input[2] <= 0.439605712890625) {\n", " var0 = 2205.980712890625;\n", " } else {\n", " var0 = 2207.697509765625;\n", " }\n", " }\n", " } else {\n", " var0 = 11482.634765625;\n", " }\n", " } else {\n", " if (input[1] <= 0.5) {\n", " if (input[0] <= 0.010869565419852734) {\n", " if (input[2] <= 0.5786382555961609) {\n", " var0 = 1629.83349609375;\n", " } else {\n", " var0 = 1631.6683349609375;\n", " }\n", " } else {\n", " if (input[2] <= 0.5325737297534943) {\n", " var0 = 2134.901611328125;\n", " } else {\n", " var0 = 2136.88232421875;\n", " }\n", " }\n", " } else {\n", " if (input[8] <= 0.5) {\n", " if (input[2] <= 0.5325038284063339) {\n", " if (input[2] <= 0.48790712654590607) {\n", " var0 = 1137.010986328125;\n", " } else {\n", " var0 = 1137.4697265625;\n", " }\n", " } else {\n", " var0 = 1141.445068359375;\n", " }\n", " } else {\n", " var0 = 1646.4296875;\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[5] <= 0.5) {\n", " var0 = 7882.429626464844;\n", " } else {\n", " var0 = 12890.0576171875;\n", " }\n", " }\n", " } else {\n", " if (input[2] <= 0.6678316295146942) {\n", " if (input[5] <= 0.5) {\n", " if (input[2] <= 0.6493778228759766) {\n", " var0 = 1633.9617919921875;\n", " } else {\n", " var0 = 1634.5733642578125;\n", " }\n", " } else {\n", " var0 = 2217.46923828125;\n", " }\n", " } else {\n", " if (input[2] <= 0.7062770128250122) {\n", " var0 = 1146.796630859375;\n", " } else {\n", " var0 = 1149.3958740234375;\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[2] <= 0.4525373727083206) {\n", " var0 = 1748.7740478515625;\n", " } else {\n", " var0 = 23082.955078125;\n", " }\n", " }\n", " } else {\n", " if (input[1] <= 0.5) {\n", " if (input[8] <= 0.5) {\n", " if (input[0] <= 0.05434782616794109) {\n", " if (input[2] <= 0.435201957821846) {\n", " var0 = 1877.929443359375;\n", " } else {\n", " var0 = 1880.487060546875;\n", " }\n", " } else {\n", " if (input[0] <= 0.07608695700764656) {\n", " if (input[6] <= 0.5) {\n", " var0 = 2026.97412109375;\n", " } else {\n", " var0 = 2020.177001953125;\n", " }\n", " } else {\n", " var0 = 2166.73193359375;\n", " }\n", " }\n", " } else {\n", " if (input[2] <= 0.4754648357629776) {\n", " var0 = 2261.56884765625;\n", " } else {\n", " var0 = 2404.73388671875;\n", " }\n", " }\n", " } else {\n", " if (input[7] <= 0.5) {\n", " if (input[6] <= 0.5) {\n", " if (input[0] <= 0.07608695700764656) {\n", " if (input[5] <= 0.5) {\n", " var0 = 1909.5274658203125;\n", " } else {\n", " var0 = 1984.4532470703125;\n", " }\n", " } else {\n", " if (input[8] <= 0.5) {\n", " var0 = 2254.796630859375;\n", " } else {\n", " var0 = 2055.324951171875;\n", " }\n", " }\n", " } else {\n", " if (input[2] <= 0.5168460607528687) {\n", " var0 = 1526.31201171875;\n", " } else {\n", " var0 = 1682.5970458984375;\n", " }\n", " }\n", " } else {\n", " if (input[0] <= 0.05434782616794109) {\n", " var0 = 1391.5286865234375;\n", " } else {\n", " if (input[2] <= 0.541730672121048) {\n", " var0 = 1532.4697265625;\n", " } else {\n", " var0 = 1534.304443359375;\n", " }\n", " }\n", " }\n", " }\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[1] <= 0.5) {\n", " if (input[0] <= 0.16304347664117813) {\n", " if (input[2] <= 0.5949951112270355) {\n", " if (input[2] <= 0.19299592077732086) {\n", " if (input[7] <= 0.5) {\n", " var0 = 2457.501953125;\n", " } else {\n", " var0 = 25081.767578125;\n", " }\n", " } else {\n", " if (input[6] <= 0.5) {\n", " if (input[7] <= 0.5) {\n", " if (input[5] <= 0.5) {\n", " if (input[0] <= 0.14130434393882751) {\n", " if (input[0] <= 0.1195652149617672) {\n", " var0 = 2690.11376953125;\n", " } else {\n", " if (input[2] <= 0.28687261790037155) {\n", " var0 = 2842.7607421875;\n", " } else {\n", " if (input[2] <= 0.4143715798854828) {\n", " var0 = 2850.683837890625;\n", " } else {\n", " var0 = 2855.4375;\n", " }\n", " }\n", " }\n", " } else {\n", " var0 = 3021.80908203125;\n", " }\n", " } else {\n", " if (input[0] <= 0.14130434393882751) {\n", " if (input[0] <= 0.1195652149617672) {\n", " var0 = 2899.4892578125;\n", " } else {\n", " if (input[2] <= 0.2549978941679001) {\n", " var0 = 3044.21337890625;\n", " } else {\n", " var0 = 3046.06201171875;\n", " }\n", " }\n", " } else {\n", " var0 = 3213.6220703125;\n", " }\n", " }\n", " } else {\n", " if (input[2] <= 0.39256255328655243) {\n", " var0 = 2464.618896484375;\n", " } else {\n", " var0 = 2473.333984375;\n", " }\n", " }\n", " } else {\n", " if (input[0] <= 0.14130434393882751) {\n", " if (input[2] <= 0.30714383721351624) {\n", " var0 = 18955.220703125;\n", " } else {\n", " if (input[2] <= 0.3882286995649338) {\n", " var0 = 13126.677734375;\n", " } else {\n", " var0 = 10795.9375;\n", " }\n", " }\n", " } else {\n", " var0 = 2632.991943359375;\n", " }\n", " }\n", " }\n", " } else {\n", " var0 = 17878.900390625;\n", " }\n", " } else {\n", " if (input[0] <= 0.25) {\n", " if (input[6] <= 0.5) {\n", " if (input[0] <= 0.18478260934352875) {\n", " if (input[8] <= 0.5) {\n", " var0 = 3385.399169921875;\n", " } else {\n", " if (input[2] <= 0.4077310189604759) {\n", " if (input[2] <= 0.1567174419760704) {\n", " var0 = 3176.28759765625;\n", " } else {\n", " var0 = 3176.81591796875;\n", " }\n", " } else {\n", " var0 = 3201.2451171875;\n", " }\n", " }\n", " } else {\n", " if (input[7] <= 0.5) {\n", " if (input[0] <= 0.20652173459529877) {\n", " if (input[2] <= 0.1819515898823738) {\n", " var0 = 3353.47021484375;\n", " } else {\n", " var0 = 3558.620361328125;\n", " }\n", " } else {\n", " if (input[2] <= 0.379840612411499) {\n", " if (input[5] <= 0.5) {\n", " var0 = 3736.464599609375;\n", " } else {\n", " var0 = 3732.625;\n", " }\n", " } else {\n", " var0 = 3556.92236328125;\n", " }\n", " }\n", " } else {\n", " if (input[2] <= 0.48944494128227234) {\n", " var0 = 3171.614990234375;\n", " } else {\n", " var0 = 3366.669677734375;\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[0] <= 0.20652173459529877) {\n", " var0 = 2974.1259765625;\n", " } else {\n", " if (input[2] <= 0.35747236013412476) {\n", " var0 = 3161.4541015625;\n", " } else {\n", " var0 = 3172.01806640625;\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[5] <= 0.5) {\n", " if (input[8] <= 0.5) {\n", " if (input[0] <= 0.29347825050354004) {\n", " if (input[2] <= 0.3088214546442032) {\n", " var0 = 3757.8447265625;\n", " } else {\n", " var0 = 3761.2919921875;\n", " }\n", " } else {\n", " if (input[2] <= 0.5088773369789124) {\n", " var0 = 3972.9248046875;\n", " } else {\n", " if (input[6] <= 0.5) {\n", " var0 = 3994.177734375;\n", " } else {\n", " var0 = 3989.841064453125;\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[0] <= 0.29347825050354004) {\n", " var0 = 4134.08251953125;\n", " } else {\n", " var0 = 4357.04345703125;\n", " }\n", " }\n", " } else {\n", " if (input[0] <= 0.27173912525177) {\n", " var0 = 4137.5224609375;\n", " } else {\n", " if (input[2] <= 0.251013558357954) {\n", " var0 = 4544.23486328125;\n", " } else {\n", " var0 = 4347.0234375;\n", " }\n", " }\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[0] <= 0.20652173459529877) {\n", " if (input[0] <= 0.14130434393882751) {\n", " if (input[2] <= 0.24311476945877075) {\n", " if (input[2] <= 0.19390463829040527) {\n", " var0 = 2352.968505859375;\n", " } else {\n", " if (input[2] <= 0.20585765689611435) {\n", " var0 = 2395.171630859375;\n", " } else {\n", " var0 = 2396.095947265625;\n", " }\n", " }\n", " } else {\n", " if (input[0] <= 0.1195652149617672) {\n", " if (input[2] <= 0.5709492415189743) {\n", " if (input[2] <= 0.3556549698114395) {\n", " var0 = 1815.8758544921875;\n", " } else {\n", " var0 = 1824.285400390625;\n", " }\n", " } else {\n", " var0 = 1837.2818603515625;\n", " }\n", " } else {\n", " if (input[2] <= 0.47868023812770844) {\n", " if (input[6] <= 0.5) {\n", " var0 = 1981.5819091796875;\n", " } else {\n", " var0 = 1977.81494140625;\n", " }\n", " } else {\n", " var0 = 1986.933349609375;\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[5] <= 0.5) {\n", " if (input[8] <= 0.5) {\n", " if (input[0] <= 0.18478260934352875) {\n", " if (input[0] <= 0.16304347664117813) {\n", " var0 = 2137.653564453125;\n", " } else {\n", " if (input[7] <= 0.5) {\n", " var0 = 2302.300048828125;\n", " } else {\n", " var0 = 2322.621826171875;\n", " }\n", " }\n", " } else {\n", " if (input[2] <= 0.2791835442185402) {\n", " var0 = 2483.736083984375;\n", " } else {\n", " if (input[2] <= 0.4129735231399536) {\n", " var0 = 2494.02197265625;\n", " } else {\n", " var0 = 2497.038330078125;\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[0] <= 0.16304347664117813) {\n", " var0 = 2534.393798828125;\n", " } else {\n", " if (input[2] <= 0.21117013040930033) {\n", " var0 = 2680.94921875;\n", " } else {\n", " var0 = 2699.568359375;\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[0] <= 0.16304347664117813) {\n", " if (input[2] <= 0.3240597993135452) {\n", " var0 = 2721.32080078125;\n", " } else {\n", " var0 = 2727.39501953125;\n", " }\n", " } else {\n", " if (input[2] <= 0.3054662346839905) {\n", " var0 = 3070.80859375;\n", " } else {\n", " var0 = 2897.323486328125;\n", " }\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[0] <= 0.25) {\n", " if (input[0] <= 0.22826086729764938) {\n", " if (input[2] <= 0.45687122642993927) {\n", " var0 = 3062.50830078125;\n", " } else {\n", " var0 = 3268.8466796875;\n", " }\n", " } else {\n", " if (input[7] <= 0.5) {\n", " var0 = 2866.091064453125;\n", " } else {\n", " var0 = 2867.11962890625;\n", " }\n", " }\n", " } else {\n", " if (input[2] <= 0.170977171510458) {\n", " var0 = 3260.198974609375;\n", " } else {\n", " if (input[0] <= 0.27173912525177) {\n", " var0 = 3645.08935546875;\n", " } else {\n", " if (input[8] <= 0.5) {\n", " var0 = 3857.75927734375;\n", " } else {\n", " var0 = 3866.855224609375;\n", " }\n", " }\n", " }\n", " }\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[2] <= 0.17160630971193314) {\n", " var0 = 21984.470703125;\n", " } else {\n", " if (input[2] <= 0.5073395222425461) {\n", " if (input[0] <= 0.489130437374115) {\n", " if (input[2] <= 0.35942958295345306) {\n", " if (input[0] <= 0.3586956560611725) {\n", " if (input[2] <= 0.24674957990646362) {\n", " var0 = 4992.37646484375;\n", " } else {\n", " var0 = 4415.15869140625;\n", " }\n", " } else {\n", " if (input[0] <= 0.42391303181648254) {\n", " if (input[6] <= 0.5) {\n", " if (input[0] <= 0.4021739065647125) {\n", " if (input[2] <= 0.2935131788253784) {\n", " if (input[2] <= 0.2709352374076843) {\n", " var0 = 5227.98876953125;\n", " } else {\n", " var0 = 5267.818359375;\n", " }\n", " } else {\n", " var0 = 5469.0068359375;\n", " }\n", " } else {\n", " var0 = 5028.146484375;\n", " }\n", " } else {\n", " var0 = 4883.8662109375;\n", " }\n", " } else {\n", " if (input[0] <= 0.45652173459529877) {\n", " var0 = 5383.5361328125;\n", " } else {\n", " var0 = 5415.6611328125;\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[0] <= 0.33695653080940247) {\n", " var0 = 3704.3544921875;\n", " } else {\n", " if (input[1] <= 0.5) {\n", " var0 = 4889.03662109375;\n", " } else {\n", " if (input[7] <= 0.5) {\n", " if (input[0] <= 0.4021739065647125) {\n", " if (input[2] <= 0.4549838900566101) {\n", " var0 = 4402.23291015625;\n", " } else {\n", " var0 = 4518.826171875;\n", " }\n", " } else {\n", " var0 = 4646.7587890625;\n", " }\n", " } else {\n", " if (input[0] <= 