diff --git a/AutoML_GSSoC.ipynb b/AutoML_GSSoC.ipynb new file mode 100644 index 0000000000..043b42531d --- /dev/null +++ b/AutoML_GSSoC.ipynb @@ -0,0 +1,4509 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": { + "id": "view-in-github", + "colab_type": "text" + }, + "source": [ + "\"Open" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "D4A_CnWX05cR" + }, + "source": [ + "# 1. Pycaret" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "eSxbMLI3yBgN", + "outputId": "c3aeb728-8c03-447b-9489-98a75445accc" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Collecting pycaret\n", + " Downloading pycaret-3.3.2-py3-none-any.whl (486 kB)\n", + "\u001b[?25l \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m0.0/486.1 kB\u001b[0m \u001b[31m?\u001b[0m eta \u001b[36m-:--:--\u001b[0m\r\u001b[2K \u001b[91m━━━━━━━\u001b[0m\u001b[91m╸\u001b[0m\u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m92.2/486.1 kB\u001b[0m \u001b[31m2.5 MB/s\u001b[0m eta \u001b[36m0:00:01\u001b[0m\r\u001b[2K \u001b[91m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[91m╸\u001b[0m \u001b[32m481.3/486.1 kB\u001b[0m \u001b[31m7.6 MB/s\u001b[0m eta \u001b[36m0:00:01\u001b[0m\r\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m486.1/486.1 kB\u001b[0m \u001b[31m5.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hRequirement already satisfied: ipython>=5.5.0 in /usr/local/lib/python3.10/dist-packages (from pycaret) (7.34.0)\n", + "Requirement already satisfied: ipywidgets>=7.6.5 in /usr/local/lib/python3.10/dist-packages (from pycaret) (7.7.1)\n", + "Requirement already satisfied: tqdm>=4.62.0 in /usr/local/lib/python3.10/dist-packages (from pycaret) (4.66.4)\n", + "Requirement already satisfied: numpy<1.27,>=1.21 in /usr/local/lib/python3.10/dist-packages (from pycaret) (1.25.2)\n", + "Requirement already satisfied: pandas<2.2.0 in /usr/local/lib/python3.10/dist-packages (from pycaret) (2.0.3)\n", + "Requirement already satisfied: jinja2>=3 in /usr/local/lib/python3.10/dist-packages (from pycaret) (3.1.4)\n", + "Requirement already satisfied: scipy<=1.11.4,>=1.6.1 in /usr/local/lib/python3.10/dist-packages (from pycaret) (1.11.4)\n", + "Collecting joblib<1.4,>=1.2.0 (from pycaret)\n", + " Downloading joblib-1.3.2-py3-none-any.whl (302 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m302.2/302.2 kB\u001b[0m \u001b[31m17.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hCollecting scikit-learn>1.4.0 (from pycaret)\n", + " Downloading scikit_learn-1.5.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (13.3 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m13.3/13.3 MB\u001b[0m \u001b[31m19.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hCollecting pyod>=1.1.3 (from pycaret)\n", + " Downloading pyod-2.0.0.tar.gz (164 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m165.0/165.0 kB\u001b[0m \u001b[31m13.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25h Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n", + "Collecting imbalanced-learn>=0.12.0 (from pycaret)\n", + " Downloading imbalanced_learn-0.12.3-py3-none-any.whl (258 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m258.3/258.3 kB\u001b[0m \u001b[31m16.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hCollecting category-encoders>=2.4.0 (from pycaret)\n", + " Downloading category_encoders-2.6.3-py2.py3-none-any.whl (81 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m81.9/81.9 kB\u001b[0m \u001b[31m5.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hRequirement already satisfied: lightgbm>=3.0.0 in /usr/local/lib/python3.10/dist-packages (from pycaret) (4.1.0)\n", + "Requirement already satisfied: numba>=0.55.0 in /usr/local/lib/python3.10/dist-packages (from pycaret) (0.58.1)\n", + "Requirement already satisfied: requests>=2.27.1 in /usr/local/lib/python3.10/dist-packages (from pycaret) (2.31.0)\n", + "Requirement already satisfied: psutil>=5.9.0 in /usr/local/lib/python3.10/dist-packages (from pycaret) (5.9.5)\n", + "Requirement already satisfied: markupsafe>=2.0.1 in /usr/local/lib/python3.10/dist-packages (from pycaret) (2.1.5)\n", + "Requirement already satisfied: importlib-metadata>=4.12.0 in /usr/local/lib/python3.10/dist-packages (from pycaret) (7.1.0)\n", + "Requirement already satisfied: nbformat>=4.2.0 in /usr/local/lib/python3.10/dist-packages (from pycaret) (5.10.4)\n", + "Requirement already satisfied: cloudpickle in /usr/local/lib/python3.10/dist-packages (from pycaret) (2.2.1)\n", + "Collecting deprecation>=2.1.0 (from pycaret)\n", + " Downloading deprecation-2.1.0-py2.py3-none-any.whl (11 kB)\n", + "Collecting xxhash (from pycaret)\n", + " Downloading xxhash-3.4.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (194 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m194.1/194.1 kB\u001b[0m \u001b[31m8.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hRequirement already satisfied: matplotlib<3.8.0 in /usr/local/lib/python3.10/dist-packages (from pycaret) (3.7.1)\n", + "Collecting scikit-plot>=0.3.7 (from pycaret)\n", + " Downloading scikit_plot-0.3.7-py3-none-any.whl (33 kB)\n", + "Requirement already satisfied: yellowbrick>=1.4 in /usr/local/lib/python3.10/dist-packages (from pycaret) (1.5)\n", + "Requirement already satisfied: plotly>=5.14.0 in /usr/local/lib/python3.10/dist-packages (from pycaret) (5.15.0)\n", + "Collecting kaleido>=0.2.1 (from pycaret)\n", + " Downloading kaleido-0.2.1-py2.py3-none-manylinux1_x86_64.whl (79.9 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m79.9/79.9 MB\u001b[0m \u001b[31m8.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hCollecting schemdraw==0.15 (from pycaret)\n", + " Downloading schemdraw-0.15-py3-none-any.whl (106 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m106.8/106.8 kB\u001b[0m \u001b[31m5.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hCollecting plotly-resampler>=0.8.3.1 (from pycaret)\n", + " Downloading plotly_resampler-0.10.0-py3-none-any.whl (80 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m80.7/80.7 kB\u001b[0m \u001b[31m5.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hRequirement already satisfied: statsmodels>=0.12.1 in /usr/local/lib/python3.10/dist-packages (from pycaret) (0.14.2)\n", + "Collecting sktime==0.26.0 (from pycaret)\n", + " Downloading sktime-0.26.0-py3-none-any.whl (21.8 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m21.8/21.8 MB\u001b[0m \u001b[31m36.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hCollecting tbats>=1.1.3 (from pycaret)\n", + " Downloading tbats-1.1.3-py3-none-any.whl (44 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m44.0/44.0 kB\u001b[0m \u001b[31m4.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hCollecting pmdarima>=2.0.4 (from pycaret)\n", + " Downloading pmdarima-2.0.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_28_x86_64.whl (2.1 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.1/2.1 MB\u001b[0m \u001b[31m47.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hCollecting wurlitzer (from pycaret)\n", + " Downloading wurlitzer-3.1.1-py3-none-any.whl (8.6 kB)\n", + "Requirement already satisfied: packaging in /usr/local/lib/python3.10/dist-packages (from sktime==0.26.0->pycaret) (24.1)\n", + "Collecting scikit-base<0.8.0 (from sktime==0.26.0->pycaret)\n", + " Downloading scikit_base-0.7.8-py3-none-any.whl (130 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m130.1/130.1 kB\u001b[0m \u001b[31m9.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hCollecting scikit-learn>1.4.0 (from pycaret)\n", + " Downloading scikit_learn-1.4.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (12.1 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m12.1/12.1 MB\u001b[0m \u001b[31m61.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hRequirement already satisfied: patsy>=0.5.1 in /usr/local/lib/python3.10/dist-packages (from category-encoders>=2.4.0->pycaret) (0.5.6)\n", + "Requirement already satisfied: threadpoolctl>=2.0.0 in /usr/local/lib/python3.10/dist-packages (from imbalanced-learn>=0.12.0->pycaret) (3.5.0)\n", + "Requirement already satisfied: zipp>=0.5 in /usr/local/lib/python3.10/dist-packages (from importlib-metadata>=4.12.0->pycaret) (3.19.2)\n", + "Requirement already satisfied: setuptools>=18.5 in /usr/local/lib/python3.10/dist-packages (from ipython>=5.5.0->pycaret) (67.7.2)\n", + "Collecting jedi>=0.16 (from ipython>=5.5.0->pycaret)\n", + " Downloading jedi-0.19.1-py2.py3-none-any.whl (1.6 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.6/1.6 MB\u001b[0m \u001b[31m52.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hRequirement already satisfied: decorator in /usr/local/lib/python3.10/dist-packages (from ipython>=5.5.0->pycaret) (4.4.2)\n", + "Requirement already satisfied: pickleshare in /usr/local/lib/python3.10/dist-packages (from ipython>=5.5.0->pycaret) (0.7.5)\n", + "Requirement already satisfied: traitlets>=4.2 in /usr/local/lib/python3.10/dist-packages (from ipython>=5.5.0->pycaret) (5.7.1)\n", + "Requirement already satisfied: prompt-toolkit!=3.0.0,!