{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "from sklearn.preprocessing import MinMaxScaler\n",
    "from sklearn.preprocessing import StandardScaler"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "# 读取约会数据\n",
    "data = pd.read_csv('./data/dating.txt')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "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>milage</th>\n",
       "      <th>Liters</th>\n",
       "      <th>Consumtime</th>\n",
       "      <th>target</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>40920</td>\n",
       "      <td>8.326976</td>\n",
       "      <td>0.953952</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>14488</td>\n",
       "      <td>7.153469</td>\n",
       "      <td>1.673904</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>26052</td>\n",
       "      <td>1.441871</td>\n",
       "      <td>0.805124</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>75136</td>\n",
       "      <td>13.147394</td>\n",
       "      <td>0.428964</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>38344</td>\n",
       "      <td>1.669788</td>\n",
       "      <td>0.134296</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   milage     Liters  Consumtime  target\n",
       "0   40920   8.326976    0.953952       3\n",
       "1   14488   7.153469    1.673904       2\n",
       "2   26052   1.441871    0.805124       1\n",
       "3   75136  13.147394    0.428964       1\n",
       "4   38344   1.669788    0.134296       1"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 归一化"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/anaconda3/lib/python3.7/site-packages/sklearn/preprocessing/data.py:334: DataConversionWarning: Data with input dtype int64, float64 were all converted to float64 by MinMaxScaler.\n",
      "  return self.partial_fit(X, y)\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "array([[0.44832535, 0.39805139, 0.56233353],\n",
       "       [0.15873259, 0.34195467, 0.98724416],\n",
       "       [0.28542943, 0.06892523, 0.47449629],\n",
       "       ...,\n",
       "       [0.29115949, 0.50910294, 0.51079493],\n",
       "       [0.52711097, 0.43665451, 0.4290048 ],\n",
       "       [0.47940793, 0.3768091 , 0.78571804]])"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 归一化处理  转换器\n",
    "# 实例化转换器\n",
    "transfer = MinMaxScaler()\n",
    "# fit:计算转换数据的参数：最小值，最大值，保存在转换器中\n",
    "# transfer.fit(data.iloc[:, :3])\n",
    "# 转换数据  \n",
    "# transfer.transform(data.iloc[:, :3])\n",
    "\n",
    "# 计算参数和转换数据\n",
    "transfer.fit_transform(data.iloc[:, :3])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 标准化"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/anaconda3/lib/python3.7/site-packages/sklearn/preprocessing/data.py:645: DataConversionWarning: Data with input dtype int64, float64 were all converted to float64 by StandardScaler.\n",
      "  return self.partial_fit(X, y)\n",
      "/anaconda3/lib/python3.7/site-packages/sklearn/base.py:464: DataConversionWarning: Data with input dtype int64, float64 were all converted to float64 by StandardScaler.\n",
      "  return self.fit(X, **fit_params).transform(X)\n"
     ]
    }
   ],
   "source": [
    "# 标准化处理  转换器\n",
    "# 实例化转换器\n",
    "transfer = StandardScaler()\n",
    "# fit:计算转换数据的参数:平均值，标准差，保存在转换器中\n",
    "# transfer.fit(data.iloc[:, :3])\n",
    "# 转换数据  \n",
    "# transfer.transform(data.iloc[:, :3])\n",
    "\n",
    "# 计算参数和转换数据\n",
    "res = transfer.fit_transform(data.iloc[:, :3])"
   ]
  },
  {
   "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
}