regression_trees_random_forest.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\n"
      ],
      "metadata": {
        "id": "4KBKXks45lDY"
      }
    },
    {
      "cell_type": "code",
      "execution_count": 1,
      "metadata": {
        "id": "ecnXiiDiBm7K"
      },
      "outputs": [],
      "source": [
        "import pandas as pd\n",
        "import numpy as np"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import tensorflow as tf \n",
        "tf.test.gpu_device_name()\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 35
        },
        "id": "9JyvlD_ijQ5v",
        "outputId": "bf09dae3-1684-4043-d805-860e02cf261b"
      },
      "execution_count": 2,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "'/device:GPU:0'"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            }
          },
          "metadata": {},
          "execution_count": 2
        }
      ]
    },
    {
      "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"
      ],
      "metadata": {
        "id": "z0oAGt2DOc-M"
      },
      "execution_count": 3,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "# Train-test-validation split"
      ],
      "metadata": {
        "id": "O667Fg5n5o9e"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# Train-test split\n",
        "\n",
        "from sklearn.model_selection import train_test_split\n",
        "\n",
        "X,y = jfk.loc[:, jfk.columns != 'DEP_DELAY'], jfk.loc[:, 'DEP_DELAY']\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": "g0Ygrf_eC1rI"
      },
      "execution_count": 4,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Test baseline model of average\n",
        "\n",
        "from sklearn.metrics import mean_squared_error as mse\n",
        "\n",
        "print('rmse for validation set is', np.sqrt(mse(y_val, y_train.mean()*np.ones(len(y_val)))))\n",
        "print('rmse for test set is', np.sqrt(mse(y_test, y_train.mean()*np.ones(len(y_test)))))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "UUcVEBTF1Vkc",
        "outputId": "6a2faf66-23c5-4b62-84f3-7280445ad7e5"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "rmse for validation set is 37.02477781979254\n",
            "rmse for test set is 36.235234518989124\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# Decision tree regressors"
      ],
      "metadata": {
        "id": "wlRRNtGK65Hw"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# Decision tree regressor with default hyperparameters\n",
        "\n",
        "from sklearn.tree import DecisionTreeRegressor\n",
        "from sklearn.metrics import mean_squared_error as mse  \n",
        "\n",
        "\n",
        "reg = DecisionTreeRegressor()\n",
        "model = reg.fit(X_train_train,y_train_train)\n",
        "pred = model.predict(X_val)\n",
        "\n",
        "print('rmse is ', np.sqrt(mse(y_val, pred)))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "EaUUUOrXVBlg",
        "outputId": "b084ac8d-c04d-4b27-e8b1-e71f1e5bebe2"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "rmse is  36.75231415797062\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Hyperparameter tuning with GridSearchCV\n",
        "\n",
        "from sklearn.model_selection import GridSearchCV\n",
        "\n",
        "param_grid = { \n",
        "    'splitter': ['best','random'],\n",
        "    'min_samples_leaf': [1,3,10],\n",
        "    'min_weight_fraction_leaf': [0.0,0.2,0.5],\n",
        "    'max_features': ['log2','sqrt',None],\n",
        "    'max_depth': [None,5,10,50,100],\n",
        "    'min_samples_split': [2,5,10,20]\n",
        "}\n",
        "\n",
        "grid_cv = GridSearchCV(DecisionTreeRegressor(),\n",
        "                          param_grid = param_grid, \n",
        "                          cv = 5,\n",
        "                          verbose=0.5)\n",
        "\n",
        "grid_cv.fit(X_train, y_train)\n",
        "\n",
        "print(grid_cv.best_params_)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "x70JqqNDAICJ",
        "outputId": "efc7c9e7-c63b-455f-b33b-5161c7f36b97"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Fitting 5 folds for each of 1080 candidates, totalling 5400 fits\n",
            "{'max_depth': 5, 'max_features': None, 'min_samples_leaf': 3, 'min_samples_split': 20, 'min_weight_fraction_leaf': 0.0, 'splitter': 'best'}\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Getting rmse on validation set with best hyperparameters\n",
        "\n",
        "reg = DecisionTreeRegressor(\n",
        "    max_depth=5,\n",
        "    max_features=None,\n",
        "    min_samples_leaf=3,\n",
        "    min_samples_split=20,\n",
        "    min_weight_fraction_leaf = 0,\n",
        "    splitter='best'\n",
        ")\n",
        "model = reg.fit(X_train_train,y_train_train)\n",
        "pred = model.predict(X_val)\n",
        "\n",
        "print('rmse is ', np.sqrt(mse(y_val, pred)))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "RRk7-YmJDugH",
        "outputId": "82bf595d-0f7e-4517-cb76-9b4ef7942a8d"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "rmse is  34.20431802031378\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Fine-tuning hyperparameters\n",
        "\n",
