Google_stock_price_pred.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "Google_stock_price_pred.ipynb",
      "provenance": [],
      "authorship_tag": "ABX9TyPtALkbS60hOlkjqF5lKRMw",
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    },
    "accelerator": "GPU"
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/github/vpavankalyan/Google-Stock-Price-Pediction/blob/main/Google_stock_price_pred.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "nk6RavdcMyRT"
      },
      "source": [
        "#Importing Libraries"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "vpw-VBkNL1I2"
      },
      "source": [
        "import pandas as pd"
      ],
      "execution_count": 1,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "04_8fBPcL58Y"
      },
      "source": [
        "import numpy as np"
      ],
      "execution_count": 2,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "sbkR6VMTL8oF"
      },
      "source": [
        "import matplotlib.pyplot as plt"
      ],
      "execution_count": 3,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "szPCjRo4MAWd"
      },
      "source": [
        "#Importing Dataset"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "ZTZy6DxKMCMt"
      },
      "source": [
        "dataset_train = pd.read_csv('/content/Google_Stock_Price_Train.csv')"
      ],
      "execution_count": 4,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "kZOYR66vMOwn"
      },
      "source": [
        "train_set = dataset_train.iloc[:, 1:2].values"
      ],
      "execution_count": 5,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "M8sHHdmHMkKo"
      },
      "source": [
        "#Feature Scaling"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "YDsC8opuMieJ"
      },
      "source": [
        "from sklearn.preprocessing import MinMaxScaler"
      ],
      "execution_count": 6,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "XSBcJ_yYNEbq"
      },
      "source": [
        "sc = MinMaxScaler(feature_range=(0,1))"
      ],
      "execution_count": 7,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "oyjv8T-UNP7k"
      },
      "source": [
        "train_set_scaled = sc.fit_transform(train_set)"
      ],
      "execution_count": 8,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "tsWXELmoNtKQ",
        "outputId": "0f797c0e-bce3-46bd-9adb-d4896fb8376d"
      },
      "source": [
        "print(train_set)"
      ],
      "execution_count": 9,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "[[325.25]\n",
            " [331.27]\n",
            " [329.83]\n",
            " ...\n",
            " [793.7 ]\n",
            " [783.33]\n",
            " [782.75]]\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "2UC19WgjIp7D",
        "outputId": "85440266-8fd5-4620-cf6a-0b244312ab11"
      },
      "source": [
        "train_set.shape"
      ],
      "execution_count": 10,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(1258, 1)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 10
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "_Z3MMMLzNorK",
        "outputId": "fe501f23-47af-45a9-a032-791b42fa52ab"
      },
      "source": [
        "print(train_set_scaled)"
      ],
      "execution_count": 11,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "[[0.08581368]\n",
            " [0.09701243]\n",
            " [0.09433366]\n",
            " ...\n",
            " [0.95725128]\n",
            " [0.93796041]\n",
            " [0.93688146]]\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "lyspWOr4OWIy"
      },
      "source": [
        "# Data Preprocessing"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "ZxsRl8vICj_G"
      },
      "source": [
        "Data Structure with 60 Timestamps and 1 Output"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "X3edEwtVNwQ8"
      },
      "source": [
        "X_train = []"
      ],
      "execution_count": 12,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "2F4ZNS6iO7YU"
      },
      "source": [
        "y_train =[]"
      ],
      "execution_count": 13,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "4fGE8a4vO9ES"
      },
      "source": [
        "for i in range(60,1258):\n",
        "  X_train.append(train_set_scaled[i-60:i,0])\n",
        "  y_train.append(train_set_scaled[i,0])\n",
        "X_train,y_train = np.array(X_train),np.array(y_train)"
      ],
      "execution_count": 14,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "z6RWzdA_QVfo",
        "outputId": "0941cd0a-86ca-4a1a-b266-d7d2d06ee63a"
      },
      "source": [
        "print(X_train)"
      ],
      "execution_count": 15,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "[[0.08581368 0.09701243 0.09433366 ... 0.07846566 0.08034452 0.08497656]\n",
            " [0.09701243 0.09433366 0.09156187 ... 0.08034452 0.08497656 0.08627874]\n",
            " [0.09433366 0.09156187 0.07984225 ... 0.08497656 0.08627874 0.08471612]\n",
            " ...\n",
            " [0.92106928 0.92438053 0.93048218 ... 0.95475854 0.95204256 0.95163331]\n",
            " [0.92438053 0.93048218 0.9299055  ... 0.95204256 0.95163331 0.95725128]\n",
            " [0.93048218 0.9299055  0.93113327 ... 0.95163331 0.95725128 0.93796041]]\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "PtBE_R3MS-TX",
        "outputId": "25183075-11f5-4822-fcf3-8aa96341e74d"
      },
      "source": [
        "X_train.shape"
      ],
      "execution_count": 16,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(1198, 60)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 16
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "jWKANLypQiCS",
        "outputId": "5a346745-1768-431c-c23e-df5cd0f62d5c"
      },
      "source": [
        "print(y_train)"
      ],
      "execution_count": 17,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "[0.08627874 0.08471612 0.07454052 ... 0.95725128 0.93796041 0.93688146]\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "ECn6qeE-TM_2",
        "outputId": "6660b9aa-25ce-474a-eedd-b14b8cc42b02"
      },
      "source": [
        "y_train.shape"
      ],
      "execution_count": 18,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(1198,)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 18
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "j-dGkj36RVOZ"
      },
      "source": [
        "Reshaping"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "VqtNpr06RWya"
      },
      "source": [
        "X_train = np.reshape(X_train,(X_train.shape[0],X_train.shape[1],1))"
      ],
