diff --git a/Recurrent_Neural_Network.ipynb b/Recurrent_Neural_Network.ipynb
new file mode 100644
index 0000000..d860261
--- /dev/null
+++ b/Recurrent_Neural_Network.ipynb
@@ -0,0 +1,595 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Recurrent Neural Network"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Part 1 - Data Preprocessing"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Importing the libraries\n",
+    "import numpy as np\n",
+    "import matplotlib.pyplot as plt\n",
+    "import pandas as pd\n",
+    "\n",
+    "# Importing the training set\n",
+    "dataset_train = pd.read_csv('Google_Stock_Price_Train.csv')\n",
+    "training_set = dataset_train.iloc[:, 1:2].values\n",
+    "\n",
+    "# Feature Scaling\n",
+    "from sklearn.preprocessing import MinMaxScaler\n",
+    "sc = MinMaxScaler(feature_range = (0, 1))\n",
+    "training_set_scaled = sc.fit_transform(training_set)\n",
+    "\n",
+    "# Creating a data structure with 60 timesteps and 1 output\n",
+    "X_train = []\n",
+    "y_train = []\n",
+    "for i in range(60, 1258):\n",
+    "    X_train.append(training_set_scaled[i-60:i, 0])\n",
+    "    y_train.append(training_set_scaled[i, 0])\n",
+    "X_train, y_train = np.array(X_train), np.array(y_train)\n",
+    "\n",
+    "# Reshaping\n",
+    "X_train = np.reshape(X_train, (X_train.shape[0], X_train.shape[1], 1))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Part 2 - Building the RNN"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch 1/100\n",
+      "1198/1198 [==============================] - 12s 10ms/step - loss: 0.0499\n",
+      "Epoch 2/100\n",
+      "1198/1198 [==============================] - 7s 6ms/step - loss: 0.0067\n",
+      "Epoch 3/100\n",
+      "1198/1198 [==============================] - 7s 6ms/step - loss: 0.0057\n",
+      "Epoch 4/100\n",
+      "1198/1198 [==============================] - 7s 6ms/step - loss: 0.0049\n",
+      "Epoch 5/100\n",
+      "1198/1198 [==============================] - 7s 6ms/step - loss: 0.0048\n",
+      "Epoch 6/100\n",
+      "1198/1198 [==============================] - 7s 6ms/step - loss: 0.0042\n",
+      "Epoch 7/100\n",
+      "1198/1198 [==============================] - 7s 6ms/step - loss: 0.0041\n",
+      "Epoch 8/100\n",
+      "1198/1198 [==============================] - 7s 6ms/step - loss: 0.0039\n",
+      "Epoch 9/100\n",
+      "1198/1198 [==============================] - 7s 6ms/step - loss: 0.0043\n",
+      "Epoch 10/100\n",
+      "1198/1198 [==============================] - 7s 6ms/step - loss: 0.0036\n",
+      "Epoch 11/100\n",
+      "1198/1198 [==============================] - 7s 6ms/step - loss: 0.0032\n",
+      "Epoch 12/100\n",
+      "1198/1198 [==============================] - 7s 6ms/step - loss: 0.0036\n",
+      "Epoch 13/100\n",
+      "1198/1198 [==============================] - 7s 6ms/step - loss: 0.0033\n",
+      "Epoch 14/100\n",
+      "1198/1198 [==============================] - 7s 6ms/step - loss: 0.0034\n",
+      "Epoch 15/100\n",
+      "1198/1198 [==============================] - 7s 6ms/step - loss: 0.0038\n",
+      "Epoch 16/100\n",
+      "1198/1198 [==============================] - 7s 6ms/step - loss: 0.0033\n",
+      "Epoch 17/100\n",
+      "1198/1198 [==============================] - 7s 6ms/step - loss: 0.0029\n",
+      "Epoch 18/100\n",
+      "1198/1198 [==============================] - 7s 6ms/step - loss: 0.0035\n",
+      "Epoch 19/100\n",
+      "1198/1198 [==============================] - 7s 6ms/step - loss: 0.0029\n",
+      "Epoch 20/100\n",
+      "1198/1198 [==============================] - 7s 6ms/step - loss: 0.0031\n",
+      "Epoch 21/100\n",
+      "1198/1198 [==============================] - 7s 6ms/step - loss: 0.0029\n",
+      "Epoch 22/100\n",
+      "1198/1198 [==============================] - 7s 6ms/step - loss: 0.0027\n",
+      "Epoch 23/100\n",
+      "1198/1198 [==============================] - 7s 6ms/step - loss: 0.0025\n",
+      "Epoch 24/100\n",
+      "1198/1198 [==============================] - 7s 6ms/step - loss: 0.0027\n",
+      "Epoch 25/100\n",
