djia_support_nikkei-test.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "import sklearn.preprocessing\n",
    "import sklearn\n",
    "import os\n",
    "from datetime import datetime, timedelta\n",
    "from tqdm import tqdm\n",
    "\n",
    "import tensorflow as tf\n",
    "from tensorflow.keras.models import Sequential, Model\n",
    "from tensorflow.keras.optimizers import Adam\n",
    "from tensorflow.keras.layers import LSTM, GRU, Bidirectional, Dense, Dropout, Input, TimeDistributed, LeakyReLU, BatchNormalization\n",
    "from tensorflow.keras import backend as K\n",
    "from tensorflow.keras.callbacks import ModelCheckpoint, ReduceLROnPlateau,TensorBoard"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['DJI_fe.csv',\n",
       " 'DJI_STO_20period_sma10.csv',\n",
       " '.DS_Store',\n",
       " 'N225.csv',\n",
       " 'DJI_modified_features - DJI.csv',\n",
       " 'preprocessed',\n",
       " 'N225fillVOL.csv',\n",
       " 'DJI_modified_sma.csv',\n",
       " 'downjone5y.csv',\n",
       " 'N225withoutNULL.csv',\n",
       " 'stocknews',\n",
       " 'dowjone1985_2019.csv',\n",
       " '.ipynb_checkpoints',\n",
       " 'DJI_ema.csv',\n",
       " 'DJI_denoise.csv',\n",
       " 'test_djia.csv']"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "os.listdir('./data/')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_nikkei = pd.read_csv('./data/N225withoutNULL.csv')\n",
    "df_djia = pd.read_csv('./data/DJI_modified_sma.csv')"
   ]
  },
  {
   "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>Date</th>\n",
       "      <th>Open</th>\n",
       "      <th>High</th>\n",
       "      <th>Low</th>\n",
       "      <th>Close</th>\n",
       "      <th>Adj Close</th>\n",
       "      <th>Volume</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1985-01-29</td>\n",
       "      <td>11843.070313</td>\n",
       "      <td>11843.070313</td>\n",
       "      <td>11843.070313</td>\n",
       "      <td>11843.070313</td>\n",
       "      <td>11843.070313</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1985-01-30</td>\n",
       "      <td>11960.629883</td>\n",
       "      <td>11960.629883</td>\n",
       "      <td>11960.629883</td>\n",
       "      <td>11960.629883</td>\n",
       "      <td>11960.629883</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1985-01-31</td>\n",
       "      <td>11992.309570</td>\n",
       "      <td>11992.309570</td>\n",
       "      <td>11992.309570</td>\n",
       "      <td>11992.309570</td>\n",
       "      <td>11992.309570</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1985-02-01</td>\n",
       "      <td>11946.959961</td>\n",
       "      <td>11946.959961</td>\n",
       "      <td>11946.959961</td>\n",
       "      <td>11946.959961</td>\n",
       "      <td>11946.959961</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1985-02-04</td>\n",
       "      <td>11891.080078</td>\n",
       "      <td>11891.080078</td>\n",
       "      <td>11891.080078</td>\n",
       "      <td>11891.080078</td>\n",
       "      <td>11891.080078</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         Date          Open          High           Low         Close  \\\n",
       "0  1985-01-29  11843.070313  11843.070313  11843.070313  11843.070313   \n",
       "1  1985-01-30  11960.629883  11960.629883  11960.629883  11960.629883   \n",
       "2  1985-01-31  11992.309570  11992.309570  11992.309570  11992.309570   \n",
       "3  1985-02-01  11946.959961  11946.959961  11946.959961  11946.959961   \n",
       "4  1985-02-04  11891.080078  11891.080078  11891.080078  11891.080078   \n",
       "\n",
       "      Adj Close  Volume  \n",
       "0  11843.070313       0  \n",
       "1  11960.629883       0  \n",
       "2  11992.309570       0  \n",
       "3  11946.959961       0  \n",
       "4  11891.080078       0  "
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_nikkei.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'1985-01-29'"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_djia['Date'][0]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Preprocess"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "  0%|          | 0/8762 [00:00<?, ?it/s]/usr/local/lib/python3.6/site-packages/ipykernel_launcher.py:7: SettingWithCopyWarning: \n",
      "A value is trying to be set on a copy of a slice from a DataFrame\n",
      "\n",
      "See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
      "  import sys\n",
      "100%|██████████| 8762/8762 [00:05<00:00, 1485.17it/s]\n"
     ]
    }
   ],
   "source": [
    "# postpone 1 day and concatenate both table\n",
    "\n",
    "# decrement datetime of djia first\n",
    "df_djia_dc = df_djia.copy()\n",
    "# df_djia_dc['Date'] = df_djia['Date'] + timedelta(days=-1)\n",
    "for i in tqdm(range(len(df_djia))):\n",
    "    df_djia_dc['Date'][i] = str((datetime.strptime(df_djia.iloc[i]['Date'], '%Y-%m-%d') + timedelta(days=-1)).date())\n",
    "\n",
    "# df_djia_dc.head()\n",
    "df = pd.merge(df_nikkei, df_djia_dc, on='Date', how='inner')\n",
    "df = df.rename({'Open_x': 'Open(Nikkei)', 'High_x': 'High(Nikkei)', 'Low_x': 'Low(Nikkei)', 'Close_x': 'Close(Nikkei)',\n",
    "                'Open_y': 'Open(DJIA)', 'High_y': 'High(DJIA)', 'Low_y': 'Low(DJIA)', 'Close_y': 'Close(DJIA)'\n",
    "               }, axis=1)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "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>Date</th>\n",
       "      <th>Open(Nikkei)</th>\n",
       "      <th>High(Nikkei)</th>\n",
       "      <th>Low(Nikkei)</th>\n",
       "      <th>Close(Nikkei)</th>\n",
       "      <th>Adj Close_x</th>\n",
       "      <th>Volume_x</th>\n",
       "      <th>Open(DJIA)</th>\n",
       "      <th>High(DJIA)</th>\n",
       "      <th>Low(DJIA)</th>\n",
       "      <th>Close(DJIA)</th>\n",
       "      <th>Adj Close_y</th>\n",
       "      <th>Volume_y</th>\n",
       "      <th>sma5</th>\n",
       "      <th>sma10</th>\n",
       "      <th>sma25</th>\n",
       "      <th>sma75</th>\n",
       "      <th>sma125</th>\n",
       "      <th>sma200</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1985-01-29</td>\n",
       "      <td>11843.070313</td>\n",
       "      <td>11843.070313</td>\n",
       "      <td>11843.070313</td>\n",
       "      <td>11843.070313</td>\n",
       "      <td>11843.070313</td>\n",
       "      <td>0</td>\n",
       "      <td>1297.369995</td>\n",
       "      <td>1305.099976</td>\n",
       "      <td>1278.930054</td>\n",
       "      <td>1287.880005</td>\n",
       "      <td>1287.880005</td>\n",
       "      <td>16820000</td>\n",
       "      <td>1287.880005</td>\n",
       "      <td>1287.880005</td>\n",
       "      <td>1287.880005</td>\n",
       "      <td>1287.880005</td>\n",
       "      <td>1287.880005</td>\n",
       "      <td>1287.880005</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1985-01-30</td>\n",
       "      <td>11960.629883</td>\n",
       "      <td>11960.629883</td>\n",
       "      <td>11960.629883</td>\n",
       "      <td>11960.629883</td>\n",
       "      <td>11960.629883</td>\n",
       "      <td>0</td>\n",
       "      <td>1283.239990</td>\n",
       "      <td>1293.400024</td>\n",
       "      <td>1272.640015</td>\n",
       "      <td>1286.770020</td>\n",
       "      <td>1286.770020</td>\n",
       "      <td>14070000</td>\n",
       "      <td>1286.770020</td>\n",
       "      <td>1286.770020</td>\n",
       "      <td>1286.770020</td>\n",
       "      <td>1286.770020</td>\n",
       "      <td>1286.770020</td>\n",
       "      <td>1286.770020</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1985-01-31</td>\n",
       "      <td>11992.309570</td>\n",
       "      <td>11992.309570</td>\n",
       "      <td>11992.309570</td>\n",
       "      <td>11992.309570</td>\n",
       "      <td>11992.309570</td>\n",
       "      <td>0</td>\n",
       "      <td>1276.939941</td>\n",
       "      <td>1286.109985</td>\n",
       "      <td>1269.770020</td>\n",
       "      <td>1277.719971</td>\n",
       "      <td>1277.719971</td>\n",
       "      <td>10980000</td>\n",
       "      <td>1277.719971</td>\n",
       "      <td>1277.719971</td>\n",
       "      <td>1277.719971</td>\n",
       "      <td>1277.719971</td>\n",
       "      <td>1277.719971</td>\n",
       "      <td>1277.719971</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1985-02-04</td>\n",
       "      <td>11891.080078</td>\n",
       "      <td>11891.080078</td>\n",
       "      <td>11891.080078</td>\n",
       "      <td>11891.080078</td>\n",
       "      <td>11891.080078</td>\n",
       "      <td>0</td>\n",
       "      <td>1294.060059</td>\n",
       "      <td>1301.130005</td>\n",
       "      <td>1278.599976</td>\n",
       "      <td>1285.229980</td>\n",
       "      <td>1285.229980</td>\n",
       "      <td>13800000</td>\n",
       "      <td>1285.535986</td>\n",
       "      <td>1285.229980</td>\n",
       "      <td>1285.229980</td>\n",
       "      <td>1285.229980</td>\n",
       "      <td>1285.229980</td>\n",
       "      <td>1285.229980</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1985-02-05</td>\n",
       "      <td>11823.429688</td>\n",
       "      <td>11823.429688</td>\n",
       "      <td>11823.429688</td>\n",
       "      <td>11823.429688</td>\n",
       "      <td>11823.429688</td>\n",
       "      <td>0</td>\n",
       "      <td>1284.890015</td>\n",
       "      <td>1294.500000</td>\n",
       "      <td>1275.069946</td>\n",
       "      <td>1280.589966</td>\n",
       "      <td>1280.589966</td>\n",
       "      <td>14610000</td>\n",
       "      <td>1284.077979</td>\n",
       "      <td>1280.589966</td>\n",
       "      <td>1280.589966</td>\n",
       "      <td>1280.589966</td>\n",
       "      <td>1280.589966</td>\n",
       "      <td>1280.589966</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         Date  Open(Nikkei)  High(Nikkei)   Low(Nikkei)  Close(Nikkei)  \\\n",
       "0  1985-01-29  11843.070313  11843.070313  11843.070313   11843.070313   \n",
       "1  1985-01-30  11960.629883  11960.629883  11960.629883   11960.629883   \n",
       "2  1985-01-31  11992.309570  11992.309570  11992.309570   11992.309570   \n",
       "3  1985-02-04  11891.080078  11891.080078  11891.080078   11891.080078   \n",
       "4  1985-02-05  11823.429688  11823.429688  11823.429688   11823.429688   \n",
       "\n",
       "    Adj Close_x  Volume_x   Open(DJIA)   High(DJIA)    Low(DJIA)  Close(DJIA)  \\\n",
       "0  11843.070313         0  1297.369995  1305.099976  1278.930054  1287.880005   \n",
       "1  11960.629883         0  1283.239990  1293.400024  1272.640015  1286.770020   \n",
       "2  11992.309570         0  1276.939941  1286.109985  1269.770020  1277.719971   \n",
       "3  11891.080078         0  1294.060059  1301.130005  1278.599976  1285.229980   \n",
       "4  11823.429688         0  1284.890015  1294.500000  1275.069946  1280.589966   \n",
       "\n",
       "   Adj Close_y  Volume_y         sma5        sma10        sma25        sma75  \\\n",
       "0  1287.880005  16820000  1287.880005  1287.880005  1287.880005  1287.880005   \n",
       "1  1286.770020  14070000  1286.770020  1286.770020  1286.770020  1286.770020   \n",
       "2  1277.719971  10980000  1277.719971  1277.719971  1277.719971  1277.719971   \n",
       "3  1285.229980  13800000  1285.535986  1285.229980  1285.229980  1285.229980   \n",
       "4  1280.589966  14610000  1284.077979  1280.589966  1280.589966  1280.589966   \n",
       "\n",
       "        sma125       sma200  \n",
       "0  1287.880005  1287.880005  \n",
       "1  1286.770020  1286.770020  \n",
       "2  1277.719971  1277.719971  \n",
       "3  1285.229980  1285.229980  \n",
       "4  1280.589966  1280.589966  "
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "# df_djia_dc.iloc[0]['Date']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "event_col = ['Open(Nikkei)', 'High(Nikkei)', 'Low(Nikkei)', 'Close(Nikkei)',\n",
    "            'Open(DJIA)', 'High(DJIA)', 'Low(DJIA)', 'Close(DJIA)'\n",
    "            ]\n",
    "total_col = df.columns\n",
    "for col in total_col:\n",
    "    if col not in event_col:\n",
    "        df = df.drop(col, axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "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>Open(Nikkei)</th>\n",
       "      <th>High(Nikkei)</th>\n",
       "      <th>Low(Nikkei)</th>\n",
       "      <th>Close(Nikkei)</th>\n",
       "      <th>Open(DJIA)</th>\n",
       "      <th>High(DJIA)</th>\n",
       "      <th>Low(DJIA)</th>\n",
       "      <th>Close(DJIA)</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>6906</th>\n",
       "      <td>22619.769531</td>\n",
       "      <td>22648.810547</td>\n",
       "      <td>22457.890625</td>\n",
       "      <td>22625.380859</td>\n",
       "      <td>26893.92969</td>\n",
       "      <td>26931.77930</td>\n",
       "      <td>26714.33984</td>\n",
       "      <td>26805.52930</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6907</th>\n",
       "      <td>22725.439453</td>\n",
       "      <td>22780.990234</td>\n",
       "      <td>22704.330078</td>\n",
       "      <td>22750.599609</td>\n",
       "      <td>26789.60938</td>\n",
       "      <td>27015.36914</td>\n",
       "      <td>26765.67969</td>\n",
       "      <td>26958.06055</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6908</th>\n",
       "      <td>22854.439453</td>\n",