      "execution_count": 19,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "ycqHmDzvVKSs",
        "outputId": "b2a085d0-928f-498d-cc8b-d7d286507997"
      },
      "source": [
        "print(X_train)"
      ],
      "execution_count": 20,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "[[[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]]]\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "alauOtWDQmHS"
      },
      "source": [
        "# Building RNN"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "_yL2x2JqKrdm"
      },
      "source": [
        "## importing related libraries"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "aOJovp_lQrmW"
      },
      "source": [
        "import tensorflow as tf"
      ],
      "execution_count": 21,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "e5dqi1c1RC3J"
      },
      "source": [
        "from keras.models import Sequential"
      ],
      "execution_count": 22,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "af7sgN0FRDJB"
      },
      "source": [
        "from keras.layers import Dense"
      ],
      "execution_count": 23,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "mth47EAUKUR6"
      },
      "source": [
        "from keras.layers import LSTM"
      ],
      "execution_count": 24,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "LMFy7TNgKVKL"
      },
      "source": [
        "from keras.layers import Dropout"
      ],
      "execution_count": 25,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "ndYzshh_KueP"
      },
      "source": [
        "## Building the RNN"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "67R9lYWUKg7d"
      },
      "source": [
        "regressor = Sequential()"
      ],
      "execution_count": 26,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "8XxaGvn8RPlo"
      },
      "source": [
        "1st Layer"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "KyfZmAJZLi9j"
      },
      "source": [
        "regressor.add(LSTM(units=50,return_sequences=True,input_shape=(X_train.shape[1],1)))"
      ],
      "execution_count": 27,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "_zUg-sIwNy9s"
      },
      "source": [
        "regressor.add(Dropout(0.2))"
      ],
      "execution_count": 28,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "-vVXVtjHPGLR"
      },
      "source": [
        "2nd Layer"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "r09V_hsAO-De"
      },
      "source": [
        "regressor.add(LSTM(units=50,return_sequences=True))"
      ],
      "execution_count": 29,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "S3KMQQXJPALm"
      },
      "source": [
        "regressor.add(Dropout(0.2))"
      ],
      "execution_count": 30,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "86bEVcmVPO1z"
      },
      "source": [
        "3rd Layer"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "fa3E216EPMOK"
      },
      "source": [
        "regressor.add(LSTM(units=50,return_sequences=True))"
      ],
      "execution_count": 31,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Koe_51jzPN3q"
      },
      "source": [
        "regressor.add(Dropout(0.2))"
      ],
      "execution_count": 32,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "lD27jYegPeaw"
      },
      "source": [
        "4th Layer"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "NBceGP38PgOf"
      },
      "source": [
        "regressor.add(LSTM(units=50))"
      ],
      "execution_count": 33,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Rrb9jwZsPu_l"
      },
      "source": [
        "regressor.add(Dropout(0.2))"
      ],
      "execution_count": 34,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "A1D-2v-BPxuR"
      },
      "source": [
        "Output Layer"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "2X9O__VBP1Ap"
      },
      "source": [
        "regressor.add(Dense(units=1))"
      ],
      "execution_count": 35,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "kLln4b0uQ-jP"
      },
      "source": [
        "Compiling the RNN"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "hfTyCrQWQvad"
      },
      "source": [
        "regressor.compile(optimizer='adam',loss='mean_squared_error')"
      ],
      "execution_count": 36,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "upj-u1UjSTVb",
        "outputId": "1a912c82-7ac8-4995-eb6e-b0993193f2d2"
      },
      "source": [
        "regressor.fit(X_train,y_train,epochs=100,batch_size=32)"
      ],
      "execution_count": 37,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Epoch 1/100\n",
            "38/38 [==============================] - 25s 16ms/step - loss: 0.0731\n",
            "Epoch 2/100\n",
            "38/38 [==============================] - 0s 12ms/step - loss: 0.0066\n",
            "Epoch 3/100\n",
            "38/38 [==============================] - 0s 12ms/step - loss: 0.0061\n",
            "Epoch 4/100\n",
            "38/38 [==============================] - 0s 12ms/step - loss: 0.0048\n",
            "Epoch 5/100\n",
            "38/38 [==============================] - 0s 12ms/step - loss: 0.0049\n",
            "Epoch 6/100\n",
            "38/38 [==============================] - 0s 13ms/step - loss: 0.0049\n",
            "Epoch 7/100\n",
            "38/38 [==============================] - 0s 12ms/step - loss: 0.0047\n",
            "Epoch 8/100\n",
            "38/38 [==============================] - 0s 12ms/step - loss: 0.0048\n",
            "Epoch 9/100\n",
            "38/38 [==============================] - 0s 13ms/step - loss: 0.0048\n",
            "Epoch 10/100\n",
            "38/38 [==============================] - 0s 13ms/step - loss: 0.0041\n",
            "Epoch 11/100\n",
            "38/38 [==============================] - 0s 12ms/step - loss: 0.0041\n",
            "Epoch 12/100\n",
            "38/38 [==============================] - 0s 12ms/step - loss: 0.0034\n",
            "Epoch 13/100\n",
            "38/38 [==============================] - 0s 13ms/step - loss: 0.0042\n",
            "Epoch 14/100\n",
            "38/38 [==============================] - 0s 13ms/step - loss: 0.0043\n",
            "Epoch 15/100\n",
            "38/38 [==============================] - 0s 12ms/step - loss: 0.0033\n",
            "Epoch 16/100\n",
            "38/38 [==============================] - 0s 13ms/step - loss: 0.0041\n",
            "Epoch 17/100\n",
            "38/38 [==============================] - 0s 12ms/step - loss: 0.0038\n",
