{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"name": "pycaret_ts_architecture.ipynb",
"provenance": [],
"collapsed_sections": [],
"authorship_tag": "ABX9TyP5Ri9a6A6rI9T3SotaFVkq",
"include_colab_link": true
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
},
"language_info": {
"name": "python"
},
"widgets": {
"application/vnd.jupyter.widget-state+json": {
"9980f0f1fe054bd7b0e456745c359bcf": {
"model_module": "@jupyter-widgets/controls",
"model_name": "IntProgressModel",
"model_module_version": "1.5.0",
"state": {
"_view_name": "ProgressView",
"style": "IPY_MODEL_516c8ff6302849dbb3ac8a97ca89ff3c",
"_dom_classes": [],
"description": "Processing: ",
"_model_name": "IntProgressModel",
"bar_style": "",
"max": 3,
"_view_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"value": 3,
"_view_count": null,
"_view_module_version": "1.5.0",
"orientation": "horizontal",
"min": 0,
"description_tooltip": null,
"_model_module": "@jupyter-widgets/controls",
"layout": "IPY_MODEL_78cf30b0d262460ebbfa30c6c82fc9ad"
}
},
"516c8ff6302849dbb3ac8a97ca89ff3c": {
"model_module": "@jupyter-widgets/controls",
"model_name": "ProgressStyleModel",
"model_module_version": "1.5.0",
"state": {
"_view_name": "StyleView",
"_model_name": "ProgressStyleModel",
"description_width": "",
"_view_module": "@jupyter-widgets/base",
"_model_module_version": "1.5.0",
"_view_count": null,
"_view_module_version": "1.2.0",
"bar_color": null,
"_model_module": "@jupyter-widgets/controls"
}
},
"78cf30b0d262460ebbfa30c6c82fc9ad": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"model_module_version": "1.2.0",
"state": {
"_view_name": "LayoutView",
"grid_template_rows": null,
"right": null,
"justify_content": null,
"_view_module": "@jupyter-widgets/base",
"overflow": null,
"_model_module_version": "1.2.0",
"_view_count": null,
"flex_flow": null,
"width": null,
"min_width": null,
"border": null,
"align_items": null,
"bottom": null,
"_model_module": "@jupyter-widgets/base",
"top": null,
"grid_column": null,
"overflow_y": null,
"overflow_x": null,
"grid_auto_flow": null,
"grid_area": null,
"grid_template_columns": null,
"flex": null,
"_model_name": "LayoutModel",
"justify_items": null,
"grid_row": null,
"max_height": null,
"align_content": null,
"visibility": null,
"align_self": null,
"height": null,
"min_height": null,
"padding": null,
"grid_auto_rows": null,
"grid_gap": null,
"max_width": null,
"order": null,
"_view_module_version": "1.2.0",
"grid_template_areas": null,
"object_position": null,
"object_fit": null,
"grid_auto_columns": null,
"margin": null,
"display": null,
"left": null
}
},
"27cc64d7b762434c83e262ca14708f4d": {
"model_module": "@jupyter-widgets/controls",
"model_name": "IntProgressModel",
"model_module_version": "1.5.0",
"state": {
"_view_name": "ProgressView",
"style": "IPY_MODEL_e4e25112bf6945a8ba2df14307b7bfff",
"_dom_classes": [],
"description": "Processing: ",
"_model_name": "IntProgressModel",
"bar_style": "",
"max": 4,
"_view_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"value": 4,
"_view_count": null,
"_view_module_version": "1.5.0",
"orientation": "horizontal",
"min": 0,
"description_tooltip": null,
"_model_module": "@jupyter-widgets/controls",
"layout": "IPY_MODEL_bf57f05fdac642fcab8339321952f6e5"
}
},
"e4e25112bf6945a8ba2df14307b7bfff": {
"model_module": "@jupyter-widgets/controls",
"model_name": "ProgressStyleModel",
"model_module_version": "1.5.0",
"state": {
"_view_name": "StyleView",
"_model_name": "ProgressStyleModel",
"description_width": "",
"_view_module": "@jupyter-widgets/base",
"_model_module_version": "1.5.0",
"_view_count": null,
"_view_module_version": "1.2.0",
"bar_color": null,
"_model_module": "@jupyter-widgets/controls"
}
},
"bf57f05fdac642fcab8339321952f6e5": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"model_module_version": "1.2.0",
"state": {
"_view_name": "LayoutView",
"grid_template_rows": null,
"right": null,
"justify_content": null,
"_view_module": "@jupyter-widgets/base",
"overflow": null,
"_model_module_version": "1.2.0",
"_view_count": null,
"flex_flow": null,
"width": null,
"min_width": null,
"border": null,
"align_items": null,
"bottom": null,
"_model_module": "@jupyter-widgets/base",
"top": null,
"grid_column": null,
"overflow_y": null,
"overflow_x": null,
"grid_auto_flow": null,
"grid_area": null,
"grid_template_columns": null,
"flex": null,