=3.0.1,<3.1.0,>=2.0.0 in /usr/local/lib/python3.10/dist-packages (from ipython>=5.5.0->pycaret) (3.0.47)\n", + "Requirement already satisfied: pygments in /usr/local/lib/python3.10/dist-packages (from ipython>=5.5.0->pycaret) (2.16.1)\n", + "Requirement already satisfied: backcall in /usr/local/lib/python3.10/dist-packages (from ipython>=5.5.0->pycaret) (0.2.0)\n", + "Requirement already satisfied: matplotlib-inline in /usr/local/lib/python3.10/dist-packages (from ipython>=5.5.0->pycaret) (0.1.7)\n", + "Requirement already satisfied: pexpect>4.3 in /usr/local/lib/python3.10/dist-packages (from ipython>=5.5.0->pycaret) (4.9.0)\n", + "Requirement already satisfied: ipykernel>=4.5.1 in /usr/local/lib/python3.10/dist-packages (from ipywidgets>=7.6.5->pycaret) (5.5.6)\n", + "Requirement already satisfied: ipython-genutils~=0.2.0 in /usr/local/lib/python3.10/dist-packages (from ipywidgets>=7.6.5->pycaret) (0.2.0)\n", + "Requirement already satisfied: widgetsnbextension~=3.6.0 in /usr/local/lib/python3.10/dist-packages (from ipywidgets>=7.6.5->pycaret) (3.6.6)\n", + "Requirement already satisfied: jupyterlab-widgets>=1.0.0 in /usr/local/lib/python3.10/dist-packages (from ipywidgets>=7.6.5->pycaret) (3.0.11)\n", + "Requirement already satisfied: contourpy>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib<3.8.0->pycaret) (1.2.1)\n", + "Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.10/dist-packages (from matplotlib<3.8.0->pycaret) (0.12.1)\n", + "Requirement already satisfied: fonttools>=4.22.0 in /usr/local/lib/python3.10/dist-packages (from matplotlib<3.8.0->pycaret) (4.53.0)\n", + "Requirement already satisfied: kiwisolver>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib<3.8.0->pycaret) (1.4.5)\n", + "Requirement already satisfied: pillow>=6.2.0 in /usr/local/lib/python3.10/dist-packages (from matplotlib<3.8.0->pycaret) (9.4.0)\n", + "Requirement already satisfied: pyparsing>=2.3.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib<3.8.0->pycaret) (3.1.2)\n", + "Requirement already satisfied: python-dateutil>=2.7 in /usr/local/lib/python3.10/dist-packages (from matplotlib<3.8.0->pycaret) (2.8.2)\n", + "Requirement already satisfied: fastjsonschema>=2.15 in /usr/local/lib/python3.10/dist-packages (from nbformat>=4.2.0->pycaret) (2.19.1)\n", + "Requirement already satisfied: jsonschema>=2.6 in /usr/local/lib/python3.10/dist-packages (from nbformat>=4.2.0->pycaret) (4.19.2)\n", + "Requirement already satisfied: jupyter-core!=5.0.*,>=4.12 in /usr/local/lib/python3.10/dist-packages (from nbformat>=4.2.0->pycaret) (5.7.2)\n", + "Requirement already satisfied: llvmlite<0.42,>=0.41.0dev0 in /usr/local/lib/python3.10/dist-packages (from numba>=0.55.0->pycaret) (0.41.1)\n", + "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas<2.2.0->pycaret) (2023.4)\n", + "Requirement already satisfied: tzdata>=2022.1 in /usr/local/lib/python3.10/dist-packages (from pandas<2.2.0->pycaret) (2024.1)\n", + "Requirement already satisfied: tenacity>=6.2.0 in /usr/local/lib/python3.10/dist-packages (from plotly>=5.14.0->pycaret) (8.3.0)\n", + "Collecting dash>=2.9.0 (from plotly-resampler>=0.8.3.1->pycaret)\n", + " Downloading dash-2.17.1-py3-none-any.whl (7.5 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m7.5/7.5 MB\u001b[0m \u001b[31m63.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hCollecting orjson<4.0.0,>=3.8.0 (from plotly-resampler>=0.8.3.1->pycaret)\n", + " Downloading orjson-3.10.5-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (144 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m145.0/145.0 kB\u001b[0m \u001b[31m3.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hCollecting tsdownsample>=0.1.3 (from plotly-resampler>=0.8.3.1->pycaret)\n", + " Downloading tsdownsample-0.1.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (2.1 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.1/2.1 MB\u001b[0m \u001b[31m48.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hRequirement already satisfied: Cython!=0.29.18,!=0.29.31,>=0.29 in /usr/local/lib/python3.10/dist-packages (from pmdarima>=2.0.4->pycaret) (3.0.10)\n", + "Requirement already satisfied: urllib3 in /usr/local/lib/python3.10/dist-packages (from pmdarima>=2.0.4->pycaret) (2.0.7)\n", + "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests>=2.27.1->pycaret) (3.3.2)\n", + "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests>=2.27.1->pycaret) (3.7)\n", + "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests>=2.27.1->pycaret) (2024.6.2)\n", + "Requirement already satisfied: Flask<3.1,>=1.0.4 in /usr/local/lib/python3.10/dist-packages (from dash>=2.9.0->plotly-resampler>=0.8.3.1->pycaret) (2.2.5)\n", + "Requirement already satisfied: Werkzeug<3.1 in /usr/local/lib/python3.10/dist-packages (from dash>=2.9.0->plotly-resampler>=0.8.3.1->pycaret) (3.0.3)\n", + "Collecting dash-html-components==2.0.0 (from dash>=2.9.0->plotly-resampler>=0.8.3.1->pycaret)\n", + " Downloading dash_html_components-2.0.0-py3-none-any.whl (4.1 kB)\n", + "Collecting dash-core-components==2.0.0 (from dash>=2.9.0->plotly-resampler>=0.8.3.1->pycaret)\n", + " Downloading dash_core_components-2.0.0-py3-none-any.whl (3.8 kB)\n", + "Collecting dash-table==5.0.0 (from dash>=2.9.0->plotly-resampler>=0.8.3.1->pycaret)\n", + " Downloading dash_table-5.0.0-py3-none-any.whl (3.9 kB)\n", + "Requirement already satisfied: typing-extensions>=4.1.1 in /usr/local/lib/python3.10/dist-packages (from dash>=2.9.0->plotly-resampler>=0.8.3.1->pycaret) (4.12.2)\n", + "Collecting retrying (from dash>=2.9.0->plotly-resampler>=0.8.3.1->pycaret)\n", + " Downloading retrying-1.3.4-py3-none-any.whl (11 kB)\n", + "Requirement already satisfied: nest-asyncio in /usr/local/lib/python3.10/dist-packages (from dash>=2.9.0->plotly-resampler>=0.8.3.1->pycaret) (1.6.0)\n", + "Requirement already satisfied: jupyter-client in /usr/local/lib/python3.10/dist-packages (from ipykernel>=4.5.1->ipywidgets>=7.6.5->pycaret) (6.1.12)\n", + "Requirement already satisfied: tornado>=4.2 in /usr/local/lib/python3.10/dist-packages (from ipykernel>=4.5.1->ipywidgets>=7.6.5->pycaret) (6.3.3)\n", + "Requirement already satisfied: parso<0.9.0,>=0.8.3 in /usr/local/lib/python3.10/dist-packages (from jedi>=0.16->ipython>=5.5.0->pycaret) (0.8.4)\n", + "Requirement already satisfied: attrs>=22.2.0 in /usr/local/lib/python3.10/dist-packages (from jsonschema>=2.6->nbformat>=4.2.0->pycaret) (23.2.0)\n", + "Requirement already satisfied: jsonschema-specifications>=2023.03.6 in /usr/local/lib/python3.10/dist-packages (from jsonschema>=2.6->nbformat>=4.2.0->pycaret) (2023.12.1)\n", + "Requirement already satisfied: referencing>=0.28.4 in /usr/local/lib/python3.10/dist-packages (from jsonschema>=2.6->nbformat>=4.2.0->pycaret) (0.35.1)\n", + "Requirement already satisfied: rpds-py>=0.7.1 in /usr/local/lib/python3.10/dist-packages (from jsonschema>=2.6->nbformat>=4.2.0->pycaret) (0.18.1)\n", + "Requirement already satisfied: platformdirs>=2.5 in /usr/local/lib/python3.10/dist-packages (from jupyter-core!=5.0.*,>=4.12->nbformat>=4.2.0->pycaret) (4.2.2)\n", + "Requirement already satisfied: six in /usr/local/lib/python3.10/dist-packages (from patsy>=0.5.1->category-encoders>=2.4.0->pycaret) (1.16.0)\n", + "Requirement already satisfied: ptyprocess>=0.5 in /usr/local/lib/python3.10/dist-packages (from pexpect>4.3->ipython>=5.5.0->pycaret) (0.7.0)\n", + "Requirement already satisfied: wcwidth in /usr/local/lib/python3.10/dist-packages (from prompt-toolkit!=3.0.0,!=3.0.1,<3.1.0,>=2.0.0->ipython>=5.5.0->pycaret) (0.2.13)\n", + "Requirement already satisfied: notebook>=4.4.1 in /usr/local/lib/python3.10/dist-packages (from widgetsnbextension~=3.6.0->ipywidgets>=7.6.5->pycaret) (6.5.5)\n", + "Requirement already satisfied: itsdangerous>=2.0 in /usr/local/lib/python3.10/dist-packages (from Flask<3.1,>=1.0.4->dash>=2.9.0->plotly-resampler>=0.8.3.1->pycaret) (2.2.0)\n", + "Requirement already satisfied: click>=8.0 in /usr/local/lib/python3.10/dist-packages (from Flask<3.1,>=1.0.4->dash>=2.9.0->plotly-resampler>=0.8.3.1->pycaret) (8.1.7)\n", + "Requirement already satisfied: pyzmq<25,>=17 in /usr/local/lib/python3.10/dist-packages (from notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets>=7.6.5->pycaret) (24.0.1)\n", + "Requirement already satisfied: argon2-cffi in /usr/local/lib/python3.10/dist-packages (from notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets>=7.6.5->pycaret) (23.1.0)\n", + "Requirement already satisfied: nbconvert>=5 in /usr/local/lib/python3.10/dist-packages (from notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets>=7.6.5->pycaret) (6.5.4)\n", + "Requirement already satisfied: Send2Trash>=1.8.0 in /usr/local/lib/python3.10/dist-packages (from notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets>=7.6.5->pycaret) (1.8.3)\n", + "Requirement already satisfied: terminado>=0.8.3 in /usr/local/lib/python3.10/dist-packages (from notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets>=7.6.5->pycaret) (0.18.1)\n", + "Requirement already satisfied: prometheus-client in /usr/local/lib/python3.10/dist-packages (from notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets>=7.6.5->pycaret) (0.20.0)\n", + "Requirement already satisfied: nbclassic>=0.4.7 in /usr/local/lib/python3.10/dist-packages (from notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets>=7.6.5->pycaret) (1.1.0)\n", + "Requirement already satisfied: notebook-shim>=0.2.3 in /usr/local/lib/python3.10/dist-packages (from nbclassic>=0.4.7->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets>=7.6.5->pycaret) (0.2.4)\n", + "Requirement already satisfied: lxml in /usr/local/lib/python3.10/dist-packages (from nbconvert>=5->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets>=7.6.5->pycaret) (4.9.4)\n", + "Requirement already satisfied: beautifulsoup4 in /usr/local/lib/python3.10/dist-packages (from nbconvert>=5->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets>=7.6.5->pycaret) (4.12.3)\n", + "Requirement already satisfied: bleach in /usr/local/lib/python3.10/dist-packages (from nbconvert>=5->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets>=7.6.5->pycaret) (6.1.0)\n", + "Requirement already satisfied: defusedxml in /usr/local/lib/python3.10/dist-packages (from nbconvert>=5->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets>=7.6.5->pycaret) (0.7.1)\n", + "Requirement already satisfied: entrypoints>=0.2.2 in /usr/local/lib/python3.10/dist-packages (from nbconvert>=5->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets>=7.6.5->pycaret) (0.4)\n", + "Requirement