LSTM_Closing_Price_Predictor.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "LSTM_Closing_Price_Predictor.ipynb",
      "provenance": [],
      "collapsed_sections": []
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "accelerator": "GPU"
  },
  "cells": [
    {
      "cell_type": "code",
      "metadata": {
        "id": "mJAud7z9rGQM",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "import tensorflow as tf\n",
        "import pandas as pd"
      ],
      "execution_count": 61,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "h3rf_V9t5Qcm",
        "colab_type": "code",
        "colab": {
          "resources": {
            "http://localhost:8080/nbextensions/google.colab/files.js": {
              "data": "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",
              "ok": true,
              "headers": [
                [
                  "content-type",
                  "application/javascript"
                ]
              ],
              "status": 200,
              "status_text": ""
            }
          },
          "base_uri": "https://localhost:8080/",
          "height": 111
        },
        "outputId": "8552a839-b221-45f6-97d3-b735b3dbe2d1"
      },
      "source": [
        "from google.colab import files\n",
        "files.upload()"
      ],
      "execution_count": 62,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/html": [
              "\n",
              "     <input type=\"file\" id=\"files-b173d180-878c-4af7-ae71-d87314e83018\" name=\"files[]\" multiple disabled\n",
              "        style=\"border:none\" />\n",
              "     <output id=\"result-b173d180-878c-4af7-ae71-d87314e83018\">\n",
              "      Upload widget is only available when the cell has been executed in the\n",
              "      current browser session. Please rerun this cell to enable.\n",
              "      </output>\n",
              "      <script src=\"/nbextensions/google.colab/files.js\"></script> "
            ],
            "text/plain": [
              "<IPython.core.display.HTML object>"
            ]
          },
          "metadata": {
            "tags": []
          }
        },
        {
          "output_type": "stream",
          "text": [
            "Saving INDU.csv to INDU (1).csv\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "{'INDU.csv': b'Date,Close\\r\\n24-06-20,25445.94\\r\\n23-06-20,26156.1\\r\\n22-06-20,26024.96\\r\\n19-06-20,25871.46\\r\\n18-06-20,26080.1\\r\\n17-06-20,26119.61\\r\\n16-06-20,26289.98\\r\\n15-06-20,25763.16\\r\\n12-06-20,25605.54\\r\\n11-06-20,25128.17\\r\\n10-06-20,26989.99\\r\\n09-06-20,27272.3\\r\\n08-06-20,27572.44\\r\\n05-06-20,27110.98\\r\\n04-06-20,26281.82\\r\\n03-06-20,26269.89\\r\\n02-06-20,25742.65\\r\\n01-06-20,25475.02\\r\\n29-05-20,25383.11\\r\\n28-05-20,25400.64\\r\\n27-05-20,25548.27\\r\\n26-05-20,24995.11\\r\\n22-05-20,24465.16\\r\\n21-05-20,24474.12\\r\\n20-05-20,24575.9\\r\\n19-05-20,24206.86\\r\\n18-05-20,24597.37\\r\\n15-05-20,23685.42\\r\\n14-05-20,23625.34\\r\\n13-05-20,23247.97\\r\\n12-05-20,23764.78\\r\\n11-05-20,24221.99\\r\\n08-05-20,24331.32\\r\\n07-05-20,23875.89\\r\\n06-05-20,23664.64\\r\\n05-05-20,23883.09\\r\\n04-05-20,23749.76\\r\\n01-05-20,23723.69\\r\\n30-04-20,24345.72\\r\\n29-04-20,24633.86\\r\\n28-04-20,24101.55\\r\\n27-04-20,24133.78\\r\\n24-04-20,23775.27\\r\\n23-04-20,23515.26\\r\\n22-04-20,23475.82\\r\\n21-04-20,23018.88\\r\\n20-04-20,23650.44\\r\\n17-04-20,24242.49\\r\\n16-04-20,23537.68\\r\\n15-04-20,23504.35\\r\\n14-04-20,23949.76\\r\\n13-04-20,23390.77\\r\\n09-04-20,23719.37\\r\\n08-04-20,23433.57\\r\\n07-04-20,22653.86\\r\\n06-04-20,22679.99\\r\\n03-04-20,21052.53\\r\\n02-04-20,21413.44\\r\\n01-04-20,20943.51\\r\\n31-03-20,21917.16\\r\\n30-03-20,22327.48\\r\\n27-03-20,21636.78\\r\\n26-03-20,22552.17\\r\\n25-03-20,21200.55\\r\\n24-03-20,20704.91\\r\\n23-03-20,18591.93\\r\\n20-03-20,19173.98\\r\\n19-03-20,20087.19\\r\\n18-03-20,19898.92\\r\\n17-03-20,21237.38\\r\\n16-03-20,20188.52\\r\\n13-03-20,23185.62\\r\\n12-03-20,21200.62\\r\\n11-03-20,23553.22\\r\\n10-03-20,25018.16\\r\\n09-03-20,23851.02\\r\\n06-03-20,25864.78\\r\\n05-03-20,26121.28\\r\\n04-03-20,27090.86\\r\\n03-03-20,25917.41\\r\\n02-03-20,26703.32\\r\\n28-02-20,25409.36\\r\\n27-02-20,25766.64\\r\\n26-02-20,26957.59\\r\\n25-02-20,27081.36\\r\\n24-02-20,27960.8\\r\\n21-02-20,28992.41\\r\\n20-02-20,29219.98\\r\\n19-02-20,29348.03\\r\\n18-02-20,29232.19\\r\\n14-02-20,29398.08\\r\\n13-02-20,29423.31\\r\\n12-02-20,29551.42\\r\\n11-02-20,29276.34\\r\\n10-02-20,29276.82\\r\\n07-02-20,29102.51\\r\\n06-02-20,29379.77\\r\\n05-02-20,29290.85\\r\\n04-02-20,28807.63\\r\\n03-02-20,28399.81\\r\\n31-01-20,28256.03\\r\\n30-01-20,28859.44\\r\\n29-01-20,28734.45\\r\\n28-01-20,28722.85\\r\\n27-01-20,28535.8\\r\\n24-01-20,28989.73\\r\\n23-01-20,29160.09\\r\\n22-01-20,29186.27\\r\\n21-01-20,29196.04\\r\\n17-01-20,29348.1\\r\\n16-01-20,29297.64\\r\\n15-01-20,29030.22\\r\\n14-01-20,28939.67\\r\\n13-01-20,28907.05\\r\\n10-01-20,28823.77\\r\\n09-01-20,28956.9\\r\\n08-01-20,28745.09\\r\\n07-01-20,28583.68\\r\\n06-01-20,28703.38\\r\\n03-01-20,28634.88\\r\\n02-01-20,28868.8\\r\\n31-12-19,28538.44\\r\\n30-12-19,28462.14\\r\\n27-12-19,28645.26