+      "1198/1198 [==============================] - 7s 6ms/step - loss: 0.0026\n",
+      "Epoch 26/100\n",
+      "1198/1198 [==============================] - 7s 6ms/step - loss: 0.0030\n",
+      "Epoch 27/100\n",
+      "1198/1198 [==============================] - 7s 6ms/step - loss: 0.0026\n",
+      "Epoch 28/100\n",
+      "1198/1198 [==============================] - 8s 7ms/step - loss: 0.0025\n",
+      "Epoch 29/100\n",
+      "1198/1198 [==============================] - 7s 6ms/step - loss: 0.0021\n",
+      "Epoch 30/100\n",
+      "1198/1198 [==============================] - 7s 6ms/step - loss: 0.0024\n",
+      "Epoch 31/100\n",
+      "1198/1198 [==============================] - 7s 6ms/step - loss: 0.0024\n",
+      "Epoch 32/100\n",
+      "1198/1198 [==============================] - 7s 6ms/step - loss: 0.0024\n",
+      "Epoch 33/100\n",
+      "1198/1198 [==============================] - 7s 6ms/step - loss: 0.0024\n",
+      "Epoch 34/100\n",
+      "1198/1198 [==============================] - 7s 6ms/step - loss: 0.0023\n",
+      "Epoch 35/100\n",
+      "1198/1198 [==============================] - 7s 6ms/step - loss: 0.0024\n",
+      "Epoch 36/100\n",
+      "1198/1198 [==============================] - 9s 7ms/step - loss: 0.0021\n",
+      "Epoch 37/100\n",
+      "1198/1198 [==============================] - 8s 7ms/step - loss: 0.0024\n",
+      "Epoch 38/100\n",
+      "1198/1198 [==============================] - 7s 6ms/step - loss: 0.0022\n",
+      "Epoch 39/100\n",
+      "1198/1198 [==============================] - 7s 6ms/step - loss: 0.0022\n",
+      "Epoch 40/100\n",
+      "1198/1198 [==============================] - 7s 6ms/step - loss: 0.0023\n",
+      "Epoch 41/100\n",
+      "1198/1198 [==============================] - 7s 6ms/step - loss: 0.0022\n",
+      "Epoch 42/100\n",
+      "1198/1198 [==============================] - 7s 6ms/step - loss: 0.0023\n",
+      "Epoch 43/100\n",
+      "1198/1198 [==============================] - 7s 6ms/step - loss: 0.0023\n",
+      "Epoch 44/100\n",
+      "1198/1198 [==============================] - 8s 7ms/step - loss: 0.0020\n",
+      "Epoch 45/100\n",
+      "1198/1198 [==============================] - 8s 7ms/step - loss: 0.0021\n",
+      "Epoch 46/100\n",
+      "1198/1198 [==============================] - 8s 7ms/step - loss: 0.0023\n",
+      "Epoch 47/100\n",
+      "1198/1198 [==============================] - 9s 7ms/step - loss: 0.0020\n",
+      "Epoch 48/100\n",
+      "1198/1198 [==============================] - 8s 7ms/step - loss: 0.0020\n",
+      "Epoch 49/100\n",
+      "1198/1198 [==============================] - 7s 6ms/step - loss: 0.0019\n",
+      "Epoch 50/100\n",
+      "1198/1198 [==============================] - 7s 6ms/step - loss: 0.0020\n",
+      "Epoch 51/100\n",
+      "1198/1198 [==============================] - 11s 9ms/step - loss: 0.0019\n",
+      "Epoch 52/100\n",
+      "1198/1198 [==============================] - 11s 9ms/step - loss: 0.0018\n",
+      "Epoch 53/100\n",
+      "1198/1198 [==============================] - 8s 7ms/step - loss: 0.0021\n",
+      "Epoch 54/100\n",
+      "1198/1198 [==============================] - 13s 11ms/step - loss: 0.0017\n",
+      "Epoch 55/100\n",
+      "1198/1198 [==============================] - 13s 11ms/step - loss: 0.0018\n",
+      "Epoch 56/100\n",
+      "1198/1198 [==============================] - 12s 10ms/step - loss: 0.0017\n",
+      "Epoch 57/100\n",
+      "1198/1198 [==============================] - 9s 8ms/step - loss: 0.0018\n",
+      "Epoch 58/100\n",
+      "1198/1198 [==============================] - 11s 9ms/step - loss: 0.0018\n",
+      "Epoch 59/100\n",
+      "1198/1198 [==============================] - 10s 9ms/step - loss: 0.0015\n",
+      "Epoch 60/100\n",
+      "1198/1198 [==============================] - 9s 7ms/step - loss: 0.0018\n",
+      "Epoch 61/100\n",
+      "1198/1198 [==============================] - 12s 10ms/step - loss: 0.0018\n",
+      "Epoch 62/100\n",
+      "1198/1198 [==============================] - 9s 8ms/step - loss: 0.0017\n",
