diabetes.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "diabetes_data = pd.read_csv(\"./diabetes.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "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": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "diabetes_data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Pregnancies                 0\n",
       "Glucose                     0\n",
       "BloodPressure               0\n",
       "SkinThickness               0\n",
       "Insulin                     0\n",
       "BMI                         0\n",
       "DiabetesPedigreeFunction    0\n",
       "Age                         0\n",
       "Outcome                     0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "diabetes_data.isna().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn import linear_model \n",
    "# logistics regression \n",
    "# decision tree\n",
    "# random forest\n",
    "# KNN\n",
    "# SVM"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "X = diabetes_data[diabetes_data.columns[:-1]]\n",
    "y = diabetes_data['Outcome']\n",
    "\n",
    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=0, stratify=y)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(768,)"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y.shape\n",
    "# print(X)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "logmodel = linear_model.LogisticRegression(max_iter=1000)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "ename": "NameError",
     "evalue": "name 'X_train' is not defined",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
      "\u001b[0;32m/var/folders/mg/pgwh8jl57vncrh0f437ppnwh0000gn/T/ipykernel_39674/1619648939.py\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mlogmodel\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfit\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mX_train\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0my_train\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
      "\u001b[0;31mNameError\u001b[0m: name 'X_train' is not defined"
     ]
    }
   ],
   "source": [
    "logmodel.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "log_prediction = logmodel.predict(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[0 0 0 0 1 0 1 0 0 0 0 0 0 0 0 0 0 0 0 1 0 0 1 1 1 1 1 0 0 0 0 0 1 0 1 0 1\n",
      " 0 0 0 0 0 1 0 1 1 0 0 1 0 0 0 0 1 0 1 0 0 0 0 0 0 1 0 0 0 0 0 0 0 0 1 0 0\n",
      " 0 0 0 0 0 1 0 0 1 0 1 1 0 0 1 0 0 0 0 1 1 0 1 1 0 0 1 0 0 0 0 0 0 1 0 0 0\n",
      " 0 0 1 0 0 0 1 0 0 0 0 1 0 0 0 0 1 0 0 0 0 0 1 1 1 1 0 0 1 0 0 1 0 0 0 0 0\n",
      " 1 0 0 1 0 0]\n"
     ]
    }
   ],
   "source": [
    "print(log_prediction)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0 --> 0\n",
      "0 --> 0\n",
      "0 --> 0\n",
      "0 --> 1\n",
      "1 --> 0\n",
      "0 --> 0\n",
      "1 --> 1\n",
      "0 --> 0\n",
      "0 --> 0\n",
      "0 --> 0\n",
      "0 --> 0\n",
      "0 --> 0\n",
      "0 --> 0\n",
      "0 --> 0\n",
      "0 --> 1\n",
      "0 --> 0\n",
      "0 --> 1\n",
      "0 --> 0\n",
      "0 --> 0\n",
      "1 --> 1\n",
      "0 --> 0\n",
      "0 --> 1\n",
      "1 --> 0\n",
      "1 --> 1\n",
      "1 --> 0\n",
      "1 --> 0\n",
      "1 --> 1\n",
      "0 --> 1\n",
      "0 --> 0\n",
      "0 --> 0\n",
      "0 --> 1\n",
      "0 --> 0\n",
      "1 --> 1\n",
      "0 --> 1\n",
      "1 --> 1\n",
      "0 --> 0\n",
      "1 --> 1\n",
      "0 --> 0\n",
      "0 --> 0\n",
      "0 --> 0\n",
      "0 --> 0\n",
      "0 --> 0\n",
      "1 --> 1\n",
      "0 --> 0\n",
      "1 --> 1\n",
      "1 --> 0\n",
      "0 --> 0\n",
      "0 --> 0\n",
      "1 --> 0\n",
      "0 --> 0\n",
      "0 --> 0\n",
      "0 --> 0\n",
      "0 --> 1\n",
      "1 --> 1\n",
      "0 --> 0\n",
      "1 --> 1\n",
      "0 --> 0\n",
      "0 --> 0\n",
      "0 --> 0\n",
      "0 --> 0\n",
      "0 --> 0\n",
      "0 --> 0\n",
      "1 --> 1\n",
      "0 --> 0\n",