\\r\\n26-12-19,28621.39\\r\\n24-12-19,28515.45\\r\\n23-12-19,28551.53\\r\\n20-12-19,28455.09\\r\\n19-12-19,28376.96\\r\\n18-12-19,28239.28\\r\\n17-12-19,28267.16\\r\\n16-12-19,28235.89\\r\\n13-12-19,28135.38\\r\\n12-12-19,28132.05\\r\\n11-12-19,27911.3\\r\\n10-12-19,27881.72\\r\\n09-12-19,27909.6\\r\\n06-12-19,28015.06\\r\\n05-12-19,27677.79\\r\\n04-12-19,27649.78\\r\\n03-12-19,27502.81\\r\\n02-12-19,27783.04\\r\\n29-11-19,28051.41\\r\\n27-11-19,28164\\r\\n26-11-19,28121.68\\r\\n25-11-19,28066.47\\r\\n22-11-19,27875.62\\r\\n21-11-19,27766.29\\r\\n20-11-19,27821.09\\r\\n19-11-19,27934.02\\r\\n18-11-19,28036.22\\r\\n15-11-19,28004.89\\r\\n14-11-19,27781.96\\r\\n13-11-19,27783.59\\r\\n12-11-19,27691.49\\r\\n11-11-19,27691.49\\r\\n08-11-19,27681.24\\r\\n07-11-19,27674.8\\r\\n06-11-19,27492.56\\r\\n05-11-19,27492.63\\r\\n04-11-19,27462.11\\r\\n01-11-19,27347.36\\r\\n31-10-19,27046.23\\r\\n30-10-19,27186.69\\r\\n29-10-19,27071.42\\r\\n28-10-19,27090.72\\r\\n25-10-19,26958.06\\r\\n24-10-19,26805.53\\r\\n23-10-19,26833.95\\r\\n22-10-19,26788.1\\r\\n21-10-19,26827.64\\r\\n18-10-19,26770.2\\r\\n17-10-19,27025.88\\r\\n16-10-19,27001.98\\r\\n15-10-19,27024.8\\r\\n14-10-19,26787.36\\r\\n11-10-19,26816.59\\r\\n10-10-19,26496.67\\r\\n09-10-19,26346.01\\r\\n08-10-19,26164.04\\r\\n07-10-19,26478.02\\r\\n04-10-19,26573.72\\r\\n03-10-19,26201.04\\r\\n02-10-19,26078.62\\r\\n01-10-19,26573.04\\r\\n30-09-19,26916.83\\r\\n27-09-19,26820.25\\r\\n26-09-19,26891.12\\r\\n25-09-19,26970.71\\r\\n24-09-19,26807.77\\r\\n23-09-19,26949.99\\r\\n20-09-19,26935.07\\r\\n19-09-19,27094.79\\r\\n18-09-19,27147.08\\r\\n17-09-19,27110.8\\r\\n16-09-19,27076.82\\r\\n13-09-19,27219.52\\r\\n12-09-19,27182.45\\r\\n11-09-19,27137.04\\r\\n10-09-19,26909.43\\r\\n09-09-19,26835.51\\r\\n06-09-19,26797.46\\r\\n05-09-19,26728.15\\r\\n04-09-19,26355.47\\r\\n03-09-19,26118.02\\r\\n30-08-19,26403.28\\r\\n29-08-19,26362.25\\r\\n28-08-19,26036.1\\r\\n27-08-19,25777.9\\r\\n26-08-19,25898.83\\r\\n23-08-19,25628.9\\r\\n22-08-19,26252.24\\r\\n21-08-19,26202.73\\r\\n20-08-19,25962.44\\r\\n19-08-19,26135.79\\r\\n16-08-19,25886.01\\r\\n15-08-19,25579.39\\r\\n14-08-19,25479.42\\r\\n13-08-19,26279.91\\r\\n12-08-19,25907.37\\r\\n09-08-19,26287.44\\r\\n08-08-19,26378.19\\r\\n07-08-19,26007.07\\r\\n06-08-19,26029.52\\r\\n05-08-19,25717.74\\r\\n02-08-19,26485.01\\r\\n01-08-19,26583.42\\r\\n31-07-19,26864.27\\r\\n30-07-19,27198.02\\r\\n29-07-19,27221.35\\r\\n26-07-19,27192.45\\r\\n25-07-19,27140.98\\r\\n24-07-19,27269.97\\r\\n23-07-19,27349.19\\r\\n22-07-19,27171.9\\r\\n19-07-19,27154.2\\r\\n18-07-19,27222.97\\r\\n17-07-19,27219.85\\r\\n16-07-19,27335.63\\r\\n15-07-19,27359.16\\r\\n12-07-19,27332.03\\r\\n11-07-19,27088.08\\r\\n10-07-19,26860.2\\r\\n09-07-19,26783.49\\r\\n08-07-19,26806.14\\r\\n05-07-19,26922.12\\r\\n03-07-19,26966\\r\\n02-07-19,26786.68\\r\\n01-07-19,26717.43\\r\\n28-06-19,26599.96\\r\\n27-06-19,26526.58\\r\\n26-06-19,26536.82\\r\\n25-06-19,26548.22\\r\\n24-06-19,26727.54\\r\\n21-06-19,26719.13\\r\\n20-06-19,26753.17\\r\\n19-06-19,26504\\r\\n18-06-19,26465.54\\r\\n17-06-19,26112.53\\r\\n14-06-19,26089.61\\r\\n13-06-19,26106.77\\r\\n12-06-19,26004.83\\r\\n11-06-19,26048.51\\r\\n10-06-19,26062.68\\r\\n07-06-19,25983.94\\r\\n06-06-19,25720.66\\r\\n05-06-19,25539.57\\r\\n04-06-19,25332.18\\r\\n03-06-19,24819.78\\r\\n31-05-19,24815.04\\r\\n30-05-19,25169.88\\r\\n29-05-19,25126.41\\r\\n28-05-19,25347.77\\r\\n24-05-19,25585.69\\r\\n23-05-19,25490.47\\r\\n22-05-19,25776.61\\r\\n21-05-19,25877.33\\r\\n20-05-19,25679.9\\r\\n17-05-19,25764\\r\\n16-05-19,25862.68\\r\\n15-05-19,25648.02\\r\\n14-05-19,25532.05\\r\\n13-05-19,25324.99\\r\\n10-05-19,25942.37\\r\\n09-05-19,25828.36\\r\\n08-05-19,25967.33\\r\\n07-05-19,25965.09\\r\\n06-05-19,26438.48\\r\\n03-05-19,26504.95\\r\\n02-05-19,26307.79\\r\\n01-05-19,26430.14\\r\\n30-04-19,26592.91\\r\\n29-04-19,26554.39\\r\\n26-04-19,26543.33\\r\\n25-04-19,26462.08\\r\\n24-04-19,26597.05\\r\\n23-04-19,26656.39\\r\\n22-04-19,26511.05\\r\\n18-04-19,26559.54\\r\\n17-04-19,26449.54\\r\\n16-04-19,26452.66\\r\\n15-04-19,26384.77\\r\\n12-04-19,26412.3\\r\\n11-04-19,26143.05\\r\\n10-04-19,26157.16\\r\\n09-04-19,26150.58\\r\\n08-04-19,26341.02\\r\\n05-04-19,26424.99\\r\\n04-04-19,26384.63\\r\\n03-04-19,26218.13\\r\\n02-04-19,26179.13\\r\\n01-04-19,26258.42\\r\\n29-03-19,25928.68\\r\\n28-03-19,25717.46\\r\\n27-03-19,25625.59\\r\\n26-03-19,25657.73\\r\\n25-03-19,25516.83\\r\\n22-03-19,25502.32\\r\\n21-03-19,25962.51\\r\\n20-03-19,25745.67\\r\\n19-03-19,25887.38\\r\\n18-03-19,25914.1\\r\\n15-03-19,25848.87\\r\\n14-03-19,25709.94\\r\\n13-03-19,25702.89\\r\\n12-03-19,25554.66\\r\\n11-03-19,25650.88\\r\\n08-03-19,25450.24\\r\\n07-03-19,25473.23\\r\\n06-03-19,25673.46\\r\\n05-03-19,25806.63\\r\\n04-03-19,25819.65\\r\\n01-03-19,26026.32\\r\\n28-02-19,25916\\r\\n27-02-19,25985.16\\r\\n26-02-19,26057.98\\r\\n25-02-19,26091.95\\r\\n22-02-19,26031.81\\r\\n21-02-19,25850.63\\r\\n20-02-19,25954.44\\r\\n19-02-19,25891.32\\r\\n15-02-19,25883.25\\r\\n14-02-19,25439.39\\r\\n13-02-19,25543.27\\r\\n12-02-19,25425.76\\r\\n11-02-19,25053.11\\r\\n08-02-19,25106.33\\r\\n07-02-19,25169.53\\r\\n06-02-19,25390.3\\r\\n05-02-19,25411.52\\r\\n04-02-19,25239.37\\r\\n01-02-19,25063.