        "from sklearn.model_selection import GridSearchCV\n",
        "\n",
        "param_grid = { \n",
        "    'splitter': ['best'],\n",
        "    'min_samples_leaf': [2,3,4,5,6],\n",
        "    'min_weight_fraction_leaf': [0],\n",
        "    'max_features': [None],\n",
        "    'max_depth': [3,4,5,6,7],\n",
        "    'min_samples_split': [15,20,25,30]\n",
        "}\n",
        "\n",
        "grid_cv = GridSearchCV(DecisionTreeRegressor(),\n",
        "                          param_grid = param_grid, \n",
        "                          cv = 5,\n",
        "                          verbose=0.5)\n",
        "\n",
        "grid_cv.fit(X_train, y_train)\n",
        "\n",
        "print(grid_cv.best_params_)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "LcvYMVaCExgy",
        "outputId": "f21a8fc6-42b5-40d8-80bf-a596c301026a"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Fitting 5 folds for each of 100 candidates, totalling 500 fits\n",
            "{'max_depth': 7, 'max_features': None, 'min_samples_leaf': 5, 'min_samples_split': 30, 'min_weight_fraction_leaf': 0, 'splitter': 'best'}\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Getting rmse on validation set with best hyperparameters\n",
        "\n",
        "reg = DecisionTreeRegressor(\n",
        "    max_depth=7,\n",
        "    max_features=None,\n",
        "    min_samples_leaf=5,\n",
        "    min_samples_split=30,\n",
        "    min_weight_fraction_leaf = 0,\n",
        "    splitter='best'\n",
        ")\n",
        "model = reg.fit(X_train_train,y_train_train)\n",
        "pred = model.predict(X_val)\n",
        "\n",
        "print('rmse is ', np.sqrt(mse(y_val, pred)))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "lEy-kdiuFMMt",
        "outputId": "f4b9cf13-0cda-4cf0-a1a1-efc1636ee667"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "rmse is  32.47632457664007\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "##pruning the decision tree to reduce variance and overfitting\n",
        "\n",
        "import matplotlib.pyplot as plt\n",
        "\n",
        "clf = DecisionTreeRegressor()\n",
        "path = clf.cost_complexity_pruning_path(X_train_train, y_train_train)\n",
        "ccp_alphas, impurities = path.ccp_alphas, path.impurities\n",
        "\n",
        "fig, ax = plt.subplots()\n",
        "ax.plot(ccp_alphas[:-1], impurities[:-1], marker=\"o\", drawstyle=\"steps-post\")\n",
        "ax.set_xlabel(\"effective alpha\")\n",
        "ax.set_ylabel(\"total impurity of leaves\")\n",
        "ax.set_title(\"Total Impurity vs effective alpha for training set\")\n",
        "\n",
        "\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 312
        },
        "id": "81lzS0WtQUQB",
        "outputId": "165ec68a-ba7f-40a1-ced7-d257b23dd34e"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "Text(0.5, 1.0, 'Total Impurity vs effective alpha for training set')"
            ]
          },
          "metadata": {},
          "execution_count": 19
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 432x288 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "print(len(ccp_alphas))\n",
        "\n",
        "##to reduce the runtime, I'll take every 100th value of ccp_alphas\n",
        "# and include the last 100 values\n",
        "ccp_alphas = np.append(ccp_alphas[:-100:100], ccp_alphas[-100:])"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "4iIe0f-r8zp4",
        "outputId": "489bc3bb-8ef6-45c8-b533-d32b0ba39411"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "12708\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "len(ccp_alphas)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "CN1_dxHi-PDz",
        "outputId": "4e1542db-eb11-4ebe-90da-613c937ac2e8"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "227"
            ]
          },
          "metadata": {},
          "execution_count": 21
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "clfs = []\n",
        "for ccp_alpha in ccp_alphas:\n",
        "    clf = DecisionTreeRegressor(random_state=0, ccp_alpha=ccp_alpha)\n",
        "    clf.fit(X_train_train, y_train_train)\n",
        "    clfs.append(clf)\n",
        "print(\n",
        "    \"Number of nodes in the last tree is: {} with ccp_alpha: {}\".format(\n",
        "        clfs[-1].tree_.node_count, ccp_alphas[-1]\n",
        "    )\n",
        ")\n",
        "\n",
        "clfs = clfs[:-1]\n",
        "ccp_alphas = ccp_alphas[:-1]\n",
        "\n",
        "node_counts = [clf.tree_.node_count for clf in clfs]\n",
        "depth = [clf.tree_.max_depth for clf in clfs]\n",
        "fig, ax = plt.subplots(2, 1)\n",
        "ax[0].plot(ccp_alphas, node_counts, marker=\"o\", drawstyle=\"steps-post\")\n",
        "ax[0].set_xlabel(\"alpha\")\n",
        "ax[0].set_ylabel(\"number of nodes\")\n",
        "ax[0].set_title(\"Number of nodes vs alpha\")\n",
        "ax[1].plot(ccp_alphas, depth, marker=\"o\", drawstyle=\"steps-post\")\n",
        "ax[1].set_xlabel(\"alpha\")\n",
        "ax[1].set_ylabel(\"depth of tree\")\n",
        "ax[1].set_title(\"Depth vs alpha\")\n",
        "fig.tight_layout()\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 314
        },
        "id": "mvwoxe2tYNyV",
