classification_random_forests.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": []
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    },
    "accelerator": "GPU",
    "gpuClass": "standard"
  },
  "cells": [
    {
      "cell_type": "markdown",
      "source": [
        "# Data cleaning"
      ],
      "metadata": {
        "id": "aGbbufTz15c8"
      }
    },
    {
      "cell_type": "code",
      "execution_count": 1,
      "metadata": {
        "id": "JTHi-6vx6utS"
      },
      "outputs": [],
      "source": [
        "import pandas as pd\n",
        "import numpy as np\n",
        "import seaborn as sns\n",
        "import matplotlib.pyplot as plt"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Load csv\n",
        "jfk = pd.read_csv('/content/JFK_flight_data.csv')\n",
        "\n",
        "# Drop null values\n",
        "jfk = jfk.dropna()\n",
        "\n",
        "# One-hot encoding for categorical variables\n",
        "one_hot = pd.get_dummies(jfk['OP_UNIQUE_CARRIER'])\n",
        "jfk = jfk.drop('OP_UNIQUE_CARRIER',axis = 1)\n",
        "jfk = jfk.join(one_hot)\n",
        "\n",
        "one_hot = pd.get_dummies(jfk['DEST'])\n",
        "jfk = jfk.drop('DEST',axis = 1)\n",
        "jfk = jfk.join(one_hot)\n",
        "\n",
        "one_hot = pd.get_dummies(jfk['Wind'])\n",
        "jfk = jfk.drop('Wind',axis = 1)\n",
        "jfk = jfk.join(one_hot)\n",
        "\n",
        "one_hot = pd.get_dummies(jfk['Condition'])\n",
        "jfk = jfk.drop('Condition',axis = 1)\n",
        "jfk = jfk.join(one_hot)\n",
        "\n",
        "jfk.loc[jfk['MONTH']==1, 'MONTH'] = 'Jan'\n",
        "jfk.loc[jfk['MONTH']==11, 'MONTH'] = 'Nov'\n",
        "jfk.loc[jfk['MONTH']==12, 'MONTH'] = 'Dec'\n",
        "one_hot = pd.get_dummies(jfk['MONTH'])\n",
        "jfk = jfk.drop('MONTH', axis = 1)\n",
        "jfk = jfk.join(one_hot)\n",
        "\n",
        "# Drop unneeded columns\n",
        "jfk = jfk.drop(columns = ['TAIL_NUM','DEP_TIME_M'])\n",
        "\n",
        "# Change type of Dew Point column to int\n",
        "jfk['Dew Point'] = jfk['Dew Point'].astype(int)\n",
        "     \n",
        "# Turn target column into a categorical variable based on whether the departure\n",
        "#     delay is 15 minutes or more.\n",
        "\n",
        "jfk['DEP_DELAY_CAT'] = jfk['DEP_DELAY'].apply(lambda x: 1 if x > 15 else 0)\n",
        "\n",
        "# Drop original departure delay column\n",
        "\n",
        "jfk = jfk.drop('DEP_DELAY', axis = 1)"
      ],
      "metadata": {
        "id": "BaL9djxC1u35"
      },
      "execution_count": 2,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "# Train-test-validation split"
      ],
      "metadata": {
        "id": "UhoxITU-19Rr"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# Train test validation split \n",
        "\n",
        "# Train-test split\n",
        "from sklearn.model_selection import train_test_split\n",
        "\n",
        "X,y = jfk.loc[:, jfk.columns != 'DEP_DELAY_CAT'], jfk.loc[:, 'DEP_DELAY_CAT']\n",
        "\n",
        "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=604)\n",
        "\n",
        "# Train-validation split\n",
        "\n",
        "X_train_train, X_val, y_train_train, y_val = train_test_split(X_train, y_train, test_size = 0.2, random_state = 604)"
      ],
      "metadata": {
        "id": "6B_rKb258k7l"
      },
      "execution_count": 3,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "# Random forest classifier"
      ],
      "metadata": {
        "id": "9thpa2NK2Iab"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# Tune hyperparameters for random forest classifier using GridSearchCV\n",
        "\n",
        "from sklearn.ensemble import RandomForestClassifier\n",
        "from sklearn.metrics import precision_score, recall_score, f1_score, accuracy_score\n",
        "from sklearn.model_selection import GridSearchCV\n",
        "\n",
        "param_grid = { \n",
        "    'n_estimators': [200, 500],\n",
        "    'max_features': ['sqrt', 'log2'],\n",
        "    'max_depth' : [2,5,10,100],\n",
        "    'criterion' :['gini', 'entropy']\n",
        "}\n",
        "\n",
        "grid_cv = GridSearchCV(RandomForestClassifier(),\n",
        "                       param_grid = param_grid, \n",
        "                       cv = 5,\n",
        "                       scoring = 'f1')\n",
        "\n",
        "grid_cv.fit(X_train, y_train)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 118
        },
        "id": "5at9C5383hNQ",
        "outputId": "a400b189-e239-4bef-9ed6-dde49ef73d2c"
      },
      "execution_count": 9,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "GridSearchCV(cv=5, estimator=RandomForestClassifier(),\n",
              "             param_grid={'criterion': ['gini', 'entropy'],\n",
              "                         'max_depth': [2, 5, 10, 100],\n",
              "                         'max_features': ['sqrt', 'log2'],\n",
              "                         'n_estimators': [200, 500]},\n",
              "             scoring='f1')"
            ],