"_model_name": "LayoutModel",
"justify_items": null,
"grid_row": null,
"max_height": null,
"align_content": null,
"visibility": null,
"align_self": null,
"height": null,
"min_height": null,
"padding": null,
"grid_auto_rows": null,
"grid_gap": null,
"max_width": null,
"order": null,
"_view_module_version": "1.2.0",
"grid_template_areas": null,
"object_position": null,
"object_fit": null,
"grid_auto_columns": null,
"margin": null,
"display": null,
"left": null
}
},
"9809210362bf479abd6e28d015dc46f9": {
"model_module": "@jupyter-widgets/controls",
"model_name": "IntProgressModel",
"model_module_version": "1.5.0",
"state": {
"_view_name": "ProgressView",
"style": "IPY_MODEL_15d608a77faa4464a2a28d24d1b95adf",
"_dom_classes": [],
"description": "Processing: ",
"_model_name": "IntProgressModel",
"bar_style": "",
"max": 4,
"_view_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"value": 4,
"_view_count": null,
"_view_module_version": "1.5.0",
"orientation": "horizontal",
"min": 0,
"description_tooltip": null,
"_model_module": "@jupyter-widgets/controls",
"layout": "IPY_MODEL_dcd168e55f8c427d80f0ac3eae746088"
}
},
"15d608a77faa4464a2a28d24d1b95adf": {
"model_module": "@jupyter-widgets/controls",
"model_name": "ProgressStyleModel",
"model_module_version": "1.5.0",
"state": {
"_view_name": "StyleView",
"_model_name": "ProgressStyleModel",
"description_width": "",
"_view_module": "@jupyter-widgets/base",
"_model_module_version": "1.5.0",
"_view_count": null,
"_view_module_version": "1.2.0",
"bar_color": null,
"_model_module": "@jupyter-widgets/controls"
}
},
"dcd168e55f8c427d80f0ac3eae746088": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"model_module_version": "1.2.0",
"state": {
"_view_name": "LayoutView",
"grid_template_rows": null,
"right": null,
"justify_content": null,
"_view_module": "@jupyter-widgets/base",
"overflow": null,
"_model_module_version": "1.2.0",
"_view_count": null,
"flex_flow": null,
"width": null,
"min_width": null,
"border": null,
"align_items": null,
"bottom": null,
"_model_module": "@jupyter-widgets/base",
"top": null,
"grid_column": null,
"overflow_y": null,
"overflow_x": null,
"grid_auto_flow": null,
"grid_area": null,
"grid_template_columns": null,
"flex": null,
"_model_name": "LayoutModel",
"justify_items": null,
"grid_row": null,
"max_height": null,
"align_content": null,
"visibility": null,
"align_self": null,
"height": null,
"min_height": null,
"padding": null,
"grid_auto_rows": null,
"grid_gap": null,
"max_width": null,
"order": null,
"_view_module_version": "1.2.0",
"grid_template_areas": null,
"object_position": null,
"object_fit": null,
"grid_auto_columns": null,
"margin": null,
"display": null,
"left": null
}
},
"89546f23763544119e3f2684c986ecc2": {
"model_module": "@jupyter-widgets/controls",
"model_name": "IntProgressModel",
"model_module_version": "1.5.0",
"state": {
"_view_name": "ProgressView",
"style": "IPY_MODEL_c60317db8b684206bdbe3b50b5e6681c",
"_dom_classes": [],
"description": "Processing: ",
"_model_name": "IntProgressModel",
"bar_style": "",
"max": 4,
"_view_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"value": 4,
"_view_count": null,
"_view_module_version": "1.5.0",
"orientation": "horizontal",
"min": 0,
"description_tooltip": null,
"_model_module": "@jupyter-widgets/controls",
"layout": "IPY_MODEL_9fa888acaa094ef8bb6e74c20b600485"
}
},
"c60317db8b684206bdbe3b50b5e6681c": {
"model_module": "@jupyter-widgets/controls",
"model_name": "ProgressStyleModel",
"model_module_version": "1.5.0",
"state": {
"_view_name": "StyleView",
"_model_name": "ProgressStyleModel",
"description_width": "",
"_view_module": "@jupyter-widgets/base",
"_model_module_version": "1.5.0",
"_view_count": null,
"_view_module_version": "1.2.0",
"bar_color": null,
"_model_module": "@jupyter-widgets/controls"
}
},
"9fa888acaa094ef8bb6e74c20b600485": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"model_module_version": "1.2.0",
"state": {
"_view_name": "LayoutView",
"grid_template_rows": null,
"right": null,
"justify_content": null,
"_view_module": "@jupyter-widgets/base",
"overflow": null,
"_model_module_version": "1.2.0",
"_view_count": null,
"flex_flow": null,
"width": null,
"min_width": null,
"border": null,
"align_items": null,
"bottom": null,
"_model_module": "@jupyter-widgets/base",
"top": null,
"grid_column": null,
"overflow_y": null,