0.3695652186870575) {\n", " var0 = 3935.179931640625;\n", " } else {\n", " var0 = 4399.73095703125;\n", " }\n", " }\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[5] <= 0.5) {\n", " if (input[8] <= 0.5) {\n", " if (input[2] <= 0.4406542330980301) {\n", " if (input[0] <= 0.532608687877655) {\n", " if (input[1] <= 0.5) {\n", " if (input[6] <= 0.5) {\n", " var0 = 6185.32080078125;\n", " } else {\n", " var0 = 6186.126953125;\n", " }\n", " } else {\n", " var0 = 5969.72314453125;\n", " }\n", " } else {\n", " var0 = 6250.43505859375;\n", " }\n", " } else {\n", " if (input[7] <= 0.5) {\n", " var0 = 5979.73095703125;\n", " } else {\n", " var0 = 5699.83740234375;\n", " }\n", " }\n", " } else {\n", " if (input[2] <= 0.4276527017354965) {\n", " var0 = 6358.7763671875;\n", " } else {\n", " var0 = 6571.0244140625;\n", " }\n", " }\n", " } else {\n", " var0 = 7325.04833984375;\n", " }\n", " }\n", " } else {\n", " if (input[0] <= 0.43478260934352875) {\n", " if (input[8] <= 0.5) {\n", " if (input[7] <= 0.5) {\n", " var0 = 12404.87890625;\n", " } else {\n", " var0 = 19214.705078125;\n", " }\n", " } else {\n", " var0 = 4320.41064453125;\n", " }\n", " } else {\n", " if (input[0] <= 0.510869562625885) {\n", " if (input[2] <= 0.6970501244068146) {\n", " if (input[0] <= 0.489130437374115) {\n", " var0 = 5438.7490234375;\n", " } else {\n", " var0 = 5709.16455078125;\n", " }\n", " } else {\n", " if (input[5] <= 0.5) {\n", " var0 = 5662.22509765625;\n", " } else {\n", " var0 = 5757.41357421875;\n", " }\n", " }\n", " } else {\n", " var0 = 6474.01318359375;\n", " }\n", " }\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[5] <= 0.5) {\n", " if (input[0] <= 0.44565217196941376) {\n", " if (input[6] <= 0.5) {\n", " if (input[3] <= 0.30000000447034836) {\n", " if (input[0] <= 0.0326086962595582) {\n", " if (input[0] <= 0.010869565419852734) {\n", " if (input[1] <= 0.5) {\n", " if (input[2] <= 0.3879490941762924) {\n", " var0 = 2201.09716796875;\n", " } else {\n", " var0 = 2219.445068359375;\n", " }\n", " } else {\n", " if (input[2] <= 0.32797424495220184) {\n", " var0 = 1711.02685546875;\n", " } else {\n", " if (input[2] <= 0.49405843019485474) {\n", " var0 = 1725.55224609375;\n", " } else {\n", " var0 = 1727.5400390625;\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[1] <= 0.5) {\n", " if (input[2] <= 0.33468475192785263) {\n", " if (input[2] <= 0.23374806344509125) {\n", " if (input[2] <= 0.21648257225751877) {\n", " var0 = 2709.11181640625;\n", " } else {\n", " var0 = 2709.243896484375;\n", " }\n", " } else {\n", " var0 = 2710.82861328125;\n", " }\n", " } else {\n", " var0 = 2719.27978515625;\n", " }\n", " } else {\n", " var0 = 2221.564453125;\n", " }\n", " }\n", " } else {\n", " if (input[0] <= 0.0652173925191164) {\n", " if (input[2] <= 0.4763735383749008) {\n", " var0 = 2362.22900390625;\n", " } else {\n", " var0 = 27724.2890625;\n", " }\n", " } else {\n", " if (input[8] <= 0.5) {\n", " if (input[2] <= 0.6170836985111237) {\n", " if (input[2] <= 0.4094785153865814) {\n", " if (input[2] <= 0.2341674491763115) {\n", " if (input[0] <= 0.2499999925494194) {\n", " var0 = 3561.888916015625;\n", " } else {\n", " var0 = 17626.240234375;\n", " }\n", " } else {\n", " if (input[0] <= 0.4021739065647125) {\n", " if (input[0] <= 0.20652174204587936) {\n", " var0 = 2902.906494140625;\n", " } else {\n", " if (input[0] <= 0.29347825050354004) {\n", " if (input[0] <= 0.260869562625885) {\n", " var0 = 3947.4130859375;\n", " } else {\n", " var0 = 4350.51416015625;\n", " }\n", " } else {\n", " if (input[2] <= 0.28952884674072266) {\n", " var0 = 5002.78271484375;\n", " } else {\n", " if (input[2] <= 0.33873896300792694) {\n", " if (input[2] <= 0.31105828285217285) {\n", " var0 = 4747.052734375;\n", " } else {\n", " var0 = 4779.6025390625;\n", " }\n", " } else {\n", " var0 = 4562.84228515625;\n", " }\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[2] <= 0.3633440434932709) {\n", " var0 = 5974.384765625;\n", " } else {\n", " var0 = 5976.8310546875;\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[0] <= 0.31521739065647125) {\n", " if (input[1] <= 0.5) {\n", " var0 = 18218.162109375;\n", " } else {\n", " var0 = 18963.171875;\n", " }\n", " } else {\n", " var0 = 5245.22705078125;\n", " }\n", " }\n", " } else {\n", " if (input[2] <= 0.8231511116027832) {\n", " if (input[0] <= 0.260869562625885) {\n", " if (input[2] <= 0.6632181704044342) {\n", " var0 = 3471.40966796875;\n", " } else {\n", " var0 = 3238.435791015625;\n", " }\n", " } else {\n", " var0 = 3875.734130859375;\n", " }\n", " } else {\n", " var0 = 2438.05517578125;\n", " }\n", " }\n", " } else {\n", " if (input[0] <= 0.32608695328235626) {\n", " if (input[0] <= 0.18478260934352875) {\n", " if (input[0] <= 0.1304347775876522) {\n", " if (input[0] <= 0.09782608598470688) {\n", " if (input[2] <= 0.3639032244682312) {\n", " var0 = 2639.04296875;\n", " } else {\n", " var0 = 2643.2685546875;\n", " }\n", " } else {\n", " var0 = 2789.057373046875;\n", " }\n", " } else {\n", " if (input[0] <= 0.16304347664117813) {\n", " var0 = 3594.1708984375;\n", " } else {\n", " var0 = 3292.52978515625;\n", " }\n", " }\n", " } else {\n", " if (input[0] <= 0.2391304299235344) {\n", " if (input[2] <= 0.32937224209308624) {\n", " var0 = 4133.6416015625;\n", " } else {\n", " var0 = 3956.071533203125;\n", " }\n", " } else {\n", " if (input[2] <= 0.28156013786792755) {\n", " if (input[0] <= 0.27173912525177) {\n", " var0 = 4032.24072265625;\n", " } else {\n", " var0 = 4239.892578125;\n", " }\n", " } else {\n", " if (input[2] <= 0.32671603560447693) {\n", " if (input[1] <= 0.5) {\n", " var0 = 4527.18310546875;\n", " } else {\n", " var0 = 4454.40283203125;\n", " }\n", " } else {\n", " if (input[2] <= 0.4024185240268707) {\n", " var0 = 4243.58984375;\n", " } else {\n", " var0 = 4462.7216796875;\n", " }\n", " }\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[0] <= 0.41304346919059753) {\n", " if (input[2] <= 0.14874876383692026) {\n", " var0 = 5116.50048828125;\n", " } else {\n", " if (input[2] <= 0.5033551603555679) {\n", " if (input[1] <= 0.5) {\n", " var0 = 5385.337890625;\n", " } else {\n", " if (input[2] <= 0.434293270111084) {\n", " var0 = 5373.3642578125;\n", " } else {\n", " var0 = 5377.4580078125;\n", " }\n", " }\n", " } else {\n", " var0 = 5630.4580078125;\n", " }\n", " }\n", " } else {\n", " if (input[1] <= 0.5) {\n", " var0 = 6373.55712890625;\n", " } else {\n", " var0 = 5855.90234375;\n", " }\n", " }\n", " }\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[0] <= 0.0326086962595582) {\n", " if (input[2] <= 0.27701660990715027) {\n", " if (input[2] <= 0.20033551007509232) {\n", " if (input[7] <= 0.5) {\n", " var0 = 2803.69775390625;\n", " } else {\n", " var0 = 11884.048828125;\n", " }\n", " } else {\n", " var0 = 2304.002197265625;\n", " }\n", " } else {\n", " if (input[1] <= 0.5) {\n", " var0 = 24059.6796875;\n", " } else {\n", " var0 = 22493.66015625;\n", " }\n", " }\n", " } else {\n", " if (input[7] <= 0.5) {\n", " if (input[0] <= 0.1195652149617672) {\n", " if (input[2] <= 0.45687122642993927) {\n", " if (input[2] <= 0.3107786774635315) {\n", " var0 = 14426.07421875;\n", " } else {\n", " var0 = 26018.951171875;\n", " }\n", " } else {\n", " var0 = 3579.82861328125;\n", " }\n", " } else {\n", " if (input[2] <= 0.4595274478197098) {\n", " if (input[0] <= 0.22826086729764938) {\n", " if (input[2] <= 0.3838249295949936) {\n", " if (input[1] <= 0.5) {\n", " if (input[2] <= 0.2855444774031639) {\n", " var0 = 4719.736328125;\n", " } else {\n", " var0 = 4618.080078125;\n", " }\n", " } else {\n", " var0 = 4877.98095703125;\n", " }\n", " } else {\n", " if (input[0] <= 0.18478260934352875) {\n", " var0 = 3877.30419921875;\n", " } else {\n", " var0 = 4058.71240234375;\n", " }\n", " }\n", " } else {\n", " if (input[2] <= 0.40507476031780243) {\n", " if (input[0] <= 0.25) {\n", " var0 = 18157.876953125;\n", " } else {\n", " if (input[0] <= 0.3586956560611725) {\n", " if (input[0] <= 0.29347826540470123) {\n", " var0 = 5693.4306640625;\n", " } else {\n", " var0 = 5261.46923828125;\n", " }\n", " } else {\n", " if (input[1] <= 0.5) {\n", " if (input[2] <= 0.18992029130458832) {\n", " var0 = 6933.2421875;\n", " } else {\n", " if (input[2] <= 0.33999715745449066) {\n", " var0 = 7281.50537109375;\n", " } else {\n", " var0 = 7537.1640625;\n", " }\n", " }\n", " } else {\n", " if (input[3] <= 0.5000000149011612) {\n", " if (input[0] <= 0.42391303181648254) {\n", " if (input[2] <= 0.26163844764232635) {\n", " var0 = 6198.751953125;\n", " } else {\n", " var0 = 6203.90185546875;\n", " }\n", " } else {\n", " if (input[2] <= 0.3280441462993622) {\n", " var0 = 6455.86279296875;\n", " } else {\n", " var0 = 6457.84326171875;\n", " }\n", " }\n", " } else {\n", " if (input[0] <= 0.4021739065647125) {\n", " var0 = 6548.19482421875;\n", " } else {\n", " var0 = 6796.86328125;\n", " }\n", " }\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[2] <= 0.4369495362043381) {\n", " if (input[2] <= 0.4223402440547943) {\n", " var0 = 4433.3876953125;\n", " } else {\n", " var0 = 4433.916015625;\n", " }\n", " } else {\n", " var0 = 5327.400390625;\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[2] <= 0.48210540413856506) {\n", " var0 = 19442.353515625;\n", " } else {\n", " if (input[0] <= 0.3586956560611725) {\n", " var0 = 5989.5234375;\n", " } else {\n", " var0 = 5729.00537109375;\n", " }\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[0] <= 0.31521739065647125) {\n", " if (input[0] <= 0.16304347291588783) {\n", " if (input[1] <= 0.5) {\n", " if (input[0] <= 0.08695651963353157) {\n", " if (input[2] <= 0.2803019508719444) {\n", " var0 = 3180.510009765625;\n", " } else {\n", " var0 = 3056.38818359375;\n", " }\n", " } else {\n", " var0 = 3500.6123046875;\n", " }\n", " } else {\n", " var0 = 2566.470703125;\n", " }\n", " } else {\n", " if (input[0] <= 0.25) {\n", " if (input[0] <= 0.22826086729764938) {\n", " if (input[2] <= 0.3618062138557434) {\n", " var0 = 4340.44091796875;\n", " } else {\n", " var0 = 4449.4619140625;\n", " }\n", " } else {\n", " var0 = 4058.1162109375;\n", " }\n", " } else {\n", " if (input[2] <= 0.5786383152008057) {\n", " if (input[1] <= 0.5) {\n", " var0 = 4949.7587890625;\n", " } else {\n", " var0 = 4837.58251953125;\n", " }\n", " } else {\n", " if (input[1] <= 0.5) {\n", " var0 = 4753.63671875;\n", " } else {\n", " if (input[0] <= 0.29347825050354004) {\n", " if (input[2] <= 0.6847476363182068) {\n", " var0 = 4463.205078125;\n", " } else {\n", " var0 = 4266.166015625;\n", " }\n", " } else {\n", " var0 = 4686.388671875;\n", " }\n", " }\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[3] <= 0.7000000178813934) {\n", " if (input[3] <= 0.5000000149011612) {\n", " if (input[0] <= 0.3804347813129425) {\n", " var0 = 5846.91748046875;\n", " } else {\n", " var0 = 5584.3056640625;\n", " }\n", " } else {\n", " if (input[0] <= 0.3804347813129425) {\n", " var0 = 6184.29931640625;\n", " } else {\n", " var0 = 6435.62353515625;\n", " }\n", " }\n", " } else {\n", " if (input[0] <= 0.3586956560611725) {\n", " var0 = 6653.78857421875;\n", " } else {\n", " var0 = 7243.8134765625;\n", " }\n", " }\n", " }\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[0] <= 0.22826086729764938) {\n", " if (input[3] <= 0.30000000447034836) {\n", " if (input[0] <= 