Stock_Price_Prediction_LSTM.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "dataset_train = pd.read_csv('Google_Stock_Price_Train.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "training_set = dataset_train.iloc[:,1:2].values  \n",
    "#Only considering the open_column because that is what we will be predictingin this model\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[325.25],\n",
       "       [331.27],\n",
       "       [329.83],\n",
       "       ...,\n",
       "       [793.7 ],\n",
       "       [783.33],\n",
       "       [782.75]])"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "training_set"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "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>Volume</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>0</td>\n",
       "      <td>1/3/2012</td>\n",
       "      <td>325.25</td>\n",
       "      <td>332.83</td>\n",
       "      <td>324.97</td>\n",
       "      <td>663.59</td>\n",
       "      <td>7,380,500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1</td>\n",
       "      <td>1/4/2012</td>\n",
       "      <td>331.27</td>\n",
       "      <td>333.87</td>\n",
       "      <td>329.08</td>\n",
       "      <td>666.45</td>\n",
       "      <td>5,749,400</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2</td>\n",
       "      <td>1/5/2012</td>\n",
       "      <td>329.83</td>\n",
       "      <td>330.75</td>\n",
       "      <td>326.89</td>\n",
       "      <td>657.21</td>\n",
       "      <td>6,590,300</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3</td>\n",
       "      <td>1/6/2012</td>\n",
       "      <td>328.34</td>\n",
       "      <td>328.77</td>\n",
       "      <td>323.68</td>\n",
       "      <td>648.24</td>\n",
       "      <td>5,405,900</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4</td>\n",
       "      <td>1/9/2012</td>\n",
       "      <td>322.04</td>\n",
       "      <td>322.29</td>\n",
       "      <td>309.46</td>\n",
       "      <td>620.76</td>\n",
       "      <td>11,688,800</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1253</td>\n",
       "      <td>12/23/2016</td>\n",
       "      <td>790.90</td>\n",
       "      <td>792.74</td>\n",
       "      <td>787.28</td>\n",
       "      <td>789.91</td>\n",
       "      <td>623,400</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1254</td>\n",
       "      <td>12/27/2016</td>\n",
       "      <td>790.68</td>\n",
       "      <td>797.86</td>\n",
       "      <td>787.66</td>\n",
       "      <td>791.55</td>\n",
       "      <td>789,100</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1255</td>\n",
       "      <td>12/28/2016</td>\n",
       "      <td>793.70</td>\n",
       "      <td>794.23</td>\n",
       "      <td>783.20</td>\n",
       "      <td>785.05</td>\n",
       "      <td>1,153,800</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1256</td>\n",
       "      <td>12/29/2016</td>\n",
       "      <td>783.33</td>\n",
       "      <td>785.93</td>\n",
       "      <td>778.92</td>\n",
       "      <td>782.79</td>\n",
       "      <td>744,300</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1257</td>\n",
       "      <td>12/30/2016</td>\n",
       "      <td>782.75</td>\n",
       "      <td>782.78</td>\n",
       "      <td>770.41</td>\n",
       "      <td>771.82</td>\n",
       "      <td>1,770,000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1258 rows × 6 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "            Date    Open    High     Low   Close      Volume\n",
       "0       1/3/2012  325.25  332.83  324.97  663.59   7,380,500\n",
       "1       1/4/2012  331.27  333.87  329.08  666.45   5,749,400\n",
       "2       1/5/2012  329.83  330.75  326.89  657.21   6,590,300\n",
       "3       1/6/2012  328.34  328.77  323.68  648.24   5,405,900\n",
       "4       1/9/2012  322.04  322.29  309.46  620.76  11,688,800\n",
       "...          ...     ...     ...     ...     ...         ...\n",
       "1253  12/23/2016  790.90  792.74  787.28  789.91     623,400\n",
       "1254  12/27/2016  790.68  797.86  787.66  791.55     789,100\n",
       "1255  12/28/2016  793.70  794.23  783.20  785.05   1,153,800\n",
       "1256  12/29/2016  783.33  785.93  778.92  782.79     744,300\n",
       "1257  12/30/2016  782.75  782.78  770.41  771.82   1,770,000\n",
       "\n",
       "[1258 rows x 6 columns]"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dataset_train"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "#We perform feature scaling to scale down the values to the same range\n",