            "Epoch 18/100\n",
            "38/38 [==============================] - 0s 13ms/step - loss: 0.0040\n",
            "Epoch 19/100\n",
            "38/38 [==============================] - 0s 13ms/step - loss: 0.0038\n",
            "Epoch 20/100\n",
            "38/38 [==============================] - 0s 13ms/step - loss: 0.0038\n",
            "Epoch 21/100\n",
            "38/38 [==============================] - 0s 12ms/step - loss: 0.0033\n",
            "Epoch 22/100\n",
            "38/38 [==============================] - 0s 12ms/step - loss: 0.0039\n",
            "Epoch 23/100\n",
            "38/38 [==============================] - 0s 13ms/step - loss: 0.0036\n",
            "Epoch 24/100\n",
            "38/38 [==============================] - 0s 12ms/step - loss: 0.0039\n",
            "Epoch 25/100\n",
            "38/38 [==============================] - 0s 12ms/step - loss: 0.0031\n",
            "Epoch 26/100\n",
            "38/38 [==============================] - 0s 12ms/step - loss: 0.0029\n",
            "Epoch 27/100\n",
            "38/38 [==============================] - 0s 13ms/step - loss: 0.0030\n",
            "Epoch 28/100\n",
            "38/38 [==============================] - 0s 13ms/step - loss: 0.0031\n",
            "Epoch 29/100\n",
            "38/38 [==============================] - 0s 12ms/step - loss: 0.0028\n",
            "Epoch 30/100\n",
            "38/38 [==============================] - 0s 13ms/step - loss: 0.0028\n",
            "Epoch 31/100\n",
            "38/38 [==============================] - 0s 13ms/step - loss: 0.0032\n",
            "Epoch 32/100\n",
            "38/38 [==============================] - 0s 13ms/step - loss: 0.0040\n",
            "Epoch 33/100\n",
            "38/38 [==============================] - 0s 12ms/step - loss: 0.0025\n",
            "Epoch 34/100\n",
            "38/38 [==============================] - 0s 12ms/step - loss: 0.0025\n",
            "Epoch 35/100\n",
            "38/38 [==============================] - 0s 13ms/step - loss: 0.0029\n",
            "Epoch 36/100\n",
            "38/38 [==============================] - 0s 12ms/step - loss: 0.0026\n",
            "Epoch 37/100\n",
            "38/38 [==============================] - 0s 13ms/step - loss: 0.0024\n",
            "Epoch 38/100\n",
            "38/38 [==============================] - 0s 13ms/step - loss: 0.0031\n",
            "Epoch 39/100\n",
            "38/38 [==============================] - 0s 13ms/step - loss: 0.0023\n",
            "Epoch 40/100\n",
            "38/38 [==============================] - 0s 12ms/step - loss: 0.0027\n",
            "Epoch 41/100\n",
            "38/38 [==============================] - 0s 12ms/step - loss: 0.0025\n",
            "Epoch 42/100\n",
            "38/38 [==============================] - 0s 12ms/step - loss: 0.0023\n",
            "Epoch 43/100\n",
            "38/38 [==============================] - 0s 12ms/step - loss: 0.0027\n",
            "Epoch 44/100\n",
            "38/38 [==============================] - 1s 13ms/step - loss: 0.0025\n",
            "Epoch 45/100\n",
            "38/38 [==============================] - 0s 13ms/step - loss: 0.0025\n",
            "Epoch 46/100\n",
            "38/38 [==============================] - 0s 13ms/step - loss: 0.0029\n",
            "Epoch 47/100\n",
            "38/38 [==============================] - 0s 13ms/step - loss: 0.0024\n",
            "Epoch 48/100\n",
            "38/38 [==============================] - 0s 13ms/step - loss: 0.0026\n",
            "Epoch 49/100\n",
            "38/38 [==============================] - 0s 13ms/step - loss: 0.0023\n",
            "Epoch 50/100\n",
            "38/38 [==============================] - 0s 13ms/step - loss: 0.0022\n",
            "Epoch 51/100\n",
            "38/38 [==============================] - 0s 13ms/step - loss: 0.0022\n",
            "Epoch 52/100\n",
            "38/38 [==============================] - 0s 12ms/step - loss: 0.0021\n",
            "Epoch 53/100\n",
            "38/38 [==============================] - 0s 12ms/step - loss: 0.0023\n",
            "Epoch 54/100\n",
            "38/38 [==============================] - 0s 13ms/step - loss: 0.0019\n",
            "Epoch 55/100\n",
            "38/38 [==============================] - 0s 12ms/step - loss: 0.0024\n",
            "Epoch 56/100\n",
            "38/38 [==============================] - 0s 12ms/step - loss: 0.0023\n",
            "Epoch 57/100\n",
            "38/38 [==============================] - 0s 12ms/step - loss: 0.0020\n",
            "Epoch 58/100\n",
            "38/38 [==============================] - 0s 13ms/step - loss: 0.0019\n",
            "Epoch 59/100\n",
            "38/38 [==============================] - 0s 13ms/step - loss: 0.0022\n",
            "Epoch 60/100\n",
            "38/38 [==============================] - 0s 13ms/step - loss: 0.0020\n",
            "Epoch 61/100\n",
            "38/38 [==============================] - 0s 12ms/step - loss: 0.0018\n",
            "Epoch 62/100\n",
            "38/38 [==============================] - 0s 13ms/step - loss: 0.0021\n",
            "Epoch 63/100\n",
            "38/38 [==============================] - 0s 13ms/step - loss: 0.0021\n",
            "Epoch 64/100\n",
            "38/38 [==============================] - 0s 12ms/step - loss: 0.0020\n",
            "Epoch 65/100\n",
            "38/38 [==============================] - 0s 12ms/step - loss: 0.0019\n",
            "Epoch 66/100\n",
            "38/38 [==============================] - 0s 13ms/step - loss: 0.0017\n",
            "Epoch 67/100\n",
            "38/38 [==============================] - 0s 13ms/step - loss: 0.0016\n",
            "Epoch 68/100\n",
            "38/38 [==============================] - 0s 13ms/step - loss: 0.0017\n",
            "Epoch 69/100\n",
            "38/38 [==============================] - 0s 13ms/step - loss: 0.0021\n",
            "Epoch 70/100\n",
            "38/38 [==============================] - 0s 12ms/step - loss: 0.0017\n",
            "Epoch 71/100\n",
            "38/38 [==============================] - 0s 13ms/step - loss: 0.0020\n",
            "Epoch 72/100\n",
            "38/38 [==============================] - 0s 12ms/step - loss: 0.0020\n",
            "Epoch 73/100\n",
            "38/38 [==============================] - 0s 13ms/step - loss: 0.0018\n",
            "Epoch 74/100\n",