89\\r\\n31-01-19,24999.67\\r\\n30-01-19,25014.86\\r\\n29-01-19,24579.96\\r\\n28-01-19,24528.22\\r\\n25-01-19,24737.2\\r\\n24-01-19,24553.24\\r\\n23-01-19,24575.62\\r\\n22-01-19,24404.48\\r\\n18-01-19,24706.35\\r\\n17-01-19,24370.1\\r\\n16-01-19,24207.16\\r\\n15-01-19,24065.59\\r\\n14-01-19,23909.84\\r\\n11-01-19,23995.95\\r\\n10-01-19,24001.92\\r\\n09-01-19,23879.12\\r\\n08-01-19,23787.45\\r\\n07-01-19,23531.35\\r\\n04-01-19,23433.16\\r\\n03-01-19,22686.22\\r\\n02-01-19,23346.24\\r\\n31-12-18,23327.46\\r\\n28-12-18,23062.4\\r\\n27-12-18,23138.82\\r\\n26-12-18,22878.45\\r\\n24-12-18,21792.2\\r\\n21-12-18,22445.37\\r\\n20-12-18,22859.6\\r\\n19-12-18,23323.66\\r\\n18-12-18,23675.64\\r\\n17-12-18,23592.98\\r\\n14-12-18,24100.51\\r\\n13-12-18,24597.38\\r\\n12-12-18,24527.27\\r\\n11-12-18,24370.24\\r\\n10-12-18,24423.26\\r\\n07-12-18,24388.95\\r\\n06-12-18,24947.67\\r\\n04-12-18,25027.07\\r\\n03-12-18,25826.43\\r\\n30-11-18,25538.46\\r\\n29-11-18,25338.84\\r\\n28-11-18,25366.43\\r\\n27-11-18,24748.73\\r\\n26-11-18,24640.24\\r\\n23-11-18,24285.95\\r\\n21-11-18,24464.69\\r\\n20-11-18,24465.64\\r\\n19-11-18,25017.44\\r\\n16-11-18,25413.22\\r\\n15-11-18,25289.27\\r\\n14-11-18,25080.5\\r\\n13-11-18,25286.49\\r\\n12-11-18,25387.18\\r\\n09-11-18,25989.3\\r\\n08-11-18,26191.22\\r\\n07-11-18,26180.3\\r\\n06-11-18,25635.01\\r\\n05-11-18,25461.7\\r\\n02-11-18,25270.83\\r\\n01-11-18,25380.74\\r\\n31-10-18,25115.76\\r\\n30-10-18,24874.64\\r\\n29-10-18,24442.92\\r\\n26-10-18,24688.31\\r\\n25-10-18,24984.55\\r\\n24-10-18,24583.42\\r\\n23-10-18,25191.43\\r\\n22-10-18,25317.41\\r\\n19-10-18,25444.34\\r\\n18-10-18,25379.45\\r\\n17-10-18,25706.68\\r\\n16-10-18,25798.42\\r\\n15-10-18,25250.55\\r\\n12-10-18,25339.99\\r\\n11-10-18,25052.83\\r\\n10-10-18,25598.74\\r\\n09-10-18,26430.57\\r\\n08-10-18,26486.78\\r\\n05-10-18,26447.05\\r\\n04-10-18,26627.48\\r\\n03-10-18,26828.39\\r\\n02-10-18,26773.94\\r\\n01-10-18,26651.21\\r\\n28-09-18,26458.31\\r\\n27-09-18,26439.93\\r\\n26-09-18,26385.28\\r\\n25-09-18,26492.21\\r\\n24-09-18,26562.05\\r\\n21-09-18,26743.5\\r\\n20-09-18,26656.98\\r\\n19-09-18,26405.76\\r\\n18-09-18,26246.96\\r\\n17-09-18,26062.12\\r\\n14-09-18,26154.67\\r\\n13-09-18,26145.99\\r\\n12-09-18,25998.92\\r\\n11-09-18,25971.06\\r\\n10-09-18,25857.07\\r\\n07-09-18,25916.54\\r\\n06-09-18,25995.87\\r\\n05-09-18,25974.99\\r\\n04-09-18,25952.48\\r\\n31-08-18,25964.82\\r\\n30-08-18,25986.92\\r\\n29-08-18,26124.57\\r\\n28-08-18,26064.02\\r\\n27-08-18,26049.64\\r\\n24-08-18,25790.35\\r\\n23-08-18,25656.98\\r\\n22-08-18,25733.6\\r\\n21-08-18,25822.29\\r\\n20-08-18,25758.69\\r\\n17-08-18,25669.32\\r\\n16-08-18,25558.73\\r\\n15-08-18,25162.41\\r\\n14-08-18,25299.92\\r\\n13-08-18,25187.7\\r\\n10-08-18,25313.14\\r\\n09-08-18,25509.23\\r\\n08-08-18,25583.75\\r\\n07-08-18,25628.91\\r\\n06-08-18,25502.18\\r\\n03-08-18,25462.58\\r\\n02-08-18,25326.16\\r\\n01-08-18,25333.82\\r\\n31-07-18,25415.19\\r\\n30-07-18,25306.83\\r\\n27-07-18,25451.06\\r\\n26-07-18,25527.07\\r\\n25-07-18,25414.1\\r\\n24-07-18,25241.94\\r\\n23-07-18,25044.29\\r\\n20-07-18,25058.12\\r\\n19-07-18,25064.5\\r\\n18-07-18,25199.29\\r\\n17-07-18,25119.89\\r\\n16-07-18,25064.36\\r\\n13-07-18,25019.41\\r\\n12-07-18,24924.89\\r\\n11-07-18,24700.45\\r\\n10-07-18,24919.66\\r\\n09-07-18,24776.59\\r\\n06-07-18,24456.48\\r\\n05-07-18,24356.74\\r\\n03-07-18,24174.82\\r\\n02-07-18,24307.18\\r\\n29-06-18,24271.41\\r\\n28-06-18,24216.05\\r\\n27-06-18,24117.59\\r\\n26-06-18,24283.11\\r\\n25-06-18,24252.8\\r\\n22-06-18,24580.89\\r\\n21-06-18,24461.7\\r\\n20-06-18,24657.8\\r\\n19-06-18,24700.21\\r\\n18-06-18,24987.47\\r\\n15-06-18,25090.48\\r\\n14-06-18,25175.31\\r\\n13-06-18,25201.2\\r\\n12-06-18,25320.73\\r\\n11-06-18,25322.31\\r\\n08-06-18,25316.53\\r\\n07-06-18,25241.41\\r\\n06-06-18,25146.39\\r\\n05-06-18,24799.98\\r\\n04-06-18,24813.69\\r\\n01-06-18,24635.21\\r\\n31-05-18,24415.84\\r\\n30-05-18,24667.78\\r\\n29-05-18,24361.45\\r\\n25-05-18,24753.09\\r\\n24-05-18,24811.76\\r\\n23-05-18,24886.81\\r\\n22-05-18,24834.41\\r\\n21-05-18,25013.29\\r\\n18-05-18,24715.09\\r\\n17-05-18,24713.98\\r\\n16-05-18,24768.93\\r\\n15-05-18,24706.41\\r\\n14-05-18,24899.41\\r\\n11-05-18,24831.17\\r\\n10-05-18,24739.53\\r\\n09-05-18,24542.54\\r\\n08-05-18,24360.21\\r\\n07-05-18,24357.32\\r\\n04-05-18,24262.51\\r\\n03-05-18,23930.15\\r\\n02-05-18,23924.98\\r\\n01-05-18,24099.05\\r\\n30-04-18,24163.15\\r\\n27-04-18,24311.19\\r\\n26-04-18,24322.34\\r\\n25-04-18,24083.83\\r\\n24-04-18,24024.13\\r\\n23-04-18,24448.69\\r\\n20-04-18,24462.94\\r\\n19-04-18,24664.89\\r\\n18-04-18,24748.07\\r\\n17-04-18,24786.63\\r\\n16-04-18,24573.04\\r\\n13-04-18,24360.14\\r\\n12-04-18,24483.05\\r\\n11-04-18,24189.45\\r\\n10-04-18,24408\\r\\n09-04-18,23979.1\\r\\n06-04-18,23932.76\\r\\n05-04-18,24505.22\\r\\n04-04-18,24264.3\\r\\n03-04-18,24033.36\\r\\n02-04-18,23644.19\\r\\n29-03-18,24103.11\\r\\n28-03-18,23848.42\\r\\n27-03-18,23857.71\\r\\n26-03-18,24202.6\\r\\n23-03-18,23533.2\\r\\n22-03-18,23957.89\\r\\n21-03-18,24682.31\\r\\n20-03-18,24727.27\\r\\n19-03-18,24610.91\\r\\n16-03-18,24946.51\\r\\n15-03-18,24873.66\\r\\n14-03-18,24758.12\\r\\n13-03-18,25007.03\\r\\n12-03-18,25178.61\\r\\n09-03-18,25335.74\\r\\n08-03-18,24895.21\\r\\n07-03-18