+      "Epoch 63/100\n",
+      "1198/1198 [==============================] - 12s 10ms/step - loss: 0.0018\n",
+      "Epoch 64/100\n",
+      "1198/1198 [==============================] - 8s 6ms/step - loss: 0.0015\n",
+      "Epoch 65/100\n",
+      "1198/1198 [==============================] - 7s 6ms/step - loss: 0.0016\n",
+      "Epoch 66/100\n",
+      "1198/1198 [==============================] - 7s 6ms/step - loss: 0.0018\n",
+      "Epoch 67/100\n",
+      "1198/1198 [==============================] - 8s 6ms/step - loss: 0.0015\n",
+      "Epoch 68/100\n",
+      "1198/1198 [==============================] - 7s 6ms/step - loss: 0.0016\n",
+      "Epoch 69/100\n",
+      "1198/1198 [==============================] - 8s 7ms/step - loss: 0.0016\n",
+      "Epoch 70/100\n",
+      "1198/1198 [==============================] - 8s 7ms/step - loss: 0.0017\n",
+      "Epoch 71/100\n",
+      "1198/1198 [==============================] - 8s 7ms/step - loss: 0.0016\n",
+      "Epoch 72/100\n",
+      "1198/1198 [==============================] - 8s 7ms/step - loss: 0.0017\n",
+      "Epoch 73/100\n",
+      "1198/1198 [==============================] - 11s 9ms/step - loss: 0.0015\n",
+      "Epoch 74/100\n",
+      "1198/1198 [==============================] - 11s 10ms/step - loss: 0.0016\n",
+      "Epoch 75/100\n",
+      "1198/1198 [==============================] - 8s 6ms/step - loss: 0.0015\n",
+      "Epoch 76/100\n",
+      "1198/1198 [==============================] - 7s 6ms/step - loss: 0.0015\n",
+      "Epoch 77/100\n",
+      "1198/1198 [==============================] - 9s 7ms/step - loss: 0.0015\n",
+      "Epoch 78/100\n",
+      "1198/1198 [==============================] - 7s 6ms/step - loss: 0.0014\n",
+      "Epoch 79/100\n",
+      "1198/1198 [==============================] - 9s 8ms/step - loss: 0.0014\n",
+      "Epoch 80/100\n",
+      "1198/1198 [==============================] - 8s 7ms/step - loss: 0.0014\n",
+      "Epoch 81/100\n",
+      "1198/1198 [==============================] - 8s 6ms/step - loss: 0.0016\n",
+      "Epoch 82/100\n",
+      "1198/1198 [==============================] - 8s 6ms/step - loss: 0.0016\n",
+      "Epoch 83/100\n",
+      "1198/1198 [==============================] - 7s 6ms/step - loss: 0.0015\n",
+      "Epoch 84/100\n",
+      "1198/1198 [==============================] - 7s 6ms/step - loss: 0.0014\n",
+      "Epoch 85/100\n",
+      "1198/1198 [==============================] - 6s 5ms/step - loss: 0.0015\n",
+      "Epoch 86/100\n",
+      "1198/1198 [==============================] - 6s 5ms/step - loss: 0.0015\n",
+      "Epoch 87/100\n",
+      "1198/1198 [==============================] - 7s 6ms/step - loss: 0.0014\n",
+      "Epoch 88/100\n",
+      "1198/1198 [==============================] - 14s 11ms/step - loss: 0.0015\n",
+      "Epoch 89/100\n",
+      "1198/1198 [==============================] - 11s 9ms/step - loss: 0.0014\n",
+      "Epoch 90/100\n",
+      "1198/1198 [==============================] - 8s 7ms/step - loss: 0.0014\n",
+      "Epoch 91/100\n",
+      "1198/1198 [==============================] - 8s 7ms/step - loss: 0.0014\n",
+      "Epoch 92/100\n",
+      "1198/1198 [==============================] - 8s 7ms/step - loss: 0.0014\n",
+      "Epoch 93/100\n",
+      "1198/1198 [==============================] - 8s 7ms/step - loss: 0.0012\n",
+      "Epoch 94/100\n",
+      "1198/1198 [==============================] - 9s 7ms/step - loss: 0.0014\n",
+      "Epoch 95/100\n",
+      "1198/1198 [==============================] - 8s 7ms/step - loss: 0.0012\n",
+      "Epoch 96/100\n",
+      "1198/1198 [==============================] - 8s 7ms/step - loss: 0.0013\n",
+      "Epoch 97/100\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "1198/1198 [==============================] - 8s 7ms/step - loss: 0.0014A: 2s - \n",
+      "Epoch 98/100\n",
+      "1198/1198 [==============================] - 8s 6ms/step - loss: 0.0014\n",
+      "Epoch 99/100\n",
+      "1198/1198 [==============================] - 8s 6ms/step - loss: 0.0012\n",
+      "Epoch 100/100\n",