"overflow_x": null,
"grid_auto_flow": null,
"grid_area": null,
"grid_template_columns": null,
"flex": null,
"_model_name": "LayoutModel",
"justify_items": null,
"grid_row": null,
"max_height": null,
"align_content": null,
"visibility": null,
"align_self": null,
"height": null,
"min_height": null,
"padding": null,
"grid_auto_rows": null,
"grid_gap": null,
"max_width": null,
"order": null,
"_view_module_version": "1.2.0",
"grid_template_areas": null,
"object_position": null,
"object_fit": null,
"grid_auto_columns": null,
"margin": null,
"display": null,
"left": null
}
},
"a98fcdc0d73443ddad2d6a986a430501": {
"model_module": "@jupyter-widgets/controls",
"model_name": "IntProgressModel",
"model_module_version": "1.5.0",
"state": {
"_view_name": "ProgressView",
"style": "IPY_MODEL_4f1c43a4ce1d4f4e81433e652849cb96",
"_dom_classes": [],
"description": "Processing: ",
"_model_name": "IntProgressModel",
"bar_style": "",
"max": 4,
"_view_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"value": 4,
"_view_count": null,
"_view_module_version": "1.5.0",
"orientation": "horizontal",
"min": 0,
"description_tooltip": null,
"_model_module": "@jupyter-widgets/controls",
"layout": "IPY_MODEL_18cb971747a54ab0a6acd4bc23afb2ca"
}
}
}
}
},
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "view-in-github",
"colab_type": "text"
},
"source": [
"<a href=\"https://colab.research.google.com/github/ngupta23/medium_articles/blob/main/time_series/pycaret/pycaret_ts_architecture.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
]
},
{
"cell_type": "code",
"metadata": {
"id": "-tCKH8JxbGu2"
},
"source": [
"try:\n",
" import pycaret\n",
"except:\n",
" !pip install pycaret-ts-alpha"
],
"execution_count": 1,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "1W1wYHilbKHC",
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "e78dc408-28f9-4f8e-a03a-28b0b2093321"
},
"source": [
"#### Import libraries ----\n",
"from pprint import pprint\n",
"from pycaret.datasets import get_data\n",
"from pycaret.internal.pycaret_experiment import TimeSeriesExperiment"
],
"execution_count": 2,
"outputs": [
{
"output_type": "stream",
"name": "stderr",
"text": [
"/usr/local/lib/python3.7/dist-packages/distributed/config.py:20: YAMLLoadWarning: calling yaml.load() without Loader=... is deprecated, as the default Loader is unsafe. Please read https://msg.pyyaml.org/load for full details.\n",
" defaults = yaml.load(f)\n"
]
}
]
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 146
},
"id": "g8NyAM33bvc8",
"outputId": "37f6dd0a-35ce-462b-a2ae-8c4afbb29e04"
},
"source": [
"#### Get the data ---\n",
"y = get_data(\"airline\")\n"
],
"execution_count": 3,
"outputs": [
{
"output_type": "display_data",
"data": {
"text/plain": [
"Period\n",
"1949-01 112.0\n",
"1949-02 118.0\n",
"1949-03 132.0\n",
"1949-04 129.0\n",
"1949-05 121.0\n",
"Freq: M, Name: Number of airline passengers, dtype: float64"
]
},
"metadata": {}
}
]
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 695,
"referenced_widgets": [
"9980f0f1fe054bd7b0e456745c359bcf",
"516c8ff6302849dbb3ac8a97ca89ff3c",
"78cf30b0d262460ebbfa30c6c82fc9ad"
]
},
"id": "WXuVXJdGb0Pb",
"outputId": "3d7a99e0-314a-4491-e8f8-8dd7fa826531"
},
"source": [
"#### Setup the experiment ----\n",
"exp = TimeSeriesExperiment()\n",
"exp.setup(data=y, fh=12, seasonal_period=12, session_id=42)"
],
"execution_count": 4,
"outputs": [
{
"output_type": "display_data",
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Description</th>\n",
" <th>Value</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>session_id</td>\n",
" <td>42</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>Original Data</td>\n",
" <td>(144, 1)</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>Missing Values</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>Transformed Train Set</td>\n",
" <td>(132,)</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>Transformed Test Set</td>\n",
" <td>(12,)</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>Fold Generator</td>\n",
" <td>ExpandingWindowSplitter</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>Fold Number</td>\n",
" <td>3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>Enforce Prediction Interval</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>Seasonal Period Tested</td>\n",