already satisfied: jupyterlab-pygments in /usr/local/lib/python3.10/dist-packages (from nbconvert>=5->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets>=7.6.5->pycaret) (0.3.0)\n", + "Requirement already satisfied: mistune<2,>=0.8.1 in /usr/local/lib/python3.10/dist-packages (from nbconvert>=5->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets>=7.6.5->pycaret) (0.8.4)\n", + "Requirement already satisfied: nbclient>=0.5.0 in /usr/local/lib/python3.10/dist-packages (from nbconvert>=5->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets>=7.6.5->pycaret) (0.10.0)\n", + "Requirement already satisfied: pandocfilters>=1.4.1 in /usr/local/lib/python3.10/dist-packages (from nbconvert>=5->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets>=7.6.5->pycaret) (1.5.1)\n", + "Requirement already satisfied: tinycss2 in /usr/local/lib/python3.10/dist-packages (from nbconvert>=5->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets>=7.6.5->pycaret) (1.3.0)\n", + "Requirement already satisfied: argon2-cffi-bindings in /usr/local/lib/python3.10/dist-packages (from argon2-cffi->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets>=7.6.5->pycaret) (21.2.0)\n", + "Requirement already satisfied: jupyter-server<3,>=1.8 in /usr/local/lib/python3.10/dist-packages (from notebook-shim>=0.2.3->nbclassic>=0.4.7->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets>=7.6.5->pycaret) (1.24.0)\n", + "Requirement already satisfied: cffi>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from argon2-cffi-bindings->argon2-cffi->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets>=7.6.5->pycaret) (1.16.0)\n", + "Requirement already satisfied: soupsieve>1.2 in /usr/local/lib/python3.10/dist-packages (from beautifulsoup4->nbconvert>=5->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets>=7.6.5->pycaret) (2.5)\n", + "Requirement already satisfied: webencodings in /usr/local/lib/python3.10/dist-packages (from bleach->nbconvert>=5->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets>=7.6.5->pycaret) (0.5.1)\n", + "Requirement already satisfied: pycparser in /usr/local/lib/python3.10/dist-packages (from cffi>=1.0.1->argon2-cffi-bindings->argon2-cffi->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets>=7.6.5->pycaret) (2.22)\n", + "Requirement already satisfied: anyio<4,>=3.1.0 in /usr/local/lib/python3.10/dist-packages (from jupyter-server<3,>=1.8->notebook-shim>=0.2.3->nbclassic>=0.4.7->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets>=7.6.5->pycaret) (3.7.1)\n", + "Requirement already satisfied: websocket-client in /usr/local/lib/python3.10/dist-packages (from jupyter-server<3,>=1.8->notebook-shim>=0.2.3->nbclassic>=0.4.7->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets>=7.6.5->pycaret) (1.8.0)\n", + "Requirement already satisfied: sniffio>=1.1 in /usr/local/lib/python3.10/dist-packages (from anyio<4,>=3.1.0->jupyter-server<3,>=1.8->notebook-shim>=0.2.3->nbclassic>=0.4.7->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets>=7.6.5->pycaret) (1.3.1)\n", + "Requirement already satisfied: exceptiongroup in /usr/local/lib/python3.10/dist-packages (from anyio<4,>=3.1.0->jupyter-server<3,>=1.8->notebook-shim>=0.2.3->nbclassic>=0.4.7->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets>=7.6.5->pycaret) (1.2.1)\n", + "Building wheels for collected packages: pyod\n", + " Building wheel for pyod (setup.py) ... \u001b[?25l\u001b[?25hdone\n", + " Created wheel for pyod: filename=pyod-2.0.0-py3-none-any.whl size=196324 sha256=71d7a67d0e4c2dd645ec7090c53b5a7b6cd5fd204a6e6be30dc6232e2b82766b\n", + " Stored in directory: /root/.cache/pip/wheels/15/0e/91/96b270e6741d4eece88727489411330226ff47ac1cb9ea0097\n", + "Successfully built pyod\n", + "Installing collected packages: kaleido, dash-table, dash-html-components, dash-core-components, xxhash, wurlitzer, tsdownsample, scikit-base, schemdraw, retrying, orjson, joblib, jedi, deprecation, scikit-learn, sktime, scikit-plot, pyod, imbalanced-learn, dash, pmdarima, plotly-resampler, category-encoders, tbats, pycaret\n", + " Attempting uninstall: joblib\n", + " Found existing installation: joblib 1.4.2\n", + " Uninstalling joblib-1.4.2:\n", + " Successfully uninstalled joblib-1.4.2\n", + " Attempting uninstall: scikit-learn\n", + " Found existing installation: scikit-learn 1.2.2\n", + " Uninstalling scikit-learn-1.2.2:\n", + " Successfully uninstalled scikit-learn-1.2.2\n", + " Attempting uninstall: imbalanced-learn\n", + " Found existing installation: imbalanced-learn 0.10.1\n", + " Uninstalling imbalanced-learn-0.10.1:\n", + " Successfully uninstalled imbalanced-learn-0.10.1\n", + "Successfully installed category-encoders-2.6.3 dash-2.17.1 dash-core-components-2.0.0 dash-html-components-2.0.0 dash-table-5.0.0 deprecation-2.1.0 imbalanced-learn-0.12.3 jedi-0.19.1 joblib-1.3.2 kaleido-0.2.1 orjson-3.10.5 plotly-resampler-0.10.0 pmdarima-2.0.4 pycaret-3.3.2 pyod-2.0.0 retrying-1.3.4 schemdraw-0.15 scikit-base-0.7.8 scikit-learn-1.4.2 scikit-plot-0.3.7 sktime-0.26.0 tbats-1.1.3 tsdownsample-0.1.3 wurlitzer-3.1.1 xxhash-3.4.1\n" + ] + } + ], + "source": [ + "!pip install pycaret\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "ipVtGHu7yiuT" + }, + "source": [ + "Regression with PyCaret\n", + "\n", + "Dataset - Boston_housing" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 1000, + "referenced_widgets": [ + "1c52e377537b43a1b687fe8d31c5fb0e", + "686f5ba4514a4535acfa9543f90d3e1f", + "f62806907897477b870ffc2def71ce9a", + "00ff02b4433b45d0a5b08a9c29cdc241", + "e18ed3b3e2f647aab0f4f01390c4bdb4", + "3dd6081acc524b3685fbaa4e456815e0", + "08f169a6bfa54fb0abca36b7514e4d57", + "337878fc244f404bb2dc3b33b4d9380e", + "38d9bc5728214b2f951963368028a884", + "7acc61bd395b4ca382d451a78c117ecf", + "b9a48aad37b341febaf8cd61fe490061", + "cfa0ede2c1764ebc8ed76a9df5cc5b69", + "4d2e26640c734c3e8c1eab52509cbcc6", + "80bf334f1d3a4343aaf6c467cc80cc68", + "8727cffbfe1846809b967a89dee1ca9a", + "91c2559aadd749cb9674df365defd00d", + "77963dee9112452b9eec9464cff72f4a", + "1d9acd20f61a480c8b2c76b7c73dcb18" + ] + }, + "id": "acTfE_74ylmB", + "outputId": "24a8c2e5-e04c-4de7-f7ee-9b3d22bec0f4" + }, + "outputs": [ + { + "data": { + "application/vnd.google.colaboratory.intrinsic+json": { + "summary": "{\n \"name\": \"evaluate_model(best_model)\",\n \"rows\": 5,\n \"fields\": [\n {\n \"column\": \"crim\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.02277820712874479,\n \"min\": 0.00632,\n \"max\": 0.06905,\n \"num_unique_values\": 5,\n \"samples\": [\n 0.02731,\n 0.06905,\n 0.02729\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"zn\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 8.049844718999244,\n \"min\": 0.0,\n \"max\": 18.0,\n \"num_unique_values\": 2,\n \"samples\": [\n 0.0,\n 18.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"indus\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 2.6551591289412393,\n \"min\": 2.18,\n \"max\": 7.07,\n \"num_unique_values\": 3,\n \"samples\": [\n 2.31,\n 7.07\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"chas\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0,\n \"min\": 0,\n \"max\": 0,\n \"num_unique_values\": 1,\n \"samples\": [\n 0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"nox\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.03376832835661252,\n \"min\": 0.458,\n \"max\": 0.538,\n \"num_unique_values\": 3,\n \"samples\": [\n 0.538\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"rm\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.3467163105479751,\n \"min\": 6.421,\n \"max\": 7.185,\n \"num_unique_values\": 5,\n \"samples\": [\n 6.421\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"age\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 12.402943199095933,\n \"min\": 45.8,\n \"max\": 78.9,\n \"num_unique_values\": 5,\n \"samples\": [\n 78.9\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"dis\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.8400812621407525,\n \"min\": 4.09,\n \"max\": 6.0622,\n \"num_unique_values\": 3,\n \"samples\": [\n 4.09\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"rad\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0,\n \"min\": 1,\n \"max\": 3,\n \"num_unique_values\": 3,\n \"samples\": [\n 1\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"tax\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 30,\n \"min\": 222,\n \"max\": 296,\n \"num_unique_values\": 3,\n \"samples\": [\n 296\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"ptratio\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 1.393915348936225,\n \"min\": 15.3,\n \"max\": 18.7,\n \"num_unique_values\": 3,\n \"samples\": [\n 15.3\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"black\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 1.8492349769566823,\n \"min\": 392.83,\n \"max\": 396.9,\n \"num_unique_values\": 3,\n \"samples\": [\n 396.9\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"lstat\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 2.346812732196585,\n \"min\": 2.94,\n \"max\": 9.14,\n \"num_unique_values\": 5,\n \"samples\": [\n 9.14\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"medv\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 6.682963414534005,\n \"min\": 21.6,\n \"max\": 36.2,\n \"num_unique_values\": 5,\n \"samples\": [\n 21.6\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}", + "type": "dataframe" + }, + "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", + "
crimzninduschasnoxrmagedisradtaxptratioblacklstatmedv
00.0063218.02.3100.5386.57565.24.0900129615.3396.904.9824.0
10.027310.07.0700.4696.42178.94.9671224217.8396.909.1421.6
20.027290.07.0700.4697.18561.14.9671224217.8392.834.0334.7
30.032370.02.1800.4586.99845.86.0622322218.7394.632.9433.4