       "      <td>22896.220703</td>\n",
       "      <td>22830.570313</td>\n",
       "      <td>22867.269531</td>\n",
       "      <td>27061.07031</td>\n",
       "      <td>27165.93945</td>\n",
       "      <td>27039.75977</td>\n",
       "      <td>27071.46094</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6909</th>\n",
       "      <td>22950.789063</td>\n",
       "      <td>23008.429688</td>\n",
       "      <td>22935.349609</td>\n",
       "      <td>22974.130859</td>\n",
       "      <td>27110.71094</td>\n",
       "      <td>27204.35938</td>\n",
       "      <td>26999.64063</td>\n",
       "      <td>27186.68945</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6910</th>\n",
       "      <td>22953.169922</td>\n",
       "      <td>22961.230469</td>\n",
       "      <td>22827.929688</td>\n",
       "      <td>22843.119141</td>\n",
       "      <td>27188.36914</td>\n",
       "      <td>27188.36914</td>\n",
       "      <td>26918.28906</td>\n",
       "      <td>27046.23047</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      Open(Nikkei)  High(Nikkei)   Low(Nikkei)  Close(Nikkei)   Open(DJIA)  \\\n",
       "6906  22619.769531  22648.810547  22457.890625   22625.380859  26893.92969   \n",
       "6907  22725.439453  22780.990234  22704.330078   22750.599609  26789.60938   \n",
       "6908  22854.439453  22896.220703  22830.570313   22867.269531  27061.07031   \n",
       "6909  22950.789063  23008.429688  22935.349609   22974.130859  27110.71094   \n",
       "6910  22953.169922  22961.230469  22827.929688   22843.119141  27188.36914   \n",
       "\n",
       "       High(DJIA)    Low(DJIA)  Close(DJIA)  \n",
       "6906  26931.77930  26714.33984  26805.52930  \n",
       "6907  27015.36914  26765.67969  26958.06055  \n",
       "6908  27165.93945  27039.75977  27071.46094  \n",
       "6909  27204.35938  26999.64063  27186.68945  \n",
       "6910  27188.36914  26918.28906  27046.23047  "
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.tail()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "def normalize_data(df, event_col):\n",
    "    min_max_scaler = sklearn.preprocessing.MinMaxScaler()\n",
    "    for col in event_col:\n",
    "        if col != 'Date':\n",
    "            df[col] = min_max_scaler.fit_transform(df[col].to_numpy().reshape(-1, 1))\n",
    "    return df\n",
    "\n",
    "def load_data(stock, seq_len):\n",
    "    data_raw = stock.as_matrix()\n",
    "    data = list()\n",
    "    for index in range(len(data_raw) - seq_len):\n",
    "        data.append(data_raw[index: index+seq_len])\n",
    "    data = np.array(data)\n",
    "    val_set_size = int(np.round(val_set_size_percentage/100*data.shape[0]))\n",
    "    test_set_size = int(np.round(test_set_size_percentage/100*data.shape[0]))\n",
    "    train_set_size = data.shape[0] - (val_set_size + test_set_size)\n",
    "    \n",
    "    x_train = data[:train_set_size, :-1, :]\n",
    "    y_train = data[:train_set_size, -1, :]\n",
    "    \n",
    "    x_val = data[train_set_size:train_set_size + val_set_size, :-1, :]\n",
    "    y_val = data[train_set_size:train_set_size + val_set_size, -1, :]\n",
    "    \n",
    "    x_test = data[train_set_size+val_set_size:,:-1,:]\n",
    "    y_test = data[train_set_size+val_set_size:,-1,:]\n",
    "    \n",
    "    return [x_train, y_train, x_val, y_val, x_test, y_test]\n",
    "    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "x_train.shape =  (5513, 19, 8)\n",
      "y_train.shape =  (5513, 8)\n",
      "x_val.shape =  (689, 19, 8)\n",
      "y_val.shape =  (689, 8)\n",
      "x_test.shape =  (689, 19, 8)\n",
      "y_test.shape =  (689, 8)\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/usr/local/lib/python3.6/site-packages/ipykernel_launcher.py:9: FutureWarning: Method .as_matrix will be removed in a future version. Use .values instead.\n",
      "  if __name__ == '__main__':\n"
     ]
    }
   ],
   "source": [
    "# parameter for preprocessing #\n",
    "\n",
    "val_set_size_percentage = 10\n",
    "test_set_size_percentage = 10\n",
    "seq_len = 20\n",
    "\n",
    "#*****************************#\n",
    "\n",
    "# normalize index\n",
    "df_norm = normalize_data(df, event_col)\n",
    "\n",
    "# split train, val, test data\n",
    "\n",
    "x_train, y_train, x_val, y_val, x_test, y_test = load_data(df_norm, seq_len)\n",
    "\n",
    "print('x_train.shape = ', x_train.shape)\n",
    "print('y_train.shape = ', y_train.shape)\n",
    "print('x_val.shape = ', x_val.shape)\n",
    "print('y_val.shape = ', y_val.shape)\n",
    "print('x_test.shape = ', x_test.shape)\n",
    "print('y_test.shape = ', y_test.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1080x720 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# plot graph before train\n",
    "\n",
    "# !set color in graph\n",
    "# color_palette = ...\n",
    "plt.figure(figsize=(15, 10))\n",
    "plt.grid()\n",
    "color_palette = plt.get_cmap('Set1')\n",
    "for i, col in enumerate(event_col):\n",
    "    plt.plot(df_norm[col], color=color_palette(i), label=col)\n",
    "plt.title('Stock price')\n",
    "plt.xlabel('Time [days]')\n",
    "plt.ylabel('Normalized price / volume')\n",
    "plt.legend()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [],
   "source": [
    "# hyperparameter \n",
    "batch_size = 1024\n",
    "epochs = 300\n",
    "\n",
    "# set up callback_list\n",
    "weight_path_model = \"saved_model/djia_nk_test.h5\"\n",
    "tensorboard_path = 'Graph/djia_support_nikkei_test'\n",
    "callbacks_list_model = [\n",
    "    TensorBoard(log_dir=tensorboard_path),\n",
    "    ModelCheckpoint(\n",
    "            weight_path_model,\n",
    "            save_best_only=True,\n",
    "            save_weights_only=True,\n",
    "            monitor='val_loss',\n",
    "            mode='min',\n",
    "            verbose=2\n",
    "        ),\n",
    "    ReduceLROnPlateau(monitor='val_loss', factor=0.8, patience=4, min_lr=1e-9)\n",
    "]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Model: \"model\"\n",
      "_________________________________________________________________\n",
      "Layer (type)                 Output Shape              Param #   \n",
      "=================================================================\n",
      "input_1 (InputLayer)         [(None, 19, 8)]           0         \n",
      "_________________________________________________________________\n",
      "gru (GRU)                    (None, 19, 256)           204288    \n",
      "_________________________________________________________________\n",
      "time_distributed (TimeDistri (None, 19, 256)           0         \n",
      "_________________________________________________________________\n",
      "time_distributed_1 (TimeDist (None, 19, 256)           1024      \n",
      "_________________________________________________________________\n",
      "gru_1 (GRU)                  (None, 128)               148224    \n",
      "_________________________________________________________________\n",
      "leaky_re_lu_1 (LeakyReLU)    (None, 128)               0         \n",
      "_________________________________________________________________\n",
      "batch_normalization_1 (Batch (None, 128)               512       \n",
      "_________________________________________________________________\n",
      "dense (Dense)                (None, 8)                 1032      \n",
      "=================================================================\n",
      "Total params: 355,080\n",
      "Trainable params: 354,312\n",
      "Non-trainable params: 768\n",
      "_________________________________________________________________\n"
     ]
    }
   ],
   "source": [
    "K.clear_session()\n",
    "\n",
    "def get_bi_gru():\n",
    "    \n",
    "    input1 = Input(shape=(19,8,))\n",
    "    x = GRU(256, return_sequences=True)(input1)\n",
    "    x = TimeDistributed(LeakyReLU())(x)\n",
    "    x = TimeDistributed(BatchNormalization())(x)\n",
    "    x = GRU(128, dropout=0.5)(x)\n",
    "    x =(LeakyReLU())(x)\n",
    "    x = (BatchNormalization())(x)\n",
    "    out = Dense(8)(x)\n",
    "\n",
    "    \n",
    "    \n",
    "    model = Model(inputs=input1, outputs=out)\n",
    "    model.compile(optimizer=Adam(lr=1e-4, decay=1e-4),\n",
    "                loss='mse',\n",
    "                metrics=['mse'])   \n",
    "    \n",
    "    return model\n",
    "\n",
    "model = get_bi_gru()\n",
    "model.summary()\n",
    "    "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Experiment and Result"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Train on 5513 samples, validate on 689 samples\n",
      "Epoch 1/300\n",
      "5120/5513 [==========================>...] - ETA: 1s - loss: 1.3406 - mse: 1.3406\n",
      "Epoch 00001: val_loss did not improve from 0.17996\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 1.3162 - mse: 1.3162 - val_loss: 0.2082 - val_mse: 0.2082\n",
      "Epoch 2/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.8645 - mse: 0.8645\n",
      "Epoch 00002: val_loss did not improve from 0.17996\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.8605 - mse: 0.8605 - val_loss: 0.2036 - val_mse: 0.2036\n",
      "Epoch 3/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.7257 - mse: 0.7257\n",
      "Epoch 00003: val_loss did not improve from 0.17996\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.7196 - mse: 0.7196 - val_loss: 0.2016 - val_mse: 0.2016\n",
      "Epoch 4/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.5933 - mse: 0.5933\n",
      "Epoch 00004: val_loss did not improve from 0.17996\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.5887 - mse: 0.5887 - val_loss: 0.1996 - val_mse: 0.1996\n",
      "Epoch 5/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.5017 - mse: 0.5017\n",
      "Epoch 00005: val_loss did not improve from 0.17996\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.4986 - mse: 0.4986 - val_loss: 0.1952 - val_mse: 0.1952\n",
      "Epoch 6/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.4277 - mse: 0.4277\n",
      "Epoch 00006: val_loss did not improve from 0.17996\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.4249 - mse: 0.4249 - val_loss: 0.1885 - val_mse: 0.1885\n",
      "Epoch 7/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.3752 - mse: 0.3752\n",
      "Epoch 00007: val_loss did not improve from 0.17996\n",
      "5513/5513 [==============================] - 6s 1ms/sample - loss: 0.3740 - mse: 0.3740 - val_loss: 0.1820 - val_mse: 0.1820\n",
      "Epoch 8/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.3288 - mse: 0.3288\n",
      "Epoch 00008: val_loss improved from 0.17996 to 0.17654, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.3275 - mse: 0.3275 - val_loss: 0.1765 - val_mse: 0.1765\n",
      "Epoch 9/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.2900 - mse: 0.2900\n",
      "Epoch 00009: val_loss improved from 0.17654 to 0.17147, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.2891 - mse: 0.2891 - val_loss: 0.1715 - val_mse: 0.1715\n",
      "Epoch 10/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.2628 - mse: 0.2628\n",
      "Epoch 00010: val_loss improved from 0.17147 to 0.16631, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.2624 - mse: 0.2624 - val_loss: 0.1663 - val_mse: 0.1663\n",
      "Epoch 11/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.2362 - mse: 0.2362\n",
      "Epoch 00011: val_loss improved from 0.16631 to 0.16045, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.2351 - mse: 0.2351 - val_loss: 0.1605 - val_mse: 0.1605\n",
      "Epoch 12/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.2156 - mse: 0.2156\n",
      "Epoch 00012: val_loss improved from 0.16045 to 0.15459, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.2150 - mse: 0.2150 - val_loss: 0.1546 - val_mse: 0.1546\n",
      "Epoch 13/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.1989 - mse: 0.1989\n",
      "Epoch 00013: val_loss improved from 0.15459 to 0.14910, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 8s 1ms/sample - loss: 0.1983 - mse: 0.1983 - val_loss: 0.1491 - val_mse: 0.1491\n",
      "Epoch 14/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.1833 - mse: 0.1833\n",
      "Epoch 00014: val_loss improved from 0.14910 to 0.14387, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.1833 - mse: 0.1833 - val_loss: 0.1439 - val_mse: 0.1439\n",
      "Epoch 15/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.1714 - mse: 0.1714\n",
      "Epoch 00015: val_loss improved from 0.14387 to 0.13912, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.1710 - mse: 0.1710 - val_loss: 0.1391 - val_mse: 0.1391\n",
      "Epoch 16/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.1598 - mse: 0.1598\n",
      "Epoch 00016: val_loss improved from 0.13912 to 0.13447, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.1592 - mse: 0.1592 - val_loss: 0.1345 - val_mse: 0.1345\n",
      "Epoch 17/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.1503 - mse: 0.1503\n",
      "Epoch 00017: val_loss improved from 0.13447 to 0.13013, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.1496 - mse: 0.1496 - val_loss: 0.1301 - val_mse: 0.1301\n",
      "Epoch 18/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.1429 - mse: 0.1429\n",
      "Epoch 00018: val_loss improved from 0.13013 to 0.12548, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 6s 1ms/sample - loss: 0.1426 - mse: 0.1426 - val_loss: 0.1255 - val_mse: 0.1255\n",
