04. tensorflow读取pandas数据训练DNN模型.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "zwBCE43Cv3PH"
   },
   "source": [
    "## Tensorflow读取pandas数据训练DNN模型"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "YQB7yiF6v9GR"
   },
   "source": [
    "数据集：心脏病数据集\n",
    "* 每一行是一个病人，包含病人的信息以及病人真的是否有心脏病；\n",
    "* 目标是使用该数据训练模型，根据病人的信息预测病人有心脏病的概率\n",
    "* 这是一个二分类的问题\n",
    "\n",
    "学习目标，怎样把Pandas的数据加载到Keras进行训练？"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "iiyC7HkqxlUD"
   },
   "source": [
    "### 1. 使用Pandas读取数据"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "5IoRbCA2n0_V"
   },
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import tensorflow as tf"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "('1.0.1', '2.1.0')"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.__version__, tf.__version__"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "UEfJ8TcMpe-2"
   },
   "outputs": [],
   "source": [
    "df = pd.read_csv(\"./datas/heart/heart.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "8FkK6QIRpjd4"
   },
   "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>sex</th>\n",
       "      <th>cp</th>\n",
       "      <th>trestbps</th>\n",
       "      <th>chol</th>\n",
       "      <th>fbs</th>\n",
       "      <th>restecg</th>\n",
       "      <th>thalach</th>\n",
       "      <th>exang</th>\n",
       "      <th>oldpeak</th>\n",
       "      <th>slope</th>\n",
       "      <th>ca</th>\n",
       "      <th>thal</th>\n",
       "      <th>target</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>63</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>145</td>\n",
       "      <td>233</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>150</td>\n",
       "      <td>0</td>\n",
       "      <td>2.3</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>fixed</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>67</td>\n",
       "      <td>1</td>\n",
       "      <td>4</td>\n",
       "      <td>160</td>\n",
       "      <td>286</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>108</td>\n",
       "      <td>1</td>\n",
       "      <td>1.5</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>normal</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>67</td>\n",
       "      <td>1</td>\n",
       "      <td>4</td>\n",
       "      <td>120</td>\n",
       "      <td>229</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>129</td>\n",
       "      <td>1</td>\n",
       "      <td>2.6</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>reversible</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>37</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>130</td>\n",
       "      <td>250</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>187</td>\n",
       "      <td>0</td>\n",
       "      <td>3.5</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>normal</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>41</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>130</td>\n",
       "      <td>204</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>172</td>\n",
       "      <td>0</td>\n",
       "      <td>1.4</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>normal</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   age  sex  cp  trestbps  chol  fbs  restecg  thalach  exang  oldpeak  slope  \\\n",
       "0   63    1   1       145   233    1        2      150      0      2.3      3   \n",
       "1   67    1   4       160   286    0        2      108      1      1.5      2   \n",
       "2   67    1   4       120   229    0        2      129      1      2.6      2   \n",
       "3   37    1   3       130   250    0        0      187      0      3.5      3   \n",
       "4   41    0   2       130   204    0        2      172      0      1.4      1   \n",
       "\n",
       "   ca        thal  target  \n",
       "0   0       fixed       0  \n",
       "1   3      normal       1  \n",
       "2   2  reversible       0  \n",
       "3   0      normal       0  \n",
       "4   0      normal       0  "
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "_MOAKz654CT5"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "age           int64\n",
       "sex           int64\n",
       "cp            int64\n",
       "trestbps      int64\n",
       "chol          int64\n",
       "fbs           int64\n",
       "restecg       int64\n",
       "thalach       int64\n",
       "exang         int64\n",
       "oldpeak     float64\n",
       "slope         int64\n",
       "ca            int64\n",
       "thal         object\n",
       "target        int64\n",
       "dtype: object"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.dtypes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "LmCl5R5C2IKo"
   },
   "outputs": [],
   "source": [
    "# 把thal列变成数字编码\n",
    "df['thal'] = pd.Categorical(df['thal'])\n",
    "df['thal'] = df['thal'].cat.codes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "s4XA1SNW2QyI"
   },
   "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>sex</th>\n",
       "      <th>cp</th>\n",
       "      <th>trestbps</th>\n",
       "      <th>chol</th>\n",
       "      <th>fbs</th>\n",
       "      <th>restecg</th>\n",
       "      <th>thalach</th>\n",
       "      <th>exang</th>\n",
       "      <th>oldpeak</th>\n",
       "      <th>slope</th>\n",
       "      <th>ca</th>\n",
       "      <th>thal</th>\n",
       "      <th>target</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>63</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>145</td>\n",
       "      <td>233</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>150</td>\n",
       "      <td>0</td>\n",