            "38/38 [==============================] - 0s 12ms/step - loss: 0.0017\n",
            "Epoch 75/100\n",
            "38/38 [==============================] - 0s 13ms/step - loss: 0.0017\n",
            "Epoch 76/100\n",
            "38/38 [==============================] - 0s 12ms/step - loss: 0.0020\n",
            "Epoch 77/100\n",
            "38/38 [==============================] - 0s 13ms/step - loss: 0.0016\n",
            "Epoch 78/100\n",
            "38/38 [==============================] - 0s 13ms/step - loss: 0.0016\n",
            "Epoch 79/100\n",
            "38/38 [==============================] - 0s 13ms/step - loss: 0.0016\n",
            "Epoch 80/100\n",
            "38/38 [==============================] - 0s 13ms/step - loss: 0.0015\n",
            "Epoch 81/100\n",
            "38/38 [==============================] - 0s 13ms/step - loss: 0.0016\n",
            "Epoch 82/100\n",
            "38/38 [==============================] - 0s 13ms/step - loss: 0.0017\n",
            "Epoch 83/100\n",
            "38/38 [==============================] - 0s 13ms/step - loss: 0.0018\n",
            "Epoch 84/100\n",
            "38/38 [==============================] - 0s 12ms/step - loss: 0.0017\n",
            "Epoch 85/100\n",
            "38/38 [==============================] - 0s 13ms/step - loss: 0.0015\n",
            "Epoch 86/100\n",
            "38/38 [==============================] - 0s 13ms/step - loss: 0.0015\n",
            "Epoch 87/100\n",
            "38/38 [==============================] - 0s 12ms/step - loss: 0.0014\n",
            "Epoch 88/100\n",
            "38/38 [==============================] - 0s 13ms/step - loss: 0.0017\n",
            "Epoch 89/100\n",
            "38/38 [==============================] - 0s 13ms/step - loss: 0.0014\n",
            "Epoch 90/100\n",
            "38/38 [==============================] - 1s 14ms/step - loss: 0.0014\n",
            "Epoch 91/100\n",
            "38/38 [==============================] - 0s 13ms/step - loss: 0.0016\n",
            "Epoch 92/100\n",
            "38/38 [==============================] - 0s 13ms/step - loss: 0.0016\n",
            "Epoch 93/100\n",
            "38/38 [==============================] - 0s 13ms/step - loss: 0.0014\n",
            "Epoch 94/100\n",
            "38/38 [==============================] - 0s 13ms/step - loss: 0.0015\n",
            "Epoch 95/100\n",
            "38/38 [==============================] - 0s 12ms/step - loss: 0.0014\n",
            "Epoch 96/100\n",
            "38/38 [==============================] - 0s 13ms/step - loss: 0.0014\n",
            "Epoch 97/100\n",
            "38/38 [==============================] - 0s 12ms/step - loss: 0.0014\n",
            "Epoch 98/100\n",
            "38/38 [==============================] - 0s 13ms/step - loss: 0.0013\n",
            "Epoch 99/100\n",
            "38/38 [==============================] - 0s 13ms/step - loss: 0.0014\n",
            "Epoch 100/100\n",
            "38/38 [==============================] - 0s 13ms/step - loss: 0.0014\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<keras.callbacks.History at 0x7f894045f450>"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 37
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "SAIkStPhTM5w"
      },
      "source": [
        "# Predicting for 2017"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "uOsdxYA5UvKq"
      },
      "source": [
        "dataset_test = pd.read_csv('/content/Google_Stock_Price_Test.csv')"
      ],
      "execution_count": 38,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Em56TbZ-UlwY"
      },
      "source": [
        "real_stock_price = dataset_test.iloc[:, 1:2].values"
      ],
      "execution_count": 39,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Eq_MNGpmUmeI",
        "outputId": "e8030e8f-e4ab-4bd6-b0f1-244ba65c59a0"
      },
      "source": [
        "print(real_stock_price)"
      ],
      "execution_count": 40,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "[[778.81]\n",
            " [788.36]\n",
            " [786.08]\n",
            " [795.26]\n",
            " [806.4 ]\n",
            " [807.86]\n",
            " [805.  ]\n",
            " [807.14]\n",
            " [807.48]\n",
            " [807.08]\n",
            " [805.81]\n",
            " [805.12]\n",
            " [806.91]\n",
            " [807.25]\n",
            " [822.3 ]\n",
            " [829.62]\n",
            " [837.81]\n",
            " [834.71]\n",
            " [814.66]\n",
            " [796.86]]\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "OjH5OOrRVaQi",
        "outputId": "cadba39d-6261-44e8-ada8-2054812a5d1e"
      },
      "source": [
        "real_stock_price.shape"
      ],
      "execution_count": 41,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(20, 1)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 41
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "DufDHX2zVkR-"
      },
      "source": [
        "dataset_total = pd.concat((dataset_train['Open'],dataset_test['Open']),axis=0)"
      ],
      "execution_count": 42,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "2ynt1T6fXFEO",
        "outputId": "e416dad4-b812-4cab-c49a-10d53d41a51f"
      },
      "source": [
        "print(dataset_total)"
      ],
      "execution_count": 43,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "0     325.25\n",
            "1     331.27\n",
            "2     329.83\n",
            "3     328.34\n",
            "4     322.04\n",
            "       ...  \n",
            "15    829.62\n",
            "16    837.81\n",
            "17    834.71\n",
            "18    814.66\n",
            "19    796.86\n",
            "Name: Open, Length: 1278, dtype: float64\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "C1rlqmBwXpnw"
      },
      "source": [
        "inputs = dataset_total[len(dataset_total)-len(dataset_test)-60:].values"
      ],
      "execution_count": 44,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "ObpRW2T0aE4H",
        "outputId": "f7095334-bc83-47c7-a383-4d88f0677968"
      },
      "source": [
        "print(inputs)"
      ],
      "execution_count": 45,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "[779.   779.66 777.71 786.66 783.76 781.22 781.65 779.8  787.85 798.24\n",
            " 803.3  795.   804.9  816.68 806.34 801.   808.35 795.47 782.89 778.2\n",
            " 767.25 750.66 774.5  783.4  779.94 791.17 756.54 755.6  746.97 755.2\n",