    "from sklearn.preprocessing import MinMaxScaler"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "sc=MinMaxScaler(feature_range = (0,1))\n",
    "training_set_scaled = sc.fit_transform(training_set)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "MinMaxScaler(copy=True, feature_range=(0, 1))"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sc"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[0.08581368],\n",
       "       [0.09701243],\n",
       "       [0.09433366],\n",
       "       ...,\n",
       "       [0.95725128],\n",
       "       [0.93796041],\n",
       "       [0.93688146]])"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "training_set_scaled"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train = []\n",
    "Y_train=[]\n",
    "\n",
    "#Create data structure with 60 time steps and 1 output that is each of my input evctor will have 60 readings\n",
    "for i in range(60,len(training_set_scaled)):\n",
    "    X_train.append(training_set_scaled[i-60:i,0])\n",
    "    Y_train.append(training_set_scaled[i,0])\n",
    "X_train,Y_train = np.array(X_train),np.array(Y_train)\n",
    "\n",
    "#So in this preprocessing step we make an array with 60 elements and then the 61st element is our output.\n",
    "#We do this thing in a sequence such that in each consecutive array the last element was output for the previous array."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[0.08581368, 0.09701243, 0.09433366, ..., 0.07846566, 0.08034452,\n",
       "        0.08497656],\n",
       "       [0.09701243, 0.09433366, 0.09156187, ..., 0.08034452, 0.08497656,\n",
       "        0.08627874],\n",
       "       [0.09433366, 0.09156187, 0.07984225, ..., 0.08497656, 0.08627874,\n",
       "        0.08471612],\n",
       "       ...,\n",
       "       [0.92106928, 0.92438053, 0.93048218, ..., 0.95475854, 0.95204256,\n",
       "        0.95163331],\n",
       "       [0.92438053, 0.93048218, 0.9299055 , ..., 0.95204256, 0.95163331,\n",
       "        0.95725128],\n",
       "       [0.93048218, 0.9299055 , 0.93113327, ..., 0.95163331, 0.95725128,\n",
       "        0.93796041]])"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_train"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0.08627874, 0.08471612, 0.07454052, ..., 0.95725128, 0.93796041,\n",
       "       0.93688146])"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Y_train"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1198"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(X_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1198"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(Y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [],
   "source": [
    "#Reshape the data according to input shape of keras documentation\n",
    "X_train=np.reshape(X_train, (X_train.shape[0],X_train.shape[1],1))\n",
    "#Input format according to keras documentation : (batch_size, timestep, dimension)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[[0.08581368],\n",
       "        [0.09701243],\n",
       "        [0.09433366],\n",
       "        ...,\n",
       "        [0.07846566],\n",
       "        [0.08034452],\n",
       "        [0.08497656]],\n",
       "\n",
       "       [[0.09701243],\n",
       "        [0.09433366],\n",
       "        [0.09156187],\n",
       "        ...,\n",
       "        [0.08034452],\n",
       "        [0.08497656],\n",
       "        [0.08627874]],\n",
       "\n",
       "       [[0.09433366],\n",
       "        [0.09156187],\n",
       "        [0.07984225],\n",
       "        ...,\n",
       "        [0.08497656],\n",
       "        [0.08627874],\n",
       "        [0.08471612]],\n",
       "\n",
       "       ...,\n",
       "\n",
       "       [[0.92106928],\n",
       "        [0.92438053],\n",
       "        [0.93048218],\n",
       "        ...,\n",
       "        [0.95475854],\n",
       "        [0.95204256],\n",
       "        [0.95163331]],\n",
       "\n",
       "       [[0.92438053],\n",
       "        [0.93048218],\n",
       "        [0.9299055 ],\n",
       "        ...,\n",
       "        [0.95204256],\n",
       "        [0.95163331],\n",
       "        [0.95725128]],\n",
       "\n",
       "       [[0.93048218],\n",
       "        [0.9299055 ],\n",
       "        [0.93113327],\n",
       "        ...,\n",
       "        [0.95163331],\n",
       "        [0.95725128],\n",
       "        [0.93796041]]])"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_train"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Using TensorFlow backend.\n",