0.10869564861059189) {\n", " if (input[1] <= 0.5) {\n", " if (input[0] <= 0.04347826074808836) {\n", " var0 = 2331.51904296875;\n", " } else {\n", " var0 = 2597.779052734375;\n", " }\n", " } else {\n", " if (input[0] <= 0.0326086962595582) {\n", " if (input[2] <= 0.21906888112425804) {\n", " var0 = 1832.093994140625;\n", " } else {\n", " var0 = 1842.51904296875;\n", " }\n", " } else {\n", " if (input[0] <= 0.05434782616794109) {\n", " var0 = 1964.780029296875;\n", " } else {\n", " var0 = 2103.080078125;\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[2] <= 0.09744159504771233) {\n", " var0 = 3378.909912109375;\n", " } else {\n", " if (input[1] <= 0.5) {\n", " var0 = 3208.787109375;\n", " } else {\n", " var0 = 3277.160888671875;\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[3] <= 0.800000011920929) {\n", " if (input[0] <= 0.1195652149617672) {\n", " if (input[1] <= 0.5) {\n", " var0 = 2913.569091796875;\n", " } else {\n", " if (input[2] <= 0.4735075682401657) {\n", " var0 = 3591.47998046875;\n", " } else {\n", " var0 = 3443.06396484375;\n", " }\n", " }\n", " } else {\n", " if (input[3] <= 0.5000000149011612) {\n", " if (input[0] <= 0.18478260934352875) {\n", " var0 = 3484.3310546875;\n", " } else {\n", " if (input[0] <= 0.20652173459529877) {\n", " var0 = 3693.427978515625;\n", " } else {\n", " var0 = 3847.674072265625;\n", " }\n", " }\n", " } else {\n", " if (input[1] <= 0.5) {\n", " if (input[2] <= 0.29036764055490494) {\n", " var0 = 4391.65185546875;\n", " } else {\n", " var0 = 4234.9267578125;\n", " }\n", " } else {\n", " if (input[0] <= 0.17391303926706314) {\n", " var0 = 3906.126953125;\n", " } else {\n", " var0 = 4260.744140625;\n", " }\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[0] <= 0.18478260189294815) {\n", " if (input[0] <= 0.09782608412206173) {\n", " if (input[2] <= 0.44694532454013824) {\n", " var0 = 4687.796875;\n", " } else {\n", " var0 = 4830.6298828125;\n", " }\n", " } else {\n", " var0 = 5080.09619140625;\n", " }\n", " } else {\n", " var0 = 5615.369140625;\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[3] <= 0.30000000447034836) {\n", " if (input[0] <= 0.32608695328235626) {\n", " if (input[2] <= 0.40919890999794006) {\n", " var0 = 3659.345947265625;\n", " } else {\n", " if (input[2] <= 0.42317909002304077) {\n", " var0 = 4076.4970703125;\n", " } else {\n", " var0 = 4149.73583984375;\n", " }\n", " }\n", " } else {\n", " if (input[2] <= 0.38962671160697937) {\n", " if (input[0] <= 0.3586956560611725) {\n", " var0 = 5003.85302734375;\n", " } else {\n", " if (input[2] <= 0.3351041376590729) {\n", " var0 = 4746.34423828125;\n", " } else {\n", " var0 = 4751.06982421875;\n", " }\n", " }\n", " } else {\n", " if (input[0] <= 0.4021739065647125) {\n", " if (input[0] <= 0.3586956560611725) {\n", " var0 = 5012.47119140625;\n", " } else {\n", " if (input[2] <= 0.44974131882190704) {\n", " var0 = 5240.76513671875;\n", " } else {\n", " var0 = 5246.046875;\n", " }\n", " }\n", " } else {\n", " var0 = 5488.26220703125;\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[0] <= 0.31521739065647125) {\n", " if (input[3] <= 0.5000000149011612) {\n", " if (input[2] <= 0.22046690434217453) {\n", " var0 = 4931.64697265625;\n", " } else {\n", " var0 = 4934.705078125;\n", " }\n", " } else {\n", " if (input[0] <= 0.25) {\n", " var0 = 5708.8671875;\n", " } else {\n", " if (input[2] <= 0.39242272078990936) {\n", " var0 = 5253.52392578125;\n", " } else {\n", " var0 = 5325.65087890625;\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[3] <= 0.9000000059604645) {\n", " if (input[0] <= 0.33695653080940247) {\n", " if (input[3] <= 0.7000000178813934) {\n", " var0 = 5972.3779296875;\n", " } else {\n", " var0 = 6059.1728515625;\n", " }\n", " } else {\n", " if (input[0] <= 0.3586956560611725) {\n", " var0 = 6196.4482421875;\n", " } else {\n", " if (input[0] <= 0.3913043439388275) {\n", " var0 = 6414.17822265625;\n", " } else {\n", " var0 = 6311.9521484375;\n", " }\n", " }\n", " }\n", " } else {\n", " var0 = 6666.2431640625;\n", " }\n", " }\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[2] <= 0.6286872029304504) {\n", " if (input[3] <= 0.7000000178813934) {\n", " if (input[7] <= 0.5) {\n", " if (input[0] <= 0.532608687877655) {\n", " if (input[3] <= 0.5000000149011612) {\n", " if (input[2] <= 0.46232347190380096) {\n", " if (input[1] <= 0.5) {\n", " if (input[2] <= 0.4304487258195877) {\n", " if (input[0] <= 0.510869562625885) {\n", " if (input[3] <= 0.30000000447034836) {\n", " var0 = 7153.5537109375;\n", " } else {\n", " if (input[2] <= 0.3439815193414688) {\n", " var0 = 7201.70068359375;\n", " } else {\n", " var0 = 7209.49169921875;\n", " }\n", " }\n", " } else {\n", " var0 = 7050.64208984375;\n", " }\n", " } else {\n", " var0 = 6238.2978515625;\n", " }\n", " } else {\n", " if (input[0] <= 0.510869562625885) {\n", " if (input[3] <= 0.30000000447034836) {\n", " if (input[0] <= 0.46739131212234497) {\n", " var0 = 6123.56884765625;\n", " } else {\n", " if (input[2] <= 0.32958196103572845) {\n", " var0 = 6664.68603515625;\n", " } else {\n", " if (input[6] <= 0.5) {\n", " var0 = 6393.603515625;\n", " } else {\n", " var0 = 6282.23486328125;\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[6] <= 0.5) {\n", " var0 = 6710.19189453125;\n", " } else {\n", " var0 = 6600.36083984375;\n", " }\n", " }\n", " } else {\n", " var0 = 6940.90966796875;\n", " }\n", " }\n", " } else {\n", " if (input[1] <= 0.5) {\n", " if (input[6] <= 0.5) {\n", " var0 = 7443.64306640625;\n", " } else {\n", " var0 = 7371.77197265625;\n", " }\n", " } else {\n", " if (input[8] <= 0.5) {\n", " var0 = 7160.09423828125;\n", " } else {\n", " if (input[2] <= 0.5259331315755844) {\n", " var0 = 7261.7412109375;\n", " } else {\n", " var0 = 7265.70263671875;\n", " }\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[2] <= 0.4623234272003174) {\n", " if (input[2] <= 0.3866908550262451) {\n", " var0 = 8059.67919921875;\n", " } else {\n", " var0 = 7954.51708984375;\n", " }\n", " } else {\n", " if (input[2] <= 0.5000698268413544) {\n", " var0 = 7418.52197265625;\n", " } else {\n", " var0 = 7196.8671875;\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[2] <= 0.4145812392234802) {\n", " if (input[1] <= 0.5) {\n", " var0 = 8310.8388671875;\n", " } else {\n", " var0 = 8410.046875;\n", " }\n", " } else {\n", " if (input[8] <= 0.5) {\n", " var0 = 7441.5009765625;\n", " } else {\n", " var0 = 7727.25341796875;\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[0] <= 0.46739131212234497) {\n", " var0 = 23563.015625;\n", " } else {\n", " if (input[3] <= 0.30000000447034836) {\n", " if (input[0] <= 0.510869562625885) {\n", " if (input[0] <= 0.489130437374115) {\n", " var0 = 6500.23583984375;\n", " } else {\n", " var0 = 6781.35400390625;\n", " }\n", " } else {\n", " if (input[2] <= 0.3941003382205963) {\n", " var0 = 7046.72216796875;\n", " } else {\n", " var0 = 7345.7265625;\n", " }\n", " }\n", " } else {\n", " if (input[2] <= 0.49405843019485474) {\n", " if (input[0] <= 0.5) {\n", " var0 = 7682.669921875;\n", " } else {\n", " var0 = 7640.30908203125;\n", " }\n", " } else {\n", " if (input[2] <= 0.5524954497814178) {\n", " var0 = 7160.330078125;\n", " } else {\n", " var0 = 7162.01220703125;\n", " }\n", " }\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[2] <= 0.3532783091068268) {\n", " if (input[2] <= 0.22032713145017624) {\n", " var0 = 8582.302734375;\n", " } else {\n", " if (input[6] <= 0.5) {\n", " var0 = 14478.330078125;\n", " } else {\n", " var0 = 15828.8212890625;\n", " }\n", " }\n", " } else {\n", " if (input[6] <= 0.5) {\n", " if (input[7] <= 0.5) {\n", " var0 = 8162.71630859375;\n", " } else {\n", " var0 = 8596.828125;\n", " }\n", " } else {\n", " var0 = 7512.26708984375;\n", " }\n", " }\n", " }\n", " } else {\n", " var0 = 28476.734375;\n", " }\n", " }\n", " } else {\n", " if (input[0] <= 0.3804347813129425) {\n", " if (input[0] <= 0.33695653080940247) {\n", " if (input[0] <= 0.25) {\n", " if (input[2] <= 0.2403886392712593) {\n", " if (input[3] <= 0.5000000149011612) {\n", " if (input[2] <= 0.20851389318704605) {\n", " var0 = 22395.744140625;\n", " } else {\n", " if (input[1] <= 0.5) {\n", " var0 = 23288.927734375;\n", " } else {\n", " var0 = 23241.474609375;\n", " }\n", " }\n", " } else {\n", " var0 = 5209.57861328125;\n", " }\n", " } else {\n", " if (input[2] <= 0.35460641980171204) {\n", " if (input[0] <= 0.07608695328235626) {\n", " var0 = 11272.3310546875;\n", " } else {\n", " if (input[2] <= 0.2682790160179138) {\n", " var0 = 3309.79248046875;\n", " } else {\n", " if (input[0] <= 0.19565217196941376) {\n", " if (input[2] <= 0.3214035779237747) {\n", " var0 = 4661.2861328125;\n", " } else {\n", " var0 = 4564.19140625;\n", " }\n", " } else {\n", " if (input[1] <= 0.5) {\n", " var0 = 4337.7353515625;\n", " } else {\n", " if (input[2] <= 0.3160911202430725) {\n", " var0 = 4435.09423828125;\n", " } else {\n", " var0 = 4438.26318359375;\n", " }\n", " }\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[0] <= 0.10869565233588219) {\n", " if (input[2] <= 0.3758562505245209) {\n", " var0 = 4915.06005859375;\n", " } else {\n", " if (input[0] <= 0.043478261679410934) {\n", " if (input[3] <= 0.5000000149011612) {\n", " var0 = 3393.3564453125;\n", " } else {\n", " var0 = 3481.867919921875;\n", " }\n", " } else {\n", " var0 = 3925.75830078125;\n", " }\n", " }\n", " } else {\n", " if (input[2] <= 0.3718719035387039) {\n", " if (input[3] <= 0.5000000074505806) {\n", " var0 = 20277.806640625;\n", " } else {\n", " var0 = 24671.6640625;\n", " }\n", " } else {\n", " if (input[2] <= 0.41038723289966583) {\n", " var0 = 16796.412109375;\n", " } else {\n", " if (input[3] <= 0.5000000074505806) {\n", " var0 = 18903.4921875;\n", " } else {\n", " var0 = 17128.42578125;\n", " }\n", " }\n", " }\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[3] <= 0.5000000149011612) {\n", " if (input[0] <= 0.29347825050354004) {\n", " if (input[2] <= 0.29218506813049316) {\n", " if (input[1] <= 0.5) {\n", " var0 = 4718.20361328125;\n", " } else {\n", " var0 = 4441.21337890625;\n", " }\n", " } else {\n", " var0 = 5031.26953125;\n", " }\n", " } else {\n", " if (input[2] <= 0.2802320569753647) {\n", " var0 = 5354.07470703125;\n", " } else {\n", " var0 = 5148.552734375;\n", " }\n", " }\n", " } else {\n", " if (input[0] <= 0.27173912525177) {\n", " var0 = 5428.7275390625;\n", " } else {\n", " if (input[2] <= 0.43562139570713043) {\n", " var0 = 6799.4580078125;\n", " } else {\n", " if (input[2] <= 0.5564797818660736) {\n", " var0 = 6551.75;\n", " } else {\n", " var0 = 6334.34375;\n", " }\n", " }\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[0] <= 0.3586956560611725) {\n", " var0 = 27375.904296875;\n", " } else {\n", " if (input[2] <= 0.39046552032232285) {\n", " var0 = 6402.29150390625;\n", " } else {\n", " if (input[3] <= 0.6000000089406967) {\n", " var0 = 24915.046875;\n", " } else {\n", " var0 = 19496.71875;\n", " }\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[0] <= 0.489130437374115) {\n", " if (input[2] <= 0.2377324029803276) {\n", " if (input[2] <= 0.17398293316364288) {\n", " if (input[2] <= 0.04382776468992233) {\n", " var0 = 6640.544921875;\n", " } else {\n", " if (input[0] <= 0.4021739065647125) {\n", " var0 = 7228.2158203125;\n", " } else {\n", " if (input[0] <= 