            "text/html": [
              "<style>#sk-container-id-2 {color: black;background-color: white;}#sk-container-id-2 pre{padding: 0;}#sk-container-id-2 div.sk-toggleable {background-color: white;}#sk-container-id-2 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-2 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-2 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-2 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-2 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-2 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-2 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-2 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-2 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-2 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-2 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-2 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-2 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-2 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-2 div.sk-item {position: relative;z-index: 1;}#sk-container-id-2 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-2 div.sk-item::before, #sk-container-id-2 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-2 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-2 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-2 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-2 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-2 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-2 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-2 div.sk-label-container {text-align: center;}#sk-container-id-2 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-2 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-2\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>GridSearchCV(cv=5, estimator=RandomForestClassifier(),\n",
              "             param_grid={&#x27;criterion&#x27;: [&#x27;gini&#x27;, &#x27;entropy&#x27;],\n",
              "                         &#x27;max_depth&#x27;: [2, 5, 10, 100],\n",
              "                         &#x27;max_features&#x27;: [&#x27;sqrt&#x27;, &#x27;log2&#x27;],\n",
              "                         &#x27;n_estimators&#x27;: [200, 500]},\n",
              "             scoring=&#x27;f1&#x27;)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-4\" type=\"checkbox\" ><label for=\"sk-estimator-id-4\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">GridSearchCV</label><div class=\"sk-toggleable__content\"><pre>GridSearchCV(cv=5, estimator=RandomForestClassifier(),\n",
              "             param_grid={&#x27;criterion&#x27;: [&#x27;gini&#x27;, &#x27;entropy&#x27;],\n",
              "                         &#x27;max_depth&#x27;: [2, 5, 10, 100],\n",
              "                         &#x27;max_features&#x27;: [&#x27;sqrt&#x27;, &#x27;log2&#x27;],\n",
              "                         &#x27;n_estimators&#x27;: [200, 500]},\n",
              "             scoring=&#x27;f1&#x27;)</pre></div></div></div><div class=\"sk-parallel\"><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-5\" type=\"checkbox\" ><label for=\"sk-estimator-id-5\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">estimator: RandomForestClassifier</label><div class=\"sk-toggleable__content\"><pre>RandomForestClassifier()</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-6\" type=\"checkbox\" ><label for=\"sk-estimator-id-6\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">RandomForestClassifier</label><div class=\"sk-toggleable__content\"><pre>RandomForestClassifier()</pre></div></div></div></div></div></div></div></div></div></div>"
            ]
          },
          "metadata": {},
          "execution_count": 9
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Hyperparameters for the best model\n",
        "\n",
        "grid_cv.best_params_"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "26lbDLCENeq8",
        "outputId": "42a335e5-c8b2-4da2-c683-691779e34d07"
      },
      "execution_count": 10,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "{'criterion': 'gini',\n",
              " 'max_depth': 100,\n",
              " 'max_features': 'sqrt',\n",
              " 'n_estimators': 500}"
            ]
          },
          "metadata": {},
          "execution_count": 10
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Get validation set scores for the best hyperparameters\n",
        "# Check accuracy score, precision, recall, f1 score\n",
        "\n",
        "rfc = RandomForestClassifier(criterion='gini', \n",
        "                             max_depth=100, \n",
        "                             max_features = 'sqrt', \n",
        "                             n_estimators = 500)\n",
        "model = rfc.fit(X_train_train, y_train_train)\n",
        "pred = model.predict(X_val)\n",
        "\n",
        "print('the accuracy is', accuracy_score(y_val, pred))\n",
        "print('the precision is', precision_score(y_val, pred))\n",
        "print('the recall is', recall_score(y_val, pred))\n",