      "0 --> 0\n",
      "0 --> 1\n",
      "0 --> 0\n",
      "0 --> 1\n",
      "0 --> 1\n",
      "0 --> 0\n",
      "0 --> 0\n",
      "1 --> 1\n",
      "0 --> 1\n",
      "0 --> 0\n",
      "0 --> 1\n",
      "0 --> 0\n",
      "0 --> 0\n",
      "0 --> 0\n",
      "0 --> 0\n",
      "1 --> 0\n",
      "0 --> 0\n",
      "0 --> 1\n",
      "1 --> 1\n",
      "0 --> 0\n",
      "1 --> 1\n",
      "1 --> 1\n",
      "0 --> 1\n",
      "0 --> 0\n",
      "1 --> 1\n",
      "0 --> 0\n",
      "0 --> 0\n",
      "0 --> 0\n",
      "0 --> 0\n",
      "1 --> 1\n",
      "1 --> 1\n",
      "0 --> 1\n",
      "1 --> 0\n",
      "1 --> 1\n",
      "0 --> 0\n",
      "0 --> 1\n",
      "1 --> 1\n",
      "0 --> 0\n",
      "0 --> 0\n",
      "0 --> 0\n",
      "0 --> 0\n",
      "0 --> 0\n",
      "0 --> 1\n",
      "1 --> 1\n",
      "0 --> 0\n",
      "0 --> 0\n",
      "0 --> 0\n",
      "0 --> 0\n",
      "0 --> 0\n",
      "1 --> 1\n",
      "0 --> 0\n",
      "0 --> 0\n",
      "0 --> 0\n",
      "1 --> 1\n",
      "0 --> 0\n",
      "0 --> 0\n",
      "0 --> 1\n",
      "0 --> 0\n",
      "1 --> 1\n",
      "0 --> 0\n",
      "0 --> 1\n",
      "0 --> 0\n",
      "0 --> 1\n",
      "1 --> 0\n",
      "0 --> 0\n",
      "0 --> 0\n",
      "0 --> 0\n",
      "0 --> 0\n",
      "0 --> 0\n",
      "1 --> 0\n",
      "1 --> 1\n",
      "1 --> 1\n",
      "1 --> 0\n",
      "0 --> 1\n",
      "0 --> 0\n",
      "1 --> 1\n",
      "0 --> 0\n",
      "0 --> 0\n",
      "1 --> 1\n",
      "0 --> 1\n",
      "0 --> 0\n",
      "0 --> 0\n",
      "0 --> 0\n",
      "0 --> 0\n",
      "1 --> 1\n",
      "0 --> 0\n",
      "0 --> 0\n",
      "1 --> 1\n",
      "0 --> 0\n",
      "0 --> 0\n"
     ]
    }
   ],
   "source": [
    "for pred, actual in zip(log_prediction, y_test):\n",
    "    print(pred, \"-->\", actual)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.7792207792207793"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "logmodel.score(X_test, y_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.metrics import confusion_matrix, ConfusionMatrixDisplay\n",
    "import matplotlib.pyplot as plt"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[89, 11],\n",
       "       [23, 31]])"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "confusion_matrix(y_test, log_prediction) "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<sklearn.metrics._plot.confusion_matrix.ConfusionMatrixDisplay at 0x7fa51945cc40>"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 432x288 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "cm_display = ConfusionMatrixDisplay(confusion_matrix(y_test, log_prediction),   display_labels = [False, True])\n",
    "cm_display.plot()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "#KNN\n",
    "from sklearn.neighbors import KNeighborsClassifier\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "knn = KNeighborsClassifier(n_neighbors=500)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "KNeighborsClassifier(n_neighbors=500)"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "knn.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
       "       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
       "       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
       "       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
       "       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
       "       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
       "       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0])"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "knn.predict(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.6493506493506493"
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "knn.score(X_test, y_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.tree import DecisionTreeClassifier"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "dt_model = DecisionTreeClassifier()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "DecisionTreeClassifier()"