0.42391303181648254) {\n", " var0 = 6985.5068359375;\n", " } else {\n", " if (input[1] <= 0.5) {\n", " var0 = 7133.90234375;\n", " } else {\n", " var0 = 7173.35986328125;\n", " }\n", " }\n", " }\n", " }\n", " } else {\n", " var0 = 8252.2841796875;\n", " }\n", " } else {\n", " if (input[2] <= 0.3107786625623703) {\n", " if (input[2] <= 0.30413807928562164) {\n", " if (input[1] <= 0.5) {\n", " var0 = 6555.0703125;\n", " } else {\n", " var0 = 6746.74267578125;\n", " }\n", " } else {\n", " var0 = 7144.86279296875;\n", " }\n", " } else {\n", " if (input[2] <= 0.3253879100084305) {\n", " var0 = 6067.126953125;\n", " } else {\n", " if (input[3] <= 0.5000000149011612) {\n", " if (input[3] <= 0.30000000447034836) {\n", " var0 = 6600.2060546875;\n", " } else {\n", " var0 = 6406.41064453125;\n", " }\n", " } else {\n", " var0 = 6748.59130859375;\n", " }\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[2] <= 0.16867046803236008) {\n", " var0 = 13725.4716796875;\n", " } else {\n", " if (input[3] <= 0.5000000149011612) {\n", " if (input[2] <= 0.2297637164592743) {\n", " var0 = 6858.4794921875;\n", " } else {\n", " if (input[2] <= 0.3585907518863678) {\n", " var0 = 7729.6455078125;\n", " } else {\n", " if (input[2] <= 0.5710890144109726) {\n", " var0 = 7639.41748046875;\n", " } else {\n", " var0 = 7650.77392578125;\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[3] <= 0.800000011920929) {\n", " if (input[1] <= 0.5) {\n", " var0 = 8538.2880859375;\n", " } else {\n", " var0 = 8606.2177734375;\n", " }\n", " } else {\n", " var0 = 9222.40234375;\n", " }\n", " }\n", " }\n", " }\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[0] <= 0.8804347813129425) {\n", " if (input[0] <= 0.72826087474823) {\n", " if (input[7] <= 0.5) {\n", " if (input[2] <= 0.2027820348739624) {\n", " if (input[0] <= 0.6630434989929199) {\n", " if (input[3] <= 0.10000000149011612) {\n", " if (input[0] <= 0.6304347813129425) {\n", " if (input[2] <= 0.10624909773468971) {\n", " var0 = 7526.70654296875;\n", " } else {\n", " var0 = 7222.7861328125;\n", " }\n", " } else {\n", " var0 = 8269.0439453125;\n", " }\n", " } else {\n", " if (input[0] <= 0.5760869383811951) {\n", " var0 = 8302.5361328125;\n", " } else {\n", " if (input[8] <= 0.5) {\n", " if (input[5] <= 0.5) {\n", " var0 = 8539.6708984375;\n", " } else {\n", " if (input[2] <= 0.1341395080089569) {\n", " var0 = 8627.541015625;\n", " } else {\n", " var0 = 8604.4833984375;\n", " }\n", " }\n", " } else {\n", " var0 = 8428.0693359375;\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[2] <= 0.16070178151130676) {\n", " if (input[2] <= 0.1423877701163292) {\n", " if (input[2] <= 0.11561580002307892) {\n", " var0 = 9264.796875;\n", " } else {\n", " var0 = 9182.169921875;\n", " }\n", " } else {\n", " var0 = 8688.8583984375;\n", " }\n", " } else {\n", " if (input[3] <= 0.30000000447034836) {\n", " var0 = 9566.9912109375;\n", " } else {\n", " var0 = 10156.783203125;\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[2] <= 0.20676637440919876) {\n", " var0 = 26236.580078125;\n", " } else {\n", " if (input[2] <= 0.36257512867450714) {\n", " if (input[2] <= 0.34740664064884186) {\n", " if (input[0] <= 0.5760869383811951) {\n", " if (input[6] <= 0.5) {\n", " if (input[2] <= 0.25366976112127304) {\n", " var0 = 7518.025390625;\n", " } else {\n", " var0 = 7419.47802734375;\n", " }\n", " } else {\n", " if (input[1] <= 0.5) {\n", " if (input[2] <= 0.2749894708395004) {\n", " if (input[2] <= 0.24003910273313522) {\n", " var0 = 7623.51806640625;\n", " } else {\n", " var0 = 7624.6298828125;\n", " }\n", " } else {\n", " var0 = 7626.9931640625;\n", " }\n", " } else {\n", " var0 = 7726.85400390625;\n", " }\n", " }\n", " } else {\n", " if (input[0] <= 0.5978260636329651) {\n", " if (input[6] <= 0.5) {\n", " var0 = 28340.189453125;\n", " } else {\n", " var0 = 9101.7978515625;\n", " }\n", " } else {\n", " if (input[2] <= 0.23954980820417404) {\n", " if (input[2] <= 0.22577938437461853) {\n", " if (input[5] <= 0.5) {\n", " var0 = 11520.099609375;\n", " } else {\n", " var0 = 8534.671875;\n", " }\n", " } else {\n", " var0 = 30284.642578125;\n", " }\n", " } else {\n", " if (input[3] <= 0.10000000149011612) {\n", " if (input[8] <= 0.5) {\n", " if (input[0] <= 0.70652174949646) {\n", " if (input[0] <= 0.6521739065647125) {\n", " var0 = 24603.048828125;\n", " } else {\n", " var0 = 25656.576171875;\n", " }\n", " } else {\n", " var0 = 8782.46875;\n", " }\n", " } else {\n", " if (input[2] <= 0.28687261044979095) {\n", " var0 = 8827.2099609375;\n", " } else {\n", " var0 = 8026.66650390625;\n", " }\n", " }\n", " } else {\n", " if (input[3] <= 0.7000000178813934) {\n", " if (input[0] <= 0.6847826242446899) {\n", " if (input[8] <= 0.5) {\n", " if (input[0] <= 0.6630434989929199) {\n", " if (input[2] <= 0.2935131937265396) {\n", " var0 = 9447.25;\n", " } else {\n", " var0 = 9447.3828125;\n", " }\n", " } else {\n", " var0 = 9282.48046875;\n", " }\n", " } else {\n", " if (input[3] <= 0.4000000134110451) {\n", " var0 = 9249.4951171875;\n", " } else {\n", " var0 = 9301.8935546875;\n", " }\n", " }\n", " } else {\n", " if (input[2] <= 0.29218506813049316) {\n", " if (input[6] <= 0.5) {\n", " var0 = 10106.1337890625;\n", " } else {\n", " var0 = 9861.025390625;\n", " }\n", " } else {\n", " if (input[0] <= 0.70652174949646) {\n", " var0 = 9617.662109375;\n", " } else {\n", " var0 = 9957.7216796875;\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[0] <= 0.6413043737411499) {\n", " var0 = 10407.0859375;\n", " } else {\n", " var0 = 11015.1748046875;\n", " }\n", " }\n", " }\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[3] <= 0.20000000298023224) {\n", " var0 = 21232.181640625;\n", " } else {\n", " var0 = 32108.662109375;\n", " }\n", " }\n", " } else {\n", " if (input[0] <= 0.6195652186870575) {\n", " if (input[3] <= 0.30000000447034836) {\n", " if (input[0] <= 0.5978260636329651) {\n", " if (input[8] <= 0.5) {\n", " if (input[1] <= 0.5) {\n", " if (input[2] <= 0.48608967661857605) {\n", " var0 = 7345.083984375;\n", " } else {\n", " var0 = 7348.14208984375;\n", " }\n", " } else {\n", " if (input[2] <= 0.4231790751218796) {\n", " var0 = 7441.05322265625;\n", " } else {\n", " if (input[2] <= 0.5574583858251572) {\n", " var0 = 7445.91796875;\n", " } else {\n", " var0 = 7448.40380859375;\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[2] <= 0.5471829473972321) {\n", " var0 = 7731.85791015625;\n", " } else {\n", " var0 = 8023.13525390625;\n", " }\n", " }\n", " } else {\n", " var0 = 8334.4580078125;\n", " }\n", " } else {\n", " if (input[5] <= 0.5) {\n", " if (input[3] <= 0.5000000149011612) {\n", " if (input[0] <= 0.5978260636329651) {\n", " if (input[2] <= 0.4094085991382599) {\n", " if (input[1] <= 0.5) {\n", " var0 = 8520.0263671875;\n", " } else {\n", " var0 = 8413.462890625;\n", " }\n", " } else {\n", " var0 = 8116.26904296875;\n", " }\n", " } else {\n", " if (input[2] <= 0.5164965689182281) {\n", " var0 = 8825.0859375;\n", " } else {\n", " var0 = 8733.2294921875;\n", " }\n", " }\n", " } else {\n", " var0 = 9414.919921875;\n", " }\n", " } else {\n", " if (input[0] <= 0.5978260636329651) {\n", " var0 = 9704.66796875;\n", " } else {\n", " var0 = 9432.92578125;\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[2] <= 0.4475744217634201) {\n", " if (input[3] <= 0.800000011920929) {\n", " if (input[3] <= 0.30000000447034836) {\n", " if (input[0] <= 0.6630434989929199) {\n", " if (input[0] <= 0.6413043737411499) {\n", " if (input[2] <= 0.42877109348773956) {\n", " var0 = 8551.3466796875;\n", " } else {\n", " var0 = 8062.76416015625;\n", " }\n", " } else {\n", " if (input[5] <= 0.5) {\n", " var0 = 8765.2490234375;\n", " } else {\n", " var0 = 8964.060546875;\n", " }\n", " }\n", " } else {\n", " if (input[3] <= 0.10000000149011612) {\n", " if (input[0] <= 0.695652186870575) {\n", " var0 = 8988.1591796875;\n", " } else {\n", " var0 = 9174.1357421875;\n", " }\n", " } else {\n", " if (input[0] <= 0.6847826242446899) {\n", " if (input[1] <= 0.5) {\n", " var0 = 9778.34765625;\n", " } else {\n", " if (input[2] <= 0.38515305519104004) {\n", " var0 = 9288.0263671875;\n", " } else {\n", " var0 = 9290.1396484375;\n", " }\n", " }\n", " } else {\n", " if (input[1] <= 0.5) {\n", " var0 = 9910.359375;\n", " } else {\n", " var0 = 9964.0595703125;\n", " }\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[2] <= 0.38235704600811005) {\n", " if (input[0] <= 0.6413043737411499) {\n", " var0 = 9620.3310546875;\n", " } else {\n", " var0 = 8968.330078125;\n", " }\n", " } else {\n", " if (input[8] <= 0.5) {\n", " if (input[2] <= 0.4231790453195572) {\n", " if (input[1] <= 0.5) {\n", " var0 = 10118.423828125;\n", " } else {\n", " var0 = 10141.1357421875;\n", " }\n", " } else {\n", " var0 = 10043.2490234375;\n", " }\n", " } else {\n", " var0 = 10269.4599609375;\n", " }\n", " }\n", " }\n", " } else {\n", " var0 = 11552.904296875;\n", " }\n", " } else {\n", " if (input[0] <= 0.6630434989929199) {\n", " if (input[3] <= 0.4000000134110451) {\n", " if (input[6] <= 0.5) {\n", " if (input[0] <= 0.6413043737411499) {\n", " var0 = 20878.78515625;\n", " } else {\n", " if (input[5] <= 0.5) {\n", " var0 = 28468.919921875;\n", " } else {\n", " var0 = 26392.259765625;\n", " }\n", " }\n", " } else {\n", " var0 = 8068.18505859375;\n", " }\n", " } else {\n", " if (input[3] <= 0.7000000178813934) {\n", " if (input[1] <= 0.5) {\n", " var0 = 10115.0087890625;\n", " } else {\n", " var0 = 9563.029296875;\n", " }\n", " } else {\n", " var0 = 10736.87109375;\n", " }\n", " }\n", " } else {\n", " if (input[1] <= 0.5) {\n", " if (input[3] <= 0.30000000447034836) {\n", " if (input[2] <= 0.48210540413856506) {\n", " var0 = 9866.3046875;\n", " } else {\n", " if (input[2] <= 0.5601845234632492) {\n", " var0 = 9872.701171875;\n", " } else {\n", " if (input[2] <= 0.6504962742328644) {\n", " var0 = 9880.068359375;\n", " } else {\n", " var0 = 9875.6806640625;\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[5] <= 0.5) {\n", " var0 = 10848.134765625;\n", " } else {\n", " var0 = 10370.912109375;\n", " }\n", " }\n", " } else {\n", " if (input[3] <= 0.10000000149011612) {\n", " if (input[0] <= 0.70652174949646) {\n", " var0 = 8457.818359375;\n", " } else {\n", " var0 = 8798.5927734375;\n", " }\n", " } else {\n", " var0 = 9391.345703125;\n", " }\n", " }\n", " }\n", " }\n", " }\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[3] <= 0.5000000149011612) {\n", " if (input[0] <= 0.5760869383811951) {\n", " if (input[2] <= 0.3987137973308563) {\n", " if (input[2] <= 0.2818397507071495) {\n", " var0 = 8211.1005859375;\n", " } else {\n", " var0 = 8219.2041015625;\n", " }\n", " } else {\n", " if (input[2] <= 0.46176426112651825) {\n", " var0 = 7633.720703125;\n", " } else {\n", " if (input[2] <= 0.5417307168245316) {\n", " var0 = 7147.47265625;\n", " } else {\n", " var0 = 7152.67138671875;\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[0] <= 0.5978260636329651) {\n", " if (input[3] <= 0.20000000298023224) {\n", " var0 = 17929.302734375;\n", " } else {\n", " if (input[2] <= 0.4371591955423355) {\n", " if (input[2] <= 0.3187473565340042) {\n", " var0 = 8515.7587890625;\n", " } else {\n", " var0 = 8516.8291015625;\n", " }\n", " } else {\n", " var0 = 8527.5322265625;\n", " }\n", " }\n", " } else {\n", " if (input[0] <= 0.6847826242446899) {\n", " if (input[3] <= 0.30000000447034836) {\n", " if (input[1] <= 0.5) {\n", " if (input[0] <= 0.6195652186870575) {\n", " if (input[2] <= 0.3894868642091751) {\n", " if (input[2] <= 0.3095204383134842) {\n", " var0 = 8232.638671875;\n", " } else {\n", " var0 = 8233.09765625;\n", " }\n", " } else {\n", " var0 = 8240.58984375;\n", " }\n", " } else {\n", " if (input[3] <= 0.10000000149011612) {\n", " if (input[0] <= 0.6630434989929199) {\n", " if (input[2] <= 0.4310079514980316) {\n", " var0 = 8280.623046875;\n", " } else {\n", " var0 = 8283.6806640625;\n", " }\n", " } else {\n", " var0 = 8601.3291015625;\n", " }\n", " } else {\n", " if (input[0] <= 0.6413043737411499) {\n", " var0 = 8569.861328125;\n", " } else {\n", " var0 = 8871.1513671875;\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[0] <= 0.6630434989929199) {\n", " if (input[2] <= 0.7554872035980225) {\n", " if (input[3] <= 0.10000000149011612) {\n", " if (input[2] <= 0.5063609778881073) {\n", " var0 = 7789.634765625;\n", " } else {\n", " var0 = 7804.16064453125;\n", " }\n", " } else {\n", " var0 = 7742.10986328125;\n", " }\n", " } else {\n", " var0 = 8083.919921875;\n", " }\n", " } else {\n", " if (input[2] <= 0.5463441610336304) {\n", " var0 = 8124.408203125;\n", " } else {\n", " var0 = 8125.78466796875;\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[2] <= 0.5878651440143585) {\n", " if (input[0] <= 0.6630434989929199) {\n", " var0 = 8978.185546875;\n", " } else {\n", " var0 = 9304.7021484375;\n", " }\n", " } else {\n", " var0 = 8347.1640625;\n", " }\n", " }\n", " } else {\n", " if (input[1] <= 0.5) {\n", " if (input[3] <= 0.10000000149011612) {\n", " var0 = 9283.5615234375;\n", " } else {\n", " if (input[3] <= 0.30000000447034836) {\n", " var0 = 9877.607421875;\n", " } else {\n", " var0 = 10107.220703125;\n", " }\n", " }\n", " } else {\n", " if (input[3] <= 0.10000000149011612) {\n", " var0 = 8442.6669921875;\n", " } else {\n", " if (input[2] <= 0.658604770898819) {\n", " if (input[2] <= 0.452537402510643) {\n", " var0 = 9377.904296875;\n", " } else {\n", " var0 = 9386.1611328125;\n", " }\n", " } else {\n", " var0 = 9058.73046875;\n", " }\n", " }\n", " }\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[0] <= 0.6847826242446899) {\n", " if (input[2] <= 0.15420101583003998) {\n", " var0 = 8605.361328125;\n", " } else {\n", " if (input[2] <= 0.621697187423706) {\n", " if (input[3] <= 0.800000011920929) {\n", " var0 = 10381.478515625;\n", " } else {\n", " var0 = 9788.8662109375;\n", " }\n", " } else {\n", " var0 = 10977.2060546875;\n", " }\n", " }\n", " } else {\n", " var0 = 19749.3828125;\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[2] <= 0.5788480043411255) {\n", " if (input[2] <= 0.28169994056224823) {\n", " if (input[2] <= 0.2777855098247528) {\n", " if (input[7] <= 0.5) {\n", " if (input[3] <= 0.10000000149011612) {\n", " if (input[0] <= 0.804347813129425) {\n", " if (input[2] <= 0.18992029875516891) {\n", " if (input[8] <= 0.5) {\n", " var0 = 10197.7724609375;\n", " } else {\n", " var0 = 9991.0380859375;\n", " }\n", " } else {\n", " if (input[1] <= 0.5) {\n", " var0 = 10355.640625;\n", " } else {\n", " var0 = 10422.9169921875;\n", " }\n", " }\n", " } else {\n", " if (input[0] <= 0.8369565010070801) {\n", " if (input[6] <= 0.5) {\n", " if (input[8] <= 0.5) {\n", " var0 = 11165.41796875;\n", " } else {\n", " var0 = 11454.021484375;\n", " }\n", " } else {\n", " var0 = 10577.0869140625;\n", " }\n", " } else {\n", " if (input[6] <= 0.5) {\n", " if (input[2] <= 0.09695229306817055) {\n", " var0 = 11534.873046875;\n", " } else {\n", " if (input[8] <= 0.5) {\n", " if (input[1] <= 0.5) {\n", " var0 = 12029.287109375;\n", " } else {\n", " var0 = 11931.125;\n", " }\n", " } else {\n", " var0 = 11830.607421875;\n", " }\n", " }\n", " } else {\n", " var0 = 11345.5185546875;\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[5] <= 0.5) {\n", " if (input[0] <= 0.77173912525177) {\n", " if (input[1] <= 0.5) {\n", " if (input[8] <= 0.5) {\n", " var0 = 11150.7802734375;\n", " } else {\n", " var0 = 10942.1318359375;\n", " }\n", " } else {\n", " var0 = 10065.4130859375;\n", " }\n", " } else {\n", " if (input[0] <= 0.804347813129425) {\n", " var0 = 12479.708984375;\n", " } else {\n", " if (input[0] <= 0.8369565010070801) {\n", " var0 = 12044.341796875;\n", " } else {\n", " var0 = 12032.326171875;\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[3] <= 0.30000000447034836) {\n", " var0 = 25517.11328125;\n", " } else {\n", " if (input[0] <= 0.782608687877655) {\n", " var0 = 11244.376953125;\n", " } else {\n", " var0 = 13047.33203125;\n", " }\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[0] <= 0.760869562625885) {\n", " var0 = 27117.994140625;\n", " } else {\n", " if (input[2] <= 0.18341952562332153) {\n", " if (input[3] <= 0.20000000298023224) {\n", " var0 = 11833.7822265625;\n", " } else {\n", " var0 = 11013.7119140625;\n", " }\n", " } else {\n", " if (input[3] <= 0.30000000447034836) {\n", " var0 = 22192.4375;\n", " } else {\n", " var0 = 12629.166015625;\n", " }\n", " }\n", " }\n", " }\n", " } else {\n", " var0 = 35160.1328125;\n", " }\n", " } else {\n", " if (input[6] <= 0.5) {\n", " if (input[2] <= 0.3917936384677887) {\n", " if (input[2] <= 0.3386690616607666) {\n", " if (input[0] <= 0.8586956262588501) {\n", " if (input[8] <= 0.5) {\n", " if (input[2] <= 0.3360128253698349) {\n", " if (input[2] <= 0.3162309229373932) {\n", " var0 = 11554.2236328125;\n", " } else {\n", " if (input[2] <= 0.3253879100084305) {\n", " var0 = 11657.71875;\n", " } else {\n", " if (input[2] <= 0.33202849328517914) {\n", " var0 = 11658.115234375;\n", " } else {\n", " var0 = 11658.37890625;\n", " }\n", " }\n", " }\n", " } else {\n", " var0 = 12096.6513671875;\n", " }\n", " } else {\n", " if (input[1] <= 0.5) {\n", " if (input[0] <= 0.79347825050354) {\n", " var0 = 11305.9345703125;\n", " } else {\n", " var0 = 11082.5771484375;\n", " }\n", " } else {\n", " var0 = 10594.501953125;\n", " }\n", " }\n", " } else {\n", " if (input[1] <= 0.5) {\n", " if (input[2] <= 0.30413809418678284) {\n", " var0 = 12222.8984375;\n", " } else {\n", " var0 = 12224.3505859375;\n", " }\n", " } else {\n", " var0 = 11735.87890625;\n", " }\n", " }\n", " } else {\n", " if (input[7] <= 0.5) {\n", " if (input[1] <= 0.5) {\n", " if (input[3] <= 0.10000000149011612) {\n", " var0 = 11286.5390625;\n", " } else {\n", " var0 = 10797.3359375;\n", " }\n", " } else {\n", " if (input[0] <= 0.79347825050354) {\n", " if (input[0] <= 0.77173912525177) {\n", " var0 = 10072.0546875;\n", " } else {\n", " var0 = 10231.5;\n", " }\n", " } else {\n", " var0 = 10796.3505859375;\n", " }\n", " }\n", " } else {\n", " var0 = 9487.64453125;\n", " }\n", " }\n", " } else {\n", " if (input[2] <= 0.41304346919059753) {\n", " if (input[2] <= 0.4048650562763214) {\n", " if (input[2] <= 0.3971060812473297) {\n", " var0 = 23045.56640625;\n", " } else {\n", " if (input[2] <= 0.4022088199853897) {\n", " var0 = 10461.9794921875;\n", " } else {\n", " var0 = 10338.931640625;\n", " }\n", " }\n", " } else {\n", " var0 = 27346.04296875;\n", " }\n", " } else {\n", " if (input[0] <= 0.79347825050354) {\n", " if (input[3] <= 0.10000000149011612) {\n", " if (input[2] <= 0.4714105427265167) {\n", " var0 = 9722.76953125;\n", " } else {\n", " var0 = 9140.951171875;\n", " }\n", " } else {\n", " if (input[3] <= 0.4000000134110451) {\n", " if (input[5] <= 0.5) {\n", " if (input[1] <= 0.5) {\n", " if (input[7] <= 0.5) {\n", " var0 = 10959.6943359375;\n", " } else {\n", " var0 = 10928.8486328125;\n", " }\n", " } else {\n", " var0 = 10825.25390625;\n", " }\n", " } else {\n", " var0 = 11512.4052734375;\n", " }\n", " } else {\n", " if (input[1] <= 0.5) {\n", " var0 = 12495.291015625;\n", " } else {\n", " if (input[2] <= 0.4382776618003845) {\n", " var0 = 11488.3173828125;\n", " } else {\n", " var0 = 11289.109375;\n", " }\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[2] <= 0.4586886018514633) {\n", " if (input[2] <= 0.45204806327819824) {\n", " if (input[3] <= 0.30000000447034836) {\n", " if (input[0] <= 0.8260869383811951) {\n", " if (input[2] <= 0.4394659101963043) {\n", " var0 = 11879.1044921875;\n", " } else {\n", " var0 = 10807.486328125;\n", " }\n", " } else {\n", " if (input[5] <= 0.5) {\n", " if (input[2] <= 0.42227034270763397) {\n", " var0 = 11842.6240234375;\n", " } else {\n", " var0 = 11946.6259765625;\n", " }\n", " } else {\n", " var0 = 12430.953125;\n", " }\n", " }\n", " } else {\n", " if (input[0] <= 0.8152173757553101) {\n", " var0 = 12268.6318359375;\n", " } else {\n", " if (input[2] <= 0.42632459104061127) {\n", " var0 = 13607.369140625;\n", " } else {\n", " var0 = 13430.2646484375;\n", " }\n", " }\n", " }\n", " } else {\n", " var0 = 20781.48828125;\n", " }\n", " } else {\n", " if (input[3] <= 0.30000000447034836) {\n", " if (input[8] <= 0.5) {\n", " if (input[2] <= 0.503914400935173) {\n", " var0 = 10594.2255859375;\n", " } else {\n", " if (input[0] <= 0.8369565010070801) {\n", " var0 = 11394.0654296875;\n", " } else {\n", " var0 = 11363.283203125;\n", " }\n", " }\n", " } else {\n", " if (input[1] <= 0.5) {\n", " if (input[2] <= 0.5073395222425461) {\n", " var0 = 12231.61328125;\n", " } else {\n", " var0 = 12235.8388671875;\n", " }\n", " } else {\n", " if (input[2] <= 0.475464791059494) {\n", " var0 = 11945.1328125;\n", " } else {\n", " if (input[2] <= 0.48608967661857605) {\n", " var0 = 11356.6611328125;\n", " } else {\n", " var0 = 11743.9345703125;\n", " }\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[0] <= 0.8152173757553101) {\n", " if (input[8] <= 0.5) {\n", " var0 = 11987.16796875;\n", " } else {\n", " var0 = 12269.6884765625;\n", " }\n", " } else {\n", " if (input[2] <= 0.5336920768022537) {\n", " if (input[8] <= 0.5) {\n", " if (input[5] <= 0.5) {\n", " var0 = 12949.1552734375;\n", " } else {\n", " var0 = 13224.056640625;\n", " }\n", " } else {\n", " var0 = 12643.3779296875;\n", " }\n", " } else {\n", " var0 = 12265.5068359375;\n", " }\n", " }\n", " }\n", " }\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[0] <= 0.75) {\n", " if (input[3] <= 0.30000000447034836) {\n", " if (input[2] <= 0.47909966111183167) {\n", " if (input[1] <= 0.5) {\n", " var0 = 9625.919921875;\n", " } else {\n", " var0 = 9724.5302734375;\n", " }\n", " } else {\n", " if (input[1] <= 0.5) {\n", " var0 = 9634.5380859375;\n", " } else {\n", " var0 = 9144.5654296875;\n", " }\n", " }\n", " } else {\n", " var0 = 10806.8388671875;\n", " }\n", " } else {\n", " if (input[3] <= 0.10000000149011612) {\n", " if (input[0] <= 0.8152173757553101) {\n", " if (input[1] <= 0.5) {\n", " if (input[2] <= 0.4749055951833725) {\n", " var0 = 10704.4697265625;\n", " } else {\n", " var0 = 10713.6435546875;\n", " }\n", " } else {\n", " var0 = 9850.431640625;\n", " }\n", " } else {\n", " if (input[2] <= 0.32392002642154694) {\n", " if (input[2] <= 0.30294980108737946) {\n", " var0 = 11073.17578125;\n", " } else {\n", " var0 = 10965.4462890625;\n", " }\n", " } else {\n", " if (input[1] <= 0.5) {\n", " if (input[2] <= 0.33650214970111847) {\n", " var0 = 11455.2802734375;\n", " } else {\n", " if (input[2] <= 0.39801476895809174) {\n", " var0 = 11842.4423828125;\n", " } else {\n", " var0 = 11848.140625;\n", " }\n", " }\n", " } else {\n", " var0 = 11362.7548828125;\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[0] <= 