      "/home/varun/Python_Environments/AI_game/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:516: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
      "  _np_qint8 = np.dtype([(\"qint8\", np.int8, 1)])\n",
      "/home/varun/Python_Environments/AI_game/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:517: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
      "  _np_quint8 = np.dtype([(\"quint8\", np.uint8, 1)])\n",
      "/home/varun/Python_Environments/AI_game/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:518: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
      "  _np_qint16 = np.dtype([(\"qint16\", np.int16, 1)])\n",
      "/home/varun/Python_Environments/AI_game/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:519: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
      "  _np_quint16 = np.dtype([(\"quint16\", np.uint16, 1)])\n",
      "/home/varun/Python_Environments/AI_game/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:520: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
      "  _np_qint32 = np.dtype([(\"qint32\", np.int32, 1)])\n",
      "/home/varun/Python_Environments/AI_game/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:525: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
      "  np_resource = np.dtype([(\"resource\", np.ubyte, 1)])\n",
      "/home/varun/Python_Environments/AI_game/lib/python3.6/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:541: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
      "  _np_qint8 = np.dtype([(\"qint8\", np.int8, 1)])\n",
      "/home/varun/Python_Environments/AI_game/lib/python3.6/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:542: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
      "  _np_quint8 = np.dtype([(\"quint8\", np.uint8, 1)])\n",
      "/home/varun/Python_Environments/AI_game/lib/python3.6/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:543: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
      "  _np_qint16 = np.dtype([(\"qint16\", np.int16, 1)])\n",
      "/home/varun/Python_Environments/AI_game/lib/python3.6/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:544: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
      "  _np_quint16 = np.dtype([(\"quint16\", np.uint16, 1)])\n",
      "/home/varun/Python_Environments/AI_game/lib/python3.6/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:545: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
      "  _np_qint32 = np.dtype([(\"qint32\", np.int32, 1)])\n",
      "/home/varun/Python_Environments/AI_game/lib/python3.6/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:550: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
      "  np_resource = np.dtype([(\"resource\", np.ubyte, 1)])\n"
     ]
    }
   ],
   "source": [
    "from keras.models import Sequential\n",
    "from keras.layers import Dense\n",
    "from keras.layers import LSTM\n",
    "from keras.layers import Dropout"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [],
   "source": [
    "regressor = Sequential()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "WARNING:tensorflow:From /home/varun/Python_Environments/AI_game/lib/python3.6/site-packages/keras/backend/tensorflow_backend.py:3733: calling dropout (from tensorflow.python.ops.nn_ops) with keep_prob is deprecated and will be removed in a future version.\n",
      "Instructions for updating:\n",
      "Please use `rate` instead of `keep_prob`. Rate should be set to `rate = 1 - keep_prob`.\n"
     ]
    }
   ],
   "source": [
    "regressor.add(LSTM(units = 50, return_sequences = True, input_shape = (X_train.shape[1],1)))\n",
    "regressor.add(Dropout(0.2))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [],
   "source": [
    "regressor.add(LSTM(units=50,return_sequences =True))\n",
    "regressor.add(Dropout(0.2))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [],
   "source": [
    "regressor.add(LSTM(units = 50, return_sequences = True))\n",
    "regressor.add(Dropout(0.2))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [],
   "source": [
    "regressor.add(LSTM(units = 50))\n",
    "regressor.add(Dropout(0.2))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [],
   "source": [
    "regressor.add(Dense(units=1))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [],
   "source": [
    "regressor.compile(optimizer = 'adam',loss = 'mean_squared_error')"
   ]
  },
  {
   "cell_type": "raw",
   "metadata": {},
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1/50\n",