" <td>12</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>Seasonality Detected</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10</th>\n",
" <td>Target Strictly Positive</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11</th>\n",
" <td>Target White Noise</td>\n",
" <td>No</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12</th>\n",
" <td>Recommended d</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13</th>\n",
" <td>Recommended Seasonal D</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14</th>\n",
" <td>CPU Jobs</td>\n",
" <td>-1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15</th>\n",
" <td>Use GPU</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16</th>\n",
" <td>Log Experiment</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>17</th>\n",
" <td>Experiment Name</td>\n",
" <td>ts-default-name</td>\n",
" </tr>\n",
" <tr>\n",
" <th>18</th>\n",
" <td>USI</td>\n",
" <td>f18d</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19</th>\n",
" <td>Imputation Type</td>\n",
" <td>simple</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Description Value\n",
"0 session_id 42\n",
"1 Original Data (144, 1)\n",
"2 Missing Values False\n",
"3 Transformed Train Set (132,)\n",
"4 Transformed Test Set (12,)\n",
"5 Fold Generator ExpandingWindowSplitter\n",
"6 Fold Number 3\n",
"7 Enforce Prediction Interval False\n",
"8 Seasonal Period Tested 12\n",
"9 Seasonality Detected True\n",
"10 Target Strictly Positive True\n",
"11 Target White Noise No\n",
"12 Recommended d 1\n",
"13 Recommended Seasonal D 1\n",
"14 CPU Jobs -1\n",
"15 Use GPU False\n",
"16 Log Experiment False\n",
"17 Experiment Name ts-default-name\n",
"18 USI f18d\n",
"19 Imputation Type simple"
]
},
"metadata": {}
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<pycaret.internal.pycaret_experiment.time_series_experiment.TimeSeriesExperiment at 0x7f39adfe0f90>"
]
},
"metadata": {},
"execution_count": 4
}
]
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 206,
"referenced_widgets": [
"27cc64d7b762434c83e262ca14708f4d",
"e4e25112bf6945a8ba2df14307b7bfff",
"bf57f05fdac642fcab8339321952f6e5",
"9809210362bf479abd6e28d015dc46f9",
"15d608a77faa4464a2a28d24d1b95adf",
"dcd168e55f8c427d80f0ac3eae746088",
"89546f23763544119e3f2684c986ecc2",
"c60317db8b684206bdbe3b50b5e6681c",
"9fa888acaa094ef8bb6e74c20b600485",
"a98fcdc0d73443ddad2d6a986a430501"
]
},
"id": "_2bvrfpIb4nt",
"outputId": "518b0374-19e0-4ec9-f0e3-e4a95ced3e3d"
},
"source": [
"#### Create different types of models ----\n",
"\n",
"# ARIMA model from `pmdarima`\n",
"arima_model = exp.create_model(\"arima\")\n",
"\n",
"# ETS and Exponential Smoothing models from `statsmodels`\n",
"ets_model = exp.create_model(\"ets\")\n",
"exp_smooth_model = exp.create_model(\"exp_smooth\")\n",
"\n",
"# Reduced Regression model using `sklearn` Linear Regression\n",
"lr_model = exp.create_model(\"lr_cds_dt\")"
],
"execution_count": 5,
"outputs": [
{
"output_type": "display_data",
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>cutoff</th>\n",
" <th>MAE</th>\n",
" <th>RMSE</th>\n",
" <th>MAPE</th>\n",
" <th>SMAPE</th>\n",
" <th>R2</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1956-12</td>\n",
" <td>38.6824</td>\n",
" <td>45.0820</td>\n",
" <td>0.0998</td>\n",
" <td>0.1051</td>\n",
" <td>0.3384</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1957-12</td>\n",
" <td>28.0608</td>\n",
" <td>34.6867</td>\n",
" <td>0.0751</td>\n",
" <td>0.0734</td>\n",
" <td>0.6848</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>1958-12</td>\n",
" <td>32.1693</td>\n",
" <td>38.2681</td>\n",
" <td>0.0737</td>\n",
" <td>0.0753</td>\n",
" <td>0.6724</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Mean</th>\n",
" <td>NaN</td>\n",
" <td>32.9708</td>\n",
" <td>39.3456</td>\n",
" <td>0.0828</td>\n",
" <td>0.0846</td>\n",
" <td>0.5652</td>\n",
" </tr>\n",
" <tr>\n",
" <th>SD</th>\n",
" <td>NaN</td>\n",
" <td>4.3731</td>\n",
" <td>4.3117</td>\n",
" <td>0.0120</td>\n",
" <td>0.0145</td>\n",
" <td>0.1604</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" cutoff MAE RMSE MAPE SMAPE R2\n",
"0 1956-12 38.6824 45.0820 0.0998 0.1051 0.3384\n",
"1 1957-12 28.0608 34.6867 0.0751 0.0734 0.6848\n",
"2 1958-12 32.1693 38.2681 0.0737 0.0753 0.6724\n",
"Mean NaN 32.9708 39.3456 0.0828 0.0846 0.5652\n",
"SD NaN 4.3731 4.3117 0.0120 0.0145 0.1604"
]
},
"metadata": {}
}
]