        "print('the f1 score is', f1_score(y_val, pred))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "BFFJglKMNcQF",
        "outputId": "49a83470-2ad3-4720-90a9-d8ff7033be85"
      },
      "execution_count": 29,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "the accuracy is 0.885491216655823\n",
            "the precision is 0.8725490196078431\n",
            "the recall is 0.14735099337748345\n",
            "the f1 score is 0.25212464589235123\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Normalized confusion matrix for the model above\n",
        "\n",
        "from sklearn.metrics import ConfusionMatrixDisplay\n",
        "\n",
        "print('Normalized Confusion Matrix for Random Forest Classifier')\n",
        "print('\\n')\n",
        "\n",
        "ConfusionMatrixDisplay.from_predictions(y_val, pred, \n",
        "                                        display_labels=['on-time','late'], \n",
        "                                        cmap=plt.cm.Blues,\n",
        "                                        normalize = 'true')"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 348
        },
        "id": "Lko9limBNdAD",
        "outputId": "cdf1a820-1c5b-4368-9d71-1cf4153292ba"
      },
      "execution_count": 30,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Normalized Confusion Matrix for Random Forest Classifier\n",
            "\n",
            "\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<sklearn.metrics._plot.confusion_matrix.ConfusionMatrixDisplay at 0x7f86b00dabb0>"
            ]
          },
          "metadata": {},
          "execution_count": 30
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 432x288 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Fine-tune the hyperparameters\n",
        "\n",
        "param_grid = { \n",
        "    'n_estimators': [200, 500],\n",
        "    'max_features': ['sqrt', 'log2'],\n",
        "    'max_depth' : [100,150,200],\n",
        "    'criterion' :['gini', 'entropy']\n",
        "}\n",
        "\n",
        "grid_cv = GridSearchCV(RandomForestClassifier(),\n",
        "                       param_grid = param_grid, \n",
        "                       cv = 5,\n",
        "                       scoring = 'f1')\n",
        "\n",
        "grid_cv.fit(X_train, y_train)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 118
        },
        "id": "F1M8ag4oRbbN",
        "outputId": "cab8f259-eeba-4669-d8b6-75e716108a92"
      },
      "execution_count": 13,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "GridSearchCV(cv=5, estimator=RandomForestClassifier(),\n",
              "             param_grid={'criterion': ['gini', 'entropy'],\n",
              "                         'max_depth': [100, 150, 200],\n",
              "                         'max_features': ['sqrt', 'log2'],\n",
              "                         'n_estimators': [200, 500]},\n",
              "             scoring='f1')"
            ],
            "text/html": [
              "<style>#sk-container-id-3 {color: black;background-color: white;}#sk-container-id-3 pre{padding: 0;}#sk-container-id-3 div.sk-toggleable {background-color: white;}#sk-container-id-3 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-3 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-3 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-3 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-3 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-3 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-3 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-3 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-3 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-3 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-3 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-3 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-3 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-3 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-3 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-3 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-3 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-3 div.sk-item {position: relative;z-index: 1;}#sk-container-id-3 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-3 div.sk-item::before, #sk-container-id-3 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-3 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-3 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-3 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-3 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-3 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-3 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-3 div.sk-label-container {text-align: center;}#sk-container-id-3 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-3 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-3\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>GridSearchCV(cv=5, estimator=RandomForestClassifier(),\n",
              "             param_grid={&#x27;criterion&#x27;: [&#x27;gini&#x27;, &#x27;entropy&#x27;],\n",
              "                         &#x27;max_depth&#x27;: [100, 150, 200],\n",