,24801.36\\r\\n06-03-18,24884.12\\r\\n05-03-18,24874.76\\r\\n02-03-18,24538.06\\r\\n01-03-18,24608.98\\r\\n28-02-18,25029.2\\r\\n27-02-18,25410.03\\r\\n26-02-18,25709.27\\r\\n23-02-18,25309.99\\r\\n22-02-18,24962.48\\r\\n21-02-18,24797.78\\r\\n20-02-18,24964.75\\r\\n16-02-18,25219.38\\r\\n15-02-18,25200.37\\r\\n14-02-18,24893.49\\r\\n13-02-18,24640.45\\r\\n12-02-18,24601.27\\r\\n09-02-18,24190.9\\r\\n08-02-18,23860.46\\r\\n07-02-18,24893.35\\r\\n06-02-18,24912.77\\r\\n05-02-18,24345.75\\r\\n02-02-18,25520.96\\r\\n01-02-18,26186.71\\r\\n31-01-18,26149.39\\r\\n30-01-18,26076.89\\r\\n29-01-18,26439.48\\r\\n26-01-18,26616.71\\r\\n25-01-18,26392.79\\r\\n24-01-18,26252.12\\r\\n23-01-18,26210.81\\r\\n22-01-18,26214.6\\r\\n19-01-18,26071.72\\r\\n18-01-18,26017.81\\r\\n17-01-18,26115.65\\r\\n16-01-18,25792.86\\r\\n12-01-18,25803.19\\r\\n11-01-18,25574.73\\r\\n10-01-18,25369.13\\r\\n09-01-18,25385.8\\r\\n08-01-18,25283\\r\\n05-01-18,25295.87\\r\\n04-01-18,25075.13\\r\\n03-01-18,24922.68\\r\\n02-01-18,24824.01\\r\\n29-12-17,24719.22\\r\\n28-12-17,24837.51\\r\\n27-12-17,24774.3\\r\\n26-12-17,24746.21\\r\\n22-12-17,24754.06\\r\\n21-12-17,24782.29\\r\\n20-12-17,24726.65\\r\\n19-12-17,24754.75\\r\\n18-12-17,24792.2\\r\\n15-12-17,24651.74\\r\\n14-12-17,24508.66\\r\\n13-12-17,24585.43\\r\\n12-12-17,24504.8\\r\\n11-12-17,24386.03\\r\\n08-12-17,24329.16\\r\\n07-12-17,24211.48\\r\\n06-12-17,24140.91\\r\\n05-12-17,24180.64\\r\\n04-12-17,24290.05\\r\\n01-12-17,24231.59\\r\\n30-11-17,24272.35\\r\\n29-11-17,23940.68\\r\\n28-11-17,23836.71\\r\\n27-11-17,23580.78\\r\\n24-11-17,23557.99\\r\\n22-11-17,23526.18\\r\\n21-11-17,23590.83\\r\\n20-11-17,23430.33\\r\\n17-11-17,23358.24\\r\\n16-11-17,23458.36\\r\\n15-11-17,23271.28\\r\\n14-11-17,23409.47\\r\\n13-11-17,23439.7\\r\\n10-11-17,23422.21\\r\\n09-11-17,23461.94\\r\\n08-11-17,23563.36\\r\\n07-11-17,23557.23\\r\\n06-11-17,23548.42\\r\\n03-11-17,23539.19\\r\\n02-11-17,23516.26\\r\\n01-11-17,23435.01\\r\\n31-10-17,23377.24\\r\\n30-10-17,23348.74\\r\\n27-10-17,23434.19\\r\\n26-10-17,23400.86\\r\\n25-10-17,23329.46\\r\\n24-10-17,23441.76\\r\\n23-10-17,23273.96\\r\\n20-10-17,23328.63\\r\\n19-10-17,23163.04\\r\\n18-10-17,23157.6\\r\\n17-10-17,22997.44\\r\\n16-10-17,22956.96\\r\\n13-10-17,22871.72\\r\\n12-10-17,22841.01\\r\\n11-10-17,22872.89\\r\\n10-10-17,22830.68\\r\\n09-10-17,22761.07\\r\\n06-10-17,22773.67\\r\\n05-10-17,22775.39\\r\\n04-10-17,22661.64\\r\\n03-10-17,22641.67\\r\\n02-10-17,22557.6\\r\\n29-09-17,22405.09\\r\\n28-09-17,22381.2\\r\\n27-09-17,22340.71\\r\\n26-09-17,22284.32\\r\\n25-09-17,22296.09\\r\\n22-09-17,22349.59\\r\\n21-09-17,22359.23\\r\\n20-09-17,22412.59\\r\\n19-09-17,22370.8\\r\\n18-09-17,22331.35\\r\\n15-09-17,22268.34\\r\\n14-09-17,22203.48\\r\\n13-09-17,22158.18\\r\\n12-09-17,22118.86\\r\\n11-09-17,22057.37\\r\\n08-09-17,21797.79\\r\\n07-09-17,21784.78\\r\\n06-09-17,21807.64\\r\\n05-09-17,21753.31\\r\\n01-09-17,21987.56\\r\\n31-08-17,21948.1\\r\\n30-08-17,21892.43\\r\\n29-08-17,21865.37\\r\\n28-08-17,21808.4\\r\\n25-08-17,21813.67\\r\\n24-08-17,21783.4\\r\\n23-08-17,21812.09\\r\\n22-08-17,21899.89\\r\\n21-08-17,21703.75\\r\\n18-08-17,21674.51\\r\\n17-08-17,21750.73\\r\\n16-08-17,22024.87\\r\\n15-08-17,21998.99\\r\\n14-08-17,21993.71\\r\\n11-08-17,21858.32\\r\\n10-08-17,21844.01\\r\\n09-08-17,22048.7\\r\\n08-08-17,22085.34\\r\\n07-08-17,22118.42\\r\\n04-08-17,22092.81\\r\\n03-08-17,22026.1\\r\\n02-08-17,22016.24\\r\\n01-08-17,21963.92\\r\\n31-07-17,21891.12\\r\\n28-07-17,21830.31\\r\\n27-07-17,21796.55\\r\\n26-07-17,21711.01\\r\\n25-07-17,21613.43\\r\\n24-07-17,21513.17\\r\\n21-07-17,21580.07\\r\\n20-07-17,21611.78\\r\\n19-07-17,21640.75\\r\\n18-07-17,21574.73\\r\\n17-07-17,21629.72\\r\\n14-07-17,21637.74\\r\\n13-07-17,21553.09\\r\\n12-07-17,21532.14\\r\\n11-07-17,21409.07\\r\\n10-07-17,21408.52\\r\\n07-07-17,21414.34\\r\\n06-07-17,21320.04\\r\\n05-07-17,21478.17\\r\\n03-07-17,21479.27\\r\\n30-06-17,21349.63\\r\\n29-06-17,21287.03\\r\\n28-06-17,21454.61\\r\\n27-06-17,21310.66\\r\\n26-06-17,21409.55\\r\\n23-06-17,21394.76\\r\\n22-06-17,21397.29\\r\\n21-06-17,21410.03\\r\\n20-06-17,21467.14\\r\\n19-06-17,21528.99\\r\\n16-06-17,21384.28\\r\\n15-06-17,21359.9\\r\\n14-06-17,21374.56\\r\\n13-06-17,21328.47\\r\\n12-06-17,21235.67\\r\\n09-06-17,21271.97\\r\\n08-06-17,21182.53\\r\\n07-06-17,21173.69\\r\\n06-06-17,21136.23\\r\\n05-06-17,21184.04\\r\\n02-06-17,21206.29\\r\\n01-06-17,21144.18\\r\\n31-05-17,21008.65\\r\\n30-05-17,21029.47\\r\\n26-05-17,21080.28\\r\\n25-05-17,21082.95\\r\\n24-05-17,21012.42\\r\\n23-05-17,20937.91\\r\\n22-05-17,20894.83\\r\\n19-05-17,20804.84\\r\\n18-05-17,20663.02\\r\\n17-05-17,20606.93\\r\\n16-05-17,20979.75\\r\\n15-05-17,20981.94\\r\\n12-05-17,20896.61\\r\\n11-05-17,20919.42\\r\\n10-05-17,20943.11\\r\\n09-05-17,20975.78\\r\\n08-05-17,21012.28\\r\\n05-05-17,21006.94\\r\\n04-05-17,20951.47\\r\\n03-05-17,20957.9\\r\\n02-05-17,20949.89\\r\\n01-05-17,20913.46\\r\\n28-04-17,20940.51\\r\\n27-04-17,20981.33\\r\\n26-04-17,20975.09\\r\\n25-04-17,20996.12\\r\\n24-04-17,20763.89\\r\\n21-04-17,20547.76\\r\\n20-04-17,20578.71\\r\\n19-04-17,20404.49\\r\\n18-04-17,20523.28\\r\\n17-04-17,20636.92\\r\\n13-04-17,20453.25\\r\\n12-04-17,20591.86\\r\\n11-04-17,20651.3\\r\