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dt_model.fit(X_train,y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "ename": "ValueError",
     "evalue": "Expected 2D array, got 1D array instead:\narray=[0. 0. 0. 1. 0. 0. 1. 0. 0. 0. 0. 0. 0. 0. 1. 0. 1. 0. 0. 1. 0. 1. 0. 1.\n 0. 0. 1. 1. 0. 0. 1. 0. 1. 1. 1. 0. 1. 0. 0. 0. 0. 0. 1. 0. 1. 0. 0. 0.\n 0. 0. 0. 0. 1. 1. 0. 1. 0. 0. 0. 0. 0. 0. 1. 0. 0. 1. 0. 1. 1. 0. 0. 1.\n 1. 0. 1. 0. 0. 0. 0. 0. 0. 1. 1. 0. 1. 1. 1. 0. 1. 0. 0. 0. 0. 1. 1. 1.\n 0. 1. 0. 1. 1. 0. 0. 0. 0. 0. 1. 1. 0. 0. 0. 0. 0. 1. 0. 0. 0. 1. 0. 0.\n 1. 0. 1. 0. 1. 0. 1. 0. 0. 0. 0. 0. 0. 0. 1. 1. 0. 1. 0. 1. 0. 0. 1. 1.\n 0. 0. 0. 0. 1. 0. 0. 1. 0. 0.].\nReshape your data either using array.reshape(-1, 1) if your data has a single feature or array.reshape(1, -1) if it contains a single sample.",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mValueError\u001b[0m                                Traceback (most recent call last)",
      "\u001b[0;32m/var/folders/mg/pgwh8jl57vncrh0f437ppnwh0000gn/T/ipykernel_24783/429653624.py\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mdt_model\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpredict\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0my_test\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m      2\u001b[0m \u001b[0mdt_model\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mscore\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mX_test\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0my_test\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/opt/homebrew/anaconda3/lib/python3.9/site-packages/sklearn/tree/_classes.py\u001b[0m in \u001b[0;36mpredict\u001b[0;34m(self, X, check_input)\u001b[0m\n\u001b[1;32m    440\u001b[0m         \"\"\"\n\u001b[1;32m    441\u001b[0m         \u001b[0mcheck_is_fitted\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 442\u001b[0;31m         \u001b[0mX\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_validate_X_predict\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mX\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcheck_input\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    443\u001b[0m         \u001b[0mproba\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtree_\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpredict\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mX\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    444\u001b[0m         \u001b[0mn_samples\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mX\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mshape\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/opt/homebrew/anaconda3/lib/python3.9/site-packages/sklearn/tree/_classes.py\u001b[0m in \u001b[0;36m_validate_X_predict\u001b[0;34m(self, X, check_input)\u001b[0m\n\u001b[1;32m    405\u001b[0m         \u001b[0;34m\"\"\"Validate the training data on predict (probabilities).\"\"\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    406\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0mcheck_input\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 407\u001b[0;31m             X = self._validate_data(X, dtype=DTYPE, accept_sparse=\"csr\",\n\u001b[0m\u001b[1;32m    408\u001b[0m                                     reset=False)\n\u001b[1;32m    409\u001b[0m             if issparse(X) and (X.indices.dtype != np.intc or\n",
