mlessentials/Lab08/Activity8.01/Activity8_01.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "D7JgAqboXaYz"
   },
   "outputs": [],
   "source": [
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "rV4rlbk_X_Cx"
   },
   "outputs": [],
   "source": [
    "mushrooms = pd.read_csv('../Dataset/agaricus-lepiota.data', header=None)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "-nC04CscYImK"
   },
   "outputs": [],
   "source": [
    "y_raw = mushrooms.iloc[:,0]\n",
    "X_raw = mushrooms.iloc[:,1:]\n",
    "y = (y_raw == 'p') * 1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "_b7quE4PYLIZ"
   },
   "outputs": [],
   "source": [
    "from sklearn import preprocessing\n",
    "encoder = preprocessing.OneHotEncoder()\n",
    "\n",
    "encoder.fit(X_raw)\n",
    "\n",
    "X = encoder.transform(X_raw).toarray()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 889
    },
    "colab_type": "code",
    "id": "gIdVSmXOYPuC",
    "outputId": "f27f27ea-6128-417d-db22-e72a2f529c5e"
   },
   "outputs": [],
   "source": [
    "#Initialize the classifier.\n",
    "from sklearn import ensemble\n",
    "rfc = ensemble.RandomForestClassifier(n_estimators=100, random_state=100)\n",
    "\n",
    "#Conduct a grid search.\n",
    "from sklearn import model_selection\n",
    "grid = {\n",
    "    'criterion': ['gini', 'entropy'],\n",
    "    'max_features': [2, 4, 6, 8, 10, 12, 14]\n",
    "}\n",
    "gscv = model_selection.GridSearchCV(estimator=rfc, param_grid=grid, cv=5, scoring='accuracy')\n",
    "gscv.fit(X,y)\n",
    "results = pd.DataFrame(gscv.cv_results_)\n",
    "results.sort_values('rank_test_score', ascending=True).head(10)\n",
    "\n",
    "#Conduct a random search.\n",
    "from scipy import stats\n",
    "max_features = X.shape[1]\n",
    "param_dist = {\n",
    "    'criterion': ['gini', 'entropy'],\n",
    "    'max_features': stats.randint(low=1, high=max_features)\n",
    "}\n",
    "rscv = model_selection.RandomizedSearchCV(estimator=rfc, param_distributions=param_dist, n_iter=50, cv=5, scoring='accuracy', random_state=100)\n",
    "rscv.fit(X,y)\n",
    "results = pd.DataFrame(rscv.cv_results_)\n",
    "results.sort_values('rank_test_score', ascending=True).head(10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 282
    },
    "colab_type": "code",
    "id": "QVVAb9cjYfhh",
    "outputId": "94a4bd34-512a-4813-e356-aaa03674b58b"
   },
   "outputs": [],
   "source": [
    "results.loc[:,'params'] = results.loc[:,'params'].astype(str)\n",
    "\n",
    "(\n",
    "    results.sort_values('rank_test_score', ascending=False)\n",
    "    .loc[:,['params','mean_test_score']]\n",
    "    .drop_duplicates()\n",
    "    .head(10)\n",
    "    .plot.barh(x='params', xlim=(0.8))\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "colab": {
   "name": "Activity8.01.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
}