Diabetes project.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "import numpy as np\n",
    "import itertools\n",
    "df_diabetes = pd.read_csv('C:/python/diabetes.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1296x1080 with 8 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "df_diabetes1=df_diabetes[df_diabetes['Outcome']==1]\n",
    "columns=df_diabetes.columns[:8]\n",
    "plt.subplots(figsize=(18,15))\n",
    "length=len(columns)\n",
    "for i,j in itertools.zip_longest(columns,range(length)):\n",
    "    plt.subplot((length/2),3,j+1)\n",
    "    plt.subplots_adjust(wspace=0.2,hspace=0.5)\n",
    "    df_diabetes1[i].hist(bins=20,edgecolor='black')\n",
    "    plt.title(i)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.ensemble import RandomForestClassifier, ExtraTreesClassifier, VotingClassifier\n",
    "from sklearn.svm import SVC\n",
    "from sklearn.neural_network import MLPClassifier\n",
    "from sklearn.metrics import accuracy_score"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Pregnancies</th>\n",
       "      <th>Glucose</th>\n",
       "      <th>BloodPressure</th>\n",
       "      <th>SkinThickness</th>\n",
       "      <th>Insulin</th>\n",
       "      <th>BMI</th>\n",
       "      <th>DiabetesPedigreeFunction</th>\n",
       "      <th>Age</th>\n",
       "      <th>Outcome</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>6</td>\n",
       "      <td>148</td>\n",
       "      <td>72</td>\n",
       "      <td>35</td>\n",
       "      <td>0</td>\n",
       "      <td>33.6</td>\n",
       "      <td>0.627</td>\n",
       "      <td>50</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>85</td>\n",
       "      <td>66</td>\n",
       "      <td>29</td>\n",
       "      <td>0</td>\n",
       "      <td>26.6</td>\n",
       "      <td>0.351</td>\n",
       "      <td>31</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>8</td>\n",
       "      <td>183</td>\n",
       "      <td>64</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>23.3</td>\n",
       "      <td>0.672</td>\n",
       "      <td>32</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>89</td>\n",
       "      <td>66</td>\n",
       "      <td>23</td>\n",
       "      <td>94</td>\n",
       "      <td>28.1</td>\n",
       "      <td>0.167</td>\n",
       "      <td>21</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>137</td>\n",
       "      <td>40</td>\n",
       "      <td>35</td>\n",
       "      <td>168</td>\n",
       "      <td>43.1</td>\n",
       "      <td>2.288</td>\n",
       "      <td>33</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Pregnancies  Glucose  BloodPressure  SkinThickness  Insulin   BMI  \\\n",
       "0            6      148             72             35        0  33.6   \n",
       "1            1       85             66             29        0  26.6   \n",
       "2            8      183             64              0        0  23.3   \n",
       "3            1       89             66             23       94  28.1   \n",
       "4            0      137             40             35      168  43.1   \n",
       "\n",
       "   DiabetesPedigreeFunction  Age  Outcome  \n",
       "0                     0.627   50        1  \n",
       "1                     0.351   31        0  \n",
       "2                     0.672   32        1  \n",
       "3                     0.167   21        0  \n",
       "4                     2.288   33        1  "
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_diabetes.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [],
   "source": [
    "X, y = df_diabetes.iloc[:, :8].values, df_diabetes.iloc[:, 8].values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train, X_test, y_train, y_test = \\\n",
    "    train_test_split(X, y, test_size=0.3,\n",
    "                    stratify=y,\n",
    "                    random_state=0)\n",
    "X_train, X_train_val, y_train, y_train_val = \\\n",
    "    train_test_split(X, y, test_size=0.3,\n",
    "                    stratify=y,\n",
    "                    random_state=0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.preprocessing import StandardScaler\n",
    "sc = StandardScaler()\n",
    "X_train_std = sc.fit_transform(X_train)\n",
    "X_train_val_std = sc.transform(X_train_val)\n",
    "X_test_std = sc.transform(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.ensemble import RandomForestClassifier, ExtraTreesClassifier, VotingClassifier\n",
    "from sklearn.svm import SVC\n",
    "from sklearn.neural_network import MLPClassifier\n",
    "from sklearn.metrics import accuracy_score\n",
    "from sklearn.linear_model import LogisticRegression"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [],
   "source": [
    "rnd_clf = RandomForestClassifier(n_estimators=200, random_state=42)\n",
    "extra_trees_clf = ExtraTreesClassifier(n_estimators=200, random_state=42)\n",
    "mlp_clf = MLPClassifier(random_state=42)\n",
    "svm_clf = SVC(gamma=\"auto\", random_state=42)\n",
    "log_clf = LogisticRegression(solver=\"liblinear\", random_state=42)\n",
    "voting_clf = VotingClassifier(\n",
    "    estimators=[('lr', log_clf), ('rf', rnd_clf), ('extra', extra_trees_clf)],\n",
    "    voting='hard')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "VotingClassifier(estimators=[('lr',\n",
       "                              LogisticRegression(C=1.0, class_weight=None,\n",
       "                                                 dual=False, fit_intercept=True,\n",
       "                                                 intercept_scaling=1,\n",
       "                                                 l1_ratio=None, max_iter=100,\n",
       "                                                 multi_class='warn',\n",