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "wfUW_tM9ibk4",
"outputId": "e170c7a1-ac4c-4099-aac2-9ff8e65ce142"
},
"source": [
"#### Check model types ----\n",
"print(type(arima_model)) # <-- sktime `pmdarima` adapter \n",
"print(type(ets_model)) # <-- sktime `statsmodels` adapter\n",
"print(type(exp_smooth_model)) # <-- sktime `statsmodels` adapter\n",
"print(type(lr_model)) # <-- Your custom sktime compatible model pipeline"
],
"execution_count": 6,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"<class 'sktime.forecasting.arima.ARIMA'>\n",
"<class 'sktime.forecasting.ets.AutoETS'>\n",
"<class 'sktime.forecasting.exp_smoothing.ExponentialSmoothing'>\n",
"<class 'pycaret.containers.models.time_series.BaseCdsDtForecaster'>\n"
]
}
]
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "44fIXKpMb81M",
"outputId": "eaaabf5a-9ac5-492f-e4e3-bf33bc4fe1f3"
},
"source": [
"#### Access internal models using `_forecaster` ----\n",
"print(type(arima_model._forecaster))\n",
"print(type(ets_model._forecaster))\n",
"print(type(exp_smooth_model._forecaster))\n",
"print(type(lr_model._forecaster))"
],
"execution_count": 7,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"<class 'pmdarima.arima.arima.ARIMA'>\n",
"<class 'statsmodels.tsa.exponential_smoothing.ets.ETSModel'>\n",
"<class 'statsmodels.tsa.holtwinters.model.ExponentialSmoothing'>\n",
"<class 'sktime.forecasting.compose._pipeline.TransformedTargetForecaster'>\n"
]
}
]
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "RvfOa4K0NGuI",
"outputId": "2b7a8053-730f-4408-e4b3-e9b84bf8ca7c"
},
"source": [
"#### What hyperparameters were used to train the model? ----\n",
"print(arima_model)"
],
"execution_count": 8,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"ARIMA(maxiter=50, method='lbfgs', order=(1, 0, 0), out_of_sample_size=0,\n",
" scoring='mse', scoring_args=None, seasonal_order=(0, 1, 0, 12),\n",
" start_params=None, suppress_warnings=False, trend=None,\n",
" with_intercept=True)\n"
]
}
]
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 430
},
"id": "WMiBrLwwMHNs",
"outputId": "81ee60d7-b1fc-4294-8240-c2700c42773e"
},
"source": [
"#### Access statistical fit properties using underlying `pmdarima`\n",
"arima_model._forecaster.summary()\n",
"\n",
"#### Alternately, use sktime's convenient wrapper to do so ---- \n",
"arima_model.summary()"
],
"execution_count": 9,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/html": [
"<table class=\"simpletable\">\n",
"<caption>SARIMAX Results</caption>\n",
"<tr>\n",
" <th>Dep. Variable:</th> <td>y</td> <th> No. Observations: </th> <td>132</td> \n",
"</tr>\n",
"<tr>\n",
" <th>Model:</th> <td>SARIMAX(1, 0, 0)x(0, 1, 0, 12)</td> <th> Log Likelihood </th> <td>-450.590</td>\n",
"</tr>\n",
"<tr>\n",
" <th>Date:</th> <td>Tue, 16 Nov 2021</td> <th> AIC </th> <td>907.180</td>\n",
"</tr>\n",
"<tr>\n",
" <th>Time:</th> <td>11:26:51</td> <th> BIC </th> <td>915.542</td>\n",
"</tr>\n",
"<tr>\n",
" <th>Sample:</th> <td>0</td> <th> HQIC </th> <td>910.576</td>\n",
"</tr>\n",
"<tr>\n",
" <th></th> <td> - 132</td> <th> </th> <td> </td> \n",
"</tr>\n",
"<tr>\n",
" <th>Covariance Type:</th> <td>opg</td> <th> </th> <td> </td> \n",
"</tr>\n",
"</table>\n",
"<table class=\"simpletable\">\n",
"<tr>\n",
" <td></td> <th>coef</th> <th>std err</th> <th>z</th> <th>P>|z|</th> <th>[0.025</th> <th>0.975]</th> \n",
"</tr>\n",
"<tr>\n",
" <th>intercept</th> <td> 5.7982</td> <td> 2.005</td> <td> 2.892</td> <td> 0.004</td> <td> 1.869</td> <td> 9.727</td>\n",
"</tr>\n",
"<tr>\n",
" <th>ar.L1</th> <td> 0.8100</td> <td> 0.061</td> <td> 13.261</td> <td> 0.000</td> <td> 0.690</td> <td> 0.930</td>\n",
"</tr>\n",
"<tr>\n",
" <th>sigma2</th> <td> 105.9407</td> <td> 12.533</td> <td> 8.453</td> <td> 0.000</td> <td> 81.377</td> <td> 130.505</td>\n",
"</tr>\n",
"</table>\n",
"<table class=\"simpletable\">\n",
"<tr>\n",
" <th>Ljung-Box (L1) (Q):</th> <td>2.30</td> <th> Jarque-Bera (JB): </th> <td>1.04</td> \n",
"</tr>\n",
"<tr>\n",
" <th>Prob(Q):</th> <td>0.13</td> <th> Prob(JB): </th> <td>0.60</td> \n",
"</tr>\n",
"<tr>\n",
" <th>Heteroskedasticity (H):</th> <td>1.34</td> <th> Skew: </th> <td>-0.07</td>\n",
"</tr>\n",
"<tr>\n",
" <th>Prob(H) (two-sided):</th> <td>0.36</td> <th> Kurtosis: </th> <td>3.43</td> \n",
"</tr>\n",
"</table><br/><br/>Warnings:<br/>[1] Covariance matrix calculated using the outer product of gradients (complex-step)."