40.069050.02.1800.4587.14754.26.0622322218.7396.905.3336.2
\n", + "
\n", + "
\n", + "\n", + "
\n", + " \n", + "\n", + " \n", + "\n", + " \n", + "
\n", + "\n", + "\n", + "
\n", + " \n", + "\n", + "\n", + "\n", + " \n", + "
\n", + "\n", + "
\n", + "
\n" + ], + "text/plain": [ + " crim zn indus chas nox rm age dis rad tax ptratio \\\n", + "0 0.00632 18.0 2.31 0 0.538 6.575 65.2 4.0900 1 296 15.3 \n", + "1 0.02731 0.0 7.07 0 0.469 6.421 78.9 4.9671 2 242 17.8 \n", + "2 0.02729 0.0 7.07 0 0.469 7.185 61.1 4.9671 2 242 17.8 \n", + "3 0.03237 0.0 2.18 0 0.458 6.998 45.8 6.0622 3 222 18.7 \n", + "4 0.06905 0.0 2.18 0 0.458 7.147 54.2 6.0622 3 222 18.7 \n", + "\n", + " black lstat medv \n", + "0 396.90 4.98 24.0 \n", + "1 396.90 9.14 21.6 \n", + "2 392.83 4.03 34.7 \n", + "3 394.63 2.94 33.4 \n", + "4 396.90 5.33 36.2 " + ] + }, + "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", + "
 DescriptionValue
0Session id123
1Targetmedv
2Target typeRegression
3Original data shape(506, 14)
4Transformed data shape(506, 14)
5Transformed train set shape(354, 14)
6Transformed test set shape(152, 14)
7Numeric features13
8PreprocessTrue
9Imputation typesimple
10Numeric imputationmean
11Categorical imputationmode
12Fold GeneratorKFold
13Fold Number10
14CPU Jobs-1
15Use GPUFalse
16Log ExperimentFalse
17Experiment Namereg-default-name
18USId45f
\n" + ], + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "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)
etExtra Trees Regressor2.03789.49582.92830.88840.12980.10000.3290
gbrGradient Boosting Regressor2.17489.68033.02740.87880.14340.11170.1430
rfRandom Forest Regressor2.231610.63103.14480.86730.14470.11290.4510
lightgbmLight Gradient Boosting Machine2.330511.57223.29690.85660.14820.11570.1790
xgboostExtreme Gradient Boosting2.415412.52253.43850.84520.15390.11960.2410
adaAdaBoost Regressor2.878915.93443.86670.80550.18030.15170.1210
dtDecision Tree Regressor2.930719.61504.25380.73680.19090.14550.0250
ridgeRidge Regression3.279322.84024.64400.73000.24600.16640.0240
lrLinear Regression3.300622.72094.64020.72950.25260.16680.7600
brBayesian Ridge3.315823.27694.68620.72580.24530.16730.0300
larLeast Angle Regression3.332722.92514.67930.72360.25570.17250.0250
lassoLasso Regression3.628827.34445.07190.67800.25780.17430.0260
llarLasso Least Angle Regression3.628927.34465.07190.67800.25780.17430.0300
enElastic Net3.662127.56985.10180.67420.25620.17430.0280
huberHuber Regressor4.005635.71805.83850.54620.30630.20640.0550
knnK Neighbors Regressor4.850747.42646.74470.42260.26110.22690.0350
ompOrthogonal Matching Pursuit5.885064.73887.87160.23490.31940.28620.0230
dummyDummy Regressor6.717086.43599.1940-0.04780.39460.36890.0210
parPassive Aggressive Regressor8.7856130.048411.1739-0.74780.46610.45570.0230
\n" + ], + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "application/vnd.jupyter.widget-view+json": { + "model_id": "1c52e377537b43a1b687fe8d31c5fb0e", + "version_major": 2, + "version_minor": 0 + }, + "text/plain": [ + "Processing: 0%| | 0/81 [00:00" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [], + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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\n", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [], + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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\n", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "application/vnd.jupyter.widget-view+json": { + "model_id": "cfa0ede2c1764ebc8ed76a9df5cc5b69", + "version_major": 2, + "version_minor": 0 + }, + "text/plain": [ + "interactive(children=(ToggleButtons(description='Plot Type:', icons=('',), options=(('Pipeline Plot', 'pipelin…" + ] + }, + "metadata": { + "application/vnd.jupyter.widget-view+json": { + "colab": { + "custom_widget_manager": { + "url": "https://ssl.gstatic.com/colaboratory-static/widgets/colab-cdn-widget-manager/2b70e893a8ba7c0f/manager.min.js" + } + } + } + }, + "output_type": "display_data" + } + ], + "source": [ + "from pycaret.datasets import get_data\n", + "from pycaret.regression import setup, compare_models, plot_model, evaluate_model\n", + "\n", + "data = get_data('boston')\n", + "\n", + "# Setting up the regression environment\n", + "reg = setup(data, target='medv', session_id=123)\n", + "\n", + "# Comparing all models\n", + "best_model = compare_models()\n", + "\n", + "# Plotting model performance\n", + "plot_model(best_model, plot='residuals')\n", + "plot_model(best_model, plot='error')\n", + "evaluate_model(best_model)\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "gE4SgNyBzFh9" + }, + "source": [ + "Classification with PyCaret\n", + "\n", + "Dataset - Iris" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 1000, + "referenced_widgets": [ + "be0becb852d74805810ce0ff949565ba", + "ec8d189a21bc40a0a09d0a7942fe7d4b", + "ceeb0fead1ff4b5aaf6ea8e2dbb3ab55", + "dc54a689d8174351b59ed81a3a629859", + "5d65b9cab121417da42c03f9e22001d4", + "e3b02bc7d049414cabecddd346c3e5e8", + "ff5a527e36954b19b8b5989e274abdc7", + "89c5db0ca21a4ac587f167d605056d54", + "6fadb209441c408eabd44af64c7161b8", + "d2131e660a4547708b034564f592368e", + "90d2a0afc4384a0786410597cf38254f", + "b4f51881b1f348278b6aab89108c04b7", + "a332739eac9a4b0c8a2bde393c6466ba", + "3058c21b2b0a496d81857d6c96258af7", + "160aac587394490faf7bfe7b93ca191f", + "90809633002c4613ada36fb86aeede20", + "40499c30f19942389529429ce08db3d0", + "65dc5783283c4f768494ef9a122ba2e2" + ] + }, + "id": "2RiHrOx6zSUC", + "outputId": "9683bfad-4bec-4192-c27c-edec2c87ba80" + }, + "outputs": [ + { + "data": { + "application/vnd.google.colaboratory.intrinsic+json": { + "summary": "{\n \"name\": \"evaluate_model(best_model)\",\n \"rows\": 5,\n \"fields\": [\n {\n \"column\": \"sepal_length\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.2073644135332772,\n \"min\": 4.6,\n \"max\": 5.1,\n \"num_unique_values\": 5,\n \"samples\": [\n 4.9,\n 5.0,\n 4.7\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"sepal_width\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.2588435821108957,\n \"min\": 3.0,\n \"max\": 3.6,\n \"num_unique_values\": 5,\n \"samples\": [\n 3.0,\n 3.6,\n 3.2\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"petal_length\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.07071067811865474,\n \"min\": 1.3,\n \"max\": 1.5,\n \"num_unique_values\": 3,\n \"samples\": [\n 1.4,\n 1.3,\n 1.5\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"petal_width\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.0,\n \"min\": 0.2,\n \"max\": 0.2,\n \"num_unique_values\": 1,\n \"samples\": [\n 0.2\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"species\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 1,\n \"samples\": [\n \"Iris-setosa\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}", + "type": "dataframe" + }, + "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", + "
sepal_lengthsepal_widthpetal_lengthpetal_widthspecies
05.13.51.40.2Iris-setosa
14.93.01.40.2Iris-setosa
24.73.21.30.2Iris-setosa
34.63.11.50.2Iris-setosa
45.03.61.40.2Iris-setosa
\n", + "
\n", + "
\n", + "\n", + "
\n", + " \n", + "\n", + " \n", + "\n", + " \n", + "
\n", + "\n", + "\n", + "
\n", + " \n", + "\n", + "\n", + "\n", + " \n", + "
\n", + "\n", + "
\n", + "
\n" + ], + "text/plain": [ + " sepal_length sepal_width petal_length petal_width species\n", + "0 5.1 3.5 1.4 0.2 Iris-setosa\n", + "1 4.9 3.0 1.4 0.2 Iris-setosa\n", + "2 4.7 3.2 1.3 0.2 Iris-setosa\n", + "3 4.6 3.1 1.5 0.2 Iris-setosa\n", + "4 5.0 3.6 1.4 0.2 Iris-setosa" + ] + }, + "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", + "
 DescriptionValue
0Session id123
1Targetspecies
2Target typeMulticlass
3Target mappingIris-setosa: 0, Iris-versicolor: 1, Iris-virginica: 2
4Original data shape(150, 5)
5Transformed data shape(150, 5)
6Transformed train set shape(105, 5)
7Transformed test set shape(45, 5)
8Numeric features4
9PreprocessTrue
10Imputation typesimple
11Numeric imputationmean
12Categorical imputationmode
13Fold GeneratorStratifiedKFold
14Fold Number10
15CPU Jobs-1
16Use GPUFalse
17Log ExperimentFalse
18Experiment Nameclf-default-name
19USI6d9d
\n" + ], + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "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", + "
 ModelAccuracyAUCRecallPrec.F1KappaMCCTT (Sec)
lrLogistic Regression0.97180.00000.97180.97800.97120.95730.96090.0510
knnK Neighbors Classifier0.97180.98300.97180.97800.97120.95730.96090.0560
qdaQuadratic Discriminant Analysis0.97180.00000.97180.97800.97120.95730.96090.0350
ldaLinear Discriminant Analysis0.97180.00000.97180.97800.97120.95730.96090.0310
lightgbmLight Gradient Boosting Machine0.95360.99350.95360.96340.95280.92980.93560.3310
nbNaive Bayes0.94450.98680.94450.95250.94380.91610.92070.0380
etExtra Trees Classifier0.94450.99350.94450.95860.94260.91610.92460.1630
gbcGradient Boosting Classifier0.93550.00000.93550.94160.93250.90230.90830.2870
dtDecision Tree Classifier0.92640.94290.92640.95020.92010.88860.90400.0400
rfRandom Forest Classifier0.92640.99090.92640.93430.92320.88860.89560.3490
xgboostExtreme Gradient Boosting0.92550.97100.92550.93600.92390.88700.89370.0650
adaAda Boost Classifier0.91550.00000.91550.94010.90970.87200.88730.1200
ridgeRidge Classifier0.82270.00000.82270.84370.81860.73200.74540.0590
svmSVM - Linear Kernel0.76180.00000.76180.66550.68880.63330.70480.0710
dummyDummy Classifier0.28640.50000.28640.08220.12770.00000.00000.0570