       "                                                 n_jobs=None, penalty='l2',\n",
       "                                                 random_state=42,\n",
       "                                                 solver='liblinear', tol=0.0001,\n",
       "                                                 verbose=0, warm_start=False)),\n",
       "                             ('rf',\n",
       "                              RandomForestClassifier(bootstrap=True,\n",
       "                                                     class_weight=None,\n",
       "                                                     criterion='gin...\n",
       "                                                   class_weight=None,\n",
       "                                                   criterion='gini',\n",
       "                                                   max_depth=None,\n",
       "                                                   max_features='auto',\n",
       "                                                   max_leaf_nodes=None,\n",
       "                                                   min_impurity_decrease=0.0,\n",
       "                                                   min_impurity_split=None,\n",
       "                                                   min_samples_leaf=1,\n",
       "                                                   min_samples_split=2,\n",
       "                                                   min_weight_fraction_leaf=0.0,\n",
       "                                                   n_estimators=200,\n",
       "                                                   n_jobs=None, oob_score=False,\n",
       "                                                   random_state=42, verbose=0,\n",
       "                                                   warm_start=False))],\n",
       "                 flatten_transform=True, n_jobs=None, voting='hard',\n",
       "                 weights=None)"
      ]
     },
     "execution_count": 31,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "voting_clf.fit(X_train_std, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.ensemble import BaggingClassifier\n",
    "from sklearn.tree import DecisionTreeClassifier\n",
    "bag_clf = BaggingClassifier(\n",
    "    DecisionTreeClassifier(splitter=\"random\", max_leaf_nodes=16, random_state=42),\n",
    "    n_estimators=500, max_samples=1.0, bootstrap=True, n_jobs=-1, random_state=42)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "LogisticRegression 0.7878787878787878\n",
      "RandomForestClassifier 0.8008658008658008\n",
      "SVC 0.6493506493506493\n",
      "MLPClassifier 0.670995670995671\n",
      "ExtraTreesClassifier 0.7878787878787878\n",
      "VotingClassifier 0.7965367965367965\n",
      "BaggingClassifier 0.7748917748917749\n"
     ]
    }
   ],
   "source": [
    "from sklearn.metrics import accuracy_score\n",
    "\n",
    "for clf in (log_clf, rnd_clf, svm_clf, mlp_clf, extra_trees_clf, voting_clf, bag_clf):\n",
    "    clf.fit(X_train, y_train)\n",
    "    y_pred = clf.predict(X_test)\n",
    "    print(clf.__class__.__name__, accuracy_score(y_test, y_pred))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.ensemble import BaggingClassifier\n",
    "from sklearn.tree import DecisionTreeClassifier\n",
    "bag_clf = BaggingClassifier(\n",
    "    DecisionTreeClassifier(splitter=\"random\", max_leaf_nodes=16, random_state=42),\n",
    "    n_estimators=500, max_samples=1.0, bootstrap=True, n_jobs=-1, random_state=42)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Is PCR useful?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "Eigenvalues \n",
      "[2.04241039 1.71892202 1.07478574 0.42789489 0.43955938 0.68393485\n",
      " 0.78361637 0.84380173]\n"
     ]
    }
   ],
   "source": [
    "import numpy as np\n",
    "cov_mat = np.cov(X_train_std.T)\n",
    "eigen_vals, eigen_vecs = np.linalg.eig(cov_mat)\n",
    "\n",
    "print('\\nEigenvalues \\n%s' % eigen_vals)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [],
   "source": [
    "tot = sum(eigen_vals)\n",
    "var_exp = [(i / tot) for i in sorted(eigen_vals, reverse=True)]\n",
    "cum_var_exp = np.cumsum(var_exp)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0.25482588, 0.46929101, 0.60338904, 0.70866784, 0.80643748,\n",
       "       0.89177014, 0.94661274, 1.        ])"
      ]
     },
     "execution_count": 37,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "cum_var_exp"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### It seems useless"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# We have to make a cross-validation model and hyperparameter tuning model."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[131  19]\n",
      " [ 27  54]]\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.83      0.87      0.85       150\n",
      "           1       0.74      0.67      0.70        81\n",
      "\n",
      "    accuracy                           0.80       231\n",
      "   macro avg       0.78      0.77      0.78       231\n",
      "weighted avg       0.80      0.80      0.80       231\n",
      "\n",
      "dd 0.8008658008658008\n"
     ]
    }
   ],
   "source": [
    "from sklearn.metrics import confusion_matrix\n",
    "from sklearn.metrics import classification_report\n",
    "rnd_clf.fit(X_train, y_train)\n",
    "y_pred = rnd_clf.predict(X_test)\n",
    "confmat = confusion_matrix(y_true=y_test, y_pred=y_pred)\n",
    "print(confmat)\n",
    "print(classification_report(y_test,y_pred))\n",
    "print(\"dd\", accuracy_score(y_test, y_pred))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Confusion matrix, recall"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}