],
"text/plain": [
"<class 'statsmodels.iolib.summary.Summary'>\n",
"\"\"\"\n",
" SARIMAX Results \n",
"==========================================================================================\n",
"Dep. Variable: y No. Observations: 132\n",
"Model: SARIMAX(1, 0, 0)x(0, 1, 0, 12) Log Likelihood -450.590\n",
"Date: Tue, 16 Nov 2021 AIC 907.180\n",
"Time: 11:26:51 BIC 915.542\n",
"Sample: 0 HQIC 910.576\n",
" - 132 \n",
"Covariance Type: opg \n",
"==============================================================================\n",
" coef std err z P>|z| [0.025 0.975]\n",
"------------------------------------------------------------------------------\n",
"intercept 5.7982 2.005 2.892 0.004 1.869 9.727\n",
"ar.L1 0.8100 0.061 13.261 0.000 0.690 0.930\n",
"sigma2 105.9407 12.533 8.453 0.000 81.377 130.505\n",
"===================================================================================\n",
"Ljung-Box (L1) (Q): 2.30 Jarque-Bera (JB): 1.04\n",
"Prob(Q): 0.13 Prob(JB): 0.60\n",
"Heteroskedasticity (H): 1.34 Skew: -0.07\n",
"Prob(H) (two-sided): 0.36 Kurtosis: 3.43\n",
"===================================================================================\n",
"\n",
"Warnings:\n",
"[1] Covariance matrix calculated using the outer product of gradients (complex-step).\n",
"\"\"\""
]
},
"metadata": {},
"execution_count": 9
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "JM4wF9EBNS6A"
},
"source": [
"**You can not starts correlating these properties to the forecasts that you see. I will write about it in a subsewquent post.** "
]
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "CoDik7uHnxBp",
"outputId": "77182486-0108-4e4f-dd03-7299fec8ad9a"
},
"source": [
"#### What hyperparameters were used to train the model? ----\n",
"print(ets_model)"
],
"execution_count": 10,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"AutoETS(additive_only=False, allow_multiplicative_trend=False, auto=False,\n",
" bounds=None, callback=None, damped_trend=False, dates=None, disp=False,\n",
" error='add', freq=None, full_output=True, ignore_inf_ic=True,\n",
" information_criterion='aic', initial_level=None, initial_seasonal=None,\n",
" initial_trend=None, initialization_method='estimated', maxiter=1000,\n",
" missing='none', n_jobs=None, restrict=True, return_params=False,\n",
" seasonal='mul', sp=12, start_params=None, trend='add')\n"
]
}
]
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 729
},
"id": "XRJ7iyNRKAUi",
"outputId": "2fca8159-0001-4f9e-ec78-ee162cc0e783"
},
"source": [
"#### Access statsitical fit properties using underlying statsmodel\n",
"ets_model._forecaster.fit().summary()\n",
"\n",
"#### Alternatively, use sktime's convenient wrapper to do so ---- \n",
"ets_model.summary()"
],
"execution_count": 11,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/html": [
"<table class=\"simpletable\">\n",
"<caption>ETS Results</caption>\n",
"<tr>\n",
" <th>Dep. Variable:</th> <td>Number of airline passengers</td> <th> No. Observations: </th> <td>132</td> \n",
"</tr>\n",
"<tr>\n",
" <th>Model:</th> <td>ETS(AAM)</td> <th> Log Likelihood </th> <td>-488.626</td>\n",
"</tr>\n",
"<tr>\n",
" <th>Date:</th> <td>Tue, 16 Nov 2021</td> <th> AIC </th> <td>1013.253</td>\n",
"</tr>\n",
"<tr>\n",
" <th>Time:</th> <td>11:26:51</td> <th> BIC </th> <td>1065.143</td>\n",
"</tr>\n",
"<tr>\n",
" <th>Sample:</th> <td>01-31-1949</td> <th> HQIC </th> <td>1034.339</td>\n",