              "                         &#x27;max_features&#x27;: [&#x27;sqrt&#x27;, &#x27;log2&#x27;],\n",
              "                         &#x27;n_estimators&#x27;: [200, 500]},\n",
              "             scoring=&#x27;f1&#x27;)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-7\" type=\"checkbox\" ><label for=\"sk-estimator-id-7\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">GridSearchCV</label><div class=\"sk-toggleable__content\"><pre>GridSearchCV(cv=5, estimator=RandomForestClassifier(),\n",
              "             param_grid={&#x27;criterion&#x27;: [&#x27;gini&#x27;, &#x27;entropy&#x27;],\n",
              "                         &#x27;max_depth&#x27;: [100, 150, 200],\n",
              "                         &#x27;max_features&#x27;: [&#x27;sqrt&#x27;, &#x27;log2&#x27;],\n",
              "                         &#x27;n_estimators&#x27;: [200, 500]},\n",
              "             scoring=&#x27;f1&#x27;)</pre></div></div></div><div class=\"sk-parallel\"><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-8\" type=\"checkbox\" ><label for=\"sk-estimator-id-8\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">estimator: RandomForestClassifier</label><div class=\"sk-toggleable__content\"><pre>RandomForestClassifier()</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-9\" type=\"checkbox\" ><label for=\"sk-estimator-id-9\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">RandomForestClassifier</label><div class=\"sk-toggleable__content\"><pre>RandomForestClassifier()</pre></div></div></div></div></div></div></div></div></div></div>"
            ]
          },
          "metadata": {},
          "execution_count": 13
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Hyperparameters for the best model\n",
        "\n",
        "grid_cv.best_params_"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "_amxqIsURcN8",
        "outputId": "a0a81a87-b959-4a5e-db66-7769cff52361"
      },
      "execution_count": 14,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "{'criterion': 'entropy',\n",
              " 'max_depth': 100,\n",
              " 'max_features': 'sqrt',\n",
              " 'n_estimators': 200}"
            ]
          },
          "metadata": {},
          "execution_count": 14
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Get validation set scores for the best hyperparameters\n",
        "\n",
        "rfc = RandomForestClassifier(criterion='entropy', \n",
        "                             max_depth=100, \n",
        "                             max_features = 'sqrt', \n",
        "                             n_estimators = 200)\n",
        "model = rfc.fit(X_train_train, y_train_train)\n",
        "pred = model.predict(X_val)\n",
        "\n",
        "print('the accuracy is', accuracy_score(y_val, pred))\n",
        "print('the precision is', precision_score(y_val, pred))\n",
        "print('the recall is', recall_score(y_val, pred))\n",
        "print('the f1 score is', f1_score(y_val, pred))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "ChxW2Z-KRm6U",
        "outputId": "90923013-381e-4a0d-e8eb-4c8c05456117"
      },
      "execution_count": 27,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "the accuracy is 0.8848405985686402\n",
            "the precision is 0.8543689320388349\n",
            "the recall is 0.1456953642384106\n",
            "the f1 score is 0.24893917963224896\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Normalized confusion matrix for the model above\n",
        "\n",
        "from sklearn.metrics import ConfusionMatrixDisplay\n",
        "\n",
        "print('Normalized Confusion Matrix for Random Forest Classifier')\n",
        "print('\\n')\n",
        "\n",
        "ConfusionMatrixDisplay.from_predictions(y_val, pred, \n",
        "                                        display_labels=['on-time','late'], \n",
        "                                        cmap=plt.cm.Blues,\n",
        "                                        normalize = 'true')"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 348
        },
        "id": "Q6j2kRx8asPz",
        "outputId": "5f50d046-56c8-47b4-c8a4-563d620d913c"
      },
      "execution_count": 28,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Normalized Confusion Matrix for Random Forest Classifier\n",
            "\n",
            "\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<sklearn.metrics._plot.confusion_matrix.ConfusionMatrixDisplay at 0x7f86b0183b20>"
            ]
          },
          "metadata": {},
          "execution_count": 28
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 432x288 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Fine-tune hyperparameters\n",
        "\n",
        "param_grid = { \n",
        "    'n_estimators': [150, 200, 250],\n",
        "    'max_features': ['sqrt'],\n",
        "    'max_depth' : [80,90,100,110,120],\n",
        "    'criterion' :['entropy']\n",
        "}\n",
        "\n",
        "grid_cv = GridSearchCV(RandomForestClassifier(),\n",