\n" + ], + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "application/vnd.jupyter.widget-view+json": { + "model_id": "be0becb852d74805810ce0ff949565ba", + "version_major": 2, + "version_minor": 0 + }, + "text/plain": [ + "Processing: 0%| | 0/65 [00:00" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [], + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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\n", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [], + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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\n", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "application/vnd.jupyter.widget-view+json": { + "model_id": "b4f51881b1f348278b6aab89108c04b7", + "version_major": 2, + "version_minor": 0 + }, + "text/plain": [ + "interactive(children=(ToggleButtons(description='Plot Type:', icons=('',), options=(('Pipeline Plot', 'pipelin…" + ] + }, + "metadata": { + "application/vnd.jupyter.widget-view+json": { + "colab": { + "custom_widget_manager": { + "url": "https://ssl.gstatic.com/colaboratory-static/widgets/colab-cdn-widget-manager/2b70e893a8ba7c0f/manager.min.js" + } + } + } + }, + "output_type": "display_data" + } + ], + "source": [ + "from pycaret.datasets import get_data\n", + "from pycaret.classification import setup, compare_models, plot_model, evaluate_model\n", + "\n", + "data = get_data('iris')\n", + "\n", + "# Setting up the classification environment\n", + "clf = setup(data, target='species', session_id=123)\n", + "\n", + "# Comparing all models\n", + "best_model = compare_models()\n", + "\n", + "# Plotting model performance\n", + "plot_model(best_model, plot='confusion_matrix')\n", + "plot_model(best_model, plot='auc')\n", + "evaluate_model(best_model)\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "jVvIVkhK1Dwr" + }, + "source": [ + "# 2. H2O AutoML" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "8M3DLmbJ1Ldl", + "outputId": "1318a8da-7213-4bf6-894e-0e1a5829b05a" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Collecting h2o\n", + " Using cached h2o-3.46.0.3.tar.gz (265.3 MB)\n", + " Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n", + "Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from h2o) (2.31.0)\n", + "Requirement already satisfied: tabulate in /usr/local/lib/python3.10/dist-packages (from h2o) (0.9.0)\n", + "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests->h2o) (3.3.2)\n", + "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->h2o) (3.7)\n", + "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->h2o) (2.0.7)\n", + "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->h2o) (2024.6.2)\n", + "Building wheels for collected packages: h2o\n", + " Building wheel for h2o (setup.py) ... \u001b[?25l\u001b[?25hdone\n", + " Created wheel for h2o: filename=h2o-3.46.0.3-py2.py3-none-any.whl size=265365897 sha256=9137cef348dfed91d85feae68edc47ce515976b85e38d5c6d5979dd82ac60eee\n", + " Stored in directory: /root/.cache/pip/wheels/c4/63/41/baa115b5255e1db3e2383bce4e2e6181746aac0b42264c242f\n", + "Successfully built h2o\n", + "Installing collected packages: h2o\n", + "Successfully installed h2o-3.46.0.3\n" + ] + } + ], + "source": [ + "!pip install h2o" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "8cnOe3dQ1TD-" + }, + "source": [ + "Regression with H2O AutoML\n", + "\n", + "Dataset - Boston_housing" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 882 + }, + "id": "jUJxPOp61SKV", + "outputId": "f7f46107-87a0-419a-f9f8-945c60281403" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Checking whether there is an H2O instance running at http://localhost:54321. connected.\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", + "
H2O_cluster_uptime:25 mins 23 secs
H2O_cluster_timezone:Etc/UTC
H2O_data_parsing_timezone:UTC
H2O_cluster_version:3.46.0.3
H2O_cluster_version_age:6 days
H2O_cluster_name:H2O_from_python_unknownUser_62vsjk
H2O_cluster_total_nodes:1
H2O_cluster_free_memory:3.085 Gb
H2O_cluster_total_cores:2
H2O_cluster_allowed_cores:2
H2O_cluster_status:locked, healthy
H2O_connection_url:http://localhost:54321
H2O_connection_proxy:{\"http\": null, \"https\": null, \"colab_language_server\": \"/usr/colab/bin/language_service\"}
H2O_internal_security:False
Python_version:3.10.12 final
\n", + "
\n" + ], + "text/plain": [ + "-------------------------- -----------------------------------------------------------------------------------------\n", + "H2O_cluster_uptime: 25 mins 23 secs\n", + "H2O_cluster_timezone: Etc/UTC\n", + "H2O_data_parsing_timezone: UTC\n", + "H2O_cluster_version: 3.46.0.3\n", + "H2O_cluster_version_age: 6 days\n", + "H2O_cluster_name: H2O_from_python_unknownUser_62vsjk\n", + "H2O_cluster_total_nodes: 1\n", + "H2O_cluster_free_memory: 3.085 Gb\n", + "H2O_cluster_total_cores: 2\n", + "H2O_cluster_allowed_cores: 2\n", + "H2O_cluster_status: locked, healthy\n", + "H2O_connection_url: http://localhost:54321\n", + "H2O_connection_proxy: {\"http\": null, \"https\": null, \"colab_language_server\": \"/usr/colab/bin/language_service\"}\n", + "H2O_internal_security: False\n", + "Python_version: 3.10.12 final\n", + "-------------------------- -----------------------------------------------------------------------------------------" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Parse progress: |████████████████████████████████████████████████████████████████| (done) 100%\n", + "AutoML progress: |███████████████████████████████████████████████████████████████| (done) 100%\n", + "model_id rmse mse mae rmsle mean_residual_deviance\n", + "StackedEnsemble_BestOfFamily_4_AutoML_3_20240618_60156 3.15382 9.94661 2.05668 0.141455 9.94661\n", + "GBM_grid_1_AutoML_3_20240618_60156_model_1 3.19951 10.2369 2.08508 0.141747 10.2369\n", + "XGBoost_grid_1_AutoML_3_20240618_60156_model_24 3.25097 10.5688 2.17213 0.14893 10.5688\n", + "StackedEnsemble_BestOfFamily_3_AutoML_3_20240618_60156 3.26392 10.6531 2.11243 0.144641 10.6531\n", + "StackedEnsemble_BestOfFamily_2_AutoML_3_20240618_60156 3.28705 10.8047 2.12499 0.145846 10.8047\n", + "GBM_grid_1_AutoML_3_20240618_60156_model_8 3.28857 10.8147 2.16152 0.147606 10.8147\n", + "StackedEnsemble_AllModels_1_AutoML_3_20240618_60156 3.30055 10.8936 2.11664 0.145208 10.8936\n", + "GBM_grid_1_AutoML_3_20240618_60156_model_26 3.31512 10.99 2.19101 0.149461 10.99\n", + "GBM_grid_1_AutoML_3_20240618_60156_model_5 3.32106 11.0294 2.20349 0.147518 11.0294\n", + "GBM_grid_1_AutoML_3_20240618_60156_model_22 3.32589 11.0616 2.11391 0.148214 11.0616\n", + "[98 rows x 6 columns]\n", + "\n", + "stackedensemble prediction progress: |███████████████████████████████████████████| (done) 100%\n", + " predict\n", + " 37.1927\n", + " 19.2904\n", + " 18.5823\n", + " 17.0585\n", + " 18.548\n", + " 19.0036\n", + " 13.9268\n", + " 17.1111\n", + " 16.4236\n", + " 19.9794\n", + "[10 rows x 1 column]\n", + "\n" + ] + } + ], + "source": [ + "import pandas as pd\n", + "import h2o\n", + "from h2o.automl import H2OAutoML\n", + "import requests\n", + "from io import StringIO\n", + "import matplotlib.pyplot as plt\n", + "import seaborn as sns\n", + "\n", + "# Download the dataset\n", + "url = \"http://lib.stat.cmu.edu/datasets/boston\"\n", + "response = requests.get(url)\n", + "data = response.text.split(\"\\n\")\n", + "\n", + "# Process the dataset\n", + "header = [\"CRIM\", \"ZN\", \"INDUS\", \"CHAS\", \"NOX\", \"RM\", \"AGE\", \"DIS\", \"RAD\", \"TAX\", \"PTRATIO\", \"B\", \"LSTAT\", \"MEDV\"]\n", + "raw_data = data[22:] # The actual data starts at line 23\n", + "\n", + "# Parsing the data into a format readable by pandas\n", + "data = []\n", + "for i in range(0, len(raw_data) - 1, 2):\n", + " row1 = list(map(float, raw_data[i].strip().split()))\n", + " row2 = list(map(float, raw_data[i+1].strip().split()))\n", + " data.append(row1 + row2)\n", + "\n", + "# Create a DataFrame\n", + "df = pd.DataFrame(data, columns=header)\n", + "\n", + "# Initialize H2O\n", + "h2o.init()\n", + "\n", + "# Convert to H2OFrame\n", + "hf = h2o.H2OFrame(df)\n", + "\n", + "# Define target and features\n", + "y = 'MEDV'\n", + "x = hf.columns\n", + "x.remove(y)\n", + "\n", + "# Split the data into train and test sets\n", + "train, test = hf.split_frame(ratios=[.8], seed=1234)\n", + "\n", + "# Run H2O AutoML\n", + "aml = H2OAutoML(max_runtime_secs=300, seed=1234)\n", + "aml.train(x=x, y=y, training_frame=train)\n", + "\n", + "# View the AutoML Leaderboard\n", + "lb = aml.leaderboard\n", + "print(lb)\n", + "\n", + "# Predict on the test set\n", + "preds = aml.leader.predict(test)\n", + "print(preds.head())\n" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 1000 + }, + "id": "N5qLbqfJ7qp8", + "outputId": "03727740-7320-4420-b68f-93b7439f59cd" + }, + "outputs": [ + { + "data": { + "image/png": "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\n", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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\n", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "# Convert predictions to a pandas DataFrame\n", + "preds_df = preds.as_data_frame()\n", + "test_df = test.as_data_frame()\n", + "\n", + "# Scatter plot of actual vs predicted values\n", + "plt.figure(figsize=(10, 6))\n", + "plt.scatter(test_df['MEDV'], preds_df['predict'], alpha=0.7)\n", + "plt.xlabel('Actual MEDV')\n", + "plt.ylabel('Predicted MEDV')\n", + "plt.title('Actual vs Predicted MEDV')\n", + "plt.plot([test_df['MEDV'].min(), test_df['MEDV'].max()], [test_df['MEDV'].min(), test_df['MEDV'].max()], 'k--', lw=3)\n", + "plt.show()\n", + "\n", + "# Residuals plot\n", + "residuals = test_df['MEDV'] - preds_df['predict']\n", + "plt.figure(figsize=(10, 6))\n", + "sns.histplot(residuals, kde=True)\n", + "plt.xlabel('Residuals')\n", + "plt.title('Distribution of Residuals')\n", + "plt.show()\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "_Mc_vH9Z1dW-" + }, + "source": [ + "Classification with H2O AutoML\n", + "\n", + "Dataset - Iris" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 934 + }, + "id": "0tzxJlKK2T4f", + "outputId": "f26f12cb-fe85-449b-e517-e1c9d7c831a4" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Checking whether there is an H2O instance running at http://localhost:54321. connected.\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", + "