\n10-04-17,20658.02\\r\\n07-04-17,20656.1\\r\\n06-04-17,20662.95\\r\\n05-04-17,20648.15\\r\\n04-04-17,20689.24\\r\\n03-04-17,20650.21\\r\\n31-03-17,20663.22\\r\\n30-03-17,20728.49\\r\\n29-03-17,20659.32\\r\\n28-03-17,20701.5\\r\\n27-03-17,20550.98\\r\\n24-03-17,20596.72\\r\\n23-03-17,20656.58\\r\\n22-03-17,20661.3\\r\\n21-03-17,20668.01\\r\\n20-03-17,20905.86\\r\\n17-03-17,20914.62\\r\\n16-03-17,20934.55\\r\\n15-03-17,20950.1\\r\\n14-03-17,20837.37\\r\\n13-03-17,20881.48\\r\\n10-03-17,20902.98\\r\\n09-03-17,20858.19\\r\\n08-03-17,20855.73\\r\\n07-03-17,20924.76\\r\\n06-03-17,20954.34\\r\\n03-03-17,21005.71\\r\\n02-03-17,21002.97\\r\\n01-03-17,21115.55\\r\\n28-02-17,20812.24\\r\\n27-02-17,20837.44\\r\\n24-02-17,20821.76\\r\\n23-02-17,20810.32\\r\\n22-02-17,20775.6\\r\\n21-02-17,20743\\r\\n17-02-17,20624.05\\r\\n16-02-17,20619.77\\r\\n15-02-17,20611.86\\r\\n14-02-17,20504.41\\r\\n13-02-17,20412.16\\r\\n10-02-17,20269.37\\r\\n09-02-17,20172.4\\r\\n08-02-17,20054.34\\r\\n07-02-17,20090.29\\r\\n06-02-17,20052.42\\r\\n03-02-17,20071.46\\r\\n02-02-17,19884.91\\r\\n01-02-17,19890.94\\r\\n31-01-17,19864.09\\r\\n30-01-17,19971.13\\r\\n27-01-17,20093.78\\r\\n26-01-17,20100.91\\r\\n25-01-17,20068.51\\r\\n24-01-17,19912.71\\r\\n23-01-17,19799.85\\r\\n20-01-17,19827.25\\r\\n19-01-17,19732.4\\r\\n18-01-17,19804.72\\r\\n17-01-17,19826.77\\r\\n13-01-17,19885.73\\r\\n12-01-17,19891\\r\\n11-01-17,19954.28\\r\\n10-01-17,19855.53\\r\\n09-01-17,19887.38\\r\\n06-01-17,19963.8\\r\\n05-01-17,19899.29\\r\\n04-01-17,19942.16\\r\\n03-01-17,19881.76\\r\\n30-12-16,19762.6\\r\\n29-12-16,19819.78\\r\\n28-12-16,19833.68\\r\\n27-12-16,19945.04\\r\\n23-12-16,19933.81\\r\\n22-12-16,19918.88\\r\\n21-12-16,19941.96\\r\\n20-12-16,19974.62\\r\\n19-12-16,19883.06\\r\\n16-12-16,19843.41\\r\\n15-12-16,19852.24\\r\\n14-12-16,19792.53\\r\\n13-12-16,19911.21\\r\\n12-12-16,19796.43\\r\\n09-12-16,19756.85\\r\\n08-12-16,19614.81\\r\\n07-12-16,19549.62\\r\\n06-12-16,19251.78\\r\\n05-12-16,19216.24\\r\\n02-12-16,19170.42\\r\\n01-12-16,19191.93\\r\\n30-11-16,19123.58\\r\\n29-11-16,19121.6\\r\\n28-11-16,19097.9\\r\\n25-11-16,19152.14\\r\\n23-11-16,19083.18\\r\\n22-11-16,19023.87\\r\\n21-11-16,18956.69\\r\\n18-11-16,18867.93\\r\\n17-11-16,18903.82\\r\\n16-11-16,18868.14\\r\\n15-11-16,18923.06\\r\\n14-11-16,18868.69\\r\\n11-11-16,18847.66\\r\\n10-11-16,18807.88\\r\\n09-11-16,18589.69\\r\\n08-11-16,18332.74\\r\\n07-11-16,18259.6\\r\\n04-11-16,17888.28\\r\\n03-11-16,17930.67\\r\\n02-11-16,17959.64\\r\\n01-11-16,18037.1\\r\\n31-10-16,18142.42\\r\\n28-10-16,18161.19\\r\\n27-10-16,18169.68\\r\\n26-10-16,18199.33\\r\\n25-10-16,18169.27\\r\\n24-10-16,18223.03\\r\\n21-10-16,18145.71\\r\\n20-10-16,18162.35\\r\\n19-10-16,18202.62\\r\\n18-10-16,18161.94\\r\\n17-10-16,18086.4\\r\\n14-10-16,18138.38\\r\\n13-10-16,18098.94\\r\\n12-10-16,18144.2\\r\\n11-10-16,18128.66\\r\\n10-10-16,18329.04\\r\\n07-10-16,18240.49\\r\\n06-10-16,18268.5\\r\\n05-10-16,18281.03\\r\\n04-10-16,18168.45\\r\\n03-10-16,18253.85\\r\\n30-09-16,18308.15\\r\\n29-09-16,18143.45\\r\\n28-09-16,18339.24\\r\\n27-09-16,18228.3\\r\\n26-09-16,18094.83\\r\\n23-09-16,18261.45\\r\\n22-09-16,18392.46\\r\\n21-09-16,18293.7\\r\\n20-09-16,18129.96\\r\\n19-09-16,18120.17\\r\\n16-09-16,18123.8\\r\\n15-09-16,18212.48\\r\\n14-09-16,18034.77\\r\\n13-09-16,18066.75\\r\\n12-09-16,18325.07\\r\\n09-09-16,18085.45\\r\\n08-09-16,18479.91\\r\\n07-09-16,18526.14\\r\\n06-09-16,18538.12\\r\\n02-09-16,18491.96\\r\\n01-09-16,18419.3\\r\\n31-08-16,18400.88\\r\\n30-08-16,18454.3\\r\\n29-08-16,18502.99\\r\\n26-08-16,18395.4\\r\\n25-08-16,18448.41\\r\\n24-08-16,18481.48\\r\\n23-08-16,18547.3\\r\\n22-08-16,18529.42\\r\\n19-08-16,18552.57\\r\\n18-08-16,18597.7\\r\\n17-08-16,18573.94\\r\\n16-08-16,18552.02\\r\\n15-08-16,18636.05\\r\\n12-08-16,18576.47\\r\\n11-08-16,18613.52\\r\\n10-08-16,18495.66\\r\\n09-08-16,18533.05\\r\\n08-08-16,18529.29\\r\\n05-08-16,18543.53\\r\\n04-08-16,18352.05\\r\\n03-08-16,18355\\r\\n02-08-16,18313.77\\r\\n01-08-16,18404.51\\r\\n29-07-16,18432.24\\r\\n28-07-16,18456.35\\r\\n27-07-16,18472.17\\r\\n26-07-16,18473.75\\r\\n25-07-16,18493.06\\r\\n22-07-16,18570.85\\r\\n21-07-16,18517.23\\r\\n20-07-16,18595.03\\r\\n19-07-16,18559.01\\r\\n18-07-16,18533.05\\r\\n15-07-16,18516.55\\r\\n14-07-16,18506.41\\r\\n13-07-16,18372.12\\r\\n12-07-16,18347.67\\r\\n11-07-16,18226.93\\r\\n08-07-16,18146.74\\r\\n07-07-16,17895.88\\r\\n06-07-16,17918.62\\r\\n05-07-16,17840.62\\r\\n01-07-16,17949.37\\r\\n30-06-16,17929.99\\r\\n29-06-16,17694.68\\r\\n28-06-16,17409.72\\r\\n27-06-16,17140.24\\r\\n24-06-16,17400.75\\r\\n23-06-16,18011.07\\r\\n22-06-16,17780.83\\r\\n21-06-16,17829.73\\r\\n20-06-16,17804.87\\r\\n17-06-16,17675.16\\r\\n16-06-16,17733.1\\r\\n15-06-16,17640.17\\r\\n14-06-16,17674.82\\r\\n13-06-16,17732.48\\r\\n10-06-16,17865.34\\r\\n09-06-16,17985.19\\r\\n08-06-16,18005.05\\r\\n07-06-16,17938.28\\r\\n06-06-16,17920.33\\r\\n03-06-16,17807.06\\r\\n02-06-16,17838.56\\r\\n01-06-16,17789.67\\r\\n31-05-16,17787.2\\r\\n27-05-16,17873.22\\r\\n26-05-16,17828.29\\r\\n25-05-16,17851.51\\r\\n24-05-16,17706.05\\r\\n23-05-16,17492.93\\r\\n20-05-16,17500.94\\r\\n19-05-16,17435.4\\r\\n18-05-16,17526.62\\r\\n17-05-16,17529.98\\r\\n16-05-16,17710.71\\r\\n13