        "outputId": "a5edbf21-8057-401a-eca8-053ec8d54b3d"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Number of nodes in the last tree is: 1 with ccp_alpha: 54.53541822630647\n"
          ]
        },
        {
          "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": [
        "train_scores = [clf.score(X_train_train, y_train_train) for clf in clfs]\n",
        "val_scores = [clf.score(X_val, y_val) for clf in clfs]\n",
        "\n",
        "fig, ax = plt.subplots()\n",
        "ax.set_xlabel(\"alpha\")\n",
        "ax.set_ylabel(\"R-squared\")\n",
        "ax.set_title(\"R-squared vs alpha for training and validation sets\")\n",
        "ax.plot(ccp_alphas, train_scores, marker=\"o\", label=\"train\", drawstyle=\"steps-post\")\n",
        "ax.plot(ccp_alphas, val_scores, marker=\"o\", label=\"validation\", drawstyle=\"steps-post\")\n",
        "ax.legend()\n",
        "plt.show()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 295
        },
        "id": "FgKFb0uxYX4V",
        "outputId": "0fe50746-7253-4139-8315-3dd87d306dce"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 432x288 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "print(val_scores)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "nnVk9cqMtlVj",
        "outputId": "be68d7f5-7fd8-48ff-be0c-324f01d82634"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "[0.03091188753519125, 0.031226267500291782, 0.031226267500291782, 0.031226267500291782, 0.031226267500291782, 0.031226267500291782, 0.031226267500291782, 0.031226267500291782, 0.031226267500291782, 0.031226267500291782, 0.031226267500291782, 0.031226267500291782, 0.031226267500291782, 0.031226267500291782, 0.031226267500291782, 0.031226267500291782, 0.031228838552402327, 0.031188624245742647, 0.03114764843233153, 0.031161289458160324, 0.031156033444342257, 0.031138771218357952, 0.031160305054234616, 0.03117503595583826, 0.03123787850064963, 0.03123787850064963, 0.031241620841985562, 0.03125906015235458, 0.03122735089425821, 0.031228071618561115, 0.03136468828287309, 0.03135775680478403, 0.03134964865637724, 0.03157527846338992, 0.03157527846338992, 0.03157527846338992, 0.03157527846338992, 0.03157527846338992, 0.03157527846338992, 0.031555021990197774, 0.031566948526274285, 0.03158263012565565, 0.03157830569287601, 0.03155714100847151, 0.03156088067621465, 0.03158679194617864, 0.031560108381670116, 0.03155778552804478, 0.03155453278966858, 0.03157765419660852, 0.03158826219090838, 0.03133901924457949, 0.03133901924457949, 0.031361071669894436, 0.031395407381362594, 0.03144855716007178, 0.03156518274956244, 0.03159941483573492, 0.03160770559542514, 0.031648906444990965, 0.0316795916519107, 0.031314071524956244, 0.031316533649629275, 0.031197359786463763, 0.03120627102038287, 0.031343550909360585, 0.03146030049883275, 0.03157142597134177, 0.031421712221873954, 0.03153008142640368, 0.03134201069748732, 0.031249063630387375, 0.031414775078398516, 0.03178358022226779, 0.03183645361229048, 0.03178125166108814, 0.031654215408584374, 0.03141916882731499, 0.031624069791276854, 0.03172004713726273, 0.03195300143014912, 0.03197476143064215, 0.032740523195887716, 0.03258651121764988, 0.03249249316795633, 0.032414647194401236, 0.03231201039532361, 0.032658576384252735, 0.03261097979828076, 0.03215333689473199, 0.03305908747418318, 0.033658337061738375, 0.03388702242019892, 0.034142369392450855, 0.0351380834225784, 0.0349813053907132, 0.03537847051384735, 0.035146612861720605, 0.03495039160585489, 0.035063589448461, 0.035796443997019534, 0.03580904038071486, 0.03664523106969464, 0.03641218266476265, 0.037054940777033085, 0.03709821453668771, 0.03703781895190161, 0.0375184935230064, 0.039017071263698355, 0.04025171060099231, 0.040742943191238945, 0.04398551154680308, 0.04423263638741892, 0.04395310660109908, 0.04681720527018507, 0.04808782228374253, 0.04944238727825545, 0.05071983944150005, 0.05036399488979537, 0.04518369594542293, 0.05622584074203474, 0.07305797082098497, 0.08828766864639448, 0.08139294543919484, 0.08901687323860585, 0.11431280719257175, 0.164186363024159, 0.1561307142162478, 0.15618906972711288, 0.15616822020921606, 0.16275592511835257, 0.1622311556053998, 0.16216206549398482, 0.17026514630782352, 0.17045652931563327, 0.17532844219320087, 0.17311354176374782, 0.17207644118754928, 0.17449526226234002, 0.174101289696319, 0.17656229951078617, 0.17669794317014564, 0.17669794317014564, 0.17669793901871056, 0.18660513409973256, 0.18711170176448144, 0.18711170176448144, 0.18807178612783437, 0.18941112217097966, 0.1891931835970473, 0.18920554361355668, 0.19184842531728186, 0.19565298052282942, 0.1953282766086648, 0.19729360132048468, 0.20552068413680114, 0.19959076227946282, 0.19587945646311755, 0.2042374340908023, 0.20531673068773404, 0.20522183998163013, 0.20533686519020666, 0.20525691088558629, 0.20392555163081316, 0.20308090202306817, 0.20308653328611437, 0.2030616686897485, 0.2010691648813976, 0.21620168781765337, 0.21699204845278708, 0.21654043477391216, 0.21420704923378808, 0.2140901290264654, 0.21335505050722914, 0.20841332091616416, 0.20505867976673364, 0.20171456294830714, 0.203937644503151, 0.20371517085145996, 0.20359215566856892, 0.2203736435072603, 0.2170356352667664, 0.22037964526817855, 0.21807693369016856, 0.20433258280879574, 