      "Epoch 19/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.1350 - mse: 0.1350\n",
      "Epoch 00019: val_loss improved from 0.12548 to 0.12085, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.1347 - mse: 0.1347 - val_loss: 0.1208 - val_mse: 0.1208\n",
      "Epoch 20/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.1262 - mse: 0.1262\n",
      "Epoch 00020: val_loss improved from 0.12085 to 0.11699, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.1263 - mse: 0.1263 - val_loss: 0.1170 - val_mse: 0.1170\n",
      "Epoch 21/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.1207 - mse: 0.1207\n",
      "Epoch 00021: val_loss improved from 0.11699 to 0.11349, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 6s 1ms/sample - loss: 0.1208 - mse: 0.1208 - val_loss: 0.1135 - val_mse: 0.1135\n",
      "Epoch 22/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.1139 - mse: 0.1139\n",
      "Epoch 00022: val_loss improved from 0.11349 to 0.10965, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 8s 2ms/sample - loss: 0.1140 - mse: 0.1140 - val_loss: 0.1097 - val_mse: 0.1097\n",
      "Epoch 23/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.1095 - mse: 0.1095\n",
      "Epoch 00023: val_loss improved from 0.10965 to 0.10554, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.1092 - mse: 0.1092 - val_loss: 0.1055 - val_mse: 0.1055\n",
      "Epoch 24/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.1037 - mse: 0.1037\n",
      "Epoch 00024: val_loss improved from 0.10554 to 0.10188, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.1039 - mse: 0.1039 - val_loss: 0.1019 - val_mse: 0.1019\n",
      "Epoch 25/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0999 - mse: 0.0999\n",
      "Epoch 00025: val_loss improved from 0.10188 to 0.09886, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 8s 1ms/sample - loss: 0.0996 - mse: 0.0996 - val_loss: 0.0989 - val_mse: 0.0989\n",
      "Epoch 26/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0959 - mse: 0.0959\n",
      "Epoch 00026: val_loss improved from 0.09886 to 0.09571, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0957 - mse: 0.0957 - val_loss: 0.0957 - val_mse: 0.0957\n",
      "Epoch 27/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0914 - mse: 0.0914\n",
      "Epoch 00027: val_loss improved from 0.09571 to 0.09269, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0915 - mse: 0.0915 - val_loss: 0.0927 - val_mse: 0.0927\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 28/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0878 - mse: 0.0878\n",
      "Epoch 00028: val_loss improved from 0.09269 to 0.08992, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 8s 1ms/sample - loss: 0.0874 - mse: 0.0874 - val_loss: 0.0899 - val_mse: 0.0899\n",
      "Epoch 29/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0833 - mse: 0.0833\n",
      "Epoch 00029: val_loss improved from 0.08992 to 0.08750, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0831 - mse: 0.0831 - val_loss: 0.0875 - val_mse: 0.0875\n",
      "Epoch 30/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0812 - mse: 0.0812\n",
      "Epoch 00030: val_loss improved from 0.08750 to 0.08467, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0811 - mse: 0.0811 - val_loss: 0.0847 - val_mse: 0.0847\n",
      "Epoch 31/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0776 - mse: 0.0776\n",
      "Epoch 00031: val_loss improved from 0.08467 to 0.08216, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 8s 1ms/sample - loss: 0.0777 - mse: 0.0777 - val_loss: 0.0822 - val_mse: 0.0822\n",
      "Epoch 32/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0746 - mse: 0.0746\n",
      "Epoch 00032: val_loss improved from 0.08216 to 0.08036, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 6s 1ms/sample - loss: 0.0745 - mse: 0.0745 - val_loss: 0.0804 - val_mse: 0.0804\n",
      "Epoch 33/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0719 - mse: 0.0719\n",
      "Epoch 00033: val_loss improved from 0.08036 to 0.07916, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 6s 1ms/sample - loss: 0.0718 - mse: 0.0718 - val_loss: 0.0792 - val_mse: 0.0792\n",
      "Epoch 34/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0691 - mse: 0.0691\n",
      "Epoch 00034: val_loss improved from 0.07916 to 0.07744, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 6s 1ms/sample - loss: 0.0691 - mse: 0.0691 - val_loss: 0.0774 - val_mse: 0.0774\n",
      "Epoch 35/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0671 - mse: 0.0671\n",
      "Epoch 00035: val_loss improved from 0.07744 to 0.07540, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0668 - mse: 0.0668 - val_loss: 0.0754 - val_mse: 0.0754\n",
      "Epoch 36/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0641 - mse: 0.0641\n",
      "Epoch 00036: val_loss improved from 0.07540 to 0.07349, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0640 - mse: 0.0640 - val_loss: 0.0735 - val_mse: 0.0735\n",
      "Epoch 37/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0619 - mse: 0.0619\n",
      "Epoch 00037: val_loss improved from 0.07349 to 0.07185, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.0620 - mse: 0.0620 - val_loss: 0.0719 - val_mse: 0.0719\n",
      "Epoch 38/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0597 - mse: 0.0597\n",
      "Epoch 00038: val_loss improved from 0.07185 to 0.07093, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 8s 1ms/sample - loss: 0.0596 - mse: 0.0596 - val_loss: 0.0709 - val_mse: 0.0709\n",
      "Epoch 39/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0578 - mse: 0.0578\n",
      "Epoch 00039: val_loss improved from 0.07093 to 0.06971, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0580 - mse: 0.0580 - val_loss: 0.0697 - val_mse: 0.0697\n",
      "Epoch 40/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0550 - mse: 0.0550\n",
      "Epoch 00040: val_loss improved from 0.06971 to 0.06812, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0550 - mse: 0.0550 - val_loss: 0.0681 - val_mse: 0.0681\n",
      "Epoch 41/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0535 - mse: 0.0535\n",
      "Epoch 00041: val_loss improved from 0.06812 to 0.06673, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0535 - mse: 0.0535 - val_loss: 0.0667 - val_mse: 0.0667\n",
      "Epoch 42/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0521 - mse: 0.0521\n",
      "Epoch 00042: val_loss improved from 0.06673 to 0.06528, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 8s 1ms/sample - loss: 0.0522 - mse: 0.0522 - val_loss: 0.0653 - val_mse: 0.0653\n",
      "Epoch 43/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0497 - mse: 0.0497\n",
      "Epoch 00043: val_loss improved from 0.06528 to 0.06453, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 8s 1ms/sample - loss: 0.0498 - mse: 0.0498 - val_loss: 0.0645 - val_mse: 0.0645\n",
      "Epoch 44/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0487 - mse: 0.0487\n",
      "Epoch 00044: val_loss improved from 0.06453 to 0.06375, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 8s 1ms/sample - loss: 0.0486 - mse: 0.0486 - val_loss: 0.0638 - val_mse: 0.0638\n",
      "Epoch 45/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0469 - mse: 0.0469\n",
      "Epoch 00045: val_loss improved from 0.06375 to 0.06232, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0467 - mse: 0.0467 - val_loss: 0.0623 - val_mse: 0.0623\n",
      "Epoch 46/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0451 - mse: 0.0451\n",
      "Epoch 00046: val_loss improved from 0.06232 to 0.06107, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0450 - mse: 0.0450 - val_loss: 0.0611 - val_mse: 0.0611\n",
      "Epoch 47/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0441 - mse: 0.0441\n",
      "Epoch 00047: val_loss improved from 0.06107 to 0.06032, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 8s 1ms/sample - loss: 0.0439 - mse: 0.0439 - val_loss: 0.0603 - val_mse: 0.0603\n",
      "Epoch 48/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0422 - mse: 0.0422\n",
      "Epoch 00048: val_loss improved from 0.06032 to 0.05953, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0422 - mse: 0.0422 - val_loss: 0.0595 - val_mse: 0.0595\n",
      "Epoch 49/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0412 - mse: 0.0412\n",
      "Epoch 00049: val_loss improved from 0.05953 to 0.05908, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 8s 1ms/sample - loss: 0.0411 - mse: 0.0411 - val_loss: 0.0591 - val_mse: 0.0591\n",
      "Epoch 50/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0395 - mse: 0.0395\n",
      "Epoch 00050: val_loss improved from 0.05908 to 0.05820, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0397 - mse: 0.0397 - val_loss: 0.0582 - val_mse: 0.0582\n",
      "Epoch 51/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0384 - mse: 0.0384\n",
      "Epoch 00051: val_loss improved from 0.05820 to 0.05672, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0383 - mse: 0.0383 - val_loss: 0.0567 - val_mse: 0.0567\n",
      "Epoch 52/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0370 - mse: 0.0370\n",
      "Epoch 00052: val_loss improved from 0.05672 to 0.05600, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0369 - mse: 0.0369 - val_loss: 0.0560 - val_mse: 0.0560\n",
      "Epoch 53/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0363 - mse: 0.0363\n",
      "Epoch 00053: val_loss improved from 0.05600 to 0.05582, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0363 - mse: 0.0363 - val_loss: 0.0558 - val_mse: 0.0558\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 54/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0347 - mse: 0.0347\n",
      "Epoch 00054: val_loss improved from 0.05582 to 0.05535, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0346 - mse: 0.0346 - val_loss: 0.0553 - val_mse: 0.0553\n",
      "Epoch 55/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0338 - mse: 0.0338\n",
      "Epoch 00055: val_loss improved from 0.05535 to 0.05467, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.0337 - mse: 0.0337 - val_loss: 0.0547 - val_mse: 0.0547\n",
      "Epoch 56/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0327 - mse: 0.0327\n",
      "Epoch 00056: val_loss improved from 0.05467 to 0.05312, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.0327 - mse: 0.0327 - val_loss: 0.0531 - val_mse: 0.0531\n",
      "Epoch 57/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0321 - mse: 0.0321\n",
      "Epoch 00057: val_loss improved from 0.05312 to 0.05155, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.0320 - mse: 0.0320 - val_loss: 0.0515 - val_mse: 0.0515\n",
      "Epoch 58/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0307 - mse: 0.0307\n",
      "Epoch 00058: val_loss improved from 0.05155 to 0.05131, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0307 - mse: 0.0307 - val_loss: 0.0513 - val_mse: 0.0513\n",
      "Epoch 59/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0297 - mse: 0.0297\n",
      "Epoch 00059: val_loss did not improve from 0.05131\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0298 - mse: 0.0298 - val_loss: 0.0516 - val_mse: 0.0516\n",
      "Epoch 60/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0292 - mse: 0.0292\n",
      "Epoch 00060: val_loss improved from 0.05131 to 0.05052, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0292 - mse: 0.0292 - val_loss: 0.0505 - val_mse: 0.0505\n",
      "Epoch 61/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0283 - mse: 0.0283\n",
      "Epoch 00061: val_loss improved from 0.05052 to 0.04931, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 8s 1ms/sample - loss: 0.0284 - mse: 0.0284 - val_loss: 0.0493 - val_mse: 0.0493\n",
      "Epoch 62/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0271 - mse: 0.0271\n",
      "Epoch 00062: val_loss improved from 0.04931 to 0.04857, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0271 - mse: 0.0271 - val_loss: 0.0486 - val_mse: 0.0486\n",
      "Epoch 63/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0263 - mse: 0.0263\n",
      "Epoch 00063: val_loss did not improve from 0.04857\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0263 - mse: 0.0263 - val_loss: 0.0487 - val_mse: 0.0487\n",
      "Epoch 64/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0259 - mse: 0.0259\n",
      "Epoch 00064: val_loss improved from 0.04857 to 0.04826, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 8s 1ms/sample - loss: 0.0259 - mse: 0.0259 - val_loss: 0.0483 - val_mse: 0.0483\n",
      "Epoch 65/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0248 - mse: 0.0248\n",
      "Epoch 00065: val_loss improved from 0.04826 to 0.04755, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 8s 2ms/sample - loss: 0.0249 - mse: 0.0249 - val_loss: 0.0476 - val_mse: 0.0476\n",
      "Epoch 66/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0241 - mse: 0.0241\n",
      "Epoch 00066: val_loss improved from 0.04755 to 0.04609, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0241 - mse: 0.0241 - val_loss: 0.0461 - val_mse: 0.0461\n",
      "Epoch 67/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0231 - mse: 0.0231\n",
      "Epoch 00067: val_loss improved from 0.04609 to 0.04527, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0233 - mse: 0.0233 - val_loss: 0.0453 - val_mse: 0.0453\n",
