{ "cells": [ { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [], "source": [ "from HiddenMess import *\n", "\n", "import pandas as pd\n", "import numpy as np\n", "import pickle\n", "import warnings\n", "warnings.filterwarnings('ignore')\n", "\n", "from sympy.parsing.sympy_parser import parse_expr\n", "from sympy import simplify, init_printing, Float\n", "from sympy.printing.str import StrPrinter\n", "\n", "init_printing(use_unicode=True)\n", "StrPrinter({'full_prec': False}).doprint(Float('10000000', 5))\n", "\n", "cm = sns.light_palette(\"green\", as_cmap=True)\n", "\n", "\n", "import matplotlib.pyplot as plt\n", "import seaborn as sns\n", "%matplotlib inline\n", "\n", "from ipywidgets import interact, interactive, fixed, interact_manual\n", "import ipywidgets as widgets" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [], "source": [ "df, medians = loadEverything()" ] }, { "cell_type": "code", "execution_count": 3, "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", "
DatasetChemical-IF05128-f1F05128-f2TowerairfoilconcretecpuenergyCoolingenergyHeatingtowerDatawineRedwineWhiteyacht
Algorithm
ElasticNet0.3754310.005082210.004572440.95736.2028210.258939.4824.40384.4057443.57870.6471880.765998.72393
IT-ELM (Lasso)0.3712430.003260833.1633425.48572.84096.9136215.4271.430930.44320727.87710.6394220.7331731.0104
IT-ELM (OMP)0.3913620.003031120.0027222624.73192.595266.8546735.81741.305260.48439723.7040.6733370.7358021.3655
Lars0.3643760.007391830.0066969428.54784.7441210.265229.10363.200192.8649529.7090.6449010.7486368.66475
Lasso0.3754310.005081910.0045721631.86966.176910.259936.93964.086734.1662633.16320.6463970.7597238.6779
MLP0.4510450.02303510.029716718.02284.769487.6671225.15163.28792.6786317.46730.6255960.6933882.19458
Ridge0.1529030.005082910.004549727.72814.8041910.265229.15193.21042.9213929.3120.6454090.7530938.70156
SymTree0.2423770.004917760.00232647nan2.205066.0730722.82161.677750.582412nan0.664746nan2.04592
XGBoost0.3303350.003661170.0044623615.9341.796614.1272838.56460.7290280.32835415.73210.5856090.6564930.796345
" ], "text/plain": [ "" ] }, "execution_count": 3, "metadata": {}, "output_type": "execute_result" } ], "source": [ "(medians\n", " .pivot(index='Algorithm', columns='Dataset', values='RMSE')\n", " .style.background_gradient(cmap=cm)\n", ")" ] }, { "cell_type": "code", "execution_count": 4, "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", "
DatasetChemical-IF05128-f1F05128-f2TowerairfoilconcretecpuenergyCoolingenergyHeatingtowerDatawineRedwineWhiteyacht
Algorithm
ElasticNet211193845520776
IT-ELM (Lasso)1.539953.54039.511.577.5133.559123326
IT-ELM (OMP)15234.524.5113276340.5486.5
Lars2211458777249101
Lasso211133845513763
MLP321502000200037550300045002855045004500375509003055028050
Ridge573325587882511116
SymTree476424nan9753296268nan380nan176
XGBoost2740.54629781276.51245.53781139.51681.52920.5734.52237.5643
" ], "text/plain": [ "" ] }, "execution_count": 4, "metadata": {}, "output_type": "execute_result" } ], "source": [ "(medians\n", " .pivot(index='Algorithm', columns='Dataset', values='Complexity')\n", " .style.background_gradient(cmap=cm)\n", ")" ] }, { "cell_type": "code", "execution_count": 5, "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", "
Rank
Algorithm
XGBoost2
SymTree3.3
IT-ELM (Lasso)3.53846
IT-ELM (OMP)3.84615
MLP5
Ridge5.69231
Lars5.76923
Lasso6.76923
ElasticNet7.76923