-05-16,17535.32\\r\\n12-05-16,17720.5\\r\\n11-05-16,17711.12\\r\\n10-05-16,17928.35\\r\\n09-05-16,17705.91\\r\\n06-05-16,17740.63\\r\\n05-05-16,17660.71\\r\\n04-05-16,17651.26\\r\\n03-05-16,17750.91\\r\\n02-05-16,17891.16\\r\\n29-04-16,17773.64\\r\\n28-04-16,17830.76\\r\\n27-04-16,18041.55\\r\\n26-04-16,17990.32\\r\\n25-04-16,17977.24\\r\\n22-04-16,18003.75\\r\\n21-04-16,17982.52\\r\\n20-04-16,18096.27\\r\\n19-04-16,18053.6\\r\\n18-04-16,18004.16\\r\\n15-04-16,17897.46\\r\\n14-04-16,17926.43\\r\\n13-04-16,17908.28\\r\\n12-04-16,17721.25\\r\\n11-04-16,17556.41\\r\\n08-04-16,17576.96\\r\\n07-04-16,17541.96\\r\\n06-04-16,17716.05\\r\\n05-04-16,17603.32\\r\\n04-04-16,17737\\r\\n01-04-16,17792.75\\r\\n31-03-16,17685.09\\r\\n30-03-16,17716.66\\r\\n29-03-16,17633.11\\r\\n28-03-16,17535.39\\r\\n24-03-16,17515.73\\r\\n23-03-16,17502.59\\r\\n22-03-16,17582.57\\r\\n21-03-16,17623.87\\r\\n18-03-16,17602.3\\r\\n17-03-16,17481.49\\r\\n16-03-16,17325.76\\r\\n15-03-16,17251.53\\r\\n14-03-16,17229.13\\r\\n11-03-16,17213.31\\r\\n10-03-16,16995.13\\r\\n09-03-16,17000.36\\r\\n08-03-16,16964.1\\r\\n07-03-16,17073.95\\r\\n04-03-16,17006.77\\r\\n03-03-16,16943.9\\r\\n02-03-16,16899.32\\r\\n01-03-16,16865.08\\r\\n29-02-16,16516.5\\r\\n26-02-16,16639.97\\r\\n25-02-16,16697.29\\r\\n24-02-16,16484.99\\r\\n23-02-16,16431.78\\r\\n22-02-16,16620.66\\r\\n19-02-16,16391.99\\r\\n18-02-16,16413.43\\r\\n17-02-16,16453.83\\r\\n16-02-16,16196.41\\r\\n12-02-16,15973.84\\r\\n11-02-16,15660.18\\r\\n10-02-16,15914.74\\r\\n09-02-16,16014.38\\r\\n08-02-16,16027.05\\r\\n05-02-16,16204.97\\r\\n04-02-16,16416.58\\r\\n03-02-16,16336.66\\r\\n02-02-16,16153.54\\r\\n01-02-16,16449.18\\r\\n29-01-16,16466.3\\r\\n28-01-16,16069.64\\r\\n27-01-16,15944.46\\r\\n26-01-16,16167.23\\r\\n25-01-16,15885.22\\r\\n22-01-16,16093.51\\r\\n21-01-16,15882.68\\r\\n20-01-16,15766.74\\r\\n19-01-16,16016.02\\r\\n15-01-16,15988.08\\r\\n14-01-16,16379.05\\r\\n13-01-16,16151.41\\r\\n12-01-16,16516.22\\r\\n11-01-16,16398.57\\r\\n08-01-16,16346.45\\r\\n07-01-16,16514.1\\r\\n06-01-16,16906.51\\r\\n05-01-16,17158.66\\r\\n04-01-16,17148.94\\r\\n31-12-15,17425.03\\r\\n30-12-15,17603.87\\r\\n29-12-15,17720.98\\r\\n28-12-15,17528.27\\r\\n24-12-15,17552.17\\r\\n23-12-15,17602.61\\r\\n22-12-15,17417.27\\r\\n21-12-15,17251.62\\r\\n18-12-15,17128.55\\r\\n17-12-15,17495.84\\r\\n16-12-15,17749.09\\r\\n15-12-15,17524.91\\r\\n14-12-15,17368.5\\r\\n11-12-15,17265.21\\r\\n10-12-15,17574.75\\r\\n09-12-15,17492.3\\r\\n08-12-15,17568\\r\\n07-12-15,17730.51\\r\\n04-12-15,17847.63\\r\\n03-12-15,17477.67\\r\\n02-12-15,17729.68\\r\\n01-12-15,17888.35\\r\\n30-11-15,17719.92\\r\\n27-11-15,17798.49\\r\\n25-11-15,17813.39\\r\\n24-11-15,17812.19\\r\\n23-11-15,17792.68\\r\\n20-11-15,17823.81\\r\\n19-11-15,17732.75\\r\\n18-11-15,17737.16\\r\\n17-11-15,17489.5\\r\\n16-11-15,17483.01\\r\\n13-11-15,17245.24\\r\\n12-11-15,17448.07\\r\\n11-11-15,17702.22\\r\\n10-11-15,17758.21\\r\\n09-11-15,17730.48\\r\\n06-11-15,17910.33\\r\\n05-11-15,17863.43\\r\\n04-11-15,17867.58\\r\\n03-11-15,17918.15\\r\\n02-11-15,17828.76\\r\\n30-10-15,17663.54\\r\\n29-10-15,17755.8\\r\\n28-10-15,17779.52\\r\\n27-10-15,17581.43\\r\\n26-10-15,17623.05\\r\\n23-10-15,17646.7\\r\\n22-10-15,17489.16\\r\\n21-10-15,17168.61\\r\\n20-10-15,17217.11\\r\\n19-10-15,17230.54\\r\\n16-10-15,17215.97\\r\\n15-10-15,17141.75\\r\\n14-10-15,16924.75\\r\\n13-10-15,17081.89\\r\\n12-10-15,17131.86\\r\\n09-10-15,17084.49\\r\\n08-10-15,17050.75\\r\\n07-10-15,16912.29\\r\\n06-10-15,16790.19\\r\\n05-10-15,16776.43\\r\\n02-10-15,16472.37\\r\\n01-10-15,16272.01\\r\\n30-09-15,16284.7\\r\\n29-09-15,16049.13\\r\\n28-09-15,16001.89\\r\\n25-09-15,16314.67\\r\\n24-09-15,16201.32\\r\\n23-09-15,16279.89\\r\\n22-09-15,16330.47\\r\\n21-09-15,16510.19\\r\\n18-09-15,16384.58\\r\\n17-09-15,16674.74\\r\\n16-09-15,16739.95\\r\\n15-09-15,16599.85\\r\\n14-09-15,16370.96\\r\\n11-09-15,16433.09\\r\\n10-09-15,16330.4\\r\\n09-09-15,16253.57\\r\\n08-09-15,16492.68\\r\\n04-09-15,16102.38\\r\\n03-09-15,16374.76\\r\\n02-09-15,16351.38\\r\\n01-09-15,16058.35\\r\\n31-08-15,16528.03\\r\\n28-08-15,16643.01\\r\\n27-08-15,16654.77\\r\\n26-08-15,16285.51\\r\\n25-08-15,15666.44\\r\\n24-08-15,15871.35\\r\\n21-08-15,16459.75\\r\\n20-08-15,16990.69\\r\\n19-08-15,17348.73\\r\\n18-08-15,17511.34\\r\\n17-08-15,17545.18\\r\\n14-08-15,17477.4\\r\\n13-08-15,17408.25\\r\\n12-08-15,17402.51\\r\\n11-08-15,17402.84\\r\\n10-08-15,17615.17\\r\\n07-08-15,17373.38\\r\\n06-08-15,17419.75\\r\\n05-08-15,17540.47\\r\\n04-08-15,17550.69\\r\\n03-08-15,17598.2\\r\\n31-07-15,17689.86\\r\\n30-07-15,17745.98\\r\\n29-07-15,17751.39\\r\\n28-07-15,17630.27\\r\\n27-07-15,17440.59\\r\\n24-07-15,17568.53\\r\\n23-07-15,17731.92\\r\\n22-07-15,17851.04\\r\\n21-07-15,17919.29\\r\\n20-07-15,18100.41\\r\\n17-07-15,18086.45\\r\\n16-07-15,18120.25\\r\\n15-07-15,18050.17\\r\\n14-07-15,18053.58\\r\\n13-07-15,17977.68\\r\\n10-07-15,17760.41\\r\\n09-07-15,17548.62\\r\\n08-07-15,17515.42\\r\\n07-07-15,17776.91\\r\\n06-07-15,17683.58\\r\\n02-07-15,17730.11\\r\\n01-07-15,17757.91\\r\\n30-06-15,17619.51\\r\\n29-06-15,17596.35\\r\\n'}"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 62