H2O_cluster_uptime:1 hour 27 mins
H2O_cluster_timezone:Etc/UTC
H2O_data_parsing_timezone:UTC
H2O_cluster_version:3.46.0.3
H2O_cluster_version_age:6 days
H2O_cluster_name:H2O_from_python_unknownUser_62vsjk
H2O_cluster_total_nodes:1
H2O_cluster_free_memory:2.940 Gb
H2O_cluster_total_cores:2
H2O_cluster_allowed_cores:2
H2O_cluster_status:locked, healthy
H2O_connection_url:http://localhost:54321
H2O_connection_proxy:{\"http\": null, \"https\": null, \"colab_language_server\": \"/usr/colab/bin/language_service\"}
H2O_internal_security:False
Python_version:3.10.12 final
\n", + "
\n" + ], + "text/plain": [ + "-------------------------- -----------------------------------------------------------------------------------------\n", + "H2O_cluster_uptime: 1 hour 27 mins\n", + "H2O_cluster_timezone: Etc/UTC\n", + "H2O_data_parsing_timezone: UTC\n", + "H2O_cluster_version: 3.46.0.3\n", + "H2O_cluster_version_age: 6 days\n", + "H2O_cluster_name: H2O_from_python_unknownUser_62vsjk\n", + "H2O_cluster_total_nodes: 1\n", + "H2O_cluster_free_memory: 2.940 Gb\n", + "H2O_cluster_total_cores: 2\n", + "H2O_cluster_allowed_cores: 2\n", + "H2O_cluster_status: locked, healthy\n", + "H2O_connection_url: http://localhost:54321\n", + "H2O_connection_proxy: {\"http\": null, \"https\": null, \"colab_language_server\": \"/usr/colab/bin/language_service\"}\n", + "H2O_internal_security: False\n", + "Python_version: 3.10.12 final\n", + "-------------------------- -----------------------------------------------------------------------------------------" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Parse progress: |████████████████████████████████████████████████████████████████| (done) 100%\n", + "AutoML progress: |███\n", + "07:04:35.986: _min_rows param, The dataset size is too small to split for min_rows=100.0: must have at least 200.0 (weighted) rows, but have only 123.0.\n", + "\n", + "████████████████████████████████████████████████████████████| (done) 100%\n", + "model_id mean_per_class_error logloss rmse mse\n", + "GLM_1_AutoML_4_20240618_70425 0.0391844 0.0802971 0.159766 0.0255252\n", + "XGBoost_grid_1_AutoML_4_20240618_70425_model_15 0.0391844 0.211914 0.2213 0.0489739\n", + "XGBoost_grid_1_AutoML_4_20240618_70425_model_29 0.0404255 0.182995 0.210106 0.0441444\n", + "XGBoost_grid_1_AutoML_4_20240618_70425_model_1 0.0404255 0.227903 0.233957 0.054736\n", + "GBM_grid_1_AutoML_4_20240618_70425_model_51 0.0404255 0.353455 0.308997 0.095479\n", + "DeepLearning_grid_1_AutoML_4_20240618_70425_model_1 0.0404255 0.0971387 0.169379 0.0286892\n", + "XGBoost_grid_1_AutoML_4_20240618_70425_model_22 0.0404255 0.275401 0.262996 0.0691669\n", + "XGBoost_grid_1_AutoML_4_20240618_70425_model_14 0.0404255 0.167819 0.199234 0.039694\n", + "XGBoost_grid_1_AutoML_4_20240618_70425_model_16 0.0404255 0.16196 0.195353 0.0381627\n", + "XGBoost_2_AutoML_4_20240618_70425 0.0404255 0.213217 0.223011 0.0497338\n", + "[113 rows x 5 columns]\n", + "\n", + "glm prediction progress: |███████████████████████████████████████████████████████| (done) 100%\n", + "predict setosa versicolor virginica\n", + "setosa 0.999139 0.000861079 8.33264e-17\n", + "setosa 0.997719 0.00228132 4.54593e-17\n", + "setosa 0.999292 0.00070779 4.59286e-20\n", + "setosa 0.999005 0.000994975 1.21531e-17\n", + "setosa 0.996481 0.00351926 2.42413e-17\n", + "setosa 0.999798 0.000202427 1.67521e-18\n", + "setosa 0.993483 0.00651718 1.27832e-16\n", + "setosa 0.999498 0.000502305 1.42709e-17\n", + "setosa 0.998004 0.00199643 3.31931e-16\n", + "setosa 0.999153 0.000846806 8.4615e-17\n", + "[10 rows x 4 columns]\n", + "\n" + ] + } + ], + "source": [ + "import h2o\n", + "from h2o.automl import H2OAutoML\n", + "from sklearn.datasets import load_iris\n", + "import pandas as pd\n", + "\n", + "# Initialize H2O\n", + "h2o.init()\n", + "\n", + "# Load dataset\n", + "iris = load_iris()\n", + "df = pd.DataFrame(data=iris.data, columns=iris.feature_names)\n", + "df['species'] = pd.Categorical.from_codes(iris.target, iris.target_names)\n", + "\n", + "# Convert to H2OFrame\n", + "hf = h2o.H2OFrame(df)\n", + "\n", + "# Define target and features\n", + "y = 'species'\n", + "x = hf.columns\n", + "x.remove(y)\n", + "\n", + "# Split the data into train and test sets\n", + "train, test = hf.split_frame(ratios=[.8], seed=1234)\n", + "\n", + "# Run H2O AutoML\n", + "aml = H2OAutoML(max_runtime_secs=300, seed=1234)\n", + "aml.train(x=x, y=y, training_frame=train)\n", + "\n", + "# View the AutoML Leaderboard\n", + "lb = aml.leaderboard\n", + "print(lb)\n", + "\n", + "# Predict on the test set\n", + "preds = aml.leader.predict(test)\n", + "print(preds.head())\n" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 666 + }, + "id": "_5y4APbk3zcf", + "outputId": "730c25ca-0496-4537-bc99-be68b0765ba1" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Predicted setosa versicolor virginica\n", + "Actual \n", + "setosa 14 0 0\n", + "versicolor 0 9 1\n", + "virginica 0 0 3\n" + ] + }, + { + "data": { + "image/png": "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\n", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "H2O session _sid_856a closed.\n" + ] + } + ], + "source": [ + "# Convert predictions to pandas DataFrame\n", + "preds_df = preds.as_data_frame()\n", + "test_df = test.as_data_frame()\n", + "\n", + "# Confusion matrix\n", + "confusion_matrix = pd.crosstab(test_df['species'], preds_df['predict'], rownames=['Actual'], colnames=['Predicted'])\n", + "print(confusion_matrix)\n", + "\n", + "# Plot confusion matrix\n", + "plt.figure(figsize=(8, 6))\n", + "sns.heatmap(confusion_matrix, annot=True, fmt=\"d\", cmap=\"Blues\", xticklabels=iris.target_names, yticklabels=iris.target_names)\n", + "plt.xlabel('Predicted')\n", + "plt.ylabel('Actual')\n", + "plt.title('Confusion Matrix')\n", + "plt.show()\n", + "\n", + "# ROC curve (for binary classification tasks)\n", + "if len(iris.target_names) == 2:\n", + " perf = aml.leader.model_performance(test_data=test)\n", + " perf.plot()\n", + "\n", + "# Shutdown H2O\n", + "h2o.shutdown()" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "9NoJBF8COwZc" + }, + "source": [ + "# 3. TPOT" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "3hpteiwWObvS", + "outputId": "586985b2-d159-410d-8140-3796a536432a" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Collecting tpot\n", + " Downloading TPOT-0.12.2-py3-none-any.whl (87 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m87.4/87.4 kB\u001b[0m \u001b[31m2.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hRequirement already satisfied: numpy>=1.16.3 in /usr/local/lib/python3.10/dist-packages (from tpot) (1.25.2)\n", + "Requirement already satisfied: scipy>=1.3.1 in /usr/local/lib/python3.10/dist-packages (from tpot) (1.11.4)\n", + "Requirement already satisfied: scikit-learn>=1.4.1 in /usr/local/lib/python3.10/dist-packages (from tpot) (1.4.2)\n", + "Collecting deap>=1.2 (from tpot)\n", + " Downloading deap-1.4.1-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (135 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m135.4/135.4 kB\u001b[0m \u001b[31m8.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hCollecting update-checker>=0.16 (from tpot)\n", + " Downloading update_checker-0.18.0-py3-none-any.whl (7.0 kB)\n", + "Requirement already satisfied: tqdm>=4.36.1 in /usr/local/lib/python3.10/dist-packages (from tpot) (4.66.4)\n", + "Collecting stopit>=1.1.1 (from tpot)\n", + " Downloading stopit-1.1.2.tar.gz (18 kB)\n", + " Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n", + "Requirement already satisfied: pandas>=0.24.2 in /usr/local/lib/python3.10/dist-packages (from tpot) (2.0.3)\n", + "Requirement already satisfied: joblib>=0.13.2 in /usr/local/lib/python3.10/dist-packages (from tpot) (1.3.2)\n", + "Requirement already satisfied: xgboost>=1.1.0 in /usr/local/lib/python3.10/dist-packages (from tpot) (2.0.3)\n", + "Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.10/dist-packages (from pandas>=0.24.2->tpot) (2.8.2)\n", + "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas>=0.24.2->tpot) (2023.4)\n", + "Requirement already satisfied: tzdata>=2022.1 in /usr/local/lib/python3.10/dist-packages (from pandas>=0.24.2->tpot) (2024.1)\n", + "Requirement already satisfied: threadpoolctl>=2.0.0 in /usr/local/lib/python3.10/dist-packages (from scikit-learn>=1.4.1->tpot) (3.5.0)\n", + "Requirement already satisfied: requests>=2.3.0 in /usr/local/lib/python3.10/dist-packages (from update-checker>=0.16->tpot) (2.31.0)\n", + "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-packages (from python-dateutil>=2.8.2->pandas>=0.24.2->tpot) (1.16.0)\n", + "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests>=2.3.0->update-checker>=0.16->tpot) (3.3.2)\n", + "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests>=2.3.0->update-checker>=0.16->tpot) (3.7)\n", + "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests>=2.3.0->update-checker>=0.16->tpot) (2.0.7)\n", + "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests>=2.3.0->update-checker>=0.16->tpot) (2024.6.2)\n", + "Building wheels for collected packages: stopit\n", + " Building wheel for stopit (setup.py) ... \u001b[?25l\u001b[?25hdone\n", + " Created wheel for stopit: filename=stopit-1.1.2-py3-none-any.whl size=11938 sha256=f573d78eb9f712ad26cd9bcb262bdf7104e9dbdb9e296f46ab68c37d1cb020ca\n", + " Stored in directory: /root/.cache/pip/wheels/af/f9/87/bf5b3d565c2a007b4dae9d8142dccc85a9f164e517062dd519\n", + "Successfully built stopit\n", + "Installing collected packages: stopit, deap, update-checker, tpot\n", + "Successfully installed deap-1.4.1 stopit-1.1.2 tpot-0.12.2 update-checker-0.18.0\n" + ] + } + ], + "source": [ + "!pip install