      "Epoch 68/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0226 - mse: 0.0226\n",
      "Epoch 00068: val_loss improved from 0.04527 to 0.04466, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0227 - mse: 0.0227 - val_loss: 0.0447 - val_mse: 0.0447\n",
      "Epoch 69/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0221 - mse: 0.0221\n",
      "Epoch 00069: val_loss improved from 0.04466 to 0.04303, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0220 - mse: 0.0220 - val_loss: 0.0430 - val_mse: 0.0430\n",
      "Epoch 70/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0215 - mse: 0.0215\n",
      "Epoch 00070: val_loss improved from 0.04303 to 0.04217, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 8s 1ms/sample - loss: 0.0214 - mse: 0.0214 - val_loss: 0.0422 - val_mse: 0.0422\n",
      "Epoch 71/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0205 - mse: 0.0205\n",
      "Epoch 00071: val_loss did not improve from 0.04217\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0205 - mse: 0.0205 - val_loss: 0.0422 - val_mse: 0.0422\n",
      "Epoch 72/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0201 - mse: 0.0201\n",
      "Epoch 00072: val_loss improved from 0.04217 to 0.04203, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0201 - mse: 0.0201 - val_loss: 0.0420 - val_mse: 0.0420\n",
      "Epoch 73/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0197 - mse: 0.0197\n",
      "Epoch 00073: val_loss improved from 0.04203 to 0.04102, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0198 - mse: 0.0198 - val_loss: 0.0410 - val_mse: 0.0410\n",
      "Epoch 74/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0190 - mse: 0.0190\n",
      "Epoch 00074: val_loss improved from 0.04102 to 0.03976, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0190 - mse: 0.0190 - val_loss: 0.0398 - val_mse: 0.0398\n",
      "Epoch 75/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0185 - mse: 0.0185\n",
      "Epoch 00075: val_loss improved from 0.03976 to 0.03868, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0184 - mse: 0.0184 - val_loss: 0.0387 - val_mse: 0.0387\n",
      "Epoch 76/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0179 - mse: 0.0179\n",
      "Epoch 00076: val_loss improved from 0.03868 to 0.03846, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 8s 1ms/sample - loss: 0.0179 - mse: 0.0179 - val_loss: 0.0385 - val_mse: 0.0385\n",
      "Epoch 77/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0175 - mse: 0.0175\n",
      "Epoch 00077: val_loss improved from 0.03846 to 0.03760, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 11s 2ms/sample - loss: 0.0175 - mse: 0.0175 - val_loss: 0.0376 - val_mse: 0.0376\n",
      "Epoch 78/300\n",
      "5120/5513 [==========================>...] - ETA: 1s - loss: 0.0170 - mse: 0.0170\n",
      "Epoch 00078: val_loss improved from 0.03760 to 0.03688, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.0170 - mse: 0.0170 - val_loss: 0.0369 - val_mse: 0.0369\n",
      "Epoch 79/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0163 - mse: 0.0163\n",
      "Epoch 00079: val_loss improved from 0.03688 to 0.03618, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 14s 3ms/sample - loss: 0.0163 - mse: 0.0163 - val_loss: 0.0362 - val_mse: 0.0362\n",
      "Epoch 80/300\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "5120/5513 [==========================>...] - ETA: 1s - loss: 0.0160 - mse: 0.0160\n",
      "Epoch 00080: val_loss improved from 0.03618 to 0.03554, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.0161 - mse: 0.0161 - val_loss: 0.0355 - val_mse: 0.0355\n",
      "Epoch 81/300\n",
      "5120/5513 [==========================>...] - ETA: 1s - loss: 0.0155 - mse: 0.0155\n",
      "Epoch 00081: val_loss improved from 0.03554 to 0.03535, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 16s 3ms/sample - loss: 0.0155 - mse: 0.0155 - val_loss: 0.0353 - val_mse: 0.0353\n",
      "Epoch 82/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0149 - mse: 0.0149\n",
      "Epoch 00082: val_loss improved from 0.03535 to 0.03436, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 11s 2ms/sample - loss: 0.0149 - mse: 0.0149 - val_loss: 0.0344 - val_mse: 0.0344\n",
      "Epoch 83/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0147 - mse: 0.0147\n",
      "Epoch 00083: val_loss improved from 0.03436 to 0.03292, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 8s 1ms/sample - loss: 0.0147 - mse: 0.0147 - val_loss: 0.0329 - val_mse: 0.0329\n",
      "Epoch 84/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0144 - mse: 0.0144\n",
      "Epoch 00084: val_loss improved from 0.03292 to 0.03202, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0144 - mse: 0.0144 - val_loss: 0.0320 - val_mse: 0.0320\n",
      "Epoch 85/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0137 - mse: 0.0137\n",
      "Epoch 00085: val_loss improved from 0.03202 to 0.03160, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.0137 - mse: 0.0137 - val_loss: 0.0316 - val_mse: 0.0316\n",
      "Epoch 86/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0137 - mse: 0.0137\n",
      "Epoch 00086: val_loss improved from 0.03160 to 0.03099, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0137 - mse: 0.0137 - val_loss: 0.0310 - val_mse: 0.0310\n",
      "Epoch 87/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0134 - mse: 0.0134\n",
      "Epoch 00087: val_loss improved from 0.03099 to 0.02998, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0133 - mse: 0.0133 - val_loss: 0.0300 - val_mse: 0.0300\n",
      "Epoch 88/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0131 - mse: 0.0131\n",
      "Epoch 00088: val_loss improved from 0.02998 to 0.02909, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 6s 1ms/sample - loss: 0.0130 - mse: 0.0130 - val_loss: 0.0291 - val_mse: 0.0291\n",
      "Epoch 89/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0127 - mse: 0.0127\n",
      "Epoch 00089: val_loss improved from 0.02909 to 0.02851, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0127 - mse: 0.0127 - val_loss: 0.0285 - val_mse: 0.0285\n",
      "Epoch 90/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0122 - mse: 0.0122\n",
      "Epoch 00090: val_loss improved from 0.02851 to 0.02796, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0122 - mse: 0.0122 - val_loss: 0.0280 - val_mse: 0.0280\n",
      "Epoch 91/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0120 - mse: 0.0120\n",
      "Epoch 00091: val_loss improved from 0.02796 to 0.02741, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0120 - mse: 0.0120 - val_loss: 0.0274 - val_mse: 0.0274\n",
      "Epoch 92/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0115 - mse: 0.0115\n",
      "Epoch 00092: val_loss improved from 0.02741 to 0.02645, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0116 - mse: 0.0116 - val_loss: 0.0264 - val_mse: 0.0264\n",
      "Epoch 93/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0114 - mse: 0.0114\n",
      "Epoch 00093: val_loss improved from 0.02645 to 0.02514, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0114 - mse: 0.0114 - val_loss: 0.0251 - val_mse: 0.0251\n",
      "Epoch 94/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0110 - mse: 0.0110\n",
      "Epoch 00094: val_loss improved from 0.02514 to 0.02397, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0110 - mse: 0.0110 - val_loss: 0.0240 - val_mse: 0.0240\n",
      "Epoch 95/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0107 - mse: 0.0107\n",
      "Epoch 00095: val_loss improved from 0.02397 to 0.02362, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0108 - mse: 0.0108 - val_loss: 0.0236 - val_mse: 0.0236\n",
      "Epoch 96/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0105 - mse: 0.0105\n",
      "Epoch 00096: val_loss improved from 0.02362 to 0.02357, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.0105 - mse: 0.0105 - val_loss: 0.0236 - val_mse: 0.0236\n",
      "Epoch 97/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0103 - mse: 0.0103\n",
      "Epoch 00097: val_loss improved from 0.02357 to 0.02265, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 13s 2ms/sample - loss: 0.0103 - mse: 0.0103 - val_loss: 0.0226 - val_mse: 0.0226\n",
      "Epoch 98/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0099 - mse: 0.0099\n",
      "Epoch 00098: val_loss improved from 0.02265 to 0.02218, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 8s 1ms/sample - loss: 0.0098 - mse: 0.0098 - val_loss: 0.0222 - val_mse: 0.0222\n",
      "Epoch 99/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0097 - mse: 0.0097\n",
      "Epoch 00099: val_loss improved from 0.02218 to 0.02168, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 12s 2ms/sample - loss: 0.0097 - mse: 0.0097 - val_loss: 0.0217 - val_mse: 0.0217\n",
      "Epoch 100/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0095 - mse: 0.0095\n",
      "Epoch 00100: val_loss improved from 0.02168 to 0.02111, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0095 - mse: 0.0095 - val_loss: 0.0211 - val_mse: 0.0211\n",
      "Epoch 101/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0093 - mse: 0.0093\n",
      "Epoch 00101: val_loss improved from 0.02111 to 0.02055, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0093 - mse: 0.0093 - val_loss: 0.0206 - val_mse: 0.0206\n",
      "Epoch 102/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0090 - mse: 0.0090\n",
      "Epoch 00102: val_loss improved from 0.02055 to 0.02015, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0090 - mse: 0.0090 - val_loss: 0.0202 - val_mse: 0.0202\n",
      "Epoch 103/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0088 - mse: 0.0088\n",
      "Epoch 00103: val_loss improved from 0.02015 to 0.01946, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0088 - mse: 0.0088 - val_loss: 0.0195 - val_mse: 0.0195\n",
      "Epoch 104/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0086 - mse: 0.0086\n",
      "Epoch 00104: val_loss improved from 0.01946 to 0.01929, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0086 - mse: 0.0086 - val_loss: 0.0193 - val_mse: 0.0193\n",
      "Epoch 105/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0084 - mse: 0.0084\n",
      "Epoch 00105: val_loss improved from 0.01929 to 0.01910, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0084 - mse: 0.0084 - val_loss: 0.0191 - val_mse: 0.0191\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 106/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0085 - mse: 0.0085\n",
      "Epoch 00106: val_loss improved from 0.01910 to 0.01854, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0085 - mse: 0.0085 - val_loss: 0.0185 - val_mse: 0.0185\n",
      "Epoch 107/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0082 - mse: 0.0082\n",
      "Epoch 00107: val_loss improved from 0.01854 to 0.01776, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 11s 2ms/sample - loss: 0.0082 - mse: 0.0082 - val_loss: 0.0178 - val_mse: 0.0178\n",
      "Epoch 108/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0079 - mse: 0.0079\n",
      "Epoch 00108: val_loss improved from 0.01776 to 0.01755, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 8s 1ms/sample - loss: 0.0080 - mse: 0.0080 - val_loss: 0.0176 - val_mse: 0.0176\n",
      "Epoch 109/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0081 - mse: 0.0081\n",
      "Epoch 00109: val_loss improved from 0.01755 to 0.01717, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0081 - mse: 0.0081 - val_loss: 0.0172 - val_mse: 0.0172\n",
      "Epoch 110/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0076 - mse: 0.0076\n",
      "Epoch 00110: val_loss improved from 0.01717 to 0.01703, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0076 - mse: 0.0076 - val_loss: 0.0170 - val_mse: 0.0170\n",
      "Epoch 111/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0075 - mse: 0.0075\n",
      "Epoch 00111: val_loss improved from 0.01703 to 0.01694, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0075 - mse: 0.0075 - val_loss: 0.0169 - val_mse: 0.0169\n",
      "Epoch 112/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0074 - mse: 0.0074\n",
      "Epoch 00112: val_loss improved from 0.01694 to 0.01643, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0074 - mse: 0.0074 - val_loss: 0.0164 - val_mse: 0.0164\n",
      "Epoch 113/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0073 - mse: 0.0073\n",
      "Epoch 00113: val_loss improved from 0.01643 to 0.01603, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.0073 - mse: 0.0073 - val_loss: 0.0160 - val_mse: 0.0160\n",
      "Epoch 114/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0072 - mse: 0.0072\n",
      "Epoch 00114: val_loss improved from 0.01603 to 0.01563, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 8s 1ms/sample - loss: 0.0072 - mse: 0.0072 - val_loss: 0.0156 - val_mse: 0.0156\n",
      "Epoch 115/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0071 - mse: 0.0071\n",
      "Epoch 00115: val_loss improved from 0.01563 to 0.01554, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0071 - mse: 0.0071 - val_loss: 0.0155 - val_mse: 0.0155\n",
      "Epoch 116/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0070 - mse: 0.0070\n",
      "Epoch 00116: val_loss improved from 0.01554 to 0.01528, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0069 - mse: 0.0069 - val_loss: 0.0153 - val_mse: 0.0153\n",