0.20198930733780218, 0.20198930733780218, 0.20384510899007624, 0.20366965545998428, 0.20367226661104842, 0.19760227819153298, 0.19314251191168352, 0.20245577068048692, 0.20245577068048692, 0.20295470340832233, 0.21144725164439093, 0.2094880220717148, 0.21014610745562345, 0.2361162485490904, 0.23449072437702512, 0.2333786683522946, 0.23139267395845065, 0.23141539337338146, 0.2318193748484908, 0.22191544503241234, 0.22190348575558572, 0.22190348575558572, 0.2216542277686281, 0.21554165108100054, 0.2118347661969162, 0.2096971568291457, 0.21167897326641483, 0.17831969098502298, 0.2141098051439888, 0.2143373818100529, 0.2102028853217479, 0.18573337198229156, 0.19965950001663868, 0.1938780497386322, 0.1901373569132485, 0.18864758444370033, 0.18456058384091156, 0.18140419002374586, 0.14819423992607172, 0.09846230258604327, 0.09754656167123144]\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "rmses = [np.sqrt(mse(clf.predict(X_val), y_val)) for clf in clfs]\n",
        "print(rmses)\n",
        "print('the minimum rmse is ',min(rmses))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "uDzpv2HltoUW",
        "outputId": "3f93478f-6283-41b1-e22a-3d5ab7cf0ad8"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "[36.44770289919009, 36.44179045589918, 36.44179045589918, 36.44179045589918, 36.44179045589918, 36.44179045589918, 36.44179045589918, 36.44179045589918, 36.44179045589918, 36.44179045589918, 36.44179045589918, 36.44179045589918, 36.44179045589918, 36.44179045589918, 36.44179045589918, 36.44179045589918, 36.44174209899122, 36.44249845108053, 36.44326910946932, 36.443012555762124, 36.44311140849979, 36.44343606677515, 36.44303107000765, 36.44275401656513, 36.44157207316663, 36.44157207316663, 36.44150168595279, 36.44117367974814, 36.44177007919736, 36.44175652365663, 36.439186916402406, 36.43931729414663, 36.439469803897396, 36.43522559474287, 36.43522559474287, 36.43522559474287, 36.43522559474287, 36.43522559474287, 36.43522559474287, 36.43560664930225, 36.43538229380197, 36.43508729799375, 36.43516864768596, 36.435566787585635, 36.435496439064764, 36.435009007133985, 36.43551096704539, 36.43555466325654, 36.43561585184664, 36.43518090338641, 36.43498134931197, 36.43966973623992, 36.43966973623992, 36.43925494319832, 36.438609099429755, 36.43760934648952, 36.43541551071878, 36.43477154827367, 36.43461558359003, 36.43384050871007, 36.43326324453433, 36.44013898235829, 36.4400926720839, 36.44233415405906, 36.44216655185739, 36.43958449869841, 36.43738844934957, 36.43529806618755, 36.43811430603527, 36.436075813138125, 36.43961346906166, 36.44136169908254, 36.43824479418347, 36.43130689586747, 36.430312142547066, 36.43135070450065, 36.43374063470815, 36.438162147516955, 36.434307740525064, 36.43250216342423, 36.42811933060556, 36.42770990815484, 36.41329888604097, 36.41619772606835, 36.417967236596276, 36.41943230796296, 36.421363855822875, 36.41484133179542, 36.415737189640524, 36.42434977095167, 36.40730208176008, 36.39601884731701, 36.39171202219556, 36.3869024772523, 36.368141797258865, 36.37109636205181, 36.36361110936216, 36.36798104858986, 36.371678920322346, 36.369545705464205, 36.35573202335051, 36.35549454639716, 36.33972654956747, 36.34412181674065, 36.33199818065715, 36.33118181018726, 36.332321183173434, 36.32325218589817, 36.294963631060895, 36.27164084834332, 36.262357115925624, 36.20101656831564, 36.196337377379116, 36.201630095647026, 36.14736350474179, 36.123262790895005, 36.09755205410582, 36.07328819123497, 36.080048724564044, 36.17832387219544, 35.968520164969696, 35.64632942599154, 35.352281246794824, 35.485703323991004, 35.33814071054951, 34.844056682153756, 33.84879834442449, 34.0115261062592, 34.01035009812112, 34.010770272236805, 33.87775091441273, 33.888366233480944, 33.88976357759566, 33.72548437595559, 33.72159466537834, 33.622425299874685, 33.667546528758976, 33.68865322974573, 33.63940567082071, 33.64743192523957, 33.59726327986786, 33.594495952463504, 33.594495952463504, 33.594496037162294, 33.39175479561476, 33.38135528462929, 33.38135528462929, 33.3616364708852, 33.33410886229389, 33.338589740395086, 33.3383356311044, 33.283956130526164, 33.20551785240169, 33.212219483317426, 33.171636039169016, 33.001207181829535, 33.124137238447396, 33.20084276805961, 33.02784834985349, 33.005442835284185, 33.007413316109364, 33.0050247112306, 33.00668505465792, 33.03432000228737, 33.0518403662223, 33.05172358903843, 33.052239210489354, 33.09353199161496, 32.77862193157241, 32.76209123336848, 32.77153792908805, 32.8203035475882, 32.822745166566484, 32.83809149109219, 32.94107499629433, 33.01080119247009, 33.08016236318569, 33.03406909526952, 33.03868474914153, 33.04123666445, 32.69126947460409, 32.761179355624115, 32.69114364153067, 32.739386847576476, 33.025873733612976, 33.074469304834494, 33.074469304834494, 33.0359890049878, 33.03962897608586, 33.03957480790448, 33.16525742963242, 33.2572967887353, 33.064801337439356, 33.064801337439356, 33.054457276370975, 32.87788742146581, 32.91870610333581, 32.90500116881474, 32.359527030827024, 32.39393883729434, 32.417459650503744, 32.45942251301454, 32.458942772246225, 32.45041115776803, 32.658928088853884, 32.65917907421183, 32.65917907421183, 32.664409729563445, 32.792420469731226, 32.86980792043485, 32.914351393224614, 32.8730563704115, 33.561392271928945, 32.82233428724211, 32.81758162695007, 32.90381847582252, 33.40964393693837, 33.122714886594096, 33.242134521759255, 33.319172922920046, 33.34980477153874, 33.433695233163974, 33.4983401246164, 34.17108867520409, 35.15446352888592, 35.17231314845527]\n",