      "\u001b[0;32m/opt/homebrew/anaconda3/lib/python3.9/site-packages/sklearn/base.py\u001b[0m in \u001b[0;36m_validate_data\u001b[0;34m(self, X, y, reset, validate_separately, **check_params)\u001b[0m\n\u001b[1;32m    419\u001b[0m             \u001b[0mout\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mX\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    420\u001b[0m         \u001b[0;32melif\u001b[0m \u001b[0misinstance\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0my\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mstr\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mand\u001b[0m \u001b[0my\u001b[0m \u001b[0;34m==\u001b[0m \u001b[0;34m'no_validation'\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 421\u001b[0;31m             \u001b[0mX\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mcheck_array\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mX\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mcheck_params\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    422\u001b[0m             \u001b[0mout\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mX\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    423\u001b[0m         \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/opt/homebrew/anaconda3/lib/python3.9/site-packages/sklearn/utils/validation.py\u001b[0m in \u001b[0;36minner_f\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m     61\u001b[0m             \u001b[0mextra_args\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m-\u001b[0m \u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mall_args\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     62\u001b[0m             \u001b[0;32mif\u001b[0m \u001b[0mextra_args\u001b[0m \u001b[0;34m<=\u001b[0m \u001b[0;36m0\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 63\u001b[0;31m                 \u001b[0;32mreturn\u001b[0m \u001b[0mf\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     64\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     65\u001b[0m             \u001b[0;31m# extra_args > 0\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/opt/homebrew/anaconda3/lib/python3.9/site-packages/sklearn/utils/validation.py\u001b[0m in \u001b[0;36mcheck_array\u001b[0;34m(array, accept_sparse, accept_large_sparse, dtype, order, copy, force_all_finite, ensure_2d, allow_nd, ensure_min_samples, ensure_min_features, estimator)\u001b[0m\n\u001b[1;32m    692\u001b[0m             \u001b[0;31m# If input is 1D raise error\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    693\u001b[0m             \u001b[0;32mif\u001b[0m \u001b[0marray\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mndim\u001b[0m \u001b[0;34m==\u001b[0m \u001b[0;36m1\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 694\u001b[0;31m                 raise ValueError(\n\u001b[0m\u001b[1;32m    695\u001b[0m                     \u001b[0;34m\"Expected 2D array, got 1D array instead:\\narray={}.\\n\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    696\u001b[0m                     \u001b[0;34m\"Reshape your data either using array.reshape(-1, 1) if \"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;31mValueError\u001b[0m: Expected 2D array, got 1D array instead:\narray=[0. 0. 0. 1. 0. 0. 1. 0. 0. 0. 0. 0. 0. 0. 1. 0. 1. 0. 0. 1. 0. 1. 0. 1.\n 0. 0. 1. 1. 0. 0. 1. 0. 1. 1. 1. 0. 1. 0. 0. 0. 0. 0. 1. 0. 1. 0. 0. 0.\n 0. 0. 0. 0. 1. 1. 0. 1. 0. 0. 0. 0. 0. 0. 1. 0. 0. 1. 0. 1. 1. 0. 0. 1.\n 1. 0. 1. 0. 0. 0. 0. 0. 0. 1. 1. 0. 1. 1. 1. 0. 1. 0. 0. 0. 0. 1. 1. 1.\n 0. 1. 0. 1. 1. 0. 0. 0. 0. 0. 1. 1. 0. 0. 0. 0. 0. 1. 0. 0. 0. 1. 0. 0.\n 1. 0. 1. 0. 1. 0. 1. 0. 0. 0. 0. 0. 0. 0. 1. 1. 0. 1. 0. 1. 0. 0. 1. 1.\n 0. 0. 0. 0. 1. 0. 0. 1. 0. 0.].\nReshape your data either using array.reshape(-1, 1) if your data has a single feature or array.reshape(1, -1) if it contains a single sample."
     ]
    }
   ],
   "source": [
    "dt_model.predict(y_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.7012987012987013"
      ]
     },
     "execution_count": 36,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dt_model.score(X_test,y_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "base",
   "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": "3.9.7"
  },
  "orig_nbformat": 4,
  "vscode": {
   "interpreter": {
    "hash": "38cca0c38332a56087b24af0bc80247f4fced29cb4f7f437d91dc159adec9c4e"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}