            " 766.92 771.37 762.61 772.63 767.73 764.26 760.   771.53 770.07 757.44\n",
            " 744.59 757.71 764.73 761.   772.48 780.   785.04 793.9  797.4  797.34\n",
            " 800.4  790.22 796.76 795.84 792.36 790.9  790.68 793.7  783.33 782.75\n",
            " 778.81 788.36 786.08 795.26 806.4  807.86 805.   807.14 807.48 807.08\n",
            " 805.81 805.12 806.91 807.25 822.3  829.62 837.81 834.71 814.66 796.86]\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "uKGxMmJuZypj"
      },
      "source": [
        "inputs = inputs.reshape(-1,1)"
      ],
      "execution_count": 46,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "W2T4MlOdZ_QW"
      },
      "source": [
        "inputs = sc.transform(inputs)"
      ],
      "execution_count": 48,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "JBEspcTOaXPC",
        "outputId": "3a524943-4d8f-41fd-fcbf-616203a26cd7"
      },
      "source": [
        "print(inputs)"
      ],
      "execution_count": 49,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "[[0.9299055 ]\n",
            " [0.93113327]\n",
            " [0.92750577]\n",
            " [0.94415507]\n",
            " [0.93876032]\n",
            " [0.93403527]\n",
            " [0.93483518]\n",
            " [0.9313937 ]\n",
            " [0.94636878]\n",
            " [0.96569685]\n",
            " [0.97510976]\n",
            " [0.95966962]\n",
            " [0.97808617]\n",
            " [1.        ]\n",
            " [0.98076494]\n",
            " [0.97083116]\n",
            " [0.98450406]\n",
            " [0.96054394]\n",
            " [0.9371419 ]\n",
            " [0.92841729]\n",
            " [0.90804747]\n",
            " [0.8771858 ]\n",
            " [0.92153434]\n",
            " [0.93809063]\n",
            " [0.93165414]\n",
            " [0.95254483]\n",
            " [0.88812412]\n",
            " [0.88637547]\n",
            " [0.87032145]\n",
            " [0.88563137]\n",
            " [0.90743359]\n",
            " [0.91571173]\n",
            " [0.89941588]\n",
            " [0.91805566]\n",
            " [0.9089404 ]\n",
            " [0.9024853 ]\n",
            " [0.89456061]\n",
            " [0.91600938]\n",
            " [0.9132934 ]\n",
            " [0.88979835]\n",
            " [0.86589404]\n",
            " [0.89030062]\n",
            " [0.90335962]\n",
            " [0.89642086]\n",
            " [0.91777662]\n",
            " [0.93176576]\n",
            " [0.94114145]\n",
            " [0.95762334]\n",
            " [0.96413424]\n",
            " [0.96402262]\n",
            " [0.96971501]\n",
            " [0.95077759]\n",
            " [0.96294367]\n",
            " [0.96123223]\n",
            " [0.95475854]\n",
            " [0.95204256]\n",
            " [0.95163331]\n",
            " [0.95725128]\n",
            " [0.93796041]\n",
            " [0.93688146]\n",
            " [0.92955205]\n",
            " [0.94731751]\n",
            " [0.94307612]\n",
            " [0.96015329]\n",
            " [0.98087655]\n",
            " [0.98359253]\n",
            " [0.97827219]\n",
            " [0.98225314]\n",
            " [0.98288563]\n",
            " [0.98214153]\n",
            " [0.979779  ]\n",
            " [0.97849542]\n",
            " [0.98182528]\n",
            " [0.98245777]\n",
            " [1.01045465]\n",
            " [1.02407173]\n",
            " [1.03930724]\n",
            " [1.03354044]\n",
            " [0.99624228]\n",
            " [0.9631297 ]]\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "ecpV9igua0Ki",
        "outputId": "9856c0e1-46e7-42a5-aa4c-5c08786c0e70"
      },
      "source": [
        "inputs.shape"
      ],
      "execution_count": 50,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(80, 1)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 50
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "ra93AZe2aciS"
      },
      "source": [
        "X_test=[]"
      ],
      "execution_count": 51,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "LJ1ELriRaylB"
      },
      "source": [
        "for i in range(60,80):\n",
        "  X_test.append(inputs[i-60:i,0])\n",
        "X_test = np.array(X_test)"
      ],
      "execution_count": 52,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "IIZDnym6bPBI"
      },
      "source": [
        "X_test = np.reshape(X_test,(X_test.shape[0],X_test.shape[1],1))"
      ],
      "execution_count": 53,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "6ZlZSYZNbYcC"
      },
      "source": [
        "pred_stock_price = regressor.predict(X_test)"
      ],
      "execution_count": 54,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "JPj5xiXebp0f"
      },
      "source": [
        "pred_stock_price=sc.inverse_transform(pred_stock_price)"
      ],
      "execution_count": 55,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "qohUELd-b-wR"
      },
      "source": [
        "# Visualizing Predictions with Real Data"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 295
        },
        "id": "gDbH1HB6cEB2",
        "outputId": "5e504ecb-ace1-41c3-f6f6-eb112d1980b0"
      },
      "source": [
        "plt.plot(real_stock_price,color='red',label='real google stock price')\n",
        "plt.plot(pred_stock_price,color='blue',label='predicted google stock price')\n",
        "plt.title('Google stock price')\n",
        "plt.xlabel('Time')\n",
        "plt.ylabel('Stock Price')\n",
        "plt.show()"
      ],
      "execution_count": 56,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYUAAAEWCAYAAACJ0YulAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4yLjIsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy+WH4yJAAAgAElEQVR4nO3debxV8/rA8c9Tp0GDSmUoTYR7jV1CuglFnUzJdOvqJ2NmyhQhrjnEFZKIUAqpa7iSlJnqliKUBs0DDUoDTef5/fGsfdqdzrDPsPba+5zn/Xqt195nrbXXes4+Z69nr+8oqopzzjkHUC7qAJxzzqUOTwrOOeeyeVJwzjmXzZOCc865bJ4UnHPOZfOk4JxzLpsnBVdmicg9IjI06jjyIiIqIk1DOnZvEXkhjGO79OZJwUVORDqLyCQR2SgivwbPrxYRiTq2wkr1RBOjqg+q6mVRx+FSjycFFykRuQl4EngU2BvYC7gS+DtQMcLQSi0RyYg6Bpe6PCm4yIhIDeBe4GpVHamq69VMU9ULVHVzbD8ReUVEVorIQhG5U0TKBdvKBT8vDO4yXgmOGzvHhcG21SJyl4gsEJGT84inhYh8JSJrReRbETkxn9h7ichSEVkvIj+JSFsRyQR6A/8QkQ0i8m2wbz0ReUdE1ojIXBG5PO445YOinHnBsaaKSINcztdKRBbnFpOINA6KmrqLyDIRWS4iN8dtv0dERorIUBH5Hbgo5x1NcPzY775YRC4K1lcSkcdEZJGI/CIiA0Vkt7zeF5f+PCm4KB0HVALeLmC/p4AawH7ACcCFwMXBtouC5aRgezXgaQARORgYAFwA7BMco35uJxCR+sB/gfuBPYCbgbdEpG4u+x4EXAscrarVgfbAAlX9AHgQeF1Vq6nqEcFLRgBLgHrAucCDItIm2HYj0AU4FdgduATYlON8mcBw4BxV/SSf9+kk4ACgHdArR/LrCIwEagLDchy/ETAGe5/rAs