            "the minimum rmse is  32.359527030827024\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "print(node_counts)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "27FRn49Iur_5",
        "outputId": "ea83ea3d-fb82-4738-d70d-fcf290a26c06"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "[30223, 26913, 26913, 26913, 26913, 26913, 26913, 26913, 26913, 26913, 26913, 26913, 26913, 26913, 26913, 26913, 26865, 26599, 26247, 26169, 26005, 25779, 25587, 25415, 24981, 24981, 24801, 24595, 24393, 24183, 23937, 23671, 23581, 22229, 22229, 22229, 22229, 22229, 22229, 22107, 21713, 21661, 21429, 21235, 20959, 20813, 20529, 20367, 20137, 19949, 19737, 19203, 19203, 19123, 18889, 18679, 18401, 18211, 18003, 17785, 17559, 17245, 17143, 16931, 16723, 16493, 16281, 16037, 15831, 15577, 15367, 15155, 14907, 14701, 14457, 14227, 14003, 13703, 13503, 13283, 13045, 12779, 12533, 12321, 12065, 11837, 11579, 11345, 11107, 10865, 10613, 10385, 10141, 9873, 9639, 9379, 9087, 8895, 8591, 8391, 8101, 7905, 7651, 7405, 7145, 6861, 6591, 6337, 6081, 5811, 5507, 5221, 4957, 4709, 4389, 4111, 3821, 3483, 3183, 2873, 2571, 2275, 1947, 1645, 1327, 943, 507, 465, 463, 459, 433, 431, 429, 427, 425, 417, 415, 413, 411, 409, 407, 395, 393, 389, 381, 379, 377, 371, 353, 351, 343, 341, 335, 331, 315, 307, 305, 303, 297, 295, 293, 289, 281, 263, 261, 257, 255, 253, 251, 249, 245, 243, 241, 239, 237, 217, 215, 209, 207, 205, 199, 197, 187, 167, 165, 161, 161, 141, 137, 135, 133, 129, 127, 125, 123, 117, 115, 111, 105, 103, 99, 95, 91, 89, 87, 83, 83, 77, 75, 73, 71, 69, 67, 65, 61, 59, 55, 53, 51, 49, 45, 43, 33, 19, 17, 13]\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "##number of nodes in tree that gives minimum rmse\n",
        "\n",
        "index = np.where(rmses == min(rmses))\n",
        "print('the number of nodes in the best decision tree is ',node_counts[index[0].item()])\n",
        "print('the best ccp_alpha is', ccp_alphas[index].item())"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Rpl0tZlSzYOU",
        "outputId": "c880fd4b-e22d-4ded-fd09-55173127ab17"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "the number of nodes in the best decision tree is  105\n",
            "the best ccp_alpha is 3.742977327945989\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "reg = DecisionTreeRegressor(ccp_alpha= 3.7429773279)\n",
        "model = reg.fit(X_train_train,y_train_train)\n",
        "pred = model.predict(X_val)\n",
        "np.sqrt(mse(pred, y_val))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "2yOtXGteHdo6",
        "outputId": "9313b31c-0dd4-480a-8d3b-74a39f9dc398"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "32.811906942764345"
            ]
          },
          "metadata": {},
          "execution_count": 37
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Hyperparameter tuning with GridSearchCV using ccp_alpha from above\n",
        "\n",
        "from sklearn.model_selection import GridSearchCV\n",
        "\n",
        "ccp_alpha = 3.74297732794\n",
        "\n",
        "param_grid = { \n",
        "    'ccp_alpha': [ccp_alpha],\n",
        "    'splitter': ['best','random'],\n",
        "    'min_samples_leaf': [1,3,10],\n",
        "    'min_weight_fraction_leaf': [0.0,0.2,0.5],\n",
        "    'max_features': ['log2','sqrt',None],\n",
        "    'max_depth': [None,5,50,100],\n",
        "    'max_leaf_nodes': [None,10,50,100]\n",
        "}\n",
        "\n",
        "grid_cv = GridSearchCV(DecisionTreeRegressor(),\n",
        "                          param_grid = param_grid, \n",
        "                          cv = 5,\n",
        "                          verbose=0.5)\n",
        "\n",
        "grid_cv.fit(X_train, y_train)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 135
        },
        "id": "MQxwkaDK0x_o",
        "outputId": "18793062-0b10-47ae-888e-c958bb5d6ed3"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Fitting 5 folds for each of 864 candidates, totalling 4320 fits\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "GridSearchCV(cv=5, estimator=DecisionTreeRegressor(),\n",
              "             param_grid={'ccp_alpha': [3.74297732794],\n",
              "                         'max_depth': [None, 5, 50, 100],\n",
              "                         'max_features': ['log2', 'sqrt', None],\n",
              "                         'max_leaf_nodes': [None, 10, 50, 100],\n",
              "                         'min_samples_leaf': [1, 3, 10],\n",
              "                         'min_weight_fraction_leaf': [0.0, 0.2, 0.5],\n",
              "                         'splitter': ['best', 'random']},\n",
              "             verbose=0.5)"
            ],
            "text/html": [