      "1198/1198 [==============================] - 8s 7ms/step - loss: 0.0521\n",
      "Epoch 2/50\n",
      "1198/1198 [==============================] - 5s 4ms/step - loss: 0.0061\n",
      "Epoch 3/50\n",
      "1198/1198 [==============================] - 5s 4ms/step - loss: 0.0055\n",
      "Epoch 4/50\n",
      "1198/1198 [==============================] - 6s 5ms/step - loss: 0.0051\n",
      "Epoch 5/50\n",
      "1198/1198 [==============================] - 5s 4ms/step - loss: 0.0053\n",
      "Epoch 6/50\n",
      "1198/1198 [==============================] - 5s 5ms/step - loss: 0.0045\n",
      "Epoch 7/50\n",
      "1198/1198 [==============================] - 5s 4ms/step - loss: 0.0044\n",
      "Epoch 8/50\n",
      "1198/1198 [==============================] - 5s 4ms/step - loss: 0.0046\n",
      "Epoch 9/50\n",
      "1198/1198 [==============================] - 5s 4ms/step - loss: 0.0047\n",
      "Epoch 10/50\n",
      "1198/1198 [==============================] - 6s 5ms/step - loss: 0.0050\n",
      "Epoch 11/50\n",
      "1198/1198 [==============================] - 5s 4ms/step - loss: 0.0050\n",
      "Epoch 12/50\n",
      "1198/1198 [==============================] - 6s 5ms/step - loss: 0.0041\n",
      "Epoch 13/50\n",
      "1198/1198 [==============================] - 6s 5ms/step - loss: 0.0041\n",
      "Epoch 14/50\n",
      "1198/1198 [==============================] - 6s 5ms/step - loss: 0.0037\n",
      "Epoch 15/50\n",
      "1198/1198 [==============================] - 5s 4ms/step - loss: 0.0039\n",
      "Epoch 16/50\n",
      "1198/1198 [==============================] - 5s 4ms/step - loss: 0.0038\n",
      "Epoch 17/50\n",
      "1198/1198 [==============================] - 5s 4ms/step - loss: 0.0036\n",
      "Epoch 18/50\n",
      "1198/1198 [==============================] - 5s 4ms/step - loss: 0.0033\n",
      "Epoch 19/50\n",
      "1198/1198 [==============================] - 5s 4ms/step - loss: 0.0035\n",
      "Epoch 20/50\n",
      "1198/1198 [==============================] - 5s 4ms/step - loss: 0.0038\n",
      "Epoch 21/50\n",
      "1198/1198 [==============================] - 4s 4ms/step - loss: 0.0034\n",
      "Epoch 22/50\n",
      "1198/1198 [==============================] - 5s 4ms/step - loss: 0.0033\n",
      "Epoch 23/50\n",
      "1198/1198 [==============================] - 5s 4ms/step - loss: 0.0034\n",
      "Epoch 24/50\n",
      "1198/1198 [==============================] - 5s 4ms/step - loss: 0.0032\n",
      "Epoch 25/50\n",
      "1198/1198 [==============================] - 5s 4ms/step - loss: 0.0031\n",
      "Epoch 26/50\n",
      "1198/1198 [==============================] - 5s 4ms/step - loss: 0.0032\n",
      "Epoch 27/50\n",
      "1198/1198 [==============================] - 5s 4ms/step - loss: 0.0032\n",
      "Epoch 28/50\n",
      "1198/1198 [==============================] - 5s 4ms/step - loss: 0.0032\n",
      "Epoch 29/50\n",
      "1198/1198 [==============================] - 5s 4ms/step - loss: 0.0031\n",
      "Epoch 30/50\n",
      "1198/1198 [==============================] - 5s 4ms/step - loss: 0.0028\n",
      "Epoch 31/50\n",
      "1198/1198 [==============================] - 5s 4ms/step - loss: 0.0027\n",
      "Epoch 32/50\n",
      "1198/1198 [==============================] - 5s 4ms/step - loss: 0.0028\n",
      "Epoch 33/50\n",
      "1198/1198 [==============================] - 5s 4ms/step - loss: 0.0031\n",
      "Epoch 34/50\n",
      "1198/1198 [==============================] - 5s 4ms/step - loss: 0.0030\n",
      "Epoch 35/50\n",
      "1198/1198 [==============================] - 5s 4ms/step - loss: 0.0028\n",
      "Epoch 36/50\n",
      "1198/1198 [==============================] - 5s 4ms/step - loss: 0.0026\n",
      "Epoch 37/50\n",
      "1198/1198 [==============================] - 6s 5ms/step - loss: 0.0028\n",
      "Epoch 38/50\n",
      "1198/1198 [==============================] - 5s 4ms/step - loss: 0.0027\n",
      "Epoch 39/50\n",
      "1198/1198 [==============================] - 5s 4ms/step - loss: 0.0027\n",
      "Epoch 40/50\n",
      "1198/1198 [==============================] - 5s 4ms/step - loss: 0.0037\n",
      "Epoch 41/50\n",
      "1198/1198 [==============================] - 5s 4ms/step - loss: 0.0034\n",
      "Epoch 42/50\n",
      "1198/1198 [==============================] - 5s 4ms/step - loss: 0.0027\n",
      "Epoch 43/50\n",
      "1198/1198 [==============================] - 5s 4ms/step - loss: 0.0026\n",
      "Epoch 44/50\n",
      "1198/1198 [==============================] - 5s 4ms/step - loss: 0.0025\n",
