{
  "cells": [
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": false
      },
      "outputs": [],
      "source": [
        "%matplotlib inline"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "\n# Regression results (Pred vs Real)\n\nGiven a trained model, it showcase the performance, along a error band\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": false
      },
      "outputs": [],
      "source": [
        "import numpy as np\nfrom sklearn.datasets import load_diabetes\nfrom sklearn.ensemble import RandomForestRegressor\nfrom sklearn.model_selection import cross_val_predict, train_test_split\n\nfrom dfds_ds_toolbox.analysis.plotting import plot_regression_predicted_vs_actual\n\n# Create a dataset to fit and predict\n\nX, y = load_diabetes(return_X_y=True, as_frame=True)\nnumeric_cols = list(X.columns)\nX_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.4, random_state=42)\ndata_train = X_train.copy()\ndata_train[\"target\"] = y_train\ndata_test = X_test.copy()\ndata_test[\"target\"] = y_test\n\nest = RandomForestRegressor()\n\n# CV predict\ny_pred = cross_val_predict(est, X_train[numeric_cols], y_train, n_jobs=-1, verbose=0)\n\nmae = (np.abs(y_train - y_pred)).mean(axis=0)\nmae_text = f\"Regression results: MAE={mae:.2f}\"\n\nfig = plot_regression_predicted_vs_actual(y_train, y_pred)\nfig.suptitle(mae_text)"
      ]
    }
  ],
  "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": "3.10.8"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 0
}