              "<style>#sk-container-id-1 {color: black;background-color: white;}#sk-container-id-1 pre{padding: 0;}#sk-container-id-1 div.sk-toggleable {background-color: white;}#sk-container-id-1 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-1 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-1 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-1 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-1 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 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-1 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-1 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-1 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 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-1 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-1 div.sk-item {position: relative;z-index: 1;}#sk-container-id-1 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-1 div.sk-item::before, #sk-container-id-1 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-1 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-1 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-1 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-1 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-1 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-1 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-1 div.sk-label-container {text-align: center;}#sk-container-id-1 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-1 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>GridSearchCV(cv=5, estimator=DecisionTreeRegressor(),\n",
              "             param_grid={&#x27;ccp_alpha&#x27;: [3.74297732794],\n",
              "                         &#x27;max_depth&#x27;: [None, 5, 50, 100],\n",
              "                         &#x27;max_features&#x27;: [&#x27;log2&#x27;, &#x27;sqrt&#x27;, None],\n",
              "                         &#x27;max_leaf_nodes&#x27;: [None, 10, 50, 100],\n",
              "                         &#x27;min_samples_leaf&#x27;: [1, 3, 10],\n",
              "                         &#x27;min_weight_fraction_leaf&#x27;: [0.0, 0.2, 0.5],\n",
              "                         &#x27;splitter&#x27;: [&#x27;best&#x27;, &#x27;random&#x27;]},\n",
              "             verbose=0.5)</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-1\" type=\"checkbox\" ><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">GridSearchCV</label><div class=\"sk-toggleable__content\"><pre>GridSearchCV(cv=5, estimator=DecisionTreeRegressor(),\n",
              "             param_grid={&#x27;ccp_alpha&#x27;: [3.74297732794],\n",
              "                         &#x27;max_depth&#x27;: [None, 5, 50, 100],\n",
              "                         &#x27;max_features&#x27;: [&#x27;log2&#x27;, &#x27;sqrt&#x27;, None],\n",
              "                         &#x27;max_leaf_nodes&#x27;: [None, 10, 50, 100],\n",
              "                         &#x27;min_samples_leaf&#x27;: [1, 3, 10],\n",
              "                         &#x27;min_weight_fraction_leaf&#x27;: [0.0, 0.2, 0.5],\n",
              "                         &#x27;splitter&#x27;: [&#x27;best&#x27;, &#x27;random&#x27;]},\n",
              "             verbose=0.5)</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-2\" type=\"checkbox\" ><label for=\"sk-estimator-id-2\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">estimator: DecisionTreeRegressor</label><div class=\"sk-toggleable__content\"><pre>DecisionTreeRegressor()</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-3\" type=\"checkbox\" ><label for=\"sk-estimator-id-3\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">DecisionTreeRegressor</label><div class=\"sk-toggleable__content\"><pre>DecisionTreeRegressor()</pre></div></div></div></div></div></div></div></div></div></div>"
            ]
          },
          "metadata": {},
          "execution_count": 38
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "grid_cv.best_params_"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "A8jbwPaTHAtY",
        "outputId": "dbb1ef81-47cf-44fa-8401-d59c27e640e1"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "{'ccp_alpha': 3.74297732794,\n",
              " 'max_depth': 5,\n",
              " 'max_features': None,\n",
              " 'max_leaf_nodes': None,\n",
              " 'min_samples_leaf': 1,\n",
              " 'min_weight_fraction_leaf': 0.0,\n",
              " 'splitter': 'best'}"
            ]
          },
          "metadata": {},
          "execution_count": 39
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "reg = DecisionTreeRegressor(ccp_alpha=3.74297732794, \n",
        "                            max_depth = 5,\n",
        "                            max_features = None,\n",
        "                            max_leaf_nodes = None,\n",
        "                            min_samples_leaf = 1,\n",
        "                            min_weight_fraction_leaf = 0.0,\n",
        "                            splitter = 'best')\n",
        "model = reg.fit(X_train_train, y_train_train) \n",
        "pred = model.predict(X_val)"
      ],
      "metadata": {
        "id": "PMjl9zjsHERz"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "print('rmse is', np.sqrt(mse(y_val, pred)))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "BVuLvNHXHcIQ",