tpot" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "WTRb7BQEPkq9" + }, + "source": [ + "Regression with TPOT\n", + "\n", + "Dataset - California_housing" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "background_save": true, + "base_uri": "https://localhost:8080/", + "height": 118, + "referenced_widgets": [ + "a68fbdcda1e440a5806d39629060468c", + "aa14cda9668345fa8ff70d7eb87bf73f", + "f2373d5705fb4b4db4f07f60ea970ced", + "4d98d1d7252b4701a6d526bc74233e64", + "f82e47539b314ef0bd9c03f811098954", + "6575ebe911e74fc6afeed006ade3b52e", + "7f1de76c602c4a6b9a82860c82a4f492", + "0ac9aa8605b0425894e30417eba03762", + "9b18efda243f4de4b574b2408c897a39", + "013513def5a84f6580865c3a5a4e63c8", + "5d54b9bdc25d43c58d867a2a8a378bca" + ] + }, + "id": "L5FXPbPZO1tR", + "outputId": "ca604697-a65e-4a7d-ebd2-8f6891d99823" + }, + "outputs": [ + { + "data": { + "application/vnd.jupyter.widget-view+json": { + "model_id": "a68fbdcda1e440a5806d39629060468c", + "version_major": 2, + "version_minor": 0 + }, + "text/plain": [ + "Optimization Progress: 0%| | 0/120 [00:00" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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\n", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "from tpot import TPOTRegressor\n", + "from sklearn.datasets import fetch_california_housing\n", + "from sklearn.model_selection import train_test_split\n", + "import matplotlib.pyplot as plt\n", + "import seaborn as sns\n", + "\n", + "# Load the California Housing dataset\n", + "california = fetch_california_housing()\n", + "X, y = california.data, california.target\n", + "\n", + "# Split data into train and test sets\n", + "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=123)\n", + "\n", + "# Initialize TPOTRegressor\n", + "tpot = TPOTRegressor(generations=5, population_size=20, verbosity=2, random_state=123, n_jobs=-1)\n", + "\n", + "# Fit TPOT on training data\n", + "tpot.fit(X_train, y_train)\n", + "\n", + "# Evaluate TPOT on test data\n", + "print(\"R2 score on test set:\", tpot.score(X_test, y_test))\n", + "\n", + "# Export the pipeline as Python code\n", + "tpot.export('tpot_california_pipeline.py')\n", + "\n", + "# Visualize results\n", + "# Scatter plot of actual vs predicted values\n", + "preds = tpot.predict(X_test)\n", + "\n", + "plt.figure(figsize=(10, 6))\n", + "plt.scatter(y_test, preds, alpha=0.7)\n", + "plt.xlabel('Actual House Price')\n", + "plt.ylabel('Predicted House Price')\n", + "plt.title('Actual vs Predicted House Price (TPOT)')\n", + "plt.plot([y_test.min(), y_test.max()], [y_test.min(), y_test.max()], 'k--', lw=3)\n", + "plt.show()\n", + "\n", + "# Residuals plot\n", + "residuals = y_test - preds\n", + "plt.figure(figsize=(10, 6))\n", + "sns.histplot(residuals, kde=True)\n", + "plt.xlabel('Residuals')\n", + "plt.title('Distribution of Residuals (TPOT)')\n", + "plt.show()\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "WUYy3Xb5PzwG" + }, + "source": [ + "Classification using TPOT\n", + "\n", + "Dataset - Iris" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "background_save": true, + "referenced_widgets": [ + "9f63ffb492744747a074530475194465" + ] + }, + "id": "qptVSmufPkKS", + "outputId": "0ec0f0de-ddc6-44ba-c1e5-22a611ec1e4b" + }, + "outputs": [ + { + "data": { + "application/vnd.jupyter.widget-view+json": { + "model_id": "9f63ffb492744747a074530475194465", + "version_major": 2, + "version_minor": 0 + }, + "text/plain": [ + "Optimization Progress: 0%| | 0/120 [00:00" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "from tpot import TPOTClassifier\n", + "from sklearn.datasets import load_iris\n", + "from sklearn.model_selection import train_test_split\n", + "from sklearn.metrics import accuracy_score, classification_report, confusion_matrix\n", + "import matplotlib.pyplot as plt\n", + "import seaborn as sns\n", + "\n", + "# Load the Iris dataset\n", + "iris = load_iris()\n", + "X, y = iris.data, iris.target\n", + "\n", + "# Split data into train and test sets\n", + "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=123)\n", + "\n", + "# Initialize TPOTClassifier\n", + "tpot = TPOTClassifier(generations=5, population_size=20, verbosity=2, random_state=123, n_jobs=-1)\n", + "\n", + "# Fit TPOT on training data\n", + "tpot.fit(X_train, y_train)\n", + "\n", + "# Evaluate TPOT on test data\n", + "y_pred = tpot.predict(X_test)\n", + "print(\"Accuracy on test set:\", accuracy_score(y_test, y_pred))\n", + "print(\"\\nClassification Report:\\n\", classification_report(y_test, y_pred))\n", + "print(\"\\nConfusion Matrix:\\n\", confusion_matrix(y_test, y_pred))\n", + "\n", + "# Export the pipeline as Python code\n", + "tpot.export('tpot_iris_pipeline.py')\n", + "\n", + "# Visualize results\n", + "# Confusion matrix heatmap\n", + "plt.figure(figsize=(8, 6))\n", + "cm = confusion_matrix(y_test, y_pred)\n", + "sns.heatmap(cm, annot=True, cmap='Blues', fmt='d', xticklabels=iris.target_names, yticklabels=iris.target_names)\n", + "plt.xlabel('Predicted')\n", + "plt.ylabel('Actual')\n", + "plt.title('Confusion Matrix (TPOT - Iris Dataset)')\n", + "plt.show()\n" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "g5YJOL1VZUgr" + }, + "outputs": [], + "source": [] + } + ], + "metadata": { + "colab": { + "provenance": [], + "authorship_tag": "ABX9TyPlDmdxD0RDmAEG46LS7H4a", + "include_colab_link": true + }, + "kernelspec": { + "display_name": "Python 3", + "name": "python3" + }, + "language_info": { + "name": "python" + }, + "widgets": { + "application/vnd.jupyter.widget-state+json": { + "00ff02b4433b45d0a5b08a9c29cdc241": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HTMLModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_7acc61bd395b4ca382d451a78c117ecf", + "placeholder": "​", + "style": "IPY_MODEL_b9a48aad37b341febaf8cd61fe490061", + "value": " 81/81 [00:31<00:00,  3.62it/s]" + } + }, + "013513def5a84f6580865c3a5a4e63c8": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "08f169a6bfa54fb0abca36b7514e4d57": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "DescriptionStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "0ac9aa8605b0425894e30417eba03762": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "160aac587394490faf7bfe7b93ca191f": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "1c52e377537b43a1b687fe8d31c5fb0e": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HBoxModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HBoxModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HBoxView", + "box_style": "", + "children": [ + "IPY_MODEL_686f5ba4514a4535acfa9543f90d3e1f", + "IPY_MODEL_f62806907897477b870ffc2def71ce9a", + "IPY_MODEL_00ff02b4433b45d0a5b08a9c29cdc241" + ], + "layout": "IPY_MODEL_e18ed3b3e2f647aab0f4f01390c4bdb4" + } + }, + "1d9acd20f61a480c8b2c76b7c73dcb18": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "3058c21b2b0a496d81857d6c96258af7": { + "model_module": "@jupyter-widgets/output", + "model_module_version": "1.0.0", + "model_name": "OutputModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/output", + "_model_module_version": "1.0.0", + "_model_name": "OutputModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/output", + "_view_module_version": "1.0.0", + "_view_name": "OutputView", + "layout": "IPY_MODEL_65dc5783283c4f768494ef9a122ba2e2", + "msg_id": "", + "outputs": [ + { + "data": { + "image/png": "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\n", + "text/plain": "
" + }, + "metadata": {}, + "output_type": "display_data" + } + ] + } + }, + "337878fc244f404bb2dc3b33b4d9380e": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "38d9bc5728214b2f951963368028a884": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "ProgressStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "ProgressStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "bar_color": null, + "description_width": "" + } + }, + "3dd6081acc524b3685fbaa4e456815e0": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "40499c30f19942389529429ce08db3d0": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "ToggleButtonsStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "ToggleButtonsStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "button_width": "", + "description_width": "", + "font_weight": "" + } + }, + "4d2e26640c734c3e8c1eab52509cbcc6": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "ToggleButtonsModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "ToggleButtonsModel", + "_options_labels": [ + "Pipeline Plot", + "Hyperparameters", + "Residuals", + "Prediction Error", + "Cooks Distance", + "Feature Selection", + "Learning Curve", + "Manifold Learning", + "Validation Curve", + "Feature Importance", + "Feature Importance (All)", + "Decision Tree", + "Interactive Residuals" + ], + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "ToggleButtonsView", + "button_style": "", + "description": "Plot Type:", + "description_tooltip": null, + "disabled": false, + "icons": [ + "" + ], + "index": 1, + "layout": "IPY_MODEL_91c2559aadd749cb9674df365defd00d", + "style": "IPY_MODEL_77963dee9112452b9eec9464cff72f4a", + "tooltips": [] + } + }, + "4d98d1d7252b4701a6d526bc74233e64": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HTMLModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_013513def5a84f6580865c3a5a4e63c8", + "placeholder": "​", + "style": "IPY_MODEL_5d54b9bdc25d43c58d867a2a8a378bca", + "value": " 63/120 [15:04<10:26, 10.99s/pipeline]" + } + }, + "5d54b9bdc25d43c58d867a2a8a378bca": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "DescriptionStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "5d65b9cab121417da42c03f9e22001d4": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": "hidden", + "width": null + } + }, + "6575ebe911e74fc6afeed006ade3b52e": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "65dc5783283c4f768494ef9a122ba2e2": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "686f5ba4514a4535acfa9543f90d3e1f": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HTMLModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_3dd6081acc524b3685fbaa4e456815e0", + "placeholder": "​", + "style": "IPY_MODEL_08f169a6bfa54fb0abca36b7514e4d57", + "value": "Processing: 100%" + } + }, + "6fadb209441c408eabd44af64c7161b8": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "ProgressStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "ProgressStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "bar_color": null, + "description_width": "" + } + }, + "77963dee9112452b9eec9464cff72f4a": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "ToggleButtonsStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "ToggleButtonsStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "button_width": "", + "description_width": "", + "font_weight": "" + } + }, + "7acc61bd395b4ca382d451a78c117ecf": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "7f1de76c602c4a6b9a82860c82a4f492": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "DescriptionStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "80bf334f1d3a4343aaf6c467cc80cc68": { + "model_module": "@jupyter-widgets/output", + "model_module_version": "1.0.0", + "model_name": "OutputModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/output", + "_model_module_version": "1.0.0", + "_model_name": "OutputModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/output", + "_view_module_version": "1.0.0", + "_view_name": "OutputView", + "layout": "IPY_MODEL_1d9acd20f61a480c8b2c76b7c73dcb18", + "msg_id": "", + "outputs": [ + { + "data": { + "application/vnd.google.colaboratory.intrinsic+json": { + "summary": "{\n \"name\": \"evaluate_model(best_model)\",\n \"rows\": 18,\n \"fields\": [\n {\n \"column\": \"Parameters\",\n \"properties\": {\n \"dtype\": \"string\",\n \"num_unique_values\": 11,\n \"samples\": [\n \"1\",\n \"False\",\n \"123\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}", + "type": "dataframe" + }, + "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
Parameters
bootstrapFalse
ccp_alpha0.0
criterionsquared_error
max_depthNone
max_features1.0
max_leaf_nodesNone
max_samplesNone
min_impurity_decrease0.0
min_samples_leaf1
min_samples_split2
min_weight_fraction_leaf0.0
monotonic_cstNone
n_estimators100
n_jobs-1
oob_scoreFalse
random_state123
verbose0
warm_startFalse
\n
\n
\n\n
\n \n\n \n\n \n
\n\n\n
\n \n\n\n\n \n
\n\n
\n
\n", + "text/plain": " Parameters\nbootstrap False\nccp_alpha 0.0\ncriterion squared_error\nmax_depth None\nmax_features 1.0\nmax_leaf_nodes None\nmax_samples None\nmin_impurity_decrease 0.0\nmin_samples_leaf 1\nmin_samples_split 2\nmin_weight_fraction_leaf 0.0\nmonotonic_cst None\nn_estimators 100\nn_jobs -1\noob_score False\nrandom_state 123\nverbose 0\nwarm_start False" + }, + "metadata": {}, + "output_type": "display_data" + } + ] + } + }, + "8727cffbfe1846809b967a89dee1ca9a": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "89c5db0ca21a4ac587f167d605056d54": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "90809633002c4613ada36fb86aeede20": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "90d2a0afc4384a0786410597cf38254f": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "DescriptionStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "91c2559aadd749cb9674df365defd00d": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "9b18efda243f4de4b574b2408c897a39": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "ProgressStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "ProgressStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "bar_color": null, + "description_width": "" + } + }, + "a332739eac9a4b0c8a2bde393c6466ba": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "ToggleButtonsModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "ToggleButtonsModel", + "_options_labels": [ + "Pipeline Plot", + "Hyperparameters", + "AUC", + "Confusion Matrix", + "Threshold", + "Precision Recall", + "Prediction Error", + "Class Report", + "Feature Selection", + "Learning Curve", + "Manifold Learning", + "Calibration Curve", + "Validation Curve", + "Dimensions", + "Feature Importance", + "Feature Importance (All)", + "Decision Boundary", + "Lift Chart", + "Gain Chart", + "Decision Tree", + "KS Statistic Plot" + ], + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "ToggleButtonsView", + "button_style": "", + "description": "Plot Type:", + "description_tooltip": null, + "disabled": false, + "icons": [ + "" + ], + "index": 0, + "layout": "IPY_MODEL_90809633002c4613ada36fb86aeede20", + "style": "IPY_MODEL_40499c30f19942389529429ce08db3d0", + "tooltips": [] + } + }, + "a68fbdcda1e440a5806d39629060468c": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HBoxModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HBoxModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HBoxView", + "box_style": "", + "children": [ + "IPY_MODEL_aa14cda9668345fa8ff70d7eb87bf73f", + "IPY_MODEL_f2373d5705fb4b4db4f07f60ea970ced", + "IPY_MODEL_4d98d1d7252b4701a6d526bc74233e64" + ], + "layout": "IPY_MODEL_f82e47539b314ef0bd9c03f811098954" + } + }, + "aa14cda9668345fa8ff70d7eb87bf73f": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HTMLModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_6575ebe911e74fc6afeed006ade3b52e", + "placeholder": "​", + "style": "IPY_MODEL_7f1de76c602c4a6b9a82860c82a4f492", + "value": "Optimization Progress:  52%" + } + }, + "b4f51881b1f348278b6aab89108c04b7": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "VBoxModel", + "state": { + "_dom_classes": [ + "widget-interact" + ], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "VBoxModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "VBoxView", + "box_style": "", + "children": [ + "IPY_MODEL_a332739eac9a4b0c8a2bde393c6466ba", + "IPY_MODEL_3058c21b2b0a496d81857d6c96258af7" + ], + "layout": "IPY_MODEL_160aac587394490faf7bfe7b93ca191f" + } + }, + "b9a48aad37b341febaf8cd61fe490061": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "DescriptionStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "be0becb852d74805810ce0ff949565ba": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HBoxModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HBoxModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HBoxView", + "box_style": "", + "children": [ + "IPY_MODEL_ec8d189a21bc40a0a09d0a7942fe7d4b", + "IPY_MODEL_ceeb0fead1ff4b5aaf6ea8e2dbb3ab55", + "IPY_MODEL_dc54a689d8174351b59ed81a3a629859" + ], + "layout": "IPY_MODEL_5d65b9cab121417da42c03f9e22001d4" + } + }, + "ceeb0fead1ff4b5aaf6ea8e2dbb3ab55": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "FloatProgressModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "FloatProgressModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "ProgressView", + "bar_style": "", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_89c5db0ca21a4ac587f167d605056d54", + "max": 65, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_6fadb209441c408eabd44af64c7161b8", + "value": 65 + } + }, + "cfa0ede2c1764ebc8ed76a9df5cc5b69": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "VBoxModel", + "state": { + "_dom_classes": [ + "widget-interact" + ], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "VBoxModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "VBoxView", + "box_style": "", + "children": [ + "IPY_MODEL_4d2e26640c734c3e8c1eab52509cbcc6", + "IPY_MODEL_80bf334f1d3a4343aaf6c467cc80cc68" + ], + "layout": "IPY_MODEL_8727cffbfe1846809b967a89dee1ca9a" + } + }, + "d2131e660a4547708b034564f592368e": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "dc54a689d8174351b59ed81a3a629859": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HTMLModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_d2131e660a4547708b034564f592368e", + "placeholder": "​", + "style": "IPY_MODEL_90d2a0afc4384a0786410597cf38254f", + "value": " 65/65 [00:22<00:00,  3.43it/s]" + } + }, + "e18ed3b3e2f647aab0f4f01390c4bdb4": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": "hidden", + "width": null + } + }, + "e3b02bc7d049414cabecddd346c3e5e8": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "ec8d189a21bc40a0a09d0a7942fe7d4b": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HTMLModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_e3b02bc7d049414cabecddd346c3e5e8", + "placeholder": "​", + "style": "IPY_MODEL_ff5a527e36954b19b8b5989e274abdc7", + "value": "Processing: 100%" + } + }, + "f2373d5705fb4b4db4f07f60ea970ced": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "FloatProgressModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "FloatProgressModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "ProgressView", + "bar_style": "", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_0ac9aa8605b0425894e30417eba03762", + "max": 120, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_9b18efda243f4de4b574b2408c897a39", + "value": 63 + } + }, + "f62806907897477b870ffc2def71ce9a": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "FloatProgressModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "FloatProgressModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "ProgressView", + "bar_style": "", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_337878fc244f404bb2dc3b33b4d9380e", + "max": 81, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_38d9bc5728214b2f951963368028a884", + "value": 81 + } + }, + "f82e47539b314ef0bd9c03f811098954": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "ff5a527e36954b19b8b5989e274abdc7": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "DescriptionStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + } + } + } + }, + "nbformat": 4, + "nbformat_minor": 0 +} \ No newline at end of file