" ], "text/plain": [ "" ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" } ], "source": [ "(medians[['Algorithm','Rank']]\n", " .groupby('Algorithm')\n", " .mean()\n", " .sort_values(by='Rank')\n", " .style.bar(color='#00CCCC'))" ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [ { "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "b4d794b668944952bcf18d8e710dd889", "version_major": 2, "version_minor": 0 }, "text/plain": [ "A Jupyter Widget" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/plain": [ "" ] }, "execution_count": 6, "metadata": {}, "output_type": "execute_result" } ], "source": [ "interact(plot_boxplots, df=fixed(df), dataset=datasets)" ] }, { "cell_type": "code", "execution_count": 7, "metadata": {}, "outputs": [ { "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "f07015f71ce04170a9c80384697f365f", "version_major": 2, "version_minor": 0 }, "text/plain": [ "A Jupyter Widget" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/plain": [ "" ] }, "execution_count": 7, "metadata": {}, "output_type": "execute_result" } ], "source": [ "interact(plot_scatterplots, df=fixed(df), dataset=datasets)" ] }, { "cell_type": "code", "execution_count": 8, "metadata": {}, "outputs": [], "source": [ "modelCPU, modelYacht, modelF1 = getModels()" ] }, { "cell_type": "code", "execution_count": 9, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "RMSE: 0.003\n" ] }, { "data": { "image/png": "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\n", "text/latex": [ "$$- 0.008335664777798533 \\operatorname{log1p}{\\left (p^{2} t^{2} v \\right )} + 0.0010508292822691216 \\sin{\\left (t v^{2} \\right )} + 0.0030634289108626912 \\cos{\\left (p \\right )} + 0.0008666900032585058 \\cos{\\left (p^{2} t v^{2} \\right )} - 4.0630979881092915 \\cdot 10^{-5} \\tan{\\left (p^{2} t^{2} v^{2} \\right )}$$" ], "text/plain": [ " ⎛ 2 2 ⎞ ⎛ 2⎞ \n", "- 0.008335664777798533⋅log1p⎝p ⋅t ⋅v⎠ + 0.0010508292822691216⋅sin⎝t⋅v ⎠ + 0.00\n", "\n", " ⎛ 2 2⎞ \n", "30634289108626912⋅cos(p) + 0.0008666900032585058⋅cos⎝p ⋅t⋅v ⎠ - 4.063097988109\n", "\n", " ⎛ 2 2 2⎞\n", "2915e-5⋅tan⎝p ⋅t ⋅v ⎠" ] }, "execution_count": 9, "metadata": {}, "output_type": "execute_result" } ], "source": [ "expr = parse_expr(genExprStr(modelF1).replace('x0', 'p').replace('x1', 'v').replace('x2','t'))\n", "print('RMSE: 0.003')\n", "simplify(expr)" ] }, { "cell_type": "code", "execution_count": 10, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "RMSE: 14.82\n" ] }, { "data": { "image/png": "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\n", "text/latex": [ "$$0.8631183430497685 cache + 1.2023140666505465 \\cdot 10^{-5} \\sqrt{maxChan maxMem^{2} minMem}$$" ], "text/plain": [ " ________________________\n", " ╱ 2 \n", "0.8631183430497685⋅cache + 1.2023140666505465e-5⋅╲╱ maxChan⋅maxMem ⋅minMem " ] }, "execution_count": 10, "metadata": {}, "output_type": "execute_result" } ], "source": [ "expr = parse_expr(genExprStr(modelCPU).replace('x2','maxMem').replace('x1', 'minMem').replace('x3', 'cache').replace('x5','maxChan'))\n", "print('RMSE: 14.82')\n", "expr.expand()#.simplify()" ] }, { "cell_type": "code", "execution_count": 11, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "RMSE: 0.97\n" ] }, { "data": { "image/png": "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\n", "text/latex": [ "$$2.104730832776085 \\sin{\\left (\\frac{x_{0} x_{3}^{3}}{x_{4}^{2}} x_{5}^{3} \\right )} - 28.69561347585639 \\tanh{\\left (\\frac{1}{x_{1}^{3} x_{3} x_{4} x_{5}} \\right )} - 837.9635200782303 \\tanh{\\left (\\frac{x_{3} x_{4}^{2}}{x_{2}^{3} x_{5}^{2}} \\right )} - \\frac{x_{2}^{3} x_{3}^{2}}{x_{1}^{3}} 1.6504203694683384 \\cdot 10^{-5} x_{4}^{2}$$" ], "text/plain": [ " ⎛ 3 3⎞ \n", " ⎜x₀⋅x₃ ⋅x₅ ⎟ ⎛ 1 ⎞ \n", "2.104730832776085⋅sin⎜──────────⎟ - 28.69561347585639⋅tanh⎜────────────⎟ - 837\n", " ⎜ 2 ⎟ ⎜ 3 ⎟ \n", " ⎝ x₄ ⎠ ⎝x₁ ⋅x₃⋅x₄⋅x₅⎠ \n", "\n", " ⎛ 2⎞ 3 2 2\n", " ⎜ x₃⋅x₄ ⎟ 1.6504203694683384e-5⋅x₂ ⋅x₃ ⋅x₄ \n", ".9635200782303⋅tanh⎜───────⎟ - ─────────────────────────────────\n", " ⎜ 3 2⎟ 3 \n", " ⎝x₂ ⋅x₅ ⎠ x₁ " ] }, "execution_count": 11, "metadata": {}, "output_type": "execute_result" } ], "source": [ "expr = parse_expr(genExprStr(modelYacht))\n", "print('RMSE: 0.97')\n", "simplify(expr)" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "Python 3", "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": "3.6.3" } }, "nbformat": 4, "nbformat_minor": 2 }