        "outputId": "362fd7e3-8abf-4763-fe81-7be8454078af"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "rmse is 33.27784044805932\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Getting test set rmse from best model above.\n",
        "\n",
        "reg = DecisionTreeRegressor(\n",
        "    max_depth=7,\n",
        "    max_features=None,\n",
        "    min_samples_leaf=5,\n",
        "    min_samples_split=30,\n",
        "    min_weight_fraction_leaf = 0,\n",
        "    splitter='best'\n",
        ")\n",
        "model = reg.fit(X_train,y_train)\n",
        "pred = model.predict(X_test)\n",
        "\n",
        "print('rmse on the test set is', np.sqrt(mse(y_test, pred)))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "6UKphbT86Wsk",
        "outputId": "747c08f3-3576-4719-ef00-9d0b8378ef31"
      },
      "execution_count": 13,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "rmse on the test set is 32.41119244691474\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# Random forest regressors"
      ],
      "metadata": {
        "id": "Dudxw005Li0r"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# Random forest regressor with default hyperparameters\n",
        "\n",
        "from sklearn.ensemble import RandomForestRegressor\n",
        "from sklearn.metrics import mean_squared_error as mse\n",
        "\n",
        "reg = RandomForestRegressor()\n",
        "model = reg.fit(X_train_train,y_train_train)\n",
        "pred = model.predict(X_val)\n",
        "\n",
        "print('rmse is ', np.sqrt(mse(y_val,pred)))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "mJVPtgKubAaS",
        "outputId": "941d44be-031a-4020-d85e-7d220e37acd7"
      },
      "execution_count": 9,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "rmse is  27.79756638485477\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Hyperparameter tuning with GridSearchCV \n",
        "# With more time, I would tune more hyperparameters\n",
        "\n",
        "from sklearn.model_selection import GridSearchCV\n",
        "\n",
        "param_grid = { \n",
        "    'n_estimators': [200, 500, 1000],\n",
        "    'max_features': [None],\n",
        "    'max_depth' : [2, 5, 10, 100, None]\n",
        "}\n",
        "\n",
        "grid_cv = GridSearchCV(RandomForestRegressor(),\n",
        "                          param_grid = param_grid, \n",
        "                          cv = 5,\n",
        "                          verbose=1)\n",
        "\n",
        "grid_cv.fit(X_train, y_train)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 135
        },
        "id": "DhvUBMLX4sqQ",
        "outputId": "668d241c-2575-4c06-e58c-5d64f6b828a4"
      },
      "execution_count": 8,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Fitting 5 folds for each of 15 candidates, totalling 75 fits\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "GridSearchCV(cv=5, estimator=RandomForestRegressor(),\n",
              "             param_grid={'max_depth': [2, 5, 10, 100, None],\n",
              "                         'max_features': [None],\n",
              "                         'n_estimators': [200, 500, 1000]},\n",
              "             verbose=1)"
            ],
            "text/html": [
              "<style>#sk-container-id-1 {color: black;background-color: white;}#sk-container-id-1 pre{padding: 0;}#sk-container-id-1 div.sk-toggleable {background-color: white;}#sk-container-id-1 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-1 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-1 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-1 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-1 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 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-1 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-1 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-1 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 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-1 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-1 div.sk-item {position: relative;z-index: 1;}#sk-container-id-1 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-1 div.sk-item::before, #sk-container-id-1 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-1 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-1 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-1 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-1 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-1 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-1 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-1 div.sk-label-container {text-align: center;}#sk-container-id-1 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-1 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>GridSearchCV(cv=5, estimator=RandomForestRegressor(),\n",
              "             param_grid={&#x27;max_depth&#x27;: [2, 5, 10, 100, None],\n",
              "                         &#x27;max_features&#x27;: [None],\n",
              "                         &#x27;n_estimators&#x27;: [200, 500, 1000]},\n",
              "             verbose=1)</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-1\" type=\"checkbox\" ><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">GridSearchCV</label><div class=\"sk-toggleable__content\"><pre>GridSearchCV(cv=5, estimator=RandomForestRegressor(),\n",