2A6cHmh4EDg3VNsfevTz4xuDTnScFFqQ6wSlW3xVbEfVv9Q0Rai0h5oDNwe3AnsQDoB/xf8JILgMdV9WdV3QDcDnQOikjOBd5V1S9UdQt2MctrsK+uwPuq+r6qZqnqOGAKdrHOaTuWzA4WkQqqukBV5+V20OBb/9+BXqr6p6pOB17AEhvAZcCdqvpTcJf0raqujjvEecBzQAdVnZzXGxn4l6puVNUZwEtYson5WlX/E/xuf+R43T+Bj1R1uKpuVdXVqjo9qNPpDvRU1TWquh5Lep0LiMOlMU8KLkqrgTrxZdyq2lJVawbbymGJowKwMO51C9nxjb9eLtsysLqJesDiuGNvCo6bm0bAeUFCWisia4FW2B3GTlR1LtADuAf4VURGiEi9PI5bD4hdUHOLvwGQa0IJ9ADeUNXv89knZnHc84XBuXPbllNeMdQFqgBT496TD4L1rpTypOCi9DWwGSvayMsqYCt20Y5pCCwNni/LZds24BdgObBvbENQFl47j/MsBl5V1ZpxS1VVfTi3nVX1NVVtFZxbgb6xTTl2XQbsISLV84h/MbB/HjGB3SmcJSI35LNPTHxdRMPg3Nkh5/O6vGJYBfwBHBL3ntRQ1WoJxOLSlCcFFxlVXQv8CxggIueKSPWg4rgZUDXYZzvwBvBAsL0RVg4fqyQdDvQUkSYiUo0dZfrbsDL0M0SkpYhUxL7Z59XMdWiwb/ug8reyiJwoIvvm3FFEDhKRNiJSCfgTu3BmBZt/ARrHKsJVdTHwFfBQcMzDgUvj4n8BuE9EDhBzuIjEJ65lQFvgBhG5qoC39C4RqSIih2B1Lq8XsH/MMOBkETlfRDJEpLaINFPVLOB54AkR2TP43euLSPsEj+vSkCcFFylVfQS7yN+KXVB/wcrQe2EXU4DrgI3Az8AXwGvAi8G2F4FXgc+A+dhF+rrg2D8Ez0dgdw0bgF+xu5OccSzG7lh6Ayuxb8+3kPtnpBJWAbsKWAHsidVlALwZPK4WkW+C512AxtgFfjRwt6p+FGx7HEt6HwK/A4OBnVr3qOoiLDHcJiL59S34FJgLjAceU9UP89k35/FPBW4C1mCVzLFK8l7BMScGLZc+Ag5K5LguPYlPsuPKiuBOYi1wgKrOjzqekiIijbGEWCG+0t65ovA7BVeqicgZQZFKVeAxYAawINqonEtdnhRcadcRK7ZZhrXh76x+e+xcnrz4yDnnXDa/U3DOOZctrQfGqlOnjjZu3DjqMJxzLq1MnTp1larm2gkx1KQgIj2xbvyKVfBdrKp/Btv6A5fEOsIEbb5fAY7Cep3+IxjSIE+NGzdmypQp4f0CzjlXConIwry2hVZ8FAwwdj3QXFUPBWJj2CAizYFaOV5yKfCbqjYFnmBHD1HnnHNJEnadQgawWzC2TRVgWTDA2aNYZ6V4HYGXg+cjgbbBgFzOOeeSJLSkoKpLsXbhi7DepOuCHpbXAu+o6vIcL6lPMGhX0AFnHbmMUxOMGT9FRKasXLkyrPCdc65MCrP4qBb27b8JNlpjVRG5EBvg66miHldVB6lqc1VtXreuD9bonHMlKczio5OB+aq6UlW3AqOwwc+aAnNFZAFQRUTmBvsvJRjlMShuqkHewxw755wLQZhJYRHQIhhiQLABvR5X1b1VtbGqNgY2BRXLAO8A3YLn5wITvOepc84lV2hNUlV1koiMBL7BxrefBgzK5yWDgVeDO4c1+OxOzjmXdKH2U1DVu4G789leLe75n1h9g3POhUcVXn0VDj0Ujjwy6mhSjg9z4ZwrW159Fbp1g6OOgq5dYWGe/bjKJE8KzrmyY9EiuO46aNUKbr8d3noLDjwQbrkFfvst6uhSgicF51zZkJUFF11kjy+/DA8+CLNnQ5cu0K8f7L8/PP44bN5lYr4yxZOCc65s6N8fPv4YnngC9tvP1jVoAEOGwLRpcMwxcNNN8Je/wPDhljzKIE8KzrnS78cf4bbb4PTT4dJLd91+xBHwwQfw4YdQowb8859w7LHwySdJDzVqnhScc6Xb1q1w4YVQrRo8/zzkN6TaKafA1KlWvLRiBZx0EpxxhiWVMsKTgnOudLv/frvQP/cc7L13wfuXL29JZPZsePhh+OwzOOww6N4dluccsq308aTgnCu9Jk+GBx6A//s/OOecwr12t92gVy+YN89aLA0ZAk2bwt13w/r1oYSbCjwpOOdKp02bLBnUq2eVzEVVpw78+98wcyacdhrcey8ccABMmlRysaYQTwrOudKpVy8rAnrpJahZs/jH239/eOMNmDgRtm2DJ58s/jFTkCcF51zpM24cPP003HADtG1bssc+9li7Yxg7FrZvL9ljpwBPCs650uW33+Dii62/wUMPhXOODh1gzRoohXPEe1JwzpUu111nzUlffdUqi8NwyinWtPWDD8I5foQ8KTjnSo8334Rhw+Cuu6B58/DOU7u29YD2pOCccylq+XK48ko4+mjo3Tv882VmWpPX1aVrgkhPCs659Kdqw1ds2gSvvAIVKoR/zsxMGx/po4/CP1cSeVJwzqW/55+HMWPgkUesgjkZjj4aatUqdUVInhScc+lt3jy48UZrenrNNck7b/ny0K6dJYVSNJ28JwXnXPravt3GKcrIsE5q5ZJ8ScvMtJZO332X3POGKNR3UER6isgPIvK9iAwXkcoiMlhEvhWR70RkpIhUC/atJCKvi8hcEZkkIo3DjM05Vwo8+ih89ZV1VGvQIPnnb9/eHktREVJoSUFE6gPXA81V9VCgPNAZ6KmqR6jq4cAi4NrgJZcCv6lqU+AJoG9YsTnnSoFvv4U+fWyguwsuiCaGffaxuRjGjInm/CEI+14rA9hNRDKAKsAyVf0dQEQE2A2IFcZ1BF4Ono8E2gb7OOfczjZvtsHu9tgDBg7Mf46EsHXoAF9+Cb//Hl0MJSi0pKCqS4HHsLuB5cA6Vf0QQEReAlYAfwGeCl5SH1gcvHYbsA6onfO4ItJdRKaIyJSVK1eGFb5zLpX16QMzZsDgwTaKaZQyM22AvAkToo2jhIRZfFQL+/bfBKgHVBWRrgCqenGwbibwj8IcV1UHqWpzVW1et27dEo7aOZfyPvzQ6hIuu8wGpovaccdB9eqlpl4hzOKjk4H5qrpSVbcCo4CWsY2quh0YAcRmvlgKNAAIiptqAKWrq6BzrngWLbL5kw8+2OY4SAUVK1pz2FLSNDXMpLAIaCEiVYK6gbbATBFpCtl1CmcCs4L93wG6Bc/PBSaoloJ32DlXMjZvhvPOgy1b4K23oGrVqCPaITMTFi6En36KOpJiywjrwKo6SURGAt8A24BpwCBggojsDgjwLXBV8JLBwKsiMhdYg7VUcs45c9NNNtbQm2/CQQdFHc3O4pumJqtHdUgknb+MN2/eXKeUwvHMnXM5vPaaNTu98Ubo1y/qaHL3179Co0ZpUbcgIlNVNddhZL1Hs3Mutf3wA1x+ObRqBQ8/HHU0ecvMhE8/hT/+iDqSYvGk4JxLXevXW+e06tXh9deTM/ppUWVmwp9/WmJIY54UnHOpKTYc9pw5MGIE1KsXdUT5a90aKldOi+Kj/HhScM6lpv79rVL5wQfhxBOjjqZgu+0GJ52U9kNeeFJwzqWeL7+Em2+Gjh3h1lujjiZxmZkwezb8/HPUkRSZJwXnXGr59Vc4/3xryTNkSLTjGhVWZqY9jh0bbRzF4EnBOZc6tm+HLl1gzRoYORJq1ow6osI54ABo0iSt6xU8KTjnUkefPjaw3IAB0KxZ1NEUnojdLYwfbz2v05AnBedcanjvPatUvuwyuPjiqKMpusxM2LjR6kXSkCcF51z0fv7Z5kf429/gqacK3j+VnXSS9adI0yIkTwrOuWj9+Sece649HznS2vqns+rVrfe1JwXnnCuC666DadPg1Vdhv/2ijqZkZGbCd9/BsmVRR1JonhScc9F56SV44QXo3RtOPz3qaEpOGjdN9aTgnIvG9Olw9dXQpg3ce2/U0ZSsww6zYTnSsHezJwXnXPKtXWv1CHvsAcOHQ/nyUUdUsmJNU8eNs/mb04gnBedccqlak9OFC21soz33jDqicGRmWvKbPDnqSArFk4JzLrn+9z/4z3/g/vuhZcuC909XJ58M5cqlXSskTwrOueQaMsRGFL3qqgJ3TWu1akGLFp4UnHMuT3/+aXUI55wDu+8edTThy8yEKVNg5cqoI0mYJwXnXPK8/baVs190UdSRJEdmptWhjBsXdSQJCzUpiEhPEflBRL4XkeEiUllEhonIT8G6F0WkQrCviEh/EZkrIt+JyJFhxuaci8CQIdCggQ0FURYcdRTUqZNWRUihJQURqQ9cDzRX1UOB8kBnYBjwF+AwYDfgsuAlHYADgqU78GxYsTnnIrB0KXz4IXTrZhWwZUG5ctCunXViy8qKOpqEhP2XyQB2E5EMoAqwTFXf1wAwGdg32Lcj8EqwaSJQU0T2CTk+51yyDB1qF8Zu3aKOJLkyM23ioOnTo44kIaElBVVdCjwGLAKWA+tU9cPY9qDY6P+A2H1VfWBx3CGWBOt2IiLdRWSKiExZmUaVN86VaapWdNSqFTRtGnU0ydWunT2mSe/mMIuPamHf/psA9YCqItI1bpcBwGeq+nlhjquqg1S1uao2r1u3bskF7JwLz+TJMGtW2algjrfXXla3kCb1CmEWH50MzFfVlaq6FRgFtAQQkbuBusCNcfsvBRrE/bxvsM45l+5ifRPOOy/qSKKRmQlff20tr1JcmElhEdBCRKqIiABtgZkichnQHuiiqvE1L+8AFwatkFpgxU3LQ4zPOZcMZa1vQm4yM23+6fHjo46kQGHWKUwCRgLfADOCcw0CBgJ7AV+LyHQR6RO85H3gZ2Au8DxwdVixOeeS6O23Yd26sll0FNOiBdSokRZFSBlhHlxV7wbuTuScQWuka8KMxzkXgbLWNyE3GRk2FtIHH1ilu0jUEeWpjDQWds5Foiz2TchLZiYsWQI//hh1JPkq438l51yoymrfhNy0b2+PKV6E5EnBOReOstw3ITcNGsAhh3hScM6VUWW5b0JeMjPhs89g48aoI8mTJwXnXDjKet+E3GRmwpYt8PHHUUeSJ08KzrmS530Tcnf88VClSkoXIXlScM6VPO+bkLtKlaBNG08Kzrkyxvsm5C0zE+bNg7lzo44kV54UnHMly/sm5C8z0x5TdNRU/4s550rWq69634T87L8/HHSQFbGlIE8KzrmS430TEtOpE3zyCaxZE3Uku/Ck4JwrOZMmwU8/eQVzQTp1slFT33sv6kh24UnBOVdyvG9CYpo3h333hdGjo45kF54UnHMl448/YMQI75uQiHLl4KyzYOzYlOvd7EnBOVcyvG9C4XTqZIl07NioI9mJJwXnXMkYMgQaNvS+CYlq3Rr22CPlipASSgoi0kpELg6e1xWRJuGG5ZxLK0uXwrhx3jehMDIy4IwzrLJ569aoo8lW4F9PRO4GegG3B6sqAEPDDMo5l2a8b0LRnH02rF1rzVNTRCIpvRNwJrARQFWXAdXDDMo5l0ZifROOP946ZrnEnXIKVK0Ko0ZFHUm2RJLClmD+ZAUQkaqJHlxEeorIDyLyvYgMF5HKInKtiMwVERWROnH7ioj0D7Z9JyJHFv7Xcc4lnfdNKLrddrNhL95+2+60UkAiSeENEXkOqCkilwMfAc8X9CIRqQ9cDzRX1UOB8kBn4EvgZGBhjpd0AA4Ilu7As4n+Es65CA0ZYsNBe9+EounUCZYvt+SaAjIK2kFVHxORU4DfgYOAPqo6rhDH301EtgJVgGWqOg1ARHLu2xF4JbgrmSgiNUVkH1VdnuC5nHPJFt83obqXKhfJaadZpfPo0XDccVFHk1BFcxPgc1W9RVVvBr4QkcYFvU5VlwKPAYuA5cA6Vf0wn5fUBxbH/bwkWJcznu4iMkVEpqxcubKgMJxzYfK+CcVXsya0bWtJQTXqaBIqPnoTiC/s2h6sy5eI1MK+/TcB6gFVRaRrUYKMp6qDVLW5qjavW7ducQ/nnCuOWN+EE0+MOpL01qmTza/w/fdRR5JQUshQ1S2xH4LnFRN43cnAfFVdqapbgVFAy3z2Xwo0iPt532Cdcy4Ved+EktOxI4ikREe2RP6SK0XkzNgPItIRWJXA6xYBLUSkilgFQltgZj77vwNcGLRCaoEVN3l9gnOpyvsmlJy997b6hDRJClcCvUVkkYgsxjqyXVHQi1R1EjAS+AaYEZxrkIhcLyJLsDuB70TkheAl7wM/A3Ox1k1XF/aXcc4lifdNKHlnnw3Tp8P8+ZGGIZpgxYaIVANQ1Q2hRlQIzZs31ylTpkQdRtmydi189pmVfZ57Lhx4YNQRuShMnGjfbAcPhksuiTqa0uHnny3BPv449OwZ6qlEZKqqNs91W15JQUS6qupQEbkxt+2q+ngJxlgknhSSYNMm+PJLGD8eJkyAqVN3dLIpVw66doW77kq9WbZUrbnk2rXWOibn44YNUK2aDUhWu7Y9xpaqVa181+Xtyiut+GjFCm+KWgTr1tnbtktVzBFH2LDjn38e6vnzSwr59VOI9Vz