      "Epoch 117/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0067 - mse: 0.0067\n",
      "Epoch 00117: val_loss improved from 0.01528 to 0.01433, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0067 - mse: 0.0067 - val_loss: 0.0143 - val_mse: 0.0143\n",
      "Epoch 118/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0066 - mse: 0.0066\n",
      "Epoch 00118: val_loss improved from 0.01433 to 0.01417, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0066 - mse: 0.0066 - val_loss: 0.0142 - val_mse: 0.0142\n",
      "Epoch 119/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0066 - mse: 0.0066\n",
      "Epoch 00119: val_loss improved from 0.01417 to 0.01392, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0065 - mse: 0.0065 - val_loss: 0.0139 - val_mse: 0.0139\n",
      "Epoch 120/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0065 - mse: 0.0065\n",
      "Epoch 00120: val_loss improved from 0.01392 to 0.01383, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0065 - mse: 0.0065 - val_loss: 0.0138 - val_mse: 0.0138\n",
      "Epoch 121/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0063 - mse: 0.0063\n",
      "Epoch 00121: val_loss did not improve from 0.01383\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0063 - mse: 0.0063 - val_loss: 0.0139 - val_mse: 0.0139\n",
      "Epoch 122/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0061 - mse: 0.0061\n",
      "Epoch 00122: val_loss improved from 0.01383 to 0.01323, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0062 - mse: 0.0062 - val_loss: 0.0132 - val_mse: 0.0132\n",
      "Epoch 123/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0061 - mse: 0.0061\n",
      "Epoch 00123: val_loss improved from 0.01323 to 0.01295, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 8s 1ms/sample - loss: 0.0061 - mse: 0.0061 - val_loss: 0.0129 - val_mse: 0.0129\n",
      "Epoch 124/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0061 - mse: 0.0061\n",
      "Epoch 00124: val_loss improved from 0.01295 to 0.01288, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0061 - mse: 0.0061 - val_loss: 0.0129 - val_mse: 0.0129\n",
      "Epoch 125/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0059 - mse: 0.0059\n",
      "Epoch 00125: val_loss did not improve from 0.01288\n",
      "5513/5513 [==============================] - 6s 1ms/sample - loss: 0.0059 - mse: 0.0059 - val_loss: 0.0132 - val_mse: 0.0132\n",
      "Epoch 126/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0058 - mse: 0.0058\n",
      "Epoch 00126: val_loss did not improve from 0.01288\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0058 - mse: 0.0058 - val_loss: 0.0133 - val_mse: 0.0133\n",
      "Epoch 127/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0058 - mse: 0.0058\n",
      "Epoch 00127: val_loss improved from 0.01288 to 0.01243, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0057 - mse: 0.0057 - val_loss: 0.0124 - val_mse: 0.0124\n",
      "Epoch 128/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0057 - mse: 0.0057\n",
      "Epoch 00128: val_loss improved from 0.01243 to 0.01223, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0058 - mse: 0.0058 - val_loss: 0.0122 - val_mse: 0.0122\n",
      "Epoch 129/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0056 - mse: 0.0056\n",
      "Epoch 00129: val_loss did not improve from 0.01223\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0057 - mse: 0.0057 - val_loss: 0.0126 - val_mse: 0.0126\n",
      "Epoch 130/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0054 - mse: 0.0054\n",
      "Epoch 00130: val_loss did not improve from 0.01223\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0055 - mse: 0.0055 - val_loss: 0.0124 - val_mse: 0.0124\n",
      "Epoch 131/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0054 - mse: 0.0054\n",
      "Epoch 00131: val_loss improved from 0.01223 to 0.01176, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0054 - mse: 0.0054 - val_loss: 0.0118 - val_mse: 0.0118\n",
      "Epoch 132/300\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0054 - mse: 0.0054\n",
      "Epoch 00132: val_loss improved from 0.01176 to 0.01156, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0054 - mse: 0.0054 - val_loss: 0.0116 - val_mse: 0.0116\n",
      "Epoch 133/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0054 - mse: 0.0054\n",
      "Epoch 00133: val_loss did not improve from 0.01156\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0054 - mse: 0.0054 - val_loss: 0.0117 - val_mse: 0.0117\n",
      "Epoch 134/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0052 - mse: 0.0052\n",
      "Epoch 00134: val_loss improved from 0.01156 to 0.01123, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 8s 1ms/sample - loss: 0.0052 - mse: 0.0052 - val_loss: 0.0112 - val_mse: 0.0112\n",
      "Epoch 135/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0052 - mse: 0.0052\n",
      "Epoch 00135: val_loss did not improve from 0.01123\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0052 - mse: 0.0052 - val_loss: 0.0113 - val_mse: 0.0113\n",
      "Epoch 136/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0051 - mse: 0.0051\n",
      "Epoch 00136: val_loss improved from 0.01123 to 0.01111, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0051 - mse: 0.0051 - val_loss: 0.0111 - val_mse: 0.0111\n",
      "Epoch 137/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0050 - mse: 0.0050\n",
      "Epoch 00137: val_loss improved from 0.01111 to 0.01082, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0051 - mse: 0.0051 - val_loss: 0.0108 - val_mse: 0.0108\n",
      "Epoch 138/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0050 - mse: 0.0050\n",
      "Epoch 00138: val_loss improved from 0.01082 to 0.01082, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.0050 - mse: 0.0050 - val_loss: 0.0108 - val_mse: 0.0108\n",
      "Epoch 139/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0049 - mse: 0.0049\n",
      "Epoch 00139: val_loss improved from 0.01082 to 0.01075, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.0049 - mse: 0.0049 - val_loss: 0.0107 - val_mse: 0.0107\n",
      "Epoch 140/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0048 - mse: 0.0048\n",
      "Epoch 00140: val_loss improved from 0.01075 to 0.01042, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.0048 - mse: 0.0048 - val_loss: 0.0104 - val_mse: 0.0104\n",
      "Epoch 141/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0048 - mse: 0.0048\n",
      "Epoch 00141: val_loss did not improve from 0.01042\n",
      "5513/5513 [==============================] - 8s 1ms/sample - loss: 0.0048 - mse: 0.0048 - val_loss: 0.0105 - val_mse: 0.0105\n",
      "Epoch 142/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0047 - mse: 0.0047\n",
      "Epoch 00142: val_loss improved from 0.01042 to 0.01035, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0047 - mse: 0.0047 - val_loss: 0.0103 - val_mse: 0.0103\n",
      "Epoch 143/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0047 - mse: 0.0047\n",
      "Epoch 00143: val_loss improved from 0.01035 to 0.01026, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0047 - mse: 0.0047 - val_loss: 0.0103 - val_mse: 0.0103\n",
      "Epoch 144/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0046 - mse: 0.0046\n",
      "Epoch 00144: val_loss improved from 0.01026 to 0.01008, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 8s 1ms/sample - loss: 0.0047 - mse: 0.0047 - val_loss: 0.0101 - val_mse: 0.0101\n",
      "Epoch 145/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0046 - mse: 0.0046\n",
      "Epoch 00145: val_loss improved from 0.01008 to 0.00992, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0046 - mse: 0.0046 - val_loss: 0.0099 - val_mse: 0.0099\n",
      "Epoch 146/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0045 - mse: 0.0045\n",
      "Epoch 00146: val_loss improved from 0.00992 to 0.00979, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0045 - mse: 0.0045 - val_loss: 0.0098 - val_mse: 0.0098\n",
      "Epoch 147/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0045 - mse: 0.0045\n",
      "Epoch 00147: val_loss improved from 0.00979 to 0.00950, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0045 - mse: 0.0045 - val_loss: 0.0095 - val_mse: 0.0095\n",
      "Epoch 148/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0044 - mse: 0.0044\n",
      "Epoch 00148: val_loss did not improve from 0.00950\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0044 - mse: 0.0044 - val_loss: 0.0096 - val_mse: 0.0096\n",
      "Epoch 149/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0044 - mse: 0.0044\n",
      "Epoch 00149: val_loss improved from 0.00950 to 0.00927, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0044 - mse: 0.0044 - val_loss: 0.0093 - val_mse: 0.0093\n",
      "Epoch 150/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0043 - mse: 0.0043\n",
      "Epoch 00150: val_loss improved from 0.00927 to 0.00908, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0043 - mse: 0.0043 - val_loss: 0.0091 - val_mse: 0.0091\n",
      "Epoch 151/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0043 - mse: 0.0043\n",
      "Epoch 00151: val_loss improved from 0.00908 to 0.00880, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0043 - mse: 0.0043 - val_loss: 0.0088 - val_mse: 0.0088\n",
      "Epoch 152/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0042 - mse: 0.0042\n",
      "Epoch 00152: val_loss did not improve from 0.00880\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0042 - mse: 0.0042 - val_loss: 0.0090 - val_mse: 0.0090\n",
      "Epoch 153/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0042 - mse: 0.0042\n",
      "Epoch 00153: val_loss did not improve from 0.00880\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0042 - mse: 0.0042 - val_loss: 0.0088 - val_mse: 0.0088\n",
      "Epoch 154/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0041 - mse: 0.0041\n",
      "Epoch 00154: val_loss improved from 0.00880 to 0.00874, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0041 - mse: 0.0041 - val_loss: 0.0087 - val_mse: 0.0087\n",
      "Epoch 155/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0041 - mse: 0.0041\n",
      "Epoch 00155: val_loss improved from 0.00874 to 0.00861, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0041 - mse: 0.0041 - val_loss: 0.0086 - val_mse: 0.0086\n",
      "Epoch 156/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0040 - mse: 0.0040\n",
      "Epoch 00156: val_loss improved from 0.00861 to 0.00836, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0040 - mse: 0.0040 - val_loss: 0.0084 - val_mse: 0.0084\n",
      "Epoch 157/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0041 - mse: 0.0041\n",
      "Epoch 00157: val_loss did not improve from 0.00836\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0041 - mse: 0.0041 - val_loss: 0.0084 - val_mse: 0.0084\n",
      "Epoch 158/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0040 - mse: 0.0040\n",
      "Epoch 00158: val_loss improved from 0.00836 to 0.00817, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0040 - mse: 0.0040 - val_loss: 0.0082 - val_mse: 0.0082\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 159/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0041 - mse: 0.0041\n",
      "Epoch 00159: val_loss improved from 0.00817 to 0.00815, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0041 - mse: 0.0041 - val_loss: 0.0082 - val_mse: 0.0082\n",
      "Epoch 160/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0039 - mse: 0.0039\n",
      "Epoch 00160: val_loss improved from 0.00815 to 0.00801, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 6s 1ms/sample - loss: 0.0039 - mse: 0.0039 - val_loss: 0.0080 - val_mse: 0.0080\n",
      "Epoch 161/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0040 - mse: 0.0040\n",
      "Epoch 00161: val_loss improved from 0.00801 to 0.00780, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0039 - mse: 0.0039 - val_loss: 0.0078 - val_mse: 0.0078\n",
      "Epoch 162/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0038 - mse: 0.0038\n",
      "Epoch 00162: val_loss improved from 0.00780 to 0.00769, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 6s 1ms/sample - loss: 0.0038 - mse: 0.0038 - val_loss: 0.0077 - val_mse: 0.0077\n",
      "Epoch 163/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0038 - mse: 0.0038\n",
      "Epoch 00163: val_loss improved from 0.00769 to 0.00756, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 6s 1ms/sample - loss: 0.0038 - mse: 0.0038 - val_loss: 0.0076 - val_mse: 0.0076\n",
      "Epoch 164/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0038 - mse: 0.0038\n",
      "Epoch 00164: val_loss improved from 0.00756 to 0.00742, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 6s 1ms/sample - loss: 0.0038 - mse: 0.0038 - val_loss: 0.0074 - val_mse: 0.0074\n",
      "Epoch 165/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0039 - mse: 0.0039\n",
      "Epoch 00165: val_loss improved from 0.00742 to 0.00717, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0039 - mse: 0.0039 - val_loss: 0.0072 - val_mse: 0.0072\n",
      "Epoch 166/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0037 - mse: 0.0037\n",