        "                       param_grid = param_grid, \n",
        "                       cv = 5,\n",
        "                       scoring = 'f1')\n",
        "\n",
        "grid_cv.fit(X_train, y_train)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 118
        },
        "id": "KWgJLQ44YVMG",
        "outputId": "348a44ee-4637-4ff2-b36e-8f21dc003633"
      },
      "execution_count": 16,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "GridSearchCV(cv=5, estimator=RandomForestClassifier(),\n",
              "             param_grid={'criterion': ['entropy'],\n",
              "                         'max_depth': [80, 90, 100, 110, 120],\n",
              "                         'max_features': ['sqrt'],\n",
              "                         'n_estimators': [150, 200, 250]},\n",
              "             scoring='f1')"
            ],
            "text/html": [
              "<style>#sk-container-id-4 {color: black;background-color: white;}#sk-container-id-4 pre{padding: 0;}#sk-container-id-4 div.sk-toggleable {background-color: white;}#sk-container-id-4 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-4 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-4 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-4 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-4 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-4 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-4 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-4 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-4 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-4 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-4 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-4 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-4 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-4 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-4 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-4 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-4 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-4 div.sk-item {position: relative;z-index: 1;}#sk-container-id-4 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-4 div.sk-item::before, #sk-container-id-4 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-4 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-4 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-4 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-4 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-4 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-4 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-4 div.sk-label-container {text-align: center;}#sk-container-id-4 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-4 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-4\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>GridSearchCV(cv=5, estimator=RandomForestClassifier(),\n",
              "             param_grid={&#x27;criterion&#x27;: [&#x27;entropy&#x27;],\n",
              "                         &#x27;max_depth&#x27;: [80, 90, 100, 110, 120],\n",
              "                         &#x27;max_features&#x27;: [&#x27;sqrt&#x27;],\n",
              "                         &#x27;n_estimators&#x27;: [150, 200, 250]},\n",
              "             scoring=&#x27;f1&#x27;)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-10\" type=\"checkbox\" ><label for=\"sk-estimator-id-10\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">GridSearchCV</label><div class=\"sk-toggleable__content\"><pre>GridSearchCV(cv=5, estimator=RandomForestClassifier(),\n",
              "             param_grid={&#x27;criterion&#x27;: [&#x27;entropy&#x27;],\n",
              "                         &#x27;max_depth&#x27;: [80, 90, 100, 110, 120],\n",
              "                         &#x27;max_features&#x27;: [&#x27;sqrt&#x27;],\n",
              "                         &#x27;n_estimators&#x27;: [150, 200, 250]},\n",
              "             scoring=&#x27;f1&#x27;)</pre></div></div></div><div class=\"sk-parallel\"><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-11\" type=\"checkbox\" ><label for=\"sk-estimator-id-11\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">estimator: RandomForestClassifier</label><div class=\"sk-toggleable__content\"><pre>RandomForestClassifier()</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-12\" type=\"checkbox\" ><label for=\"sk-estimator-id-12\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">RandomForestClassifier</label><div class=\"sk-toggleable__content\"><pre>RandomForestClassifier()</pre></div></div></div></div></div></div></div></div></div></div>"
            ]
          },
          "metadata": {},
          "execution_count": 16
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Hyperparameters for the best model\n",
        "\n",
        "grid_cv.best_params_"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "mjzR5K5FYj_2",
        "outputId": "e0a95092-67e9-442b-f767-d5d15370151f"
      },
      "execution_count": 17,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "{'criterion': 'entropy',\n",
              " 'max_depth': 100,\n",