0.77173912525177) {\n", " if (input[1] <= 0.5) {\n", " var0 = 11163.568359375;\n", " } else {\n", " var0 = 11253.4208984375;\n", " }\n", " } else {\n", " if (input[3] <= 0.5000000149011612) {\n", " if (input[3] <= 0.30000000447034836) {\n", " var0 = 11674.1298828125;\n", " } else {\n", " var0 = 11881.3583984375;\n", " }\n", " } else {\n", " if (input[0] <= 0.804347813129425) {\n", " var0 = 12105.3203125;\n", " } else {\n", " var0 = 12363.546875;\n", " }\n", " }\n", " }\n", " }\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[2] <= 0.5891933143138885) {\n", " if (input[0] <= 0.77173912525177) {\n", " var0 = 33471.97265625;\n", " } else {\n", " var0 = 30063.580078125;\n", " }\n", " } else {\n", " if (input[2] <= 0.5984901487827301) {\n", " var0 = 20462.998046875;\n", " } else {\n", " if (input[0] <= 0.8586956262588501) {\n", " if (input[2] <= 0.7205368280410767) {\n", " if (input[5] <= 0.5) {\n", " if (input[2] <= 0.6632181704044342) {\n", " if (input[1] <= 0.5) {\n", " var0 = 10579.7109375;\n", " } else {\n", " if (input[0] <= 0.760869562625885) {\n", " var0 = 10325.2060546875;\n", " } else {\n", " var0 = 10450.5517578125;\n", " }\n", " }\n", " } else {\n", " var0 = 9504.310546875;\n", " }\n", " } else {\n", " if (input[2] <= 0.6388228535652161) {\n", " var0 = 11396.900390625;\n", " } else {\n", " var0 = 11566.30078125;\n", " }\n", " }\n", " } else {\n", " if (input[7] <= 0.5) {\n", " var0 = 11576.1298828125;\n", " } else {\n", " var0 = 12592.5341796875;\n", " }\n", " }\n", " } else {\n", " if (input[2] <= 0.801621675491333) {\n", " if (input[2] <= 0.6616803705692291) {\n", " var0 = 11856.4111328125;\n", " } else {\n", " var0 = 24227.337890625;\n", " }\n", " } else {\n", " var0 = 11381.3251953125;\n", " }\n", " }\n", " }\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[3] <= 0.7000000178813934) {\n", " if (input[3] <= 0.10000000149011612) {\n", " if (input[0] <= 0.9239130616188049) {\n", " if (input[1] <= 0.5) {\n", " if (input[2] <= 0.26163844764232635) {\n", " if (input[2] <= 0.2271074876189232) {\n", " if (input[5] <= 0.5) {\n", " var0 = 13012.208984375;\n", " } else {\n", " var0 = 13204.2861328125;\n", " }\n", " } else {\n", " var0 = 28923.13671875;\n", " }\n", " } else {\n", " if (input[5] <= 0.5) {\n", " if (input[2] <= 0.3525793105363846) {\n", " var0 = 12233.828125;\n", " } else {\n", " if (input[2] <= 0.4588284194469452) {\n", " var0 = 12622.1796875;\n", " } else {\n", " var0 = 12644.5888671875;\n", " }\n", " }\n", " } else {\n", " if (input[2] <= 0.2855444848537445) {\n", " var0 = 12815.4453125;\n", " } else {\n", " if (input[2] <= 0.41835591197013855) {\n", " var0 = 13217.0947265625;\n", " } else {\n", " var0 = 13228.8466796875;\n", " }\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[2] <= 0.2749195992946625) {\n", " var0 = 12323.935546875;\n", " } else {\n", " if (input[2] <= 0.3439815044403076) {\n", " var0 = 30259.99609375;\n", " } else {\n", " if (input[2] <= 0.46707673370838165) {\n", " var0 = 12731.0;\n", " } else {\n", " var0 = 21797.0;\n", " }\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[0] <= 0.967391312122345) {\n", " if (input[1] <= 0.5) {\n", " if (input[6] <= 0.5) {\n", " if (input[0] <= 0.945652186870575) {\n", " if (input[5] <= 0.5) {\n", " var0 = 13415.0380859375;\n", " } else {\n", " if (input[2] <= 0.33999717980623245) {\n", " var0 = 13616.3583984375;\n", " } else {\n", " var0 = 13635.6376953125;\n", " }\n", " }\n", " } else {\n", " if (input[8] <= 0.5) {\n", " var0 = 14043.4765625;\n", " } else {\n", " var0 = 13844.796875;\n", " }\n", " }\n", " } else {\n", " if (input[2] <= 0.4721095860004425) {\n", " var0 = 13041.9208984375;\n", " } else {\n", " var0 = 13470.8603515625;\n", " }\n", " }\n", " } else {\n", " if (input[0] <= 0.945652186870575) {\n", " if (input[5] <= 0.5) {\n", " if (input[8] <= 0.5) {\n", " if (input[7] <= 0.5) {\n", " var0 = 12574.048828125;\n", " } else {\n", " var0 = 12557.60546875;\n", " }\n", " } else {\n", " var0 = 12950.0712890625;\n", " }\n", " } else {\n", " var0 = 13143.3369140625;\n", " }\n", " } else {\n", " if (input[5] <= 0.5) {\n", " if (input[8] <= 0.5) {\n", " if (input[6] <= 0.5) {\n", " var0 = 12981.345703125;\n", " } else {\n", " var0 = 12957.1181640625;\n", " }\n", " } else {\n", " var0 = 13352.099609375;\n", " }\n", " } else {\n", " var0 = 13555.0048828125;\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[1] <= 0.5) {\n", " if (input[0] <= 0.989130437374115) {\n", " if (input[2] <= 0.3409757614135742) {\n", " if (input[2] <= 0.20320142060518265) {\n", " var0 = 14451.8349609375;\n", " } else {\n", " if (input[2] <= 0.24702918529510498) {\n", " var0 = 14254.6083984375;\n", " } else {\n", " var0 = 14256.1923828125;\n", " }\n", " }\n", " } else {\n", " if (input[2] <= 0.4895847290754318) {\n", " var0 = 13880.94921875;\n", " } else {\n", " var0 = 13887.96875;\n", " }\n", " }\n", " } else {\n", " if (input[5] <= 0.5) {\n", " if (input[8] <= 0.5) {\n", " if (input[6] <= 0.5) {\n", " var0 = 14313.8466796875;\n", " } else {\n", " var0 = 14319.03125;\n", " }\n", " } else {\n", " var0 = 14692.6689453125;\n", " }\n", " } else {\n", " var0 = 14901.5166015625;\n", " }\n", " }\n", " } else {\n", " if (input[0] <= 0.989130437374115) {\n", " if (input[5] <= 0.5) {\n", " if (input[7] <= 0.5) {\n", " var0 = 13393.755859375;\n", " } else {\n", " var0 = 13405.390625;\n", " }\n", " } else {\n", " if (input[2] <= 0.48343348503112793) {\n", " var0 = 13974.455078125;\n", " } else {\n", " var0 = 13981.8505859375;\n", " }\n", " }\n", " } else {\n", " if (input[5] <= 0.5) {\n", " if (input[8] <= 0.5) {\n", " if (input[2] <= 0.5780790746212006) {\n", " var0 = 13822.802734375;\n", " } else {\n", " var0 = 13831.115234375;\n", " }\n", " } else {\n", " var0 = 14210.5361328125;\n", " }\n", " } else {\n", " var0 = 14410.931640625;\n", " }\n", " }\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[2] <= 0.47923943400382996) {\n", " if (input[0] <= 0.945652186870575) {\n", " if (input[3] <= 0.30000000447034836) {\n", " if (input[2] <= 0.2542988657951355) {\n", " var0 = 13112.6044921875;\n", " } else {\n", " var0 = 12333.828125;\n", " }\n", " } else {\n", " if (input[7] <= 0.5) {\n", " if (input[2] <= 0.434293270111084) {\n", " if (input[2] <= 0.35181036591529846) {\n", " var0 = 14382.708984375;\n", " } else {\n", " if (input[6] <= 0.5) {\n", " var0 = 14119.6201171875;\n", " } else {\n", " var0 = 14007.2216796875;\n", " }\n", " }\n", " } else {\n", " var0 = 14590.6318359375;\n", " }\n", " } else {\n", " if (input[3] <= 0.5000000149011612) {\n", " var0 = 12925.8857421875;\n", " } else {\n", " if (input[0] <= 0.9021739363670349) {\n", " if (input[2] <= 0.30644480884075165) {\n", " var0 = 14001.1337890625;\n", " } else {\n", " var0 = 14001.287109375;\n", " }\n", " } else {\n", " var0 = 13919.8232421875;\n", " }\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[2] <= 0.3959876745939255) {\n", " if (input[2] <= 0.23304906487464905) {\n", " if (input[2] <= 0.17796728014945984) {\n", " var0 = 14349.8544921875;\n", " } else {\n", " var0 = 30166.619140625;\n", " }\n", " } else {\n", " if (input[3] <= 0.5000000149011612) {\n", " if (input[3] <= 0.30000000447034836) {\n", " var0 = 13937.666015625;\n", " } else {\n", " if (input[2] <= 0.31406402587890625) {\n", " var0 = 14988.431640625;\n", " } else {\n", " var0 = 15019.759765625;\n", " }\n", " }\n", " } else {\n", " var0 = 16455.70703125;\n", " }\n", " }\n", " } else {\n", " var0 = 27000.984375;\n", " }\n", " }\n", " } else {\n", " if (input[2] <= 0.5638193488121033) {\n", " if (input[0] <= 0.967391312122345) {\n", " if (input[2] <= 0.5210400521755219) {\n", " var0 = 36910.609375;\n", " } else {\n", " if (input[0] <= 0.945652186870575) {\n", " if (input[6] <= 0.5) {\n", " var0 = 28287.8984375;\n", " } else {\n", " var0 = 27941.287109375;\n", " }\n", " } else {\n", " var0 = 31620.001953125;\n", " }\n", " }\n", " } else {\n", " var0 = 14474.6748046875;\n", " }\n", " } else {\n", " if (input[6] <= 0.5) {\n", " if (input[3] <= 0.30000000447034836) {\n", " var0 = 14418.2802734375;\n", " } else {\n", " if (input[2] <= 0.6401509642601013) {\n", " var0 = 15230.32421875;\n", " } else {\n", " var0 = 15555.1884765625;\n", " }\n", " }\n", " } else {\n", " var0 = 12347.171875;\n", " }\n", " }\n", " }\n", " }\n", " } else {\n", " var0 = 36580.28125;\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[2] <= 0.36893609166145325) {\n", " if (input[0] <= 0.5) {\n", " if (input[2] <= 0.17398294061422348) {\n", " if (input[0] <= 0.45652173459529877) {\n", " if (input[0] <= 0.18478260934352875) {\n", " if (input[0] <= 0.0326086962595582) {\n", " if (input[0] <= 0.010869565419852734) {\n", " var0 = 13747.8720703125;\n", " } else {\n", " var0 = 13844.505859375;\n", " }\n", " } else {\n", " if (input[2] <= 0.12218648567795753) {\n", " if (input[3] <= 0.20000000298023224) {\n", " var0 = 14571.890625;\n", " } else {\n", " var0 = 14455.64453125;\n", " }\n", " } else {\n", " if (input[8] <= 0.5) {\n", " var0 = 15359.1044921875;\n", " } else {\n", " var0 = 14711.744140625;\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[2] <= 0.04781208001077175) {\n", " var0 = 15006.5791015625;\n", " } else {\n", " if (input[6] <= 0.5) {\n", " if (input[2] <= 0.07703059166669846) {\n", " var0 = 16776.3046875;\n", " } else {\n", " var0 = 16420.494140625;\n", " }\n", " } else {\n", " var0 = 15820.69921875;\n", " }\n", " }\n", " }\n", " } else {\n", " var0 = 19444.265625;\n", " }\n", " } else {\n", " if (input[0] <= 0.0326086962595582) {\n", " if (input[5] <= 0.5) {\n", " if (input[6] <= 0.5) {\n", " if (input[8] <= 0.5) {\n", " var0 = 18223.451171875;\n", " } else {\n", " if (input[1] <= 0.5) {\n", " if (input[2] <= 0.32937224209308624) {\n", " var0 = 17468.984375;\n", " } else {\n", " var0 = 17748.505859375;\n", " }\n", " } else {\n", " var0 = 17352.6796875;\n", " }\n", " }\n", " } else {\n", " if (input[1] <= 0.5) {\n", " if (input[2] <= 0.3155319094657898) {\n", " var0 = 16884.923828125;\n", " } else {\n", " var0 = 17081.080078125;\n", " }\n", " } else {\n", " var0 = 16297.845703125;\n", " }\n", " }\n", " } else {\n", " var0 = 15518.1806640625;\n", " }\n", " } else {\n", " if (input[0] <= 0.43478260934352875) {\n", " if (input[2] <= 0.21515446156263351) {\n", " if (input[0] <= 0.15217391215264797) {\n", " var0 = 26125.673828125;\n", " } else {\n", " if (input[7] <= 0.5) {\n", " var0 = 18765.875;\n", " } else {\n", " var0 = 19361.998046875;\n", " }\n", " }\n", " } else {\n", " if (input[2] <= 0.23018310964107513) {\n", " if (input[7] <= 0.5) {\n", " if (input[1] <= 0.5) {\n", " var0 = 17496.306640625;\n", " } else {\n", " var0 = 17904.52734375;\n", " }\n", " } else {\n", " var0 = 16577.779296875;\n", " }\n", " } else {\n", " if (input[0] <= 0.1304347775876522) {\n", " if (input[0] <= 0.08695651963353157) {\n", " if (input[0] <= 0.05434782616794109) {\n", " var0 = 17560.37890625;\n", " } else {\n", " var0 = 17942.10546875;\n", " }\n", " } else {\n", " var0 = 18328.23828125;\n", " }\n", " } else {\n", " if (input[3] <= 0.7000000178813934) {\n", " if (input[5] <= 0.5) {\n", " if (input[2] <= 0.32937227189540863) {\n", " if (input[0] <= 0.3586956560611725) {\n", " if (input[0] <= 0.21739130467176437) {\n", " var0 = 18310.7421875;\n", " } else {\n", " if (input[2] <= 