{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "6GidYkS3bVYK"
   },
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.ensemble import RandomForestClassifier\n",
    "from sklearn.metrics import accuracy_score"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "9eyKK38Rbanb"
   },
   "outputs": [],
   "source": [
    "file_url = '../Dataset/openml_phpZNNasq.csv'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "_id92wzgbc4Y"
   },
   "outputs": [],
   "source": [
    "df = pd.read_csv(file_url)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "VeD8BgUcb3cD"
   },
   "outputs": [],
   "source": [
    "df.drop(columns='animal', inplace=True)\n",
    "y = df.pop('type')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "wiSxDUrVd5ZE"
   },
   "outputs": [],
   "source": [
    "X_train, X_test, y_train, y_test = train_test_split(df, y, test_size=0.4, random_state=188)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 136
    },
    "colab_type": "code",
    "id": "9uqyaQ_Sd5ZB",
    "outputId": "37f61ce7-2919-46e2-b02f-06104b194cad"
   },
   "outputs": [],
   "source": [
    "rf_model = RandomForestClassifier(random_state=42, n_estimators=30, max_depth=5)\n",
    "rf_model.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "4LQz_9AId5ZA"
   },
   "outputs": [],
   "source": [
    "train_preds = rf_model.predict(X_train)\n",
    "test_preds = rf_model.predict(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "aMN0ckfjd5Y8"
   },
   "outputs": [],
   "source": [
    "train_acc = accuracy_score(y_train, train_preds)\n",
    "test_acc = accuracy_score(y_test, test_preds)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 51
    },
    "colab_type": "code",
    "id": "fd8CL_NMd5Y0",
    "outputId": "4aa6f1bf-e512-4414-b65f-5b37550af617"
   },
   "outputs": [],
   "source": [
    "print(train_acc)\n",
    "print(test_acc)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 136
    },
    "colab_type": "code",
    "id": "83LhoI9_d5Yw",
    "outputId": "1fdd9b2d-e41b-4719-c9fa-698996f32ccb"
   },
   "outputs": [],
   "source": [
    "rf_model2 = RandomForestClassifier(random_state=42, n_estimators=30, max_depth=2)\n",
    "rf_model2.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "dQogC4wjiuAv"
   },
   "outputs": [],
   "source": [
    "train_preds2 = rf_model2.predict(X_train)\n",
    "test_preds2 = rf_model2.predict(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "aKMos2Ooi_qJ"
   },
   "outputs": [],
   "source": [
    "train_acc2 = accuracy_score(y_train, train_preds2)\n",
    "test_acc2 = accuracy_score(y_test, test_preds2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 51
    },
    "colab_type": "code",
    "id": "39QZnnn1i4pT",
    "outputId": "42047520-00c7-46f5-e48e-7ae62738b9b3"
   },
   "outputs": [],
   "source": [
    "print(train_acc2)\n",
    "print(test_acc2)"
   ]
  }
 ],
 "metadata": {
  "colab": {
   "collapsed_sections": [],
   "name": "Exercise4_03.ipynb",
   "provenance": []
  },
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}