              " 'max_features': 'sqrt',\n",
              " 'n_estimators': 250}"
            ]
          },
          "metadata": {},
          "execution_count": 17
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Get validation set scores for the best hyperparameters\n",
        "\n",
        "rfc = RandomForestClassifier(criterion='entropy', \n",
        "                             max_depth=100, \n",
        "                             max_features = 'sqrt', \n",
        "                             n_estimators = 250)\n",
        "model = rfc.fit(X_train_train, y_train_train)\n",
        "pred = model.predict(X_val)\n",
        "\n",
        "print('the accuracy is', accuracy_score(y_val, pred))\n",
        "print('the precision is', precision_score(y_val, pred))\n",
        "print('the recall is', recall_score(y_val, pred))\n",
        "print('the f1 score is', f1_score(y_val, pred))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "L-KuC58SaYYu",
        "outputId": "a6cdeb0b-f245-475a-99e4-55fb4fd52668"
      },
      "execution_count": 25,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "the accuracy is 0.884406853177185\n",
            "the precision is 0.8380952380952381\n",
            "the recall is 0.1456953642384106\n",
            "the f1 score is 0.24823695345557123\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Normalized confusion matrix for the model above\n",
        "\n",
        "from sklearn.metrics import ConfusionMatrixDisplay\n",
        "\n",
        "print('Normalized Confusion Matrix for Random Forest Classifier')\n",
        "print('\\n')\n",
        "\n",
        "ConfusionMatrixDisplay.from_predictions(y_val, pred, \n",
        "                                        display_labels=['on-time','late'], \n",
        "                                        cmap=plt.cm.Blues,\n",
        "                                        normalize = 'true')"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 348
        },
        "id": "-laJShdjMtbN",
        "outputId": "e35dd140-c9ac-4bfc-8757-e330cab879e3"
      },
      "execution_count": 26,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Normalized Confusion Matrix for Random Forest Classifier\n",
            "\n",
            "\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<sklearn.metrics._plot.confusion_matrix.ConfusionMatrixDisplay at 0x7f86b02b8700>"
            ]
          },
          "metadata": {},
          "execution_count": 26
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 432x288 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Get test error for the best model hyperparameters\n",
        "\n",
        "rfc = RandomForestClassifier(criterion='entropy', \n",
        "                             max_depth=100, \n",
        "                             max_features = 'sqrt', \n",
        "                             n_estimators = 200)\n",
        "model = rfc.fit(X_train, y_train)\n",
        "pred = model.predict(X_test)\n",
        "\n",
        "print('the accuracy is', accuracy_score(y_test, pred))\n",
        "print('the precision is', precision_score(y_test, pred))\n",
        "print('the recall is', recall_score(y_test, pred))\n",
        "print('the f1 score is', f1_score(y_test, pred))"
      ],
      "metadata": {
        "id": "ytLY_Y_xDQqS",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "b56efada-b7f5-4e13-c455-41c174fd8849"
      },
      "execution_count": 22,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "the accuracy is 0.871616932685635\n",
            "the precision is 0.8413793103448276\n",
            "the recall is 0.14541120381406436\n",
            "the f1 score is 0.24796747967479676\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Normalized confusion matrix for the test set \n",
        "\n",
        "from sklearn.metrics import ConfusionMatrixDisplay\n",
        "\n",
        "print('Normalized Confusion Matrix for Random Forest Classifier on the Test Set')\n",
        "print('\\n')\n",
        "\n",
        "ConfusionMatrixDisplay.from_predictions(y_test, pred, \n",
        "                                        display_labels=['on-time','late'], \n",
        "                                        cmap=plt.cm.Blues,\n",
        "                                        normalize = 'true')"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 348
        },
        "id": "huRHx-MIbGJ3",
        "outputId": "fe88b562-3653-4706-bc3a-b519b713de1e"
      },
      "execution_count": 24,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Normalized Confusion Matrix for Random Forest Classifier on the Test Set\n",
            "\n",
            "\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<sklearn.metrics._plot.confusion_matrix.ConfusionMatrixDisplay at 0x7f86b048af70>"
            ]
          },
          "metadata": {},
          "execution_count": 24
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 432x288 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {
            "needs_background": "light"
          }
        }
      ]
    }
  ]
}