machine_learning/logistic_regression_7/logistic_regression.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "799f31eb",
   "metadata": {},
   "source": [
    "线性回归预测的是连续数值，逻辑回归预测的是离散数值。"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "fc3c8eef",
   "metadata": {},
   "source": [
    "线性回归：  \n",
    "1.预测天气  \n",
    "2.预测股票  \n",
    "3.预测房价  \n",
    "逻辑回归：  \n",
    "1.邮件是否是垃圾邮件  \n",
    "2.猫狗分类  \n",
    "3.是否贷款"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "0b62f4a6",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "efe20171",
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.read_csv(\"insurance_data.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "a0336e69",
   "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>age</th>\n",
       "      <th>bought_insurance</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>22</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>25</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>47</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>52</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>46</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   age  bought_insurance\n",
       "0   22                 0\n",
       "1   25                 0\n",
       "2   47                 1\n",
       "3   52                 0\n",
       "4   46                 1"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "50fb949d",
   "metadata": {},
   "outputs": [],
   "source": [
    "%matplotlib inline\n",
    "import matplotlib.pyplot as plt"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "e77e37f4",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.collections.PathCollection at 0x2716f2d0608>"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.scatter(df.age, df.bought_insurance, marker=\"+\", color='r')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "bf219340",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(27, 2)"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "3a6ed8a7",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "c85065da",
   "metadata": {},
   "outputs": [],
   "source": [
    "x_train, x_test, y_train, y_test = train_test_split(df[['age']], df.bought_insurance, train_size=0.9, random_state=10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "16437565",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(24, 3)"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(x_train), len(x_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "4d83ec8c",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.linear_model import LogisticRegression"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "61312ccd",
   "metadata": {},
   "outputs": [],
   "source": [
    "lr = LogisticRegression()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "dac8d670",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "LogisticRegression()"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "lr.fit(x_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "698480b6",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(array([1, 1, 0], dtype=int64),\n",
       " 7     1\n",
       " 5     1\n",
       " 18    0\n",
       " Name: bought_insurance, dtype: int64)"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "lr.predict(x_test), y_test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "89c91628",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1.0"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "lr.score(x_test, y_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "452bb440",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[0.06470723, 0.93529277],\n",
       "       [0.10327405, 0.89672595],\n",
       "       [0.92775095, 0.07224905]])"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "lr.predict_proba(x_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "1246d4de",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "D:\\envs\\stark-lin\\lib\\site-packages\\sklearn\\base.py:451: UserWarning: X does not have valid feature names, but LogisticRegression was fitted with feature names\n",
      "  \"X does not have valid feature names, but\"\n",
      "D:\\envs\\stark-lin\\lib\\site-packages\\sklearn\\base.py:451: UserWarning: X does not have valid feature names, but LogisticRegression was fitted with feature names\n",
      "  \"X does not have valid feature names, but\"\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "(array([1], dtype=int64), array([0], dtype=int64))"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "lr.predict([[53]]), lr.predict([[20]])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "bc340fea",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.8.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}