      "Epoch 45/50\n",
      "1198/1198 [==============================] - 7s 5ms/step - loss: 0.0024\n",
      "Epoch 46/50\n",
      "1198/1198 [==============================] - 5s 4ms/step - loss: 0.0026\n",
      "Epoch 47/50\n",
      "1198/1198 [==============================] - 5s 4ms/step - loss: 0.0024\n",
      "Epoch 48/50\n",
      "1198/1198 [==============================] - 5s 4ms/step - loss: 0.0024\n",
      "Epoch 49/50\n",
      "1198/1198 [==============================] - 5s 4ms/step - loss: 0.0026\n",
      "Epoch 50/50\n",
      "1198/1198 [==============================] - 5s 4ms/step - loss: 0.0023\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<keras.callbacks.History at 0x7fa2d624be48>"
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "regressor.fit(X_train,Y_train,epochs = 50, batch_size=32)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [],
   "source": [
    "dataset_test=pd.read_csv('Google_Stock_Price_Test.csv')\n",
    "real_stock_price=dataset_test.iloc[:,1:2].values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [],
   "source": [
    "dataset_total=pd.concat((dataset_train['Open'],dataset_test['Open']),axis=0)\n",
    "inputs = dataset_total[len(dataset_total)-len(dataset_test)-60:].values\n",
    "inputs=inputs.reshape(-1,1)\n",
    "inputs=sc.transform(inputs)\n",
    "X_test=[]\n",
    "for i in range(60, 80):\n",
    "    X_test.append(inputs[i-60:i, 0])\n",
    "X_test = np.array(X_test)\n",
    "X_test = np.reshape(X_test, (X_test.shape[0], X_test.shape[1], 1))\n",
    "predicted_stock_price = regressor.predict(X_test)\n",
    "predicted_stock_price = sc.inverse_transform(predicted_stock_price)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "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": [
    "# Visualising the results\n",
    "plt.plot(real_stock_price, color = 'red', label = 'Real Google Stock Price')\n",
    "plt.plot(predicted_stock_price, color = 'blue', label = 'Predicted Google Stock Price')\n",
    "plt.title('Google Stock Price Prediction')\n",
    "plt.xlabel('Time')\n",
    "plt.ylabel('Google Stock Price')\n",
    "plt.legend()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[788.23816],\n",
       "       [785.74927],\n",
       "       [785.44336],\n",
       "       [786.3645 ],\n",
       "       [789.27795],\n",
       "       [794.7899 ],\n",
       "       [800.5874 ],\n",
       "       [804.0711 ],\n",
       "       [805.55145],\n",
       "       [805.793  ],\n",
       "       [805.40784],\n",
       "       [804.68036],\n",
       "       [803.9277 ],\n",
       "       [803.8246 ],\n",
       "       [804.3196 ],\n",
       "       [808.0447 ],\n",
       "       [814.378  ],\n",
       "       [821.95404],\n",
       "       [827.30176],\n",
       "       [825.6316 ]], dtype=float32)"
      ]
     },
     "execution_count": 40,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "predicted_stock_price"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "WARNING:tensorflow:From /home/varun/Python_Environments/AI_game/lib/python3.6/site-packages/keras/backend/tensorflow_backend.py:541: The name tf.placeholder is deprecated. Please use tf.compat.v1.placeholder instead.\n",
      "\n",
      "WARNING:tensorflow:From /home/varun/Python_Environments/AI_game/lib/python3.6/site-packages/keras/backend/tensorflow_backend.py:4432: The name tf.random_uniform is deprecated. Please use tf.random.uniform instead.\n",
      "\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/varun/Python_Environments/AI_game/lib/python3.6/site-packages/ipykernel_launcher.py:5: UserWarning: Update your `Dense` call to the Keras 2 API: `Dense(16, activation=\"relu\", kernel_initializer=\"uniform\")`\n",
      "  \"\"\"\n",
      "/home/varun/Python_Environments/AI_game/lib/python3.6/site-packages/ipykernel_launcher.py:7: UserWarning: Update your `Dense` call to the Keras 2 API: `Dense(1, activation=\"linear\", kernel_initializer=\"uniform\")`\n",
      "  import sys\n"
     ]
    }
   ],
   "source": [
    "#Using a different regressor model for this application:\n",
    "\n",
    "regressor.add(LSTM(128, input_shape=(X_train.shape[1],1), return_sequences=True)) \n",
    " \n",
    "regressor.add(LSTM(64, return_sequences=False)) \n",
    " \n",
    "regressor.add(Dense(16,init='uniform',activation='relu')) \n",
    " \n",
    "regressor.add(Dense(1,init='uniform',activation='linear')) "
   ]
  },
  {
   "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": "3.6.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}