"</tr>\n",
"<tr>\n",
" <th></th> <td>- 12-31-1959</td> <th> Scale </th> <td>96.116</td> \n",
"</tr>\n",
"<tr>\n",
" <th>Covariance Type:</th> <td>approx</td> <th> </th> <td> </td> \n",
"</tr>\n",
"</table>\n",
"<table class=\"simpletable\">\n",
"<tr>\n",
" <td></td> <th>coef</th> <th>std err</th> <th>z</th> <th>P>|z|</th> <th>[0.025</th> <th>0.975]</th> \n",
"</tr>\n",
"<tr>\n",
" <th>smoothing_level</th> <td> 0.3734</td> <td> 0.067</td> <td> 5.550</td> <td> 0.000</td> <td> 0.242</td> <td> 0.505</td>\n",
"</tr>\n",
"<tr>\n",
" <th>smoothing_trend</th> <td> 3.734e-05</td> <td> nan</td> <td> nan</td> <td> nan</td> <td> nan</td> <td> nan</td>\n",
"</tr>\n",
"<tr>\n",
" <th>smoothing_seasonal</th> <td> 0.6265</td> <td> 0.067</td> <td> 9.296</td> <td> 0.000</td> <td> 0.494</td> <td> 0.759</td>\n",
"</tr>\n",
"<tr>\n",
" <th>initial_level</th> <td> 109.3470</td> <td> nan</td> <td> nan</td> <td> nan</td> <td> nan</td> <td> nan</td>\n",
"</tr>\n",
"<tr>\n",
" <th>initial_trend</th> <td> 2.6555</td> <td> nan</td> <td> nan</td> <td> nan</td> <td> nan</td> <td> nan</td>\n",
"</tr>\n",
"<tr>\n",
" <th>initial_seasonal.0</th> <td> 0.9773</td> <td> nan</td> <td> nan</td> <td> nan</td> <td> nan</td> <td> nan</td>\n",
"</tr>\n",
"<tr>\n",
" <th>initial_seasonal.1</th> <td> 0.8482</td> <td> nan</td> <td> nan</td> <td> nan</td> <td> nan</td> <td> nan</td>\n",
"</tr>\n",
"<tr>\n",
" <th>initial_seasonal.2</th> <td> 0.9508</td> <td> nan</td> <td> nan</td> <td> nan</td> <td> nan</td> <td> nan</td>\n",
"</tr>\n",
"<tr>\n",
" <th>initial_seasonal.3</th> <td> 1.0885</td> <td> nan</td> <td> nan</td> <td> nan</td> <td> nan</td> <td> nan</td>\n",
"</tr>\n",
"<tr>\n",
" <th>initial_seasonal.4</th> <td> 1.1927</td> <td> nan</td> <td> nan</td> <td> nan</td> <td> nan</td> <td> nan</td>\n",
"</tr>\n",
"<tr>\n",
" <th>initial_seasonal.5</th> <td> 1.2076</td> <td> nan</td> <td> nan</td> <td> nan</td> <td> nan</td> <td> nan</td>\n",
"</tr>\n",
"<tr>\n",
" <th>initial_seasonal.6</th> <td> 1.1092</td> <td> nan</td> <td> nan</td> <td> nan</td> <td> nan</td> <td> nan</td>\n",
"</tr>\n",
"<tr>\n",
" <th>initial_seasonal.7</th> <td> 1.0129</td> <td> nan</td> <td> nan</td> <td> nan</td> <td> nan</td> <td> nan</td>\n",
"</tr>\n",
"<tr>\n",
" <th>initial_seasonal.8</th> <td> 1.0970</td> <td> nan</td> <td> nan</td> <td> nan</td> <td> nan</td> <td> nan</td>\n",
"</tr>\n",
"<tr>\n",
" <th>initial_seasonal.9</th> <td> 1.1541</td> <td> nan</td> <td> nan</td> <td> nan</td> <td> nan</td> <td> nan</td>\n",
"</tr>\n",
"<tr>\n",
" <th>initial_seasonal.10</th> <td> 1.0517</td> <td> nan</td> <td> nan</td> <td> nan</td> <td> nan</td> <td> nan</td>\n",
"</tr>\n",
"<tr>\n",
" <th>initial_seasonal.11</th> <td> 1.0000</td> <td> nan</td> <td> nan</td> <td> nan</td> <td> nan</td> <td> nan</td>\n",
"</tr>\n",
"</table>\n",
"<table class=\"simpletable\">\n",
"<tr>\n",
" <th>Ljung-Box (Q):</th> <td>41.34</td> <th> Jarque-Bera (JB): </th> <td>1.25</td>\n",
"</tr>\n",
"<tr>\n",
" <th>Prob(Q):</th> <td>0.02</td> <th> Prob(JB): </th> <td>0.54</td>\n",
"</tr>\n",
"<tr>\n",
" <th>Heteroskedasticity (H):</th> <td>2.21</td> <th> Skew: </th> <td>0.11</td>\n",
"</tr>\n",
"<tr>\n",
" <th>Prob(H) (two-sided):</th> <td>0.01</td> <th> Kurtosis: </th> <td>3.42</td>\n",
"</tr>\n",
"</table><br/><br/>Warnings:<br/>[1] Covariance matrix calculated using numerical (complex-step) differentiation."