2v3hZsmWLdaKZMMGWr7+2wboyMqBFC7jzTmjTBpo0gSefhAEDYNgwK1e+805bH7ZZs6zs9ddfd1zkc7vwb9tWtONXqLBzkogt8cmjTh1o1sySYbonkC1b8n4Pcz7Gnk+aZHeKnhAKZeFCePBBeOklaN8e3nwTKleO26FTJ7j3XvjlF9hrr0hizLf4SETKA9er6hPJCylxfqdQArZvh2nTdiSBzz+3uwMROPJISwBt28Lf/27frHNavhz69oWBA+1YF18Md9wBjRqVbJzr1sHrr9unaeJEW1e9urXxrlFjx2Nez3Ouq1YN1q+3OXJzLqtX571+06ad46pTx4pRWra0x6OPtt69qUgVpkyxhDpmjH3LX7fO7qgKsvvuO7+Xe+wBDzwAhxwSftylwIIFlgyGDLGPVocO1sWjbVv4z3/iPlrffmtfNgYNgssvDy2eIhUfxb14sqoeE0pkxeRJoYi2b4cXXrALwyef2IUB7APepo0tJ5wAtWolfsylS+Ghh+D55+3ic+ml0Ls3NGhQ8GvzkpUFH39siWDUKLt4HXKIJZ6uXaP5JvXnn/Dbb3ZBnTIFvvrKltmzbXtGhn2o4xNFw4bR3U1s22aJftQou/osWQLly1sFcdOmuybN3BJq9er2Gldo8+fvSAblytl1/rbbbCbOl1+26pgWLeD99+2tRtX+LgcdZCtDkl9SQFXzXYAngKeB44EjY0tBr0vGctRRR6krgv79VUG1SRPVyy5Tfe011eXLS+bYixapXnmlaoUKqhUrql57rerSpYU7xs8/q/bpo9qokcVZs6bqVVepTp6smpVVMnGWtJUrVd99V7V3b9UTT1StUsViB9V69VTPOUe1Xz/Vr79W/fPPcGPZtEn17bdVL7pItXZti6FyZdWOHVWHDFFdtSrc8zudN0/1kktUMzJUK1Wyj8Hixbvu9+abts+RR9q/kKqq3nSTfXbWrg0tPmCK5nXNz2tD9g7wcS7LhIJel4zFk0IRbNqkuvfeqq1bh3uBXbBA9fLLd3wqbrgh/8SzYYPqyy/bBRVURVTbtVMdPlz1jz/CizMsW7eqTp2q+tRTqv/8p2rjxjuSRMWKqscdp9qtmyW/F19UHT9ede5c1c2bi3a+tWtVhw2z5FO1qp2nRg3Vrl1V33rL3l8XurlzVS++WLV8efu3v+461SVL8n/Ne+/Zvoccorpsmap+8YX9/V57LbQ4i5sU6hS0T1SLJ4UieOIJ+7N/8klyzvfzz/aVqXx51d12U73xRtUVK2xbVpZ9AC69VLV6dYtr//1V77/f7jhKm2XL7AJ9882qxx+vWr++Jb9Ysoglw/r1VVu2VO3SRfX221UHDlQdM0Z15kzVjRt3HG/5ctvWvr3dmYEl/CuvVB07tugJxhXanDl2Y1a+vN2UXX994W6Qx4+3XN60qerC+dtV99pL9bzzQos3v6SQX5PUM4AXga3Y2Efnq+pXJVKgVUK8TqGQNm6E/faDQw+1JqbJNHcu3HcfDB1qzS3+8Q9r6jp7tjUBPf98qyto1Sr9W/MUxpYtVs6/cKHVRi5cuPPzxYt3bUVVt64tM2fuKIPu1MmWY4/1ISeSaM4cq28fOtQarV15Jdx6K+yzT+GP9fXXVgFdowZ8dNxdHPDff8PKlTmaJ5WMovZT+A5LBLNE5FjgEVU9ocSjKwZPCoX02GNwyy1W8diqVTQxzJ5tTe5GjLAWTRddZOPw59ayyVmjgOXLd04YCxfCsmXW0unss63yvSwl0hQwZ459xxk2DCpVsmRwyy1FSwbxpk2Ddu0gY/tmPvrtSA55ty+cfnrJBB2nqEnhG1U9Mq+fU4EnhULYsMH6EPztb/BhfiOYJ0lWln+jdWnpf/+zxnkAV11lyWDvvUvu+D/+CCefrGxZsYaxpz/NUe/cXXIHDxS189qeOXoz7/SzpkCPZlcITz8Nq1bBv/4VdSTGE4JLQ4sXw5lnWmvoL76A+rvM+FJ8Bx8Mn38utD0iizbv9eT9T7fx9xMKnA+txOT3yXwe680cW3L+7NLF77/Do49agWUKzOzkXDrasAHOOMP6L773XjgJIWb//eHzxyazl66gXaYktQowz/SjqinyldIV21NPWY/cVLlLcC7NbN8O//wnzJhhfcqS0ZG7QdcT+KzHoZxS9StOO60eI0eGUr2wC7+HL+3WrbMK5jPOsIpJ51yh9eoF774L/fvbmEVJUa0ae7c/gk8qZXLYYUqnTvDGG+Gf1pNCaffvf9sAZvfcE3UkzqWl55+Hfv3guuvgmmuSfPJOnai9bAbjH51GixbQpYsNmRGmApOCiFTKZd0e4YTjStRvv8ETT8BZZ9ngds65Qhk/Hq6+2qrjHo+iac0ZZ0D58uw+7i0++MAG0Lv4YnjmmfBOmcidwigRqRD7QUT2AcaFF5IrMU88YcVHfpfgXKHNmmWjgx90kHWryUheA6AdateG1q1h9GiqVoV33rHWT9deG16SSiQp/Ad4Q0TKi0hjYCxwezjhuBKzerUVHZ17rk3c4ZxL2OrVVqlbsaK1NNp99wiDOfts673+009UrgwjR1qfz8MOC+d0BSYFVX0e+AhLDu8CV6pqCvR+cvnq18/a0N1d8h1fnCvNtmyx6/CSJTbaeOPGEQd01ln2OHo0YMNpvPQSnHJKOKfLMymIyI2xBagMNASmAy3ymqIzl2P0FJEfROR7ERkuIpVFpImITBKRuSLyuohUDPatFPw8N9jeuPi/Xhm1apU1kzj/fBvnyDmXEFW44gqbhvyll1KkW8+++1rLwVGjknK6/O4U4juqVQNGAXNJsPOaiNQHrgeaq+qhQHmgM9AXeEJVmwK/AZcGL7kU+C1Y/0SwnyuKRx+1HjZ+l+BcoTzyiLXuuftua+mTMjp1svE1liwJ/1x5DZ9a3AWoDywG9sA6yb0HtAdWARnBPscBY4PnY4HjgucZwX6S3zl86OxcrFhhE7xccEHUkTiXVt56y0Yf79IlBedymjnTgnvqqRI5HPkMnZ1Ik9RxIlIz7udaIjI2gWSzFHgMWAQsB9YBU4G1qhobC3hJkDzikwjB9nVA7YLO43J45BGbMrJPn6gjcS5tTJ1qM7y2aAEvvpiCg87+5S/w179m1yuEKZHWR3VVdW3sB1X9DdizoBeJSC2gI9AEqAdUBTKLGGf8cbuLyBQRmbJy5criHq50Wb4cBgyw/+4DD4w6GufSwtKl1sxzzz2tYjmE6QtKRqdO8Omn1jQqRIkkhe0i0jD2g4g0AnIfb3tnJwPzVXWlqm7F6iT+DtQUkViL332BpcHzpUCD4BwZQA1gl99eVQepanNVbV63bt0EwihD+vaFrVvhrruijsS5tBAb5G79emt6utdeUUeUj06dbBCmd98N9TSJJIU7gC9E5FURGQp8RmL9FBZhLZWqiIgAbYEfsTmezw326Qa8HTx/J/iZYPuEoOzLJWLpUhg4ELp1s5m4nHP5ysqym+pvv4XXX0+DhnpHHQUNGoRehFRgHz1V/UBEjgRaBKt6qOqqBF43SURGAt8A24BpwCDgv8AIEbk/WDc4eMlg4FURmQuswVoquUQ99JB9i7jzzqgjcdAW904AABhzSURBVC4t3H47vP22td7u0CHqaBIgYncLgwbZ1LpVq4ZzmkS+jIvImUDr4MdPVPW9UKIpJJ95LbB4sd0dXHQRPPdc1NE4l/IGD4bLLrNxjZ5+OgUrlvPyySdw0knWrfmcc4p8mPxmXkuk9dHDwA1Y0c+PwA0i8mCRo3El78EHrdfNHXdEHYlzKe/TT21O5Xbt4Mkn0yghgM2tXrt2qB3ZEhni6VSgmapmAYjIy1ixT+/QonKJW7Bgx9eehg0L3N25smzuXBvC4oADbG6CSAa5K46MDGsqNWqUjcdRsWKJnyLR+RRqxj2vUeJRuKJ74AH7qtPbc7Rz+Vm71loaiVgDnhrpeiXr1MlGP/7441AOn0hSeAiYJiJDgruEqYAXH6WCn3+2PvlXXGHjozjncrVtG/zjHzBvnn3J3n//qCMqhlNOsUrmkJqmJtL6aLiIfALE5nLspaorQonGFc7999vt5G23RR2JcymtZ0/48EMraW3duuD9U1rlyvD553DwwaEcvsCkICLjVbUt1o8g5zoXlTlz4JVXbI7AevWijsa5lDVggLUwuvlmuOSSqKMpIX/7W2iHzjMpiEhloApQJxiyIlZHvzs7xityUbnvPqtk6tUr6kicS1njxsH111tdwsMPRx1NesjvTuEKoAc2btFUdiSF34GnQ47L5WfmTBg2DG68EfbeO+ponEtJs2bBeefBIYfYx6V8+agjSg95JgVVfRJ4UkSuU9WnkhiTy4+q9bjZfXe49daoo3EuJcWm06xUyeY1rl7gDDAuJr/io6OBxbGEICIXAucAC4F7VHVNckJ0Oxk2zHo1DhwIPiCgc7vYssU6+y5ZYq02GzWKOqL0kl+T1OeALQAi0hp4GHgFm+dgUPihuV389psVGR17LFx+edTROJdyVOGaa6zX8uDBKTKdZprJr06hfNzdwD+AQar6FvCWiEwPPzS3i9697b74ww+hXKL9Dp0rO/79b3jhBRvx5YILoo4mPeV3ZSkfN+9BW2BC3LZ06xye/iZNssHurr8emjWLOhrnUs5//ws33WRFR/feG3U06Su/i/tw4FMRWQX8AXwOICJNsSIklyzbttkIXvXq+X+7c7n4/nvo3Nma77/8st9IF0d+rY8eEJHxwD7Ah3ET3pQDrktGcC7w9NMwfTq8+aY3o3Auh19/tZZG1atbS6OQphkoM/ItBlLVibmsmx1eOG4XS5fa9JodOhRr/HTnSqPNm218uF9+sZEf6nu32mLzuoFU16OHFR+l1UwgzoVP1RrhffWVDYPdPNcpY1xheclbKvvgA5th6c47Yb/9oo7GuZTSty+8+qpVs513XtTRlB4JTceZqkr1dJx//GEziVeoYDOLV6oUdUTOpYzRo22ynC5drD+n30QXTn7TcXrxUap68EGbL2HCBE8IzsV55x3rg3DssdZBzRNCyQqt+EhEDhKR6XHL7yLSQ0SOEJGvRWSGiLwrIrvHveZ2EZkrIj+JSPuwYkt5s2bZvXHXrjZJt3MOgGeesYrlQw+15LDbblFHVPqElhRU9SdVbaaqzYCjgE3AaOAF4DZVPSz4+RYAETkY6AwcAmQCA0Sk7I1rGBvwrmpVeOyxqKNxLiVkZdl8CNdea81PP/4Y9twz6qhKp2RVNLcF5qnqQuBA4LNg/ThskD2AjsAIVd2sqvOBucAxSYovdbz2mv3HP/QQ7LVX1NE4F7k//rCpNPv1s6QwapT3RQhTspJCZ6yHNMAPWAIAOA9oEDyvDyyOe80ScpnMR0S6i8gUEZmycuXKkMKNSGzAu2OOge7do47GucitWgUnn2yN8Pr1g/79fV6EsIWeFESkInAm8Gaw6hLgahGZClQnGIk1Uao6SFWbq2rzuqVt6Og77rBPwcCB3k/flXnz5kHLljB1qnXmv/FGr1ROhmS0PuoAfKOqvwCo6iygHYCIHAicFuy3lB13DQD7BuvKhsmTLRlcf32o8686lw4mTrQpNFWtAV7LllFHVHYk4+toF3YUHSEiewaP5YA7gYHBpneAziJSSUSaAAcAk5MQX+Gpwpw59lgSYgPe7bOPD3jnyrzRo63RXY0a8PXXnhCSLdSkICJVgVOAUXGru4jIbGAWsAx4CUBVfwDeAH4EPgCuUdXtYcZXZAMHwoEHwkEHWUHnqlXFO94zz8C0aTYY/O67F7y/c6XUv/9tQ3w1a2YJ4YADoo6o7PEezYW1cqUlhP33h8qV4csvoWJFOPdc+7bfqlXhCj6XLoW//hX+/nd4/30vNHVl0vbtNhfCk09aT+WhQ70PQpjy69HstZmFdccdsGEDvPIKfPEFzJhhLYX++19o3RoOOcT+s3/7LbHj9ewJW7f6gHeuzNq0ycYuevJJ+zi88YYnhCh5UiiMKVNsrr/rr4eDD7Z1hx4KTz1l3/gHD7ZB3Xv0sAlxLrrI7oHzuhv74ANrVnHHHXbn4VwZs3IltGkD//mPJYXHH/cmp1Hz4qNEZWVZjdeCBTB7dv5l/9Om2dSZw4bZXcXhh8MVV9iwFbHX+YB3roybPRtOPdW+T732mg1f4ZLDi49Kwiuv2DzJjzxScGXw3/5mldHLlllyKF8errnG7h4uv9zuOB56yAa8GzDAE4Irc774wr5j/f47fPKJJ4RU4ncKiVi3bkfl8hdfFL5jmaolgueeg+HDrRAVbKjHoUNLPl7nUkRWFsyda7PJTp9uN9HTp8OKFdayaMwYLzmNgg+dXVz33GOFn2PGFK2nsQgcfbQt/fpZIvjsM3vuXCnx55/w/fc7X/y//RY2brTtGRnWDqN9e7uZ/r//gz32iDZmtyu/UyjIDz/AEUfAZZdZkZBzZZwqrF5tF/z4O4BZs6xpKVh7i2bN7OLfrJktBx/sJaWpwu8UikrVWhrtvjs88EDU0ZRpq1dblc7EibZMn25/nkqVbKlYcefHgtZVqgTVqtlSvXr+j1WqlL3Wwhs2wPz5