      "Epoch 00166: val_loss improved from 0.00717 to 0.00708, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 8s 1ms/sample - loss: 0.0037 - mse: 0.0037 - val_loss: 0.0071 - val_mse: 0.0071\n",
      "Epoch 167/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0036 - mse: 0.0036\n",
      "Epoch 00167: val_loss did not improve from 0.00708\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0037 - mse: 0.0037 - val_loss: 0.0072 - val_mse: 0.0072\n",
      "Epoch 168/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0036 - mse: 0.0036\n",
      "Epoch 00168: val_loss did not improve from 0.00708\n",
      "5513/5513 [==============================] - 6s 1ms/sample - loss: 0.0037 - mse: 0.0037 - val_loss: 0.0073 - val_mse: 0.0073\n",
      "Epoch 169/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0037 - mse: 0.0037\n",
      "Epoch 00169: val_loss did not improve from 0.00708\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0037 - mse: 0.0037 - val_loss: 0.0073 - val_mse: 0.0073\n",
      "Epoch 170/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0037 - mse: 0.0037\n",
      "Epoch 00170: val_loss improved from 0.00708 to 0.00697, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0037 - mse: 0.0037 - val_loss: 0.0070 - val_mse: 0.0070\n",
      "Epoch 171/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0036 - mse: 0.0036\n",
      "Epoch 00171: val_loss improved from 0.00697 to 0.00688, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0036 - mse: 0.0036 - val_loss: 0.0069 - val_mse: 0.0069\n",
      "Epoch 172/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0036 - mse: 0.0036\n",
      "Epoch 00172: val_loss improved from 0.00688 to 0.00684, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0036 - mse: 0.0036 - val_loss: 0.0068 - val_mse: 0.0068\n",
      "Epoch 173/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0035 - mse: 0.0035\n",
      "Epoch 00173: val_loss improved from 0.00684 to 0.00663, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0035 - mse: 0.0035 - val_loss: 0.0066 - val_mse: 0.0066\n",
      "Epoch 174/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0035 - mse: 0.0035\n",
      "Epoch 00174: val_loss did not improve from 0.00663\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.0036 - mse: 0.0036 - val_loss: 0.0069 - val_mse: 0.0069\n",
      "Epoch 175/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0035 - mse: 0.0035\n",
      "Epoch 00175: val_loss did not improve from 0.00663\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0036 - mse: 0.0036 - val_loss: 0.0068 - val_mse: 0.0068\n",
      "Epoch 176/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0035 - mse: 0.0035\n",
      "Epoch 00176: val_loss improved from 0.00663 to 0.00661, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0035 - mse: 0.0035 - val_loss: 0.0066 - val_mse: 0.0066\n",
      "Epoch 177/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0034 - mse: 0.0034\n",
      "Epoch 00177: val_loss improved from 0.00661 to 0.00643, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 6s 1ms/sample - loss: 0.0034 - mse: 0.0034 - val_loss: 0.0064 - val_mse: 0.0064\n",
      "Epoch 178/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0035 - mse: 0.0035\n",
      "Epoch 00178: val_loss did not improve from 0.00643\n",
      "5513/5513 [==============================] - 6s 1ms/sample - loss: 0.0035 - mse: 0.0035 - val_loss: 0.0066 - val_mse: 0.0066\n",
      "Epoch 179/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0034 - mse: 0.0034\n",
      "Epoch 00179: val_loss did not improve from 0.00643\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0034 - mse: 0.0034 - val_loss: 0.0065 - val_mse: 0.0065\n",
      "Epoch 180/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0034 - mse: 0.0034\n",
      "Epoch 00180: val_loss improved from 0.00643 to 0.00619, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 8s 1ms/sample - loss: 0.0034 - mse: 0.0034 - val_loss: 0.0062 - val_mse: 0.0062\n",
      "Epoch 181/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0034 - mse: 0.0034\n",
      "Epoch 00181: val_loss improved from 0.00619 to 0.00604, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 8s 1ms/sample - loss: 0.0034 - mse: 0.0034 - val_loss: 0.0060 - val_mse: 0.0060\n",
      "Epoch 182/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0033 - mse: 0.0033\n",
      "Epoch 00182: val_loss improved from 0.00604 to 0.00603, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 6s 1ms/sample - loss: 0.0034 - mse: 0.0034 - val_loss: 0.0060 - val_mse: 0.0060\n",
      "Epoch 183/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0033 - mse: 0.0033\n",
      "Epoch 00183: val_loss did not improve from 0.00603\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0033 - mse: 0.0033 - val_loss: 0.0061 - val_mse: 0.0061\n",
      "Epoch 184/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0033 - mse: 0.0033\n",
      "Epoch 00184: val_loss improved from 0.00603 to 0.00591, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0033 - mse: 0.0033 - val_loss: 0.0059 - val_mse: 0.0059\n",
      "Epoch 185/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0033 - mse: 0.0033\n",
      "Epoch 00185: val_loss improved from 0.00591 to 0.00585, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 6s 1ms/sample - loss: 0.0033 - mse: 0.0033 - val_loss: 0.0059 - val_mse: 0.0059\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 186/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0033 - mse: 0.0033\n",
      "Epoch 00186: val_loss did not improve from 0.00585\n",
      "5513/5513 [==============================] - 6s 1ms/sample - loss: 0.0033 - mse: 0.0033 - val_loss: 0.0060 - val_mse: 0.0060\n",
      "Epoch 187/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0033 - mse: 0.0033\n",
      "Epoch 00187: val_loss did not improve from 0.00585\n",
      "5513/5513 [==============================] - 6s 1ms/sample - loss: 0.0033 - mse: 0.0033 - val_loss: 0.0060 - val_mse: 0.0060\n",
      "Epoch 188/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0032 - mse: 0.0032\n",
      "Epoch 00188: val_loss improved from 0.00585 to 0.00579, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0032 - mse: 0.0032 - val_loss: 0.0058 - val_mse: 0.0058\n",
      "Epoch 189/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0032 - mse: 0.0032\n",
      "Epoch 00189: val_loss improved from 0.00579 to 0.00578, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0032 - mse: 0.0032 - val_loss: 0.0058 - val_mse: 0.0058\n",
      "Epoch 190/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0032 - mse: 0.0032\n",
      "Epoch 00190: val_loss did not improve from 0.00578\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0032 - mse: 0.0032 - val_loss: 0.0058 - val_mse: 0.0058\n",
      "Epoch 191/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0032 - mse: 0.0032\n",
      "Epoch 00191: val_loss did not improve from 0.00578\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0032 - mse: 0.0032 - val_loss: 0.0059 - val_mse: 0.0059\n",
      "Epoch 192/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0032 - mse: 0.0032\n",
      "Epoch 00192: val_loss improved from 0.00578 to 0.00568, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0032 - mse: 0.0032 - val_loss: 0.0057 - val_mse: 0.0057\n",
      "Epoch 193/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0031 - mse: 0.0031\n",
      "Epoch 00193: val_loss did not improve from 0.00568\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0031 - mse: 0.0031 - val_loss: 0.0057 - val_mse: 0.0057\n",
      "Epoch 194/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0032 - mse: 0.0032\n",
      "Epoch 00194: val_loss did not improve from 0.00568\n",
      "5513/5513 [==============================] - 6s 1ms/sample - loss: 0.0032 - mse: 0.0032 - val_loss: 0.0057 - val_mse: 0.0057\n",
      "Epoch 195/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0031 - mse: 0.0031\n",
      "Epoch 00195: val_loss improved from 0.00568 to 0.00548, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 8s 2ms/sample - loss: 0.0032 - mse: 0.0032 - val_loss: 0.0055 - val_mse: 0.0055\n",
      "Epoch 196/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0032 - mse: 0.0032\n",
      "Epoch 00196: val_loss did not improve from 0.00548\n",
      "5513/5513 [==============================] - 8s 1ms/sample - loss: 0.0032 - mse: 0.0032 - val_loss: 0.0055 - val_mse: 0.0055\n",
      "Epoch 197/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0030 - mse: 0.0030\n",
      "Epoch 00197: val_loss improved from 0.00548 to 0.00541, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 8s 1ms/sample - loss: 0.0030 - mse: 0.0030 - val_loss: 0.0054 - val_mse: 0.0054\n",
      "Epoch 198/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0030 - mse: 0.0030\n",
      "Epoch 00198: val_loss did not improve from 0.00541\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.0030 - mse: 0.0030 - val_loss: 0.0054 - val_mse: 0.0054\n",
      "Epoch 199/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0031 - mse: 0.0031\n",
      "Epoch 00199: val_loss improved from 0.00541 to 0.00539, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0031 - mse: 0.0031 - val_loss: 0.0054 - val_mse: 0.0054\n",
      "Epoch 200/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0030 - mse: 0.0030\n",
      "Epoch 00200: val_loss improved from 0.00539 to 0.00532, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.0030 - mse: 0.0030 - val_loss: 0.0053 - val_mse: 0.0053\n",
      "Epoch 201/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0030 - mse: 0.0030\n",
      "Epoch 00201: val_loss improved from 0.00532 to 0.00529, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.0030 - mse: 0.0030 - val_loss: 0.0053 - val_mse: 0.0053\n",
      "Epoch 202/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0030 - mse: 0.0030\n",
      "Epoch 00202: val_loss improved from 0.00529 to 0.00521, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0030 - mse: 0.0030 - val_loss: 0.0052 - val_mse: 0.0052\n",
      "Epoch 203/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0029 - mse: 0.0029\n",
      "Epoch 00203: val_loss improved from 0.00521 to 0.00508, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 6s 1ms/sample - loss: 0.0030 - mse: 0.0030 - val_loss: 0.0051 - val_mse: 0.0051\n",
      "Epoch 204/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0029 - mse: 0.0029\n",
      "Epoch 00204: val_loss did not improve from 0.00508\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0030 - mse: 0.0030 - val_loss: 0.0051 - val_mse: 0.0051\n",
      "Epoch 205/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0030 - mse: 0.0030\n",
      "Epoch 00205: val_loss did not improve from 0.00508\n",
      "5513/5513 [==============================] - 12s 2ms/sample - loss: 0.0030 - mse: 0.0030 - val_loss: 0.0053 - val_mse: 0.0053\n",
      "Epoch 206/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0030 - mse: 0.0030\n",
      "Epoch 00206: val_loss did not improve from 0.00508\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.0030 - mse: 0.0030 - val_loss: 0.0053 - val_mse: 0.0053\n",
      "Epoch 207/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0029 - mse: 0.0029\n",
      "Epoch 00207: val_loss improved from 0.00508 to 0.00501, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0029 - mse: 0.0029 - val_loss: 0.0050 - val_mse: 0.0050\n",
      "Epoch 208/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0029 - mse: 0.0029\n",
      "Epoch 00208: val_loss improved from 0.00501 to 0.00487, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0029 - mse: 0.0029 - val_loss: 0.0049 - val_mse: 0.0049\n",
      "Epoch 209/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0029 - mse: 0.0029\n",
      "Epoch 00209: val_loss improved from 0.00487 to 0.00482, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0029 - mse: 0.0029 - val_loss: 0.0048 - val_mse: 0.0048\n",
      "Epoch 210/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0029 - mse: 0.0029\n",
      "Epoch 00210: val_loss did not improve from 0.00482\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0029 - mse: 0.0029 - val_loss: 0.0049 - val_mse: 0.0049\n",
      "Epoch 211/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0029 - mse: 0.0029\n",
      "Epoch 00211: val_loss did not improve from 0.00482\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0028 - mse: 0.0028 - val_loss: 0.0049 - val_mse: 0.0049\n",
      "Epoch 212/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0029 - mse: 0.0029\n",
      "Epoch 00212: val_loss did not improve from 0.00482\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0028 - mse: 0.0028 - val_loss: 0.0049 - val_mse: 0.0049\n",
      "Epoch 213/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0029 - mse: 0.0029\n",
      "Epoch 00213: val_loss did not improve from 0.00482\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0029 - mse: 0.0029 - val_loss: 0.0049 - val_mse: 0.0049\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 214/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0029 - mse: 0.0029\n",
      "Epoch 00214: val_loss improved from 0.00482 to 0.00482, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0029 - mse: 0.0029 - val_loss: 0.0048 - val_mse: 0.0048\n",
      "Epoch 215/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0029 - mse: 0.0029\n",
      "Epoch 00215: val_loss improved from 0.00482 to 0.00475, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0029 - mse: 0.0029 - val_loss: 0.0048 - val_mse: 0.0048\n",