       "      <td>2.3</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>67</td>\n",
       "      <td>1</td>\n",
       "      <td>4</td>\n",
       "      <td>160</td>\n",
       "      <td>286</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>108</td>\n",
       "      <td>1</td>\n",
       "      <td>1.5</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>67</td>\n",
       "      <td>1</td>\n",
       "      <td>4</td>\n",
       "      <td>120</td>\n",
       "      <td>229</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>129</td>\n",
       "      <td>1</td>\n",
       "      <td>2.6</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>4</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>37</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>130</td>\n",
       "      <td>250</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>187</td>\n",
       "      <td>0</td>\n",
       "      <td>3.5</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>41</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>130</td>\n",
       "      <td>204</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>172</td>\n",
       "      <td>0</td>\n",
       "      <td>1.4</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   age  sex  cp  trestbps  chol  fbs  restecg  thalach  exang  oldpeak  slope  \\\n",
       "0   63    1   1       145   233    1        2      150      0      2.3      3   \n",
       "1   67    1   4       160   286    0        2      108      1      1.5      2   \n",
       "2   67    1   4       120   229    0        2      129      1      2.6      2   \n",
       "3   37    1   3       130   250    0        0      187      0      3.5      3   \n",
       "4   41    0   2       130   204    0        2      172      0      1.4      1   \n",
       "\n",
       "   ca  thal  target  \n",
       "0   0     2       0  \n",
       "1   3     3       1  \n",
       "2   2     4       0  \n",
       "3   0     3       0  \n",
       "4   0     3       0  "
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "WWRhH6r4xxQu"
   },
   "source": [
    "### 2. 将数据加载到tf.data.Dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "2wwhILm1ycSp"
   },
   "outputs": [],
   "source": [
    "# 要预测的目标，这是个二分类问题\n",
    "target = df.pop('target')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "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>sex</th>\n",
       "      <th>cp</th>\n",
       "      <th>trestbps</th>\n",
       "      <th>chol</th>\n",
       "      <th>fbs</th>\n",
       "      <th>restecg</th>\n",
       "      <th>thalach</th>\n",
       "      <th>exang</th>\n",
       "      <th>oldpeak</th>\n",
       "      <th>slope</th>\n",
       "      <th>ca</th>\n",
       "      <th>thal</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>63</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>145</td>\n",
       "      <td>233</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>150</td>\n",
       "      <td>0</td>\n",
       "      <td>2.3</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>67</td>\n",
       "      <td>1</td>\n",
       "      <td>4</td>\n",
       "      <td>160</td>\n",
       "      <td>286</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>108</td>\n",
       "      <td>1</td>\n",
       "      <td>1.5</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>67</td>\n",
       "      <td>1</td>\n",
       "      <td>4</td>\n",
       "      <td>120</td>\n",
       "      <td>229</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>129</td>\n",
       "      <td>1</td>\n",
       "      <td>2.6</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>37</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>130</td>\n",
       "      <td>250</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>187</td>\n",
       "      <td>0</td>\n",
       "      <td>3.5</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>41</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>130</td>\n",
       "      <td>204</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>172</td>\n",
       "      <td>0</td>\n",
       "      <td>1.4</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   age  sex  cp  trestbps  chol  fbs  restecg  thalach  exang  oldpeak  slope  \\\n",
       "0   63    1   1       145   233    1        2      150      0      2.3      3   \n",
       "1   67    1   4       160   286    0        2      108      1      1.5      2   \n",
       "2   67    1   4       120   229    0        2      129      1      2.6      2   \n",
       "3   37    1   3       130   250    0        0      187      0      3.5      3   \n",
       "4   41    0   2       130   204    0        2      172      0      1.4      1   \n",
       "\n",
       "   ca  thal  \n",
       "0   0     2  \n",
       "1   3     3  \n",
       "2   2     4  \n",
       "3   0     3  \n",
       "4   0     3  "
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    0\n",
       "1    1\n",
       "2    0\n",
       "3    0\n",
       "4    0\n",
       "Name: target, dtype: int64"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "target.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[ 63. ,   1. ,   1. , 145. , 233. ,   1. ,   2. , 150. ,   0. ,\n",
       "          2.3,   3. ,   0. ,   2. ],\n",
       "       [ 67. ,   1. ,   4. , 160. , 286. ,   0. ,   2. , 108. ,   1. ,\n",
       "          1.5,   2. ,   3. ,   3. ],\n",
       "       [ 67. ,   1. ,   4. , 120. , 229. ,   0. ,   2. , 129. ,   1. ,\n",
       "          2.6,   2. ,   2. ,   4. ],\n",
       "       [ 37. ,   1. ,   3. , 130. , 250. ,   0. ,   0. , 187. ,   0. ,\n",
       "          3.5,   3. ,   0. ,   3. ],\n",
       "       [ 41. ,   0. ,   2. , 130. , 204. ,   0. ,   2. , 172. ,   0. ,\n",