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "cyDkEgiC5eRr",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "df = pd.read_csv('INDU.csv')"
      ],
      "execution_count": 63,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "fQCXY1Yl6DGH",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "df['Date'] = pd.to_datetime(df['Date'], dayfirst=True)\n",
        "df.set_index(\"Date\", drop=False, inplace=True)"
      ],
      "execution_count": 64,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "XVchf71k6Kvb",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "df  =df.iloc[::-1]"
      ],
      "execution_count": 65,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "ndJv8b0y630b",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "df.drop(labels=['Date'],axis =1, inplace=True)\n",
        "\n"
      ],
      "execution_count": 66,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "w_DDHe8mB4Mx",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 436
        },
        "outputId": "d481352c-51bd-4ad6-c8da-5e7e520f5079"
      },
      "source": [
        "df\n"
      ],
      "execution_count": 67,
      "outputs": [
        {
          "output_type": "execute_result",
          "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>Close</th>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Date</th>\n",
              "      <th></th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>2015-06-29</th>\n",
              "      <td>17596.35</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2015-06-30</th>\n",
              "      <td>17619.51</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2015-07-01</th>\n",
              "      <td>17757.91</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2015-07-02</th>\n",
              "      <td>17730.11</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2015-07-06</th>\n",
              "      <td>17683.58</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>...</th>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2020-06-18</th>\n",
              "      <td>26080.10</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2020-06-19</th>\n",
              "      <td>25871.46</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2020-06-22</th>\n",
              "      <td>26024.96</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2020-06-23</th>\n",
              "      <td>26156.10</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2020-06-24</th>\n",
              "      <td>25445.94</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>1257 rows × 1 columns</p>\n",
              "</div>"
            ],
            "text/plain": [
              "               Close\n",
              "Date                \n",
              "2015-06-29  17596.35\n",
              "2015-06-30  17619.51\n",
              "2015-07-01  17757.91\n",
              "2015-07-02  17730.11\n",
              "2015-07-06  17683.58\n",
              "...              ...\n",
              "2020-06-18  26080.10\n",
              "2020-06-19  25871.46\n",
              "2020-06-22  26024.96\n",
              "2020-06-23  26156.10\n",
              "2020-06-24  25445.94\n",
              "\n",
              "[1257 rows x 1 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 67
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "dryoIu__7j-3",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "import tensorflow as tf\n",
        "from tensorflow.keras.models import Sequential\n",
        "from tensorflow.keras.layers import Dense,LSTM, Dropout\n",
        "from tensorflow.keras.preprocessing.sequence import TimeseriesGenerator\n",
        "import numpy as np"
      ],
      "execution_count": 68,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Mumq-s0K7j01",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "series = np.array(df['Close'])\n",
        "y_true = series[-1]\n",
        "y_test = series[-11:-1]\n",
        "series = series[:-11]"
      ],
      "execution_count": 72,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "6flMCaFwN85K",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 34
        },
        "outputId": "d6e5f394-c858-43e3-c40f-d4e93be872ff"
      },
      "source": [
        "len(y_test)"
      ],
      "execution_count": 10,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "30"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 10
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "u_1vlPok7jro",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "def split_sequence(seq, n_steps):\n",
        "    X, y= list(), list()\n",
        "    for i in range(len(seq)):\n",
        "        end_ix = i + n_steps\n",
        "        \n",
        "        if end_ix > len(seq)-1:\n",
        "            break\n",
        "        seq_x, seq_y = seq[i:end_ix], seq[end_ix]\n",
        "        X.append(seq_x)\n",
        "        y.append(seq_y)\n",
        "    return np.array(X), np.array(y)"
      ],
      "execution_count": 73,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "eA9EkFDg8C29",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 143
        },
        "outputId": "e454c66b-373e-46f8-81d5-16f49f7e1757"
      },
      "source": [
        "# -*- coding: utf-8 -*-\n",