0.31720952689647675) {\n", " if (input[0] <= 0.30434782803058624) {\n", " if (input[1] <= 0.5) {\n", " var0 = 19107.779296875;\n", " } else {\n", " var0 = 19199.943359375;\n", " }\n", " } else {\n", " if (input[6] <= 0.5) {\n", " var0 = 18972.494140625;\n", " } else {\n", " var0 = 19040.876953125;\n", " }\n", " }\n", " } else {\n", " var0 = 19521.96875;\n", " }\n", " }\n", " } else {\n", " if (input[7] <= 0.5) {\n", " var0 = 20234.85546875;\n", " } else {\n", " var0 = 19539.2421875;\n", " }\n", " }\n", " } else {\n", " if (input[8] <= 0.5) {\n", " if (input[2] <= 0.3618062138557434) {\n", " if (input[3] <= 0.4000000134110451) {\n", " var0 = 19719.6953125;\n", " } else {\n", " var0 = 19933.45703125;\n", " }\n", " } else {\n", " var0 = 19350.369140625;\n", " }\n", " } else {\n", " var0 = 20745.98828125;\n", " }\n", " }\n", " } else {\n", " if (input[3] <= 0.30000000447034836) {\n", " var0 = 20296.86328125;\n", " } else {\n", " var0 = 20984.09375;\n", " }\n", " }\n", " } else {\n", " var0 = 21472.478515625;\n", " }\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[3] <= 0.10000000149011612) {\n", " var0 = 20149.322265625;\n", " } else {\n", " if (input[2] <= 0.34384170174598694) {\n", " if (input[6] <= 0.5) {\n", " var0 = 21659.9296875;\n", " } else {\n", " var0 = 21082.16015625;\n", " }\n", " } else {\n", " var0 = 22462.04296875;\n", " }\n", " }\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[0] <= 0.8152173757553101) {\n", " if (input[2] <= 0.3049768954515457) {\n", " if (input[0] <= 0.6195652186870575) {\n", " if (input[8] <= 0.5) {\n", " if (input[2] <= 0.20103450864553452) {\n", " if (input[0] <= 0.554347813129425) {\n", " if (input[2] <= 0.1367957405745983) {\n", " var0 = 19798.0546875;\n", " } else {\n", " var0 = 19964.74609375;\n", " }\n", " } else {\n", " var0 = 19594.810546875;\n", " }\n", " } else {\n", " var0 = 19515.541015625;\n", " }\n", " } else {\n", " if (input[0] <= 0.532608687877655) {\n", " var0 = 21348.705078125;\n", " } else {\n", " if (input[3] <= 0.30000000447034836) {\n", " if (input[2] <= 0.23640429228544235) {\n", " var0 = 21677.283203125;\n", " } else {\n", " var0 = 21774.322265625;\n", " }\n", " } else {\n", " var0 = 21880.8203125;\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[3] <= 0.30000000447034836) {\n", " if (input[8] <= 0.5) {\n", " if (input[1] <= 0.5) {\n", " if (input[7] <= 0.5) {\n", " var0 = 23401.306640625;\n", " } else {\n", " var0 = 23244.791015625;\n", " }\n", " } else {\n", " var0 = 21978.677734375;\n", " }\n", " } else {\n", " var0 = 24393.623046875;\n", " }\n", " } else {\n", " if (input[2] <= 0.241437129676342) {\n", " if (input[0] <= 0.77173912525177) {\n", " if (input[3] <= 0.5000000149011612) {\n", " var0 = 24667.419921875;\n", " } else {\n", " if (input[0] <= 0.75) {\n", " var0 = 24869.8359375;\n", " } else {\n", " var0 = 24873.384765625;\n", " }\n", " }\n", " } else {\n", " var0 = 25382.296875;\n", " }\n", " } else {\n", " if (input[0] <= 0.6630434989929199) {\n", " if (input[8] <= 0.5) {\n", " var0 = 24180.93359375;\n", " } else {\n", " var0 = 24535.69921875;\n", " }\n", " } else {\n", " if (input[8] <= 0.5) {\n", " var0 = 23306.546875;\n", " } else {\n", " var0 = 23807.240234375;\n", " }\n", " }\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[2] <= 0.3075632154941559) {\n", " var0 = 37829.72265625;\n", " } else {\n", " if (input[8] <= 0.5) {\n", " if (input[3] <= 0.4000000134110451) {\n", " if (input[0] <= 0.5760869681835175) {\n", " var0 = 22144.03125;\n", " } else {\n", " if (input[0] <= 0.6413043737411499) {\n", " var0 = 23065.419921875;\n", " } else {\n", " var0 = 23568.271484375;\n", " }\n", " }\n", " } else {\n", " var0 = 25309.48828125;\n", " }\n", " } else {\n", " if (input[0] <= 0.5760869681835175) {\n", " var0 = 32787.45703125;\n", " } else {\n", " var0 = 24915.220703125;\n", " }\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[2] <= 0.22955402731895447) {\n", " if (input[8] <= 0.5) {\n", " if (input[2] <= 0.18341952562332153) {\n", " var0 = 27037.9140625;\n", " } else {\n", " var0 = 26926.513671875;\n", " }\n", " } else {\n", " var0 = 25678.779296875;\n", " }\n", " } else {\n", " if (input[0] <= 0.8695652186870575) {\n", " if (input[7] <= 0.5) {\n", " var0 = 27218.4375;\n", " } else {\n", " var0 = 27533.912109375;\n", " }\n", " } else {\n", " if (input[2] <= 0.2732419818639755) {\n", " var0 = 27808.724609375;\n", " } else {\n", " if (input[0] <= 0.9130434989929199) {\n", " var0 = 30184.9375;\n", " } else {\n", " if (input[5] <= 0.5) {\n", " if (input[0] <= 0.989130437374115) {\n", " if (input[0] <= 0.95652174949646) {\n", " var0 = 28868.6640625;\n", " } else {\n", " var0 = 28950.46875;\n", " }\n", " } else {\n", " var0 = 29330.982421875;\n", " }\n", " } else {\n", " var0 = 29523.166015625;\n", " }\n", " }\n", " }\n", " }\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[0] <= 0.70652174949646) {\n", " if (input[0] <= 0.18478260934352875) {\n", " if (input[2] <= 0.5255836248397827) {\n", " if (input[2] <= 0.38850829005241394) {\n", " if (input[1] <= 0.5) {\n", " if (input[2] <= 0.3717321306467056) {\n", " var0 = 33307.55078125;\n", " } else {\n", " if (input[8] <= 0.5) {\n", " var0 = 33900.65234375;\n", " } else {\n", " var0 = 33907.546875;\n", " }\n", " }\n", " } else {\n", " var0 = 32548.33984375;\n", " }\n", " } else {\n", " if (input[0] <= 0.05434782709926367) {\n", " if (input[8] <= 0.5) {\n", " if (input[7] <= 0.5) {\n", " if (input[5] <= 0.5) {\n", " if (input[2] <= 0.5042639076709747) {\n", " var0 = 34779.61328125;\n", " } else {\n", " var0 = 34828.65234375;\n", " }\n", " } else {\n", " var0 = 34617.83984375;\n", " }\n", " } else {\n", " if (input[2] <= 0.43562139570713043) {\n", " var0 = 34303.16796875;\n", " } else {\n", " var0 = 34439.85546875;\n", " }\n", " }\n", " } else {\n", " var0 = 33750.29296875;\n", " }\n", " } else {\n", " if (input[5] <= 0.5) {\n", " if (input[0] <= 0.1304347850382328) {\n", " if (input[1] <= 0.5) {\n", " var0 = 35595.58984375;\n", " } else {\n", " var0 = 35585.57421875;\n", " }\n", " } else {\n", " var0 = 36085.21875;\n", " }\n", " } else {\n", " var0 = 34254.0546875;\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[2] <= 0.7939325869083405) {\n", " if (input[2] <= 0.7180203795433044) {\n", " if (input[2] <= 0.6065986156463623) {\n", " if (input[2] <= 0.5740248262882233) {\n", " if (input[0] <= 0.0652173925191164) {\n", " var0 = 37465.34375;\n", " } else {\n", " var0 = 37484.44921875;\n", " }\n", " } else {\n", " var0 = 37165.1640625;\n", " }\n", " } else {\n", " if (input[2] <= 0.6816720366477966) {\n", " if (input[0] <= 0.08695652149617672) {\n", " var0 = 38344.56640625;\n", " } else {\n", " var0 = 38126.24609375;\n", " }\n", " } else {\n", " var0 = 38792.6875;\n", " }\n", " }\n", " } else {\n", " if (input[3] <= 0.10000000149011612) {\n", " var0 = 39722.74609375;\n", " } else {\n", " var0 = 40904.19921875;\n", " }\n", " }\n", " } else {\n", " if (input[3] <= 0.30000000447034836) {\n", " var0 = 44501.3984375;\n", " } else {\n", " var0 = 42112.234375;\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[2] <= 0.5186634659767151) {\n", " if (input[0] <= 0.44565217196941376) {\n", " if (input[3] <= 0.10000000149011612) {\n", " if (input[0] <= 0.22826086729764938) {\n", " var0 = 34672.1484375;\n", " } else {\n", " if (input[6] <= 0.5) {\n", " if (input[7] <= 0.5) {\n", " var0 = 37270.15234375;\n", " } else {\n", " var0 = 37742.57421875;\n", " }\n", " } else {\n", " if (input[1] <= 0.5) {\n", " var0 = 37079.37109375;\n", " } else {\n", " if (input[0] <= 0.29347826540470123) {\n", " var0 = 36197.69921875;\n", " } else {\n", " var0 = 35491.640625;\n", " }\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[2] <= 0.39843417704105377) {\n", " var0 = 43943.875;\n", " } else {\n", " if (input[2] <= 0.4528169482946396) {\n", " var0 = 37701.875;\n", " } else {\n", " if (input[2] <= 0.4847616106271744) {\n", " if (input[8] <= 0.5) {\n", " var0 = 40182.24609375;\n", " } else {\n", " var0 = 39983.42578125;\n", " }\n", " } else {\n", " if (input[5] <= 0.5) {\n", " if (input[3] <= 0.4000000134110451) {\n", " var0 = 38709.17578125;\n", " } else {\n", " var0 = 38746.35546875;\n", " }\n", " } else {\n", " var0 = 39047.28515625;\n", " }\n", " }\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[0] <= 0.6847826242446899) {\n", " if (input[2] <= 0.4509296864271164) {\n", " if (input[3] <= 0.5000000149011612) {\n", " if (input[5] <= 0.5) {\n", " if (input[3] <= 0.30000000447034836) {\n", " if (input[2] <= 0.38815879821777344) {\n", " var0 = 39725.51953125;\n", " } else {\n", " var0 = 39727.61328125;\n", " }\n", " } else {\n", " var0 = 40003.33203125;\n", " }\n", " } else {\n", " if (input[0] <= 0.52173912525177) {\n", " var0 = 39125.33203125;\n", " } else {\n", " var0 = 39556.49609375;\n", " }\n", " }\n", " } else {\n", " if (input[7] <= 0.5) {\n", " var0 = 40720.55078125;\n", " } else {\n", " var0 = 40941.28515625;\n", " }\n", " }\n", " } else {\n", " if (input[3] <= 0.10000000149011612) {\n", " var0 = 40974.1640625;\n", " } else {\n", " var0 = 41034.22265625;\n", " }\n", " }\n", " } else {\n", " if (input[6] <= 0.5) {\n", " if (input[2] <= 0.42632459104061127) {\n", " var0 = 41097.16015625;\n", " } else {\n", " var0 = 41919.09765625;\n", " }\n", " } else {\n", " var0 = 42856.83984375;\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[1] <= 0.5) {\n", " if (input[0] <= 0.42391304671764374) {\n", " if (input[0] <= 0.27173912525177) {\n", " var0 = 40932.4296875;\n", " } else {\n", " if (input[8] <= 0.5) {\n", " var0 = 58571.07421875;\n", " } else {\n", " var0 = 55135.40234375;\n", " }\n", " }\n", " } else {\n", " if (input[2] <= 0.574024885892868) {\n", " if (input[0] <= 0.6195652186870575) {\n", " var0 = 42111.6640625;\n", " } else {\n", " var0 = 42969.8515625;\n", " }\n", " } else {\n", " if (input[2] <= 0.6064588129520416) {\n", " var0 = 48885.13671875;\n", " } else {\n", " if (input[2] <= 0.7401090264320374) {\n", " if (input[0] <= 0.54347825050354) {\n", " var0 = 43896.375;\n", " } else {\n", " var0 = 42983.45703125;\n", " }\n", " } else {\n", " var0 = 45863.203125;\n", " }\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[0] <= 0.2391304299235344) {\n", " if (input[3] <= 0.10000000149011612) {\n", " var0 = 39611.7578125;\n", " } else {\n", " var0 = 51194.55859375;\n", " }\n", " } else {\n", " if (input[0] <= 0.42391303181648254) {\n", " if (input[2] <= 0.5340415835380554) {\n", " var0 = 36950.2578125;\n", " } else {\n", " if (input[3] <= 0.30000000447034836) {\n", " if (input[7] <= 0.5) {\n", " var0 = 39774.27734375;\n", " } else {\n", " var0 = 39871.703125;\n", " }\n", " } else {\n", " if (input[0] <= 0.27173912525177) {\n", " var0 = 39241.44140625;\n", " } else {\n", " var0 = 38711.0;\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[2] <= 0.6586047112941742) {\n", " if (input[2] <= 0.5325038433074951) {\n", " var0 = 40273.64453125;\n", " } else {\n", " if (input[3] <= 0.10000000149011612) {\n", " var0 = 41676.08203125;\n", " } else {\n", " if (input[3] <= 0.5000000149011612) {\n", " if (input[3] <= 0.30000000447034836) {\n", " var0 = 42211.13671875;\n", " } else {\n", " var0 = 42560.4296875;\n", " }\n", " } else {\n", " if (input[0] <= 0.4891304224729538) {\n", " var0 = 41949.2421875;\n", " } else {\n", " var0 = 