{
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "\n# Linear Tree Classification\n"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "Installation\n\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": false
      },
      "outputs": [],
      "source": [
        "# To install the required package, use the following command:\n# !pip install modeva"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "Authentication\n\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": false
      },
      "outputs": [],
      "source": [
        "# To get authentication, use the following command: (To get full access please replace the token to your own token)\n# from modeva.utils.authenticate import authenticate\n# authenticate(auth_code='eaaa4301-b140-484c-8e93-f9f633c8bacb')"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "Import required modules\n\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": false
      },
      "outputs": [],
      "source": [
        "from modeva import DataSet\nfrom modeva import TestSuite\nfrom modeva.models import MoLGBMClassifier, MoGLMTreeBoostClassifier, MoNeuralTreeClassifier"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "Load and prepare dataset\n\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": false
      },
      "outputs": [],
      "source": [
        "ds = DataSet()\nds.load(name=\"TaiwanCredit\")\nds.set_random_split()\nds.set_target(\"FlagDefault\")"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "## LGBM Linear Tree model\n\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": false
      },
      "outputs": [],
      "source": [
        "model = MoLGBMClassifier(linear_trees=True, max_depth=2, verbose=-1, random_state=0)\nmodel.fit(ds.train_x, ds.train_y.ravel())"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "Basic accuracy analysis\n\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": false
      },
      "outputs": [],
      "source": [
        "ts = TestSuite(ds, model)\nresults = ts.diagnose_accuracy_table()\nresults.table"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "Feature importance analysis\n\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": false
      },
      "outputs": [],
      "source": [
        "results = ts.interpret_fi()\nresults.plot()"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "Local feature importance analysis\n\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": false
      },
      "outputs": [],
      "source": [
        "results = ts.interpret_local_fi(sample_index=1, centered=True)\nresults.plot()"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "## Boosted GLMTree model\n\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": false
      },
      "outputs": [],
      "source": [
        "model = MoGLMTreeBoostClassifier(max_depth=1, n_estimators=100,\n                                 reg_lambda=0.001, verbose=True, random_state=0)\nmodel.fit(ds.train_x, ds.train_y.ravel())"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "Basic accuracy analysis\n\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": false
      },
      "outputs": [],
      "source": [
        "ts = TestSuite(ds, model)\nresults = ts.diagnose_accuracy_table()\nresults.table"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "Main effect plot for numerical feature\n\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": false
      },
      "outputs": [],
      "source": [
        "results = ts.interpret_effects(features=\"PAY_1\")\nresults.plot()"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "Main effect plot for categorical feature\n\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": false
      },
      "outputs": [],
      "source": [
        "results = ts.interpret_effects(features=\"EDUCATION\")\nresults.plot()"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "## Neural Tree model with Monotonicity Constraints\n\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": false
      },
      "outputs": [],
      "source": [
        "modelnn = MoNeuralTreeClassifier(estimator=model,\n                                 nn_temperature=0.0001,\n                                 nn_max_epochs=20,\n                                 feature_names=ds.feature_names,\n                                 mono_increasing_list=(\"PAY_1\",),\n                                 mono_sample_size=1000,\n                                 reg_mono=10,\n                                 verbose=True,\n                                 random_state=0)\nmodelnn.fit(ds.train_x, ds.train_y.ravel())"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "Basic accuracy analysis\n\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": false
      },
      "outputs": [],
      "source": [
        "ts = TestSuite(ds, modelnn)\nresults = ts.diagnose_accuracy_table()\nresults.table"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "Feature importance analysis\n\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": false
      },
      "outputs": [],
      "source": [
        "results = ts.interpret_fi()\nresults.plot()"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "Main effect plot\n\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": false
      },
      "outputs": [],
      "source": [
        "results = ts.interpret_effects(features=\"PAY_1\")\nresults.plot()"
      ]
    }
  ],
  "metadata": {
    "kernelspec": {
      "display_name": "Python 3",
      "language": "python",
      "name": "python3"
    },
    "language_info": {
      "codemirror_mode": {
        "name": "ipython",
        "version": 3
      },
      "file_extension": ".py",
      "mimetype": "text/x-python",
      "name": "python",
      "nbconvert_exporter": "python",
      "pygments_lexer": "ipython3",
      "version": "3.11.11"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 0
}