              "             param_grid={&#x27;max_depth&#x27;: [2, 5, 10, 100, None],\n",
              "                         &#x27;max_features&#x27;: [None],\n",
              "                         &#x27;n_estimators&#x27;: [200, 500, 1000]},\n",
              "             verbose=1)</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-2\" type=\"checkbox\" ><label for=\"sk-estimator-id-2\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">estimator: RandomForestRegressor</label><div class=\"sk-toggleable__content\"><pre>RandomForestRegressor()</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-3\" type=\"checkbox\" ><label for=\"sk-estimator-id-3\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">RandomForestRegressor</label><div class=\"sk-toggleable__content\"><pre>RandomForestRegressor()</pre></div></div></div></div></div></div></div></div></div></div>"
            ]
          },
          "metadata": {},
          "execution_count": 8
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Best hyperparameters from GridSearchCV above\n",
        "\n",
        "grid_cv.best_params_"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "UK5VCpDiI7fR",
        "outputId": "895d26c3-7daf-4e2e-ec46-bb3d55b64182"
      },
      "execution_count": 9,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "{'max_depth': None, 'max_features': None, 'n_estimators': 200}"
            ]
          },
          "metadata": {},
          "execution_count": 9
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Fitting a model with the best hyperparameters\n",
        "\n",
        "reg = RandomForestRegressor(max_depth=None,\n",
        "                            max_features=None,\n",
        "                            n_estimators=200)\n",
        "model = reg.fit(X_train_train, y_train_train)\n",
        "pred = model.predict(X_val)\n",
        "print('rmse is', np.sqrt(mse(y_val, pred)))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "nNaLBTDeI_PL",
        "outputId": "17a191f4-c2b8-4a14-bbb9-50ea6d6c3ae6"
      },
      "execution_count": 10,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "rmse is 27.608551580242747\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Get rmse for test set\n",
        "\n",
        "reg = RandomForestRegressor(max_depth=None,\n",
        "                            max_features=None,\n",
        "                            n_estimators=200)\n",
        "model = reg.fit(X_train, y_train)\n",
        "pred = model.predict(X_test)\n",
        "print('rmse is', np.sqrt(mse(y_test, pred)))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "3tJ0wasBz-DM",
        "outputId": "fa50de88-ebc3-4e72-95a0-1c1a3aedab31"
      },
      "execution_count": 10,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "rmse is 27.92586254078418\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Given more time, I would fine-tune the hyperparameters and\n",
        "#  tune more hyperparameters"
      ],
      "metadata": {
        "id": "d00q0Ih9XJsv"
      },
      "execution_count": 11,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "# Extra trees regressor"
      ],
      "metadata": {
        "id": "bY_4Vm5WZVKx"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# Extra tree regressor with default hyperparameters\n",
        "\n",
        "from sklearn.ensemble import ExtraTreesRegressor\n",
        "from sklearn.metrics import mean_squared_error as mse \n",
        "\n",
        "reg = ExtraTreesRegressor()\n",
        "model = reg.fit(X_train_train, y_train_train)\n",
        "pred = model.predict(X_val)\n",
        "\n",
        "print('rmse is', np.sqrt(mse(pred, y_val)))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Y_M-5DI56Oa6",
        "outputId": "14bf59be-7ff0-476c-ff08-782c013c6e65"
      },
      "execution_count": 6,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "rmse is 28.194632818655215\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Increase the number of estimators\n",
        "# With more time, I would tune hyperparameters\n",
        "\n",
        "reg = ExtraTreesRegressor(n_estimators = 1000)\n",
        "model = reg.fit(X_train_train, y_train_train) \n",
        "pred = model.predict(X_val)\n",
        "\n",
        "print('rmse is', np.sqrt(mse(pred, y_val)))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Nflpvv8Z66j8",
        "outputId": "12409d91-890b-444d-e962-a63853d7997a"
      },
      "execution_count": 7,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "rmse is 28.36173942460358\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Get test set error on better of the two\n",
        "\n",
        "reg = ExtraTreesRegressor()\n",
        "model = reg.fit(X_train, y_train)\n",
        "pred = model.predict(X_test)\n",
        "\n",
        "print('rmse is', np.sqrt(mse(pred, y_test)))"
      ],
      "metadata": {
        "id": "6TOYDx877RSr",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "da872e1d-d0d8-4eeb-a77b-39112fb9d647"
      },
      "execution_count": 8,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "rmse is 29.637591863329945\n"
          ]
        }
      ]
    }
  ]
}