],
"text/plain": [
"<class 'statsmodels.iolib.summary.Summary'>\n",
"\"\"\"\n",
" ETS Results \n",
"========================================================================================\n",
"Dep. Variable: Number of airline passengers No. Observations: 132\n",
"Model: ETS(AAM) Log Likelihood -488.626\n",
"Date: Tue, 16 Nov 2021 AIC 1013.253\n",
"Time: 11:26:51 BIC 1065.143\n",
"Sample: 01-31-1949 HQIC 1034.339\n",
" - 12-31-1959 Scale 96.116\n",
"Covariance Type: approx \n",
"=======================================================================================\n",
" coef std err z P>|z| [0.025 0.975]\n",
"---------------------------------------------------------------------------------------\n",
"smoothing_level 0.3734 0.067 5.550 0.000 0.242 0.505\n",
"smoothing_trend 3.734e-05 nan nan nan nan nan\n",
"smoothing_seasonal 0.6265 0.067 9.296 0.000 0.494 0.759\n",
"initial_level 109.3470 nan nan nan nan nan\n",
"initial_trend 2.6555 nan nan nan nan nan\n",
"initial_seasonal.0 0.9773 nan nan nan nan nan\n",
"initial_seasonal.1 0.8482 nan nan nan nan nan\n",
"initial_seasonal.2 0.9508 nan nan nan nan nan\n",
"initial_seasonal.3 1.0885 nan nan nan nan nan\n",
"initial_seasonal.4 1.1927 nan nan nan nan nan\n",
"initial_seasonal.5 1.2076 nan nan nan nan nan\n",
"initial_seasonal.6 1.1092 nan nan nan nan nan\n",
"initial_seasonal.7 1.0129 nan nan nan nan nan\n",
"initial_seasonal.8 1.0970 nan nan nan nan nan\n",
"initial_seasonal.9 1.1541 nan nan nan nan nan\n",
"initial_seasonal.10 1.0517 nan nan nan nan nan\n",
"initial_seasonal.11 1.0000 nan nan nan nan nan\n",
"===================================================================================\n",
"Ljung-Box (Q): 41.34 Jarque-Bera (JB): 1.25\n",
"Prob(Q): 0.02 Prob(JB): 0.54\n",
"Heteroskedasticity (H): 2.21 Skew: 0.11\n",
"Prob(H) (two-sided): 0.01 Kurtosis: 3.42\n",
"===================================================================================\n",
"\n",
"Warnings:\n",
"[1] Covariance matrix calculated using numerical (complex-step) differentiation.\n",
"\"\"\""
]
},
"metadata": {},
"execution_count": 11
}
]
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "JwUusEPSc44V",
"outputId": "2bb38069-9062-439b-f407-2893e647e8d7"
},
"source": [
"#### sktime pipelines are similar to sklearn.\n",
"#### Access steps using `named_steps` attribute\n",
"print(lr_model._forecaster.named_steps.keys(), \"\\n\\n\")\n",
"\n",
"#### Details about the steps ----\n",
"pprint(lr_model._forecaster.named_steps)"
],
"execution_count": 12,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"dict_keys(['conditional_deseasonalise', 'detrend', 'forecast']) \n",
"\n",
"\n",
"{'conditional_deseasonalise': ConditionalDeseasonalizer(model='additive', seasonality_test=None, sp=1),\n",
" 'detrend': Detrender(forecaster=PolynomialTrendForecaster(degree=1, regressor=None,\n",
" with_intercept=True)),\n",
" 'forecast': RecursiveTabularRegressionForecaster(estimator=LinearRegression(copy_X=True,\n",
" fit_intercept=True,\n",
" n_jobs=-1,\n",
" normalize=False,\n",
" positive=False),\n",
" window_length=10)}\n"
]
}
]
}
]
}