machine_learning/saving_model_4/linear_regression.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "ae02d6c8",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "from sklearn import linear_model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "6729b5ba",
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.read_csv(\"housing_price.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "717fda9f",
   "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>area</th>\n",
       "      <th>price</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>86.45</td>\n",
       "      <td>117.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>91.57</td>\n",
       "      <td>98.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>85.52</td>\n",
       "      <td>114.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>103.60</td>\n",
       "      <td>146.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>105.25</td>\n",
       "      <td>106.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>99.00</td>\n",
       "      <td>109.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>87.95</td>\n",
       "      <td>91.5</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     area  price\n",
       "0   86.45  117.0\n",
       "1   91.57   98.0\n",
       "2   85.52  114.0\n",
       "3  103.60  146.0\n",
       "4  105.25  106.0\n",
       "5   99.00  109.0\n",
       "6   87.95   91.5"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "8bae038f",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.collections.PathCollection at 0x193b20e02c8>"
      ]
     },
     "execution_count": 5,
     "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": [
    "%matplotlib inline\n",
    "plt.xlabel(\"area\")\n",
    "plt.ylabel(\"price\")\n",
    "plt.scatter(df.area, df.price, c='r')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "1dbdd68d",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(7, 1)"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[[\"area\"]].shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "c147b635",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "LinearRegression()"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model = linear_model.LinearRegression()\n",
    "model.fit(df[[\"area\"]].values, df.price.values)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "cd1a7008",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(array([0.83809367]), 32.70161672527138)"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model.coef_, model.intercept_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "d7e74d63",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([115.93269948])"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model.predict(np.array([[99.31]]))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "4fffcc21",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([115.93269948])"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "price = model.coef_ * 99.31 + model.intercept_\n",
    "price"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "528624fa",
   "metadata": {},
   "source": [
    "## 1.pickle保存加载模型"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "e29158e1",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pickle"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "54dc5fe3",
   "metadata": {},
   "outputs": [],
   "source": [
    "with open(\"linear_model.pkl\", 'wb') as f:\n",
    "    pickle.dump(model, f)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "3871ee93",
   "metadata": {},
   "outputs": [],
   "source": [
    "with open(\"linear_model.pkl\", 'rb') as f:\n",
    "    loaded_model = pickle.load(f)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "1dd7555a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(array([0.83809367]), 32.70161672527138)"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "loaded_model.coef_, loaded_model.intercept_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "b5177ecc",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([108.13004737])"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model.predict(np.array([[90]]))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a4e5a9cc",
   "metadata": {},
   "source": [
    "## 2.joblib保存加载模型"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7ad03fc7",
   "metadata": {},
   "source": [
    "注意：sklearn 0.21.3以后需要单独安装joblib。"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "d6bec1b5",
   "metadata": {},
   "outputs": [
    {
     "ename": "ImportError",
     "evalue": "cannot import name 'joblib' from 'sklearn.externals' (D:\\envs\\stark-lin\\lib\\site-packages\\sklearn\\externals\\__init__.py)",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mImportError\u001b[0m                               Traceback (most recent call last)",
      "\u001b[1;32m~\\AppData\\Local\\Temp\\ipykernel_17608\\1043709584.py\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[1;32mfrom\u001b[0m \u001b[0msklearn\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mexternals\u001b[0m \u001b[1;32mimport\u001b[0m \u001b[0mjoblib\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m",
      "\u001b[1;31mImportError\u001b[0m: cannot import name 'joblib' from 'sklearn.externals' (D:\\envs\\stark-lin\\lib\\site-packages\\sklearn\\externals\\__init__.py)"
     ]
    }
   ],
   "source": [
    "from sklearn.externals import joblib"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "23fee355",
   "metadata": {},
   "outputs": [],
   "source": [
    "import joblib"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "id": "68b07903",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['joblib_model.pkl']"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "joblib.dump(model, 'joblib_model.pkl')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "id": "8814bd49",
   "metadata": {},
   "outputs": [],
   "source": [
    "jm = joblib.load('joblib_model.pkl')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "id": "4b6180a7",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(array([0.83809367]), 32.70161672527138)"
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "jm.coef_, jm.intercept_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "id": "42a138b9",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([124.89192085])"
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "jm.predict([[110]])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "dfc90bd0",
   "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": "3.7.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}