      "Epoch 216/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0028 - mse: 0.0028\n",
      "Epoch 00216: val_loss did not improve from 0.00475\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0028 - mse: 0.0028 - val_loss: 0.0048 - val_mse: 0.0048\n",
      "Epoch 217/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0028 - mse: 0.0028\n",
      "Epoch 00217: val_loss improved from 0.00475 to 0.00474, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0028 - mse: 0.0028 - val_loss: 0.0047 - val_mse: 0.0047\n",
      "Epoch 218/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0028 - mse: 0.0028\n",
      "Epoch 00218: val_loss improved from 0.00474 to 0.00470, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0028 - mse: 0.0028 - val_loss: 0.0047 - val_mse: 0.0047\n",
      "Epoch 219/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0028 - mse: 0.0028\n",
      "Epoch 00219: val_loss did not improve from 0.00470\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0028 - mse: 0.0028 - val_loss: 0.0047 - val_mse: 0.0047\n",
      "Epoch 220/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0028 - mse: 0.0028\n",
      "Epoch 00220: val_loss improved from 0.00470 to 0.00470, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0029 - mse: 0.0029 - val_loss: 0.0047 - val_mse: 0.0047\n",
      "Epoch 221/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0028 - mse: 0.0028\n",
      "Epoch 00221: val_loss improved from 0.00470 to 0.00463, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 8s 1ms/sample - loss: 0.0028 - mse: 0.0028 - val_loss: 0.0046 - val_mse: 0.0046\n",
      "Epoch 222/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0027 - mse: 0.0027\n",
      "Epoch 00222: val_loss did not improve from 0.00463\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0027 - mse: 0.0027 - val_loss: 0.0046 - val_mse: 0.0046\n",
      "Epoch 223/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0028 - mse: 0.0028\n",
      "Epoch 00223: val_loss improved from 0.00463 to 0.00463, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0028 - mse: 0.0028 - val_loss: 0.0046 - val_mse: 0.0046\n",
      "Epoch 224/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0029 - mse: 0.0029\n",
      "Epoch 00224: val_loss improved from 0.00463 to 0.00452, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0029 - mse: 0.0029 - val_loss: 0.0045 - val_mse: 0.0045\n",
      "Epoch 225/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0028 - mse: 0.0028\n",
      "Epoch 00225: val_loss improved from 0.00452 to 0.00452, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 6s 1ms/sample - loss: 0.0028 - mse: 0.0028 - val_loss: 0.0045 - val_mse: 0.0045\n",
      "Epoch 226/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0027 - mse: 0.0027\n",
      "Epoch 00226: val_loss did not improve from 0.00452\n",
      "5513/5513 [==============================] - 6s 1ms/sample - loss: 0.0028 - mse: 0.0028 - val_loss: 0.0046 - val_mse: 0.0046\n",
      "Epoch 227/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0029 - mse: 0.0029\n",
      "Epoch 00227: val_loss did not improve from 0.00452\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0029 - mse: 0.0029 - val_loss: 0.0046 - val_mse: 0.0046\n",
      "Epoch 228/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0028 - mse: 0.0028\n",
      "Epoch 00228: val_loss did not improve from 0.00452\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.0028 - mse: 0.0028 - val_loss: 0.0046 - val_mse: 0.0046\n",
      "Epoch 229/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0027 - mse: 0.0027\n",
      "Epoch 00229: val_loss did not improve from 0.00452\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.0027 - mse: 0.0027 - val_loss: 0.0046 - val_mse: 0.0046\n",
      "Epoch 230/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0027 - mse: 0.0027\n",
      "Epoch 00230: val_loss improved from 0.00452 to 0.00447, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 8s 1ms/sample - loss: 0.0028 - mse: 0.0028 - val_loss: 0.0045 - val_mse: 0.0045\n",
      "Epoch 231/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0027 - mse: 0.0027\n",
      "Epoch 00231: val_loss improved from 0.00447 to 0.00446, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 12s 2ms/sample - loss: 0.0027 - mse: 0.0027 - val_loss: 0.0045 - val_mse: 0.0045\n",
      "Epoch 232/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0028 - mse: 0.0028\n",
      "Epoch 00232: val_loss did not improve from 0.00446\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.0028 - mse: 0.0028 - val_loss: 0.0045 - val_mse: 0.0045\n",
      "Epoch 233/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0027 - mse: 0.0027\n",
      "Epoch 00233: val_loss did not improve from 0.00446\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.0027 - mse: 0.0027 - val_loss: 0.0045 - val_mse: 0.0045\n",
      "Epoch 234/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0027 - mse: 0.0027\n",
      "Epoch 00234: val_loss did not improve from 0.00446\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.0027 - mse: 0.0027 - val_loss: 0.0045 - val_mse: 0.0045\n",
      "Epoch 235/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0027 - mse: 0.0027\n",
      "Epoch 00235: val_loss did not improve from 0.00446\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.0027 - mse: 0.0027 - val_loss: 0.0045 - val_mse: 0.0045\n",
      "Epoch 236/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0028 - mse: 0.0028\n",
      "Epoch 00236: val_loss did not improve from 0.00446\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.0028 - mse: 0.0028 - val_loss: 0.0045 - val_mse: 0.0045\n",
      "Epoch 237/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0027 - mse: 0.0027\n",
      "Epoch 00237: val_loss did not improve from 0.00446\n",
      "5513/5513 [==============================] - 8s 1ms/sample - loss: 0.0027 - mse: 0.0027 - val_loss: 0.0045 - val_mse: 0.0045\n",
      "Epoch 238/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0027 - mse: 0.0027\n",
      "Epoch 00238: val_loss improved from 0.00446 to 0.00445, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0027 - mse: 0.0027 - val_loss: 0.0044 - val_mse: 0.0044\n",
      "Epoch 239/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0027 - mse: 0.0027\n",
      "Epoch 00239: val_loss improved from 0.00445 to 0.00440, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0027 - mse: 0.0027 - val_loss: 0.0044 - val_mse: 0.0044\n",
      "Epoch 240/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0027 - mse: 0.0027\n",
      "Epoch 00240: val_loss improved from 0.00440 to 0.00439, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0027 - mse: 0.0027 - val_loss: 0.0044 - val_mse: 0.0044\n",
      "Epoch 241/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0027 - mse: 0.0027\n",
      "Epoch 00241: val_loss improved from 0.00439 to 0.00435, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 6s 1ms/sample - loss: 0.0027 - mse: 0.0027 - val_loss: 0.0044 - val_mse: 0.0044\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 242/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0027 - mse: 0.0027\n",
      "Epoch 00242: val_loss improved from 0.00435 to 0.00432, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 6s 1ms/sample - loss: 0.0027 - mse: 0.0027 - val_loss: 0.0043 - val_mse: 0.0043\n",
      "Epoch 243/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0028 - mse: 0.0028\n",
      "Epoch 00243: val_loss did not improve from 0.00432\n",
      "5513/5513 [==============================] - 6s 1ms/sample - loss: 0.0028 - mse: 0.0028 - val_loss: 0.0043 - val_mse: 0.0043\n",
      "Epoch 244/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0027 - mse: 0.0027\n",
      "Epoch 00244: val_loss did not improve from 0.00432\n",
      "5513/5513 [==============================] - 6s 1ms/sample - loss: 0.0027 - mse: 0.0027 - val_loss: 0.0043 - val_mse: 0.0043\n",
      "Epoch 245/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0027 - mse: 0.0027\n",
      "Epoch 00245: val_loss did not improve from 0.00432\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0027 - mse: 0.0027 - val_loss: 0.0043 - val_mse: 0.0043\n",
      "Epoch 246/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0027 - mse: 0.0027\n",
      "Epoch 00246: val_loss did not improve from 0.00432\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0027 - mse: 0.0027 - val_loss: 0.0044 - val_mse: 0.0044\n",
      "Epoch 247/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0027 - mse: 0.0027\n",
      "Epoch 00247: val_loss did not improve from 0.00432\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0027 - mse: 0.0027 - val_loss: 0.0044 - val_mse: 0.0044\n",
      "Epoch 248/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0027 - mse: 0.0027\n",
      "Epoch 00248: val_loss improved from 0.00432 to 0.00432, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0027 - mse: 0.0027 - val_loss: 0.0043 - val_mse: 0.0043\n",
      "Epoch 249/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0026 - mse: 0.0026\n",
      "Epoch 00249: val_loss improved from 0.00432 to 0.00432, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 8s 1ms/sample - loss: 0.0027 - mse: 0.0027 - val_loss: 0.0043 - val_mse: 0.0043\n",
      "Epoch 250/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0026 - mse: 0.0026\n",
      "Epoch 00250: val_loss improved from 0.00432 to 0.00430, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0026 - mse: 0.0026 - val_loss: 0.0043 - val_mse: 0.0043\n",
      "Epoch 251/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0027 - mse: 0.0027\n",
      "Epoch 00251: val_loss improved from 0.00430 to 0.00430, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 6s 1ms/sample - loss: 0.0027 - mse: 0.0027 - val_loss: 0.0043 - val_mse: 0.0043\n",
      "Epoch 252/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0026 - mse: 0.0026\n",
      "Epoch 00252: val_loss did not improve from 0.00430\n",
      "5513/5513 [==============================] - 6s 1ms/sample - loss: 0.0026 - mse: 0.0026 - val_loss: 0.0043 - val_mse: 0.0043\n",
      "Epoch 253/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0026 - mse: 0.0026\n",
      "Epoch 00253: val_loss improved from 0.00430 to 0.00430, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 6s 1ms/sample - loss: 0.0027 - mse: 0.0027 - val_loss: 0.0043 - val_mse: 0.0043\n",
      "Epoch 254/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0026 - mse: 0.0026\n",
      "Epoch 00254: val_loss did not improve from 0.00430\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0026 - mse: 0.0026 - val_loss: 0.0043 - val_mse: 0.0043\n",
      "Epoch 255/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0028 - mse: 0.0028\n",
      "Epoch 00255: val_loss did not improve from 0.00430\n",
      "5513/5513 [==============================] - 8s 1ms/sample - loss: 0.0028 - mse: 0.0028 - val_loss: 0.0043 - val_mse: 0.0043\n",
      "Epoch 256/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0026 - mse: 0.0026\n",
      "Epoch 00256: val_loss did not improve from 0.00430\n",
      "5513/5513 [==============================] - 6s 1ms/sample - loss: 0.0026 - mse: 0.0026 - val_loss: 0.0043 - val_mse: 0.0043\n",
      "Epoch 257/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0027 - mse: 0.0027\n",
      "Epoch 00257: val_loss did not improve from 0.00430\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0027 - mse: 0.0027 - val_loss: 0.0043 - val_mse: 0.0043\n",
      "Epoch 258/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0026 - mse: 0.0026\n",
      "Epoch 00258: val_loss did not improve from 0.00430\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0026 - mse: 0.0026 - val_loss: 0.0043 - val_mse: 0.0043\n",
      "Epoch 259/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0027 - mse: 0.0027\n",
      "Epoch 00259: val_loss did not improve from 0.00430\n",
      "5513/5513 [==============================] - 6s 1ms/sample - loss: 0.0027 - mse: 0.0027 - val_loss: 0.0043 - val_mse: 0.0043\n",
      "Epoch 260/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0026 - mse: 0.0026\n",
      "Epoch 00260: val_loss improved from 0.00430 to 0.00428, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0026 - mse: 0.0026 - val_loss: 0.0043 - val_mse: 0.0043\n",
      "Epoch 261/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0027 - mse: 0.0027\n",
      "Epoch 00261: val_loss improved from 0.00428 to 0.00428, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 6s 1ms/sample - loss: 0.0027 - mse: 0.0027 - val_loss: 0.0043 - val_mse: 0.0043\n",
      "Epoch 262/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0027 - mse: 0.0027\n",
      "Epoch 00262: val_loss improved from 0.00428 to 0.00426, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 6s 1ms/sample - loss: 0.0026 - mse: 0.0026 - val_loss: 0.0043 - val_mse: 0.0043\n",
      "Epoch 263/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0026 - mse: 0.0026\n",
      "Epoch 00263: val_loss improved from 0.00426 to 0.00426, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 6s 1ms/sample - loss: 0.0026 - mse: 0.0026 - val_loss: 0.0043 - val_mse: 0.0043\n",
      "Epoch 264/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0027 - mse: 0.0027\n",
      "Epoch 00264: val_loss improved from 0.00426 to 0.00423, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 6s 1ms/sample - loss: 0.0027 - mse: 0.0027 - val_loss: 0.0042 - val_mse: 0.0042\n",