42124.515625;\n", " }\n", " }\n", " }\n", " }\n", " } else {\n", " var0 = 46151.125;\n", " }\n", " }\n", " }\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[3] <= 0.5000000149011612) {\n", " if (input[0] <= 0.8369565010070801) {\n", " if (input[2] <= 0.6463022232055664) {\n", " if (input[2] <= 0.4048650711774826) {\n", " var0 = 41999.51953125;\n", " } else {\n", " if (input[2] <= 0.4953865110874176) {\n", " if (input[5] <= 0.5) {\n", " if (input[8] <= 0.5) {\n", " var0 = 43813.8671875;\n", " } else {\n", " var0 = 43921.18359375;\n", " }\n", " } else {\n", " var0 = 43254.41796875;\n", " }\n", " } else {\n", " if (input[5] <= 0.5) {\n", " if (input[0] <= 0.760869562625885) {\n", " var0 = 44400.40625;\n", " } else {\n", " var0 = 44423.8046875;\n", " }\n", " } else {\n", " var0 = 44641.19921875;\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[0] <= 0.72826087474823) {\n", " var0 = 47462.89453125;\n", " } else {\n", " var0 = 47269.85546875;\n", " }\n", " }\n", " } else {\n", " if (input[2] <= 0.4420522451400757) {\n", " if (input[7] <= 0.5) {\n", " if (input[0] <= 0.989130437374115) {\n", " var0 = 47305.3046875;\n", " } else {\n", " var0 = 47291.0546875;\n", " }\n", " } else {\n", " var0 = 45008.95703125;\n", " }\n", " } else {\n", " if (input[2] <= 0.4620438665151596) {\n", " var0 = 52590.828125;\n", " } else {\n", " if (input[2] <= 0.5459946095943451) {\n", " if (input[2] <= 0.5278903543949127) {\n", " if (input[0] <= 0.989130437374115) {\n", " var0 = 47055.53125;\n", " } else {\n", " var0 = 46889.26171875;\n", " }\n", " } else {\n", " var0 = 47403.87890625;\n", " }\n", " } else {\n", " if (input[7] <= 0.5) {\n", " if (input[0] <= 0.9239130616188049) {\n", " if (input[2] <= 0.6016356647014618) {\n", " var0 = 47896.79296875;\n", " } else {\n", " var0 = 48173.359375;\n", " }\n", " } else {\n", " if (input[3] <= 0.10000000149011612) {\n", " var0 = 48824.44921875;\n", " } else {\n", " var0 = 48517.5625;\n", " }\n", " }\n", " } else {\n", " if (input[0] <= 0.9021739363670349) {\n", " if (input[2] <= 0.6939745247364044) {\n", " var0 = 48970.24609375;\n", " } else {\n", " var0 = 48675.51953125;\n", " }\n", " } else {\n", " var0 = 48673.55859375;\n", " }\n", " }\n", " }\n", " }\n", " }\n", " }\n", " } else {\n", " if (input[0] <= 0.75) {\n", " var0 = 60021.3984375;\n", " } else {\n", " if (input[2] <= 0.6122605502605438) {\n", " if (input[0] <= 0.9347826242446899) {\n", " if (input[1] <= 0.5) {\n", " var0 = 46661.44140625;\n", " } else {\n", " var0 = 46130.52734375;\n", " }\n", " } else {\n", " var0 = 46718.1640625;\n", " }\n", " } else {\n", " var0 = 48549.1796875;\n", " }\n", " }\n", " }\n", " }\n", " }\n", " }\n", " return var0;\n", " }\n", "}\n", "\n" ] } ], "source": [ "# transpiles learned function to java\n", "print(convert_model(dt, language = 'java'))" ] }, { "attachments": {}, "cell_type": "markdown", "id": "ed00202c", "metadata": {}, "source": [ "## ✅ Deploy Model\n", "This function deploys the entire ML pipeline on the cloud.\n", "\n", "**AWS:** When deploying model on AWS S3, environment variables must be configured using the command-line interface. To configure AWS environment variables, type `aws configure` in terminal. The following information is required which can be generated using the Identity and Access Management (IAM) portal of your amazon console account:\n", "\n", "- AWS Access Key ID\n", "- AWS Secret Key Access\n", "- Default Region Name (can be seen under Global settings on your AWS console)\n", "- Default output format (must be left blank)\n", "\n", "**GCP:** To deploy a model on Google Cloud Platform ('gcp'), the project must be created using the command-line or GCP console. Once the project is created, you must create a service account and download the service account key as a JSON file to set environment variables in your local environment. Learn more about it: https://cloud.google.com/docs/authentication/production\n", "\n", "**Azure:** To deploy a model on Microsoft Azure ('azure'), environment variables for the connection string must be set in your local environment. Go to settings of storage account on Azure portal to access the connection string required.\n", "AZURE_STORAGE_CONNECTION_STRING (required as environment variable)\n", "Learn more about it: https://docs.microsoft.com/en-us/azure/storage/blobs/storage-quickstart-blobs-python?toc=%2Fpython%2Fazure%2FTOC.json" ] }, { "cell_type": "code", "execution_count": null, "id": "40b20a18", "metadata": {}, "outputs": [], "source": [ "# deploy model on aws s3\n", "# deploy_model(best, model_name = 'my_first_platform_on_aws',\n", "# platform = 'aws', authentication = {'bucket' : 'pycaret-test'})" ] }, { "cell_type": "code", "execution_count": null, "id": "9e236516", "metadata": {}, "outputs": [], "source": [ "# load model from aws s3\n", "# loaded_from_aws = load_model(model_name = 'my_first_platform_on_aws', platform = 'aws',\n", "# authentication = {'bucket' : 'pycaret-test'})\n", "\n", "# loaded_from_aws" ] }, { "attachments": {}, "cell_type": "markdown", "id": "e169ae86", "metadata": {}, "source": [ "## ✅ Save / Load Model\n", "This function saves the transformation pipeline and a trained model object into the current working directory as a pickle file for later use." ] }, { "cell_type": "code", "execution_count": null, "id": "bc5cf24a", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Transformation Pipeline and Model Successfully Saved\n" ] }, { "data": { "text/plain": [ "(Pipeline(memory=FastMemory(location=C:\\Users\\owner\\AppData\\Local\\Temp\\joblib),\n", " steps=[('numerical_imputer',\n", " TransformerWrapper(include=['age', 'bmi', 'children'],\n", " transformer=SimpleImputer())),\n", " ('categorical_imputer',\n", " TransformerWrapper(include=['sex', 'smoker', 'region'],\n", " transformer=SimpleImputer(strategy='most_frequent'))),\n", " ('ordinal_encoding',\n", " TransformerW...\n", " 'female': 0,\n", " 'male': 1}},\n", " {'col': 'smoker',\n", " 'mapping': {nan: -1,\n", " 'no': 0,\n", " 'yes': 1}}]))),\n", " ('onehot_encoding',\n", " TransformerWrapper(include=['region'],\n", " transformer=OneHotEncoder(cols=['region'],\n", " handle_missing='return_nan',\n", " use_cat_names=True))),\n", " ('normalize', TransformerWrapper(transformer=MinMaxScaler())),\n", " ('trained_model', GradientBoostingRegressor(random_state=123))]),\n", " 'my_first_model.pkl')" ] }, "execution_count": 96, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# save model\n", "save_model(best, 'my_first_model')" ] }, { "cell_type": "code", "execution_count": null, "id": "e8478d34", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Transformation Pipeline and Model Successfully Loaded\n" ] }, { "data": { "text/html": [ "
Pipeline(memory=FastMemory(location=C:\\Users\\owner\\AppData\\Local\\Temp\\joblib),\n",
       "         steps=[('numerical_imputer',\n",
       "                 TransformerWrapper(include=['age', 'bmi', 'children'],\n",
       "                                    transformer=SimpleImputer())),\n",
       "                ('categorical_imputer',\n",
       "                 TransformerWrapper(include=['sex', 'smoker', 'region'],\n",
       "                                    transformer=SimpleImputer(strategy='most_frequent'))),\n",
       "                ('ordinal_encoding',\n",
       "                 TransformerW...\n",
       "                                                                                     'female': 0,\n",
       "                                                                                     'male': 1}},\n",
       "                                                                        {'col': 'smoker',\n",
       "                                                                         'mapping': {nan: -1,\n",
       "                                                                                     'no': 0,\n",
       "                                                                                     'yes': 1}}]))),\n",
       "                ('onehot_encoding',\n",
       "                 TransformerWrapper(include=['region'],\n",
       "                                    transformer=OneHotEncoder(cols=['region'],\n",
       "                                                              handle_missing='return_nan',\n",
       "                                                              use_cat_names=True))),\n",
       "                ('normalize', TransformerWrapper(transformer=MinMaxScaler())),\n",
       "                ('trained_model', GradientBoostingRegressor(random_state=123))])
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
" ], "text/plain": [ "Pipeline(memory=FastMemory(location=C:\\Users\\owner\\AppData\\Local\\Temp\\joblib),\n", " steps=[('numerical_imputer',\n", " TransformerWrapper(include=['age', 'bmi', 'children'],\n", " transformer=SimpleImputer())),\n", " ('categorical_imputer',\n", " TransformerWrapper(include=['sex', 'smoker', 'region'],\n", " transformer=SimpleImputer(strategy='most_frequent'))),\n", " ('ordinal_encoding',\n", " TransformerW...\n", " 'female': 0,\n", " 'male': 1}},\n", " {'col': 'smoker',\n", " 'mapping': {nan: -1,\n", " 'no': 0,\n", " 'yes': 1}}]))),\n", " ('onehot_encoding',\n", " TransformerWrapper(include=['region'],\n", " transformer=OneHotEncoder(cols=['region'],\n", " handle_missing='return_nan',\n", " use_cat_names=True))),\n", " ('normalize', TransformerWrapper(transformer=MinMaxScaler())),\n", " ('trained_model', GradientBoostingRegressor(random_state=123))])" ] }, "execution_count": 97, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# load model\n", "loaded_from_disk = load_model('my_first_model')\n", "loaded_from_disk" ] }, { "attachments": {}, "cell_type": "markdown", "id": "de5eee8c", "metadata": {}, "source": [ "## ✅ Save / Load Experiment\n", "This function saves all the experiment variables on disk, allowing to later resume without rerunning the setup function." ] }, { "cell_type": "code", "execution_count": null, "id": "6a3c61b6", "metadata": {}, "outputs": [], "source": [ "# save experiment\n", "save_experiment('my_experiment')" ] }, { "cell_type": "code", "execution_count": null, "id": "83252c09", "metadata": {}, "outputs": [ { "data": { "text/html": [ "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
 DescriptionValue
0Session id123
1Targetcharges
2Target typeRegression
3Original data shape(1338, 7)
4Transformed data shape(1338, 10)
5Transformed train set shape(936, 10)
6Transformed test set shape(402, 10)
7Ordinal features2
8Numeric features3
9Categorical features3
10PreprocessTrue
11Imputation typesimple
12Numeric imputationmean
13Categorical imputationmode
14Maximum one-hot encoding25
15Encoding methodNone
16NormalizeTrue
17Normalize methodminmax
18Fold GeneratorKFold
19Fold Number10
20CPU Jobs-1
21Use GPUFalse
22Log ExperimentFalse
23Experiment Namereg-default-name
24USI7443
\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "# load experiment from disk\n", "exp_from_disk = load_experiment('my_experiment', data=data)" ] }, { "cell_type": "code", "execution_count": null, "id": "154571c1", "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": ".venv", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.11.9" } }, "nbformat": 4, "nbformat_minor": 5 }