        "\"\"\"\n",
        "Created on Thu Jun 25 00:01:34 2020\n",
        "\n",
        "@author: ROHAN\n",
        "\"\"\"\n",
        "\n",
        "outputs = []\n",
        "for n_steps in [10]:\n",
        "  X, y = split_sequence(series, n_steps)\n",
        "  # define generator\n",
        "  n_input = n_steps\n",
        "  '''\n",
        "  generator = TimeseriesGenerator(series, series, length=n_input, batch_size=8)\n",
        "  for i in range(len(generator)):\n",
        "    x, y = generator[i]\n",
        "    print('%s => %s' % (x, y))\n",
        "  '''   \n",
        "  # define model\n",
        "  \n",
        "  model = Sequential([\n",
        "  tf.keras.layers.Bidirectional(LSTM(64,activation='relu', return_sequences=True, input_shape=(n_input,1))),\n",
        "  tf.keras.layers.Bidirectional(LSTM(32, activation='relu')),\n",
        "  Dense(1)\n",
        "  ])\n",
        "\n",
        "  model.compile(optimizer='adam', loss='mean_squared_error')\n",
        "\n",
        "  X = X.reshape((X.shape[0], X.shape[1], 1))\n",
        "\n",
        "  model.fit(X,y, epochs=100, verbose=0)\n",
        "\n",
        "  # make a one step prediction out of sample\n",
        "  x_input = y_test.reshape((1, n_input,1))\n",
        "  yhat = model.predict(x_input, verbose=0)\n",
        "  outputs.append(yhat)\n"
      ],
      "execution_count": 74,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "WARNING:tensorflow:Layer lstm_34 will not use cuDNN kernel since it doesn't meet the cuDNN kernel criteria. It will use generic GPU kernel as fallback when running on GPU\n",
            "WARNING:tensorflow:Layer lstm_34 will not use cuDNN kernel since it doesn't meet the cuDNN kernel criteria. It will use generic GPU kernel as fallback when running on GPU\n",
            "WARNING:tensorflow:Layer lstm_34 will not use cuDNN kernel since it doesn't meet the cuDNN kernel criteria. It will use generic GPU kernel as fallback when running on GPU\n",
            "WARNING:tensorflow:Layer lstm_35 will not use cuDNN kernel since it doesn't meet the cuDNN kernel criteria. It will use generic GPU kernel as fallback when running on GPU\n",
            "WARNING:tensorflow:Layer lstm_35 will not use cuDNN kernel since it doesn't meet the cuDNN kernel criteria. It will use generic GPU kernel as fallback when running on GPU\n",
            "WARNING:tensorflow:Layer lstm_35 will not use cuDNN kernel since it doesn't meet the cuDNN kernel criteria. It will use generic GPU kernel as fallback when running on GPU\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "EpTPcNGcASvH",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 34
        },
        "outputId": "a96bdc5b-030e-4396-8ab6-42ece695d891"
      },
      "source": [
        "outputs"
      ],
      "execution_count": 75,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "[array([[26015.984]], dtype=float32)]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 75
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "b5CyvGiAE-K5",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 34
        },
        "outputId": "d9013991-84e1-411d-8807-24b6de2c730b"
      },
      "source": [
        "y_true"
      ],
      "execution_count": 76,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "25445.94"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 76
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "73DSNX6qdxd3",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "x_input = y_test.reshape((1, n_input,1))\n",
        "for i in range(30):\n",
        "  yhat = model.predict(x_input, verbose=0)\n",
        "  outputs.append(yhat)"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "vv952Zl0hbtF",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 105
        },
        "outputId": "fabbae0d-d903-47b8-c2ff-69713d206a0a"
      },
      "source": [
        "y_test\n"
      ],
      "execution_count": 46,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([23764.78, 23247.97, 23625.34, 23685.42, 24597.37, 24206.86,\n",
              "       24575.9 , 24474.12, 24465.16, 24995.11, 25548.27, 25400.64,\n",
              "       25383.11, 25475.02, 25742.65, 26269.89, 26281.82, 27110.98,\n",
              "       27572.44, 27272.3 , 26989.99, 25128.17, 25605.54, 25763.16,\n",
              "       26289.98, 26119.61, 26080.1 , 25871.46, 26024.96, 26156.1 ])"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 46
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "2eCEZKinhfJG",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 301
        },
        "outputId": "9e5c67ee-6df4-45a6-e9fa-b1579e2fac1d"
      },
      "source": [
        "from pandas.plotting import autocorrelation_plot\n",
        "autocorrelation_plot(series)"
      ],
      "execution_count": 47,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<matplotlib.axes._subplots.AxesSubplot at 0x7f01f045a780>"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 47
        },
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 432x288 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": [],
            "needs_background": "light"
          }
        }
      ]
    }
  ]
}