      "Epoch 265/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0026 - mse: 0.0026\n",
      "Epoch 00265: val_loss improved from 0.00423 to 0.00423, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 6s 1ms/sample - loss: 0.0027 - mse: 0.0027 - val_loss: 0.0042 - val_mse: 0.0042\n",
      "Epoch 266/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0027 - mse: 0.0027\n",
      "Epoch 00266: val_loss did not improve from 0.00423\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0027 - mse: 0.0027 - val_loss: 0.0042 - val_mse: 0.0042\n",
      "Epoch 267/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0026 - mse: 0.0026\n",
      "Epoch 00267: val_loss improved from 0.00423 to 0.00422, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0026 - mse: 0.0026 - val_loss: 0.0042 - val_mse: 0.0042\n",
      "Epoch 268/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0026 - mse: 0.0026\n",
      "Epoch 00268: val_loss improved from 0.00422 to 0.00420, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0026 - mse: 0.0026 - val_loss: 0.0042 - val_mse: 0.0042\n",
      "Epoch 269/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0026 - mse: 0.0026\n",
      "Epoch 00269: val_loss improved from 0.00420 to 0.00419, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0026 - mse: 0.0026 - val_loss: 0.0042 - val_mse: 0.0042\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 270/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0026 - mse: 0.0026\n",
      "Epoch 00270: val_loss improved from 0.00419 to 0.00419, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.0026 - mse: 0.0026 - val_loss: 0.0042 - val_mse: 0.0042\n",
      "Epoch 271/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0026 - mse: 0.0026\n",
      "Epoch 00271: val_loss did not improve from 0.00419\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0026 - mse: 0.0026 - val_loss: 0.0042 - val_mse: 0.0042\n",
      "Epoch 272/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0027 - mse: 0.0027\n",
      "Epoch 00272: val_loss did not improve from 0.00419\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0027 - mse: 0.0027 - val_loss: 0.0042 - val_mse: 0.0042\n",
      "Epoch 273/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0027 - mse: 0.0027\n",
      "Epoch 00273: val_loss did not improve from 0.00419\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.0027 - mse: 0.0027 - val_loss: 0.0042 - val_mse: 0.0042\n",
      "Epoch 274/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0026 - mse: 0.0026\n",
      "Epoch 00274: val_loss improved from 0.00419 to 0.00419, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.0026 - mse: 0.0026 - val_loss: 0.0042 - val_mse: 0.0042\n",
      "Epoch 275/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0027 - mse: 0.0027\n",
      "Epoch 00275: val_loss did not improve from 0.00419\n",
      "5513/5513 [==============================] - 8s 1ms/sample - loss: 0.0027 - mse: 0.0027 - val_loss: 0.0042 - val_mse: 0.0042\n",
      "Epoch 276/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0026 - mse: 0.0026\n",
      "Epoch 00276: val_loss improved from 0.00419 to 0.00417, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0026 - mse: 0.0026 - val_loss: 0.0042 - val_mse: 0.0042\n",
      "Epoch 277/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0026 - mse: 0.0026\n",
      "Epoch 00277: val_loss did not improve from 0.00417\n",
      "5513/5513 [==============================] - 8s 1ms/sample - loss: 0.0026 - mse: 0.0026 - val_loss: 0.0042 - val_mse: 0.0042\n",
      "Epoch 278/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0026 - mse: 0.0026\n",
      "Epoch 00278: val_loss did not improve from 0.00417\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0026 - mse: 0.0026 - val_loss: 0.0042 - val_mse: 0.0042\n",
      "Epoch 279/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0026 - mse: 0.0026\n",
      "Epoch 00279: val_loss did not improve from 0.00417\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0026 - mse: 0.0026 - val_loss: 0.0042 - val_mse: 0.0042\n",
      "Epoch 280/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0027 - mse: 0.0027\n",
      "Epoch 00280: val_loss did not improve from 0.00417\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0027 - mse: 0.0027 - val_loss: 0.0042 - val_mse: 0.0042\n",
      "Epoch 281/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0026 - mse: 0.0026\n",
      "Epoch 00281: val_loss did not improve from 0.00417\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0026 - mse: 0.0026 - val_loss: 0.0042 - val_mse: 0.0042\n",
      "Epoch 282/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0026 - mse: 0.0026\n",
      "Epoch 00282: val_loss improved from 0.00417 to 0.00416, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 6s 1ms/sample - loss: 0.0026 - mse: 0.0026 - val_loss: 0.0042 - val_mse: 0.0042\n",
      "Epoch 283/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0026 - mse: 0.0026\n",
      "Epoch 00283: val_loss improved from 0.00416 to 0.00415, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 8s 1ms/sample - loss: 0.0026 - mse: 0.0026 - val_loss: 0.0042 - val_mse: 0.0042\n",
      "Epoch 284/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0026 - mse: 0.0026\n",
      "Epoch 00284: val_loss improved from 0.00415 to 0.00415, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0026 - mse: 0.0026 - val_loss: 0.0042 - val_mse: 0.0042\n",
      "Epoch 285/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0026 - mse: 0.0026\n",
      "Epoch 00285: val_loss improved from 0.00415 to 0.00415, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 6s 1ms/sample - loss: 0.0026 - mse: 0.0026 - val_loss: 0.0041 - val_mse: 0.0041\n",
      "Epoch 286/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0026 - mse: 0.0026\n",
      "Epoch 00286: val_loss improved from 0.00415 to 0.00414, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 6s 1ms/sample - loss: 0.0026 - mse: 0.0026 - val_loss: 0.0041 - val_mse: 0.0041\n",
      "Epoch 287/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0026 - mse: 0.0026\n",
      "Epoch 00287: val_loss improved from 0.00414 to 0.00413, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 6s 1ms/sample - loss: 0.0026 - mse: 0.0026 - val_loss: 0.0041 - val_mse: 0.0041\n",
      "Epoch 288/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0025 - mse: 0.0025\n",
      "Epoch 00288: val_loss improved from 0.00413 to 0.00412, saving model to saved_model/djia_nk_test.h5\n",
      "5513/5513 [==============================] - 6s 1ms/sample - loss: 0.0026 - mse: 0.0026 - val_loss: 0.0041 - val_mse: 0.0041\n",
      "Epoch 289/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0026 - mse: 0.0026\n",
      "Epoch 00289: val_loss did not improve from 0.00412\n",
      "5513/5513 [==============================] - 6s 1ms/sample - loss: 0.0026 - mse: 0.0026 - val_loss: 0.0041 - val_mse: 0.0041\n",
      "Epoch 290/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0026 - mse: 0.0026\n",
      "Epoch 00290: val_loss did not improve from 0.00412\n",
      "5513/5513 [==============================] - 6s 1ms/sample - loss: 0.0026 - mse: 0.0026 - val_loss: 0.0041 - val_mse: 0.0041\n",
      "Epoch 291/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0026 - mse: 0.0026\n",
      "Epoch 00291: val_loss did not improve from 0.00412\n",
      "5513/5513 [==============================] - 6s 1ms/sample - loss: 0.0026 - mse: 0.0026 - val_loss: 0.0041 - val_mse: 0.0041\n",
      "Epoch 292/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0026 - mse: 0.0026\n",
      "Epoch 00292: val_loss did not improve from 0.00412\n",
      "5513/5513 [==============================] - 6s 1ms/sample - loss: 0.0026 - mse: 0.0026 - val_loss: 0.0041 - val_mse: 0.0041\n",
      "Epoch 293/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0026 - mse: 0.0026\n",
      "Epoch 00293: val_loss did not improve from 0.00412\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0026 - mse: 0.0026 - val_loss: 0.0041 - val_mse: 0.0041\n",
      "Epoch 294/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0026 - mse: 0.0026\n",
      "Epoch 00294: val_loss did not improve from 0.00412\n",
      "5513/5513 [==============================] - 8s 1ms/sample - loss: 0.0027 - mse: 0.0027 - val_loss: 0.0041 - val_mse: 0.0041\n",
      "Epoch 295/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0026 - mse: 0.0026\n",
      "Epoch 00295: val_loss did not improve from 0.00412\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0026 - mse: 0.0026 - val_loss: 0.0041 - val_mse: 0.0041\n",
      "Epoch 296/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0026 - mse: 0.0026\n",
      "Epoch 00296: val_loss did not improve from 0.00412\n",
      "5513/5513 [==============================] - 6s 1ms/sample - loss: 0.0026 - mse: 0.0026 - val_loss: 0.0041 - val_mse: 0.0041\n",
      "Epoch 297/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0026 - mse: 0.0026\n",
      "Epoch 00297: val_loss did not improve from 0.00412\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0026 - mse: 0.0026 - val_loss: 0.0041 - val_mse: 0.0041\n",
      "Epoch 298/300\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0026 - mse: 0.0026\n",
      "Epoch 00298: val_loss did not improve from 0.00412\n",
      "5513/5513 [==============================] - 8s 1ms/sample - loss: 0.0026 - mse: 0.0026 - val_loss: 0.0041 - val_mse: 0.0041\n",
      "Epoch 299/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0026 - mse: 0.0026\n",
      "Epoch 00299: val_loss did not improve from 0.00412\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0026 - mse: 0.0026 - val_loss: 0.0041 - val_mse: 0.0041\n",
      "Epoch 300/300\n",
      "5120/5513 [==========================>...] - ETA: 0s - loss: 0.0026 - mse: 0.0026\n",
      "Epoch 00300: val_loss did not improve from 0.00412\n",
      "5513/5513 [==============================] - 7s 1ms/sample - loss: 0.0026 - mse: 0.0026 - val_loss: 0.0042 - val_mse: 0.0042\n"
     ]
    }
   ],
   "source": [
    "history = model.fit(x_train, y_train, epochs=epochs , callbacks=callbacks_list_model,\n",
    "          validation_data=(x_val, y_val),batch_size=batch_size) "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "dict_keys(['loss', 'mse', 'val_loss', 'val_mse', 'lr'])\n"
     ]
    }
   ],
   "source": [
    "print(history.history.keys())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.title(\"Loss (MSE)\")\n",
    "plt.plot(history.history['loss'],color = 'blue',label=\"train_loss\")\n",
    "plt.plot(history.history['val_loss'],color = 'red',label=\"val_loss\")\n",
    "plt.xlabel(\"epochs\")\n",
    "plt.ylabel(\"loss\")\n",
    "plt.legend()\n",
    "plt.savefig('loss_support.png')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [],
   "source": [
    "y_train_pred = model.predict(x_train)\n",
    "y_val_pred = model.predict(x_val)\n",
    "y_test_pred = model.predict(x_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [],
   "source": [
    "#fix!\n",
    "def plot_compare(x, event_col):\n",
    "#     Col = {'Open':0, 'High':1, 'Low':2, 'Close':3}\n",
    "    Col = dict()\n",
    "    count = 0\n",
    "    for i, col in enumerate(event_col):\n",
    "        Col[col] = i\n",
    "    ft = Col[x]\n",
    "    plt.figure(figsize=(15, 5))\n",
    "    plt.subplot(1, 2, 1)\n",
    "\n",
    "    plt.plot(np.arange(y_train.shape[0]), y_train[:, ft], color='blue', label='train target')\n",
    "\n",
    "    plt.plot(np.arange(y_train.shape[0], y_train.shape[0] + y_val.shape[0]), y_val[:, ft], \n",
    "             color='gray', label='val target')\n",
    "    plt.plot(np.arange(y_train.shape[0] + y_val.shape[0], y_train.shape[0] + y_val.shape[0] + y_test.shape[0]),\n",
    "            y_test[:, ft], color='black', label='test target')\n",
    "    plt.plot(np.arange(y_train_pred.shape[0]), y_train_pred[:, ft],\n",
    "            color='red', label='train prediction') \n",
    "    plt.plot(np.arange(y_train_pred.shape[0], y_train_pred.shape[0] + y_val_pred.shape[0]),\n",
    "            y_val_pred[:, ft], color='orange', label='val prediction')\n",
    "    plt.plot(np.arange(y_train_pred.shape[0] + y_val_pred.shape[0],\n",
    "            y_train_pred.shape[0] + y_val_pred.shape[0] + y_test_pred.shape[0]),\n",
    "            y_test_pred[:, ft], color ='green', label='test prediction')\n",
    "    plt.title('past and future stock price :' + x)\n",
    "    plt.xlabel('Time [Days]')\n",
    "    plt.ylabel('Normalized price')\n",
    "    plt.legend(loc='best')\n",
    "\n",
    "    plt.subplot(1, 2, 2)\n",
    "    plt.plot(np.arange(y_train.shape[0], y_train.shape[0] + y_test.shape[0]),\n",
    "            y_test[:, ft], color='black', label='test target')\n",
    "    plt.plot(np.arange(y_train.shape[0], y_train.shape[0] + y_test_pred.shape[0]),\n",
    "            y_test_pred[:, ft], color='green', label='test prediction')\n",
    "    plt.title('future stock prices :' + x)\n",
    "    plt.xlabel('Time [Days]')\n",
    "    plt.ylabel('Normalized price')\n",
    "    plt.legend(loc='best')\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1080x360 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plot_compare('Close(DJIA)', event_col)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "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": "3.6.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}