uS8LFsD69Tv23Xdfu+h36rQjCTRu7MN3pStPCvkZOdIGXhkwAGrXjjqaMmPrVvjuux0JYOJEK5cGu9AcfjiceaZd4DdvtmXLlp0f//zTqoJyro/fvnVrYvGUK7drAqlWzc5foYIVi8Q/5rYut225LbFjJrK+fHlLVuXK2RJ7ntu6nM+zsqzVz4IFuV/4c3bSr1oVmjSx5aST7PHQQ+0murSNS1nWefFRXjZutJ7GtWtbJbE3ng7NkiU7J4CpU+2iDbD33nDccTb1YosWcNRRdkEuCVu32jfi9ettye15Xus2bLAEs3WrDV2V32P881T9uFWsCI0a7bjwN26843mTJlCnTtm7WyrNvPioKB56CBYvtgbUnhBK1B9/WEOsL76wJLA0GAu3UiW76F91lSWAFi2gQYPwLkYVKkCtWrYkS1bWjkSR2xJLNImsz8qyRXXX57mti38ONv5i7KJfr54X9zjjSSE38+bBo49aZ7NWraKOplRZtgzOOgv+9z9rinjCCTsSwBFH2DfW0qxcuR11Gs6lIk8KuenZ065OjzwSdSSlyv/+Zwlh3TobHvmss6KOyDmXk98w5vT++/Duu9Cnj91fuxLx2ms2XmCFCvDVV54QnEtVnhTibd4MN9xg8yTccEPU0ZQKWVnQu7d13j76aLtbOPzwqKNyzuXFi4/iPfGEtX0cO7b0F24nwfr1Vi3zzjs25NPTT/vb6lyq86QQs2QJ3HeflWu0axd1NGlv/nzrSzBzJvTvD9de600anUsHnhRibrnFyjoefzzqSNLep5/alIrbt9uUESefHHVEzrlEeZ0C2Ni9I0ZAr17WaNsV2XPPWRKoUwcmT/aE4Fy6CS0piMhBIjI9bvldRHqISDMRmRismyIixwT7i4j0F5G5IvKdiBwZVmw72bbNxjdq1MiSgiuSrVutiOjKKy0RTJrkk647l45CKz5S1Z+AZgAiUh5YCowGngf+papjRORU4BHgRKADcECwHAs8GzyG69lnbZ7lUaN8YtgiWrPG5tidMMEmX+/b1zuBO5euklWn0BaYp6oLRUSB2NRlNYBlwfOOwCtqgzFNFJGaIrKPqi4PLapff4W77oJTTvGG80U0cyaccYaNCDJkCHTrFnVEzrniSFZS6AwMD573AMaKyGNY8VXLYH19YHHca5YE63ZKCiLSHegO0LBhw+JF1bu3DXzXv783jSmC99+Hzp1taOmPP7bpFZ1z6S30imYRqQicCbwZrLoK6KmqDYCewODCHE9VB6lqc1VtXrc4Y/ZOngyDB0OPHvCXvxT9OGWQKjz2GJx+OjRtah3SPCE4Vzoko/VRB+AbVf0l+LkbMCp4/iZwTPB8KdAg7nX7ButKXlaW1YruvbcVH7mEqcJtt1kL3nPPhc8/t5FMnXOlQzKSQhd2FB2B1SGcEDxvA8wJnr8DXBi0QmoBrAutPmHoUPt6+8gjNquaS0gsITzyiA1vPWKETb7inCs9Qq1TEJGqwCnAFXGrLweeFJEM4E+C+gHgfeBUYC6wCbg4tMA6dbKhOrt2De0UpY0q3H77joTwzDNeDeNcaeQzr7kCxRJC376WEJ5+2idkcS6d5Tfzmn+0Xb5UrZFW377WMc0TgnOlm3+8XZ5iCeHhhy0hPPOMJwTnSjv/iLtcqcIdd1hCuOIKTwjOlRX+MXe7iCWEhx6yhDBggCcE58oK/6i7najCnXdaQuje3ROCc2WNf9xdtlhCePBBmynt2Wc9IThX1vhH3gGWEO66a0dCGDjQE4JzZZF/7F12QnjgAbjsMk8IzpVl/tEv41ShT58dCeG55zwhOFeW+ce/DIslhPvv94TgnDN+CSijVOHuuy0hXHqpJwTnnPHLQBkUSwj33WcJYdAgTwjOOZOsmddcipgxA3r2hPHj4ZJLPCE453bml4MyYtUquPpqaNYMpk2Dp56C55/3hOCc25nfKZRyW7fauEX/+hesXw/XXAP33AN77BF1ZM65VORJoRR7/3248Ub46Sdo3x4efxwOPjjqqJxzqcwLD0qhmTOhQwc47TSrVH7vPRgzxhOCc65gnhRKkTVr4IYb4LDD4Ouv7c5gxgxLDj51pnMuEV58VAps22b9DPr0gbVrbXTTe++FunWjjsw5l25Cu1MQkYNEZHrc8ruI9BCR1+PWLRCR6XGvuV1E5orITyLSPqzY1q+HV16xSth0N26ctSi69todLYuefdYTgnOuaEJLCqr6k6o2U9VmwFHAJmC0qv4jbv1bwCgAETkY6AwcAmQCA0SkfBixvfEGdOsG++8PTz4JGzeGcZZwzZkDZ54J7drBH3/A6NHw0Udw+OFRR+acS2fJqlNoC8xT1YWxFSIiwPnA8GBVR2CEqm5W1fnAXOCYMIK55BL473+hcWPo0QMaNrQmm6tXh3G2krF5M3z6qfVEPv54qzT++GObLvPHH+Gss7zewDlXfMlKCp3ZcfGPOR74RVXnBD/XBxbHbV8SrCtxInDqqfDZZ/Dll9CqlbXdb9jQksSiRWGctXC2bYPJk+2i364d1KoFJ55oYxVt3gy33mp3C716QaVKUUfrnCstQq9oFpGKwJnA7Tk2dWHXRJHI8boD3QEaNmxY7PhatoS334YffoBHH7WOXs88AxdcYBfeZDXjzMqyGCZMsOXTT2HdOtt26KFWedymDbRuDTVrJicm51zZI6oa7glEOgLXqGq7uHUZwFLgKFVdEqy7HUBVHwp+Hgvco6pf53Xs5s2b65QpU0o03kWLrCnn88/Dpk1Wbn/bbXDccSV6GlRh3rwdSWDCBFi50rY1bWoJoE0buzvYa6+SPbdzrmwTkamq2jzXbUlICiOAsar6Uty6TOB2VT0hbt0hwGtYPUI9YDxwgKpuz+vYYSSFmNWr4emnoX9/a//furUV1XTokHjZfVYWLF8OCxbsusyaBUuW2H716kHbtpYETjoJGjUK5VdyzjkgwqQgIlWBRcB+qroubv0QYKKqDsyx/x3AJcA2oIeqjsnv+GEmhZiNG+GFF6BfP1i82Fr39OoF559vg8mtWLHrBX/+fHtctAi2bNn5eHvtZRXc++1nFcZt2sCBB3olsXMueSK9UwhTMpJCzNatMHw49O1rrX1q1bKEkfOiv+eedtHPuTRpYhXZVaokJVznnMtTfknBezQnqEIFuPBC6NrVxhIaPXrXBNCokV/0nXPpzZNCIZUrZ5XPZ54ZdSTOOVfyfEA855xz2TwpOOecy+ZJwTnnXDZPCs4557J5UnDOOZfNk4JzzrlsnhScc85l86TgnHMuW1oPcyEiK4GFBe6YuzrAqhIMp6SlenyQ+jF6fMXj8RVPKsfXSFVznbQ3rZNCcYjIlLzG/kgFqR4fpH6MHl/xeHzFk+rx5cWLj5xzzmXzpOCccy5bWU4Kg6IOoACpHh+kfoweX/F4fMWT6vHlqszWKTjnnNtVWb5TcM45l4MnBeecc9lKfVIQkUwR+UlE5orIbblsryQirwfbJ4lI4yTG1kBEPhaRH0XkBxG5IZd9ThSRdSIyPVj6JCu+4PwLRGRGcO5d5j4V0z94/74TkSOTGNtBce/LdBH5XUR65Ngn6e+fiLwoIr+KyPdx6/YQkXEiMid4rJXHa7sF+8wRkW5JjO9REZkV/A1Hi0jNPF6b7/9DiPHdIyJL4/6Op+bx2nw/7yHG93pcbAtEZHoerw39/Ss2VS21C1AemAfsB1QEvgUOzrHP1cDA4Hln4PUkxrcPcGTwvDowO5f4TgTei/A9XADUyWf7qcAYQIAWwKQI/9YrsE45kb5/QGvgSOD7uHWPALcFz28D+ubyuj2An4PHWsHzWkmKrx2QETzvm1t8ifw/hBjfPcDNCfwP5Pt5Dyu+HNv7AX2iev+Ku5T2O4VjgLmq+rOqbgFGAB1z7NMReDl4PhJoKyKSjOBUdbmqfhM8Xw/MBOon49wlqCPwipqJQE0R2SeCONoC81S1qD3cS4yqfgasybE6/v/sZeCsXF7aHhinqmtU9TdgHJCZjPhU9UNV3Rb8OBHYt6TPm6g83r9EJPJ5L7b84guuHecDw0v6vMlS2pNCfWBx3M9L2PWim71P8KFYB9ROSnRxgmKrvwGTctl8nIh8KyJjROSQpAYGCnwoIlNFpHsu2xN5j5OhM3l/EKN8/2L2UtXlwfMVwF657JMq7+Ul2N1fbgr6fwjTtUHx1ot5FL+lwvt3PPCLqs7JY3uU719CSntSSAsiUg14C+ihqr/n2PwNViRyBPAU8J8kh9dKVY8EOgDXiEjrJJ+/QCJSETgTeDOXzVG/f7tQK0dIybbgInIHsA0YlscuUf0/PAvsDzQDlmNFNKmoC/nfJaT856m0J4WlQIO4n/cN1uW6j4hkADWA1UmJzs5ZAUsIw1R1VM7tqvq7qm4Inr8PVBCROsmKT1WXBo+/AqOxW/R4ibzHYesAfKOqv+TcEPX7F+eXWLFa8PhrLvtE+l6KyEXA6cAFQeLaRQL/D6FQ1V9UdbuqZgHP53HeqN+/DOBs4PW89onq/SuM0p4U/gccICJNgm+TnYF3cuzzDhBr5XEuMCGvD0RJC8ofBwMzVfXxPPbZO1bHISLHYH+zpCQtEakqItVjz7HKyO9z7PYOcGHQCqkFsC6umCRZ8vx2FuX7l0P8/1k34O1c9hkLtBORWkHxSLtgXehEJBO4FThTVTflsU8i/w9hxRdfT9Upj/Mm8nkP08nALFVdktvGKN+/Qom6pjvsBWsdMxtrlXBHsO5e7J8foDJW7DAXmAzsl8TYWmHFCN8B04PlVOBK4Mpgn2uBH7CWFBOBlkmMb7/gvN8GMcTev/j4BHgmeH9nAM2T/Petil3ka8Sti/T9wxLUcmArVq59KVZPNR6YA3wE7BHs2xx4Ie61lwT/i3OBi5MY31ysPD72fxhrkVcPeD+//4ckxfdq8P/1HXah3ydnfMHPu3zekxFfsH5I7P8ubt+kv3/FXXyYC+ecc9lKe/GRc865QvCk4JxzLpsnBeecc9k8KTjnnMvmScE551w2TwrOJUBEaseNgrkibsTODSIyIOr4nCsp3iTVuUISkXuADar6WNSxOFfS/E7BuWIQm6/hveD5PSLysoh8LiILReRsEXkkGD//g2BIE0TkKBH5NBgUbWxEo8o6lytPCs6VrP2BNtgAfUOBj1X1MOAP4LQgMTwFnKuqRwEvAg9EFaxzOWVEHYBzpcwYVd0qIjOwSV8+CNbPABoDBwGHAuOCIZnKY0MmOJcSPCk4V7I2A6hqlohs1R2VdlnY502AH1T1uKgCdC4/XnzkXHL9BNQVkePAhk6PcOIf53bhScG5JFKbJvJcoK+IfIuNSNoy2qic28GbpDrnnMvmdwrOOeeyeVJwzjmXzZOCc865bJ4UnHPOZfOk4JxzLpsnBeecc9k8KTjnnMv2/wAqJnIIdM+5AAAAAElFTkSuQmCC\n",
            "text/plain": [
              "<Figure size 432x288 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": [],
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "crDuyGfDhtEn"
      },
      "source": [
        "# Evaluation"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "dUq1ADZ1hwUN"
      },
      "source": [
        "import math\n",
        "from sklearn.metrics import mean_squared_error\n",
        "rmse = math.sqrt(mean_squared_error(real_stock_price, pred_stock_price))\n",
        "rmse = rmse/800"
      ],
      "execution_count": 61,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "Dp_cK0lwiEiI"
      },
      "source": [
        "for a relative error we will divide by rough range of values in this case 800"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "cj3rI0wdh5Gi",
        "outputId": "ec1082bc-df0f-4c40-9782-c8de269250fa"
      },
      "source": [
        "print(rmse)"
      ],
      "execution_count": 62,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "0.03122453990975413\n"
          ],
          "name": "stdout"
        }
      ]
    }
  ]
}