       "          1.4,   1. ,   0. ,   3. ]])"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head().values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0, 1, 0, 0, 0], dtype=int64)"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "target.head().values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "W6Yc-D3aqyBb"
   },
   "outputs": [],
   "source": [
    "# 构建dataset，其实是把pandas数据转换成numpy数组进行转换的\n",
    "dataset = tf.data.Dataset.from_tensor_slices((df.values, target.values))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "chEnp_Swsf0a"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Features: [ 63.    1.    1.  145.  233.    1.    2.  150.    0.    2.3   3.    0.\n",
      "   2. ], Label: 0\n",
      "Features: [ 67.    1.    4.  160.  286.    0.    2.  108.    1.    1.5   2.    3.\n",
      "   3. ], Label: 1\n",
      "Features: [ 67.    1.    4.  120.  229.    0.    2.  129.    1.    2.6   2.    2.\n",
      "   4. ], Label: 0\n",
      "Features: [ 37.    1.    3.  130.  250.    0.    0.  187.    0.    3.5   3.    0.\n",
      "   3. ], Label: 0\n",
      "Features: [ 41.    0.    2.  130.  204.    0.    2.  172.    0.    1.4   1.    0.\n",
      "   3. ], Label: 0\n"
     ]
    }
   ],
   "source": [
    "for features, label in dataset.take(5):\n",
    "    print('Features: {}, Label: {}'.format(features, label))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "R3dQ-83Ztsgl"
   },
   "outputs": [],
   "source": [
    "# Shuffle and batch the dataset.\n",
    "train_dataset = dataset.shuffle(len(df)).batch(1)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "bB9C0XJkyQEk"
   },
   "source": [
    "### 3. 创建并训练模型"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "FQd9PcPRpkP4"
   },
   "outputs": [],
   "source": [
    "model = tf.keras.Sequential([\n",
    "    tf.keras.layers.Dense(10, input_shape=(df.shape[1],)),\n",
    "    tf.keras.layers.Dense(10, activation='relu'),\n",
    "    tf.keras.layers.Dense(1)\n",
    "])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "model.compile(optimizer='adam',\n",
    "            loss=tf.keras.losses.BinaryCrossentropy(from_logits=True),\n",
    "            metrics=['accuracy'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Model: \"sequential\"\n",
      "_________________________________________________________________\n",
      "Layer (type)                 Output Shape              Param #   \n",
      "=================================================================\n",
      "dense (Dense)                (None, 10)                140       \n",
      "_________________________________________________________________\n",
      "dense_1 (Dense)              (None, 10)                110       \n",
      "_________________________________________________________________\n",
      "dense_2 (Dense)              (None, 1)                 11        \n",
      "=================================================================\n",
      "Total params: 261\n",
      "Trainable params: 261\n",
      "Non-trainable params: 0\n",
      "_________________________________________________________________\n"
     ]
    }
   ],
   "source": [
    "model.summary()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "ybDzNUheqxJw"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Train for 303 steps\n",
      "Epoch 1/15\n",
      "303/303 [==============================] - 1s 2ms/step - loss: 2.0987 - accuracy: 0.7063\n",
      "Epoch 2/15\n",
      "303/303 [==============================] - 0s 776us/step - loss: 0.6882 - accuracy: 0.7393\n",
      "Epoch 3/15\n",
      "303/303 [==============================] - 0s 851us/step - loss: 0.7454 - accuracy: 0.7360\n",
      "Epoch 4/15\n",
      "303/303 [==============================] - 0s 792us/step - loss: 0.6366 - accuracy: 0.7459\n",
      "Epoch 5/15\n",
      "303/303 [==============================] - 0s 795us/step - loss: 0.5402 - accuracy: 0.7756\n",
      "Epoch 6/15\n",
      "303/303 [==============================] - 0s 914us/step - loss: 0.5967 - accuracy: 0.7459\n",
      "Epoch 7/15\n",
      "303/303 [==============================] - 0s 785us/step - loss: 0.6007 - accuracy: 0.7393\n",
      "Epoch 8/15\n",
      "303/303 [==============================] - 0s 792us/step - loss: 0.5631 - accuracy: 0.7756\n",
      "Epoch 9/15\n",
      "303/303 [==============================] - 0s 818us/step - loss: 0.5815 - accuracy: 0.7228\n",
      "Epoch 10/15\n",
      "303/303 [==============================] - 0s 789us/step - loss: 0.5864 - accuracy: 0.7525\n",
      "Epoch 11/15\n",
      "303/303 [==============================] - 0s 891us/step - loss: 0.5792 - accuracy: 0.7756\n",
      "Epoch 12/15\n",
      "303/303 [==============================] - 0s 878us/step - loss: 0.5497 - accuracy: 0.7690\n",
      "Epoch 13/15\n",
      "303/303 [==============================] - 0s 743us/step - loss: 0.5645 - accuracy: 0.7492\n",
      "Epoch 14/15\n",
      "303/303 [==============================] - 0s 848us/step - loss: 0.5158 - accuracy: 0.7987\n",
      "Epoch 15/15\n",
      "303/303 [==============================] - 0s 792us/step - loss: 0.5034 - accuracy: 0.7921\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<tensorflow.python.keras.callbacks.History at 0x1c03bdcc148>"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model.fit(train_dataset, epochs=15)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "colab": {
   "collapsed_sections": [],
   "name": "pandas_dataframe.ipynb",
   "private_outputs": true,
   "provenance": [],
   "toc_visible": true
  },
  "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": "3.7.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}