+      "1198/1198 [==============================] - 8s 6ms/step - loss: 0.0014\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "<keras.callbacks.History at 0x7f321882f6a0>"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Importing the Keras libraries and packages\n",
+    "from keras.models import Sequential\n",
+    "from keras.layers import Dense\n",
+    "from keras.layers import LSTM, GRU\n",
+    "from keras.layers import Dropout\n",
+    "from keras.optimizers import SGD\n",
+    "\n",
+    "# Initialising the RNN\n",
+    "regressor = Sequential()\n",
+    "\n",
+    "# Adding the first GRU layer and some Dropout regularisation\n",
+    "regressor.add(GRU(units = 50, return_sequences = True, input_shape = (X_train.shape[1], 1)))\n",
+    "regressor.add(Dropout(0.2))\n",
+    "\n",
+    "# Adding a second GRU layer and some Dropout regularisation\n",
+    "regressor.add(GRU(units = 50, return_sequences = True))\n",
+    "regressor.add(Dropout(0.2))\n",
+    "\n",
+    "# Adding a third GRU layer and some Dropout regularisation\n",
+    "regressor.add(GRU(units = 50, return_sequences = True))\n",
+    "regressor.add(Dropout(0.2))\n",
+    "\n",
+    "# Adding a fourth GRU layer and some Dropout regularisation\n",
+    "regressor.add(GRU(units = 50))\n",
+    "regressor.add(Dropout(0.2))\n",
+    "\n",
+    "# Adding the output layer\n",
+    "regressor.add(Dense(units = 1))\n",
+    "\n",
+    "# Compiling the RNN\n",
+    "regressor.compile(optimizer = 'adam', loss = 'mean_squared_error')\n",
+    "\n",
+    "# Fitting the RNN to the Training set\n",
+    "regressor.fit(X_train, y_train, epochs = 100, batch_size = 32)\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Part 3 - Making the predictions and visualising the results"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# Getting the real stock price of 2017\n",
+    "dataset_test = pd.read_csv('Google_Stock_Price_Test.csv')\n",
+    "real_stock_price = dataset_test.iloc[:, 1:2].values\n",
+    "\n",
+    "# Getting the predicted stock price of 2017\n",
+    "dataset_total = pd.concat((dataset_train['Open'], dataset_test['Open']), axis = 0)\n",
+    "inputs = dataset_total[len(dataset_total) - len(dataset_test) - 60:].values\n",
+    "inputs = inputs.reshape(-1,1)\n",
+    "inputs = sc.transform(inputs)\n",
+    "X_test = []\n",
+    "for i in range(60, 80):\n",
+    "    X_test.append(inputs[i-60:i, 0])\n",
+    "X_test = np.array(X_test)\n",
+    "X_test = np.reshape(X_test, (X_test.shape[0], X_test.shape[1], 1))\n",
+    "predicted_stock_price = regressor.predict(X_test)\n",
+    "predicted_stock_price = sc.inverse_transform(predicted_stock_price)\n",
+    "\n",
+    "# Visualising the results\n",
+    "plt.plot(real_stock_price, color = 'red', label = 'Real Google Stock Price')\n",
+    "plt.plot(predicted_stock_price, color = 'blue', label = 'Predicted Google Stock Price')\n",
+    "plt.title('Google Stock Price Prediction')\n",
+    "plt.xlabel('Time')\n",
+    "plt.ylabel('Google Stock Price')\n",
+    "plt.legend()\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Trocando Paramêtros"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch 1/50\n",
+      "1198/1198 [==============================] - 9s 7ms/step - loss: 0.1577\n",
+      "Epoch 2/50\n",
+      "1198/1198 [==============================] - 3s 2ms/step - loss: 0.0929\n",
+      "Epoch 3/50\n",
+      "1198/1198 [==============================] - 4s 3ms/step - loss: 0.0592\n",
+      "Epoch 4/50\n",
+      "1198/1198 [==============================] - 2s 2ms/step - loss: 0.0376\n",
+      "Epoch 5/50\n",
+      "1198/1198 [==============================] - 2s 2ms/step - loss: 0.0199\n",
+      "Epoch 6/50\n",
+      "1198/1198 [==============================] - 2s 2ms/step - loss: 0.0104\n",
+      "Epoch 7/50\n",
+      "1198/1198 [==============================] - 2s 2ms/step - loss: 0.0067\n",
+      "Epoch 8/50\n",
+      "1198/1198 [==============================] - 2s 2ms/step - loss: 0.0055\n",
+      "Epoch 9/50\n",
+      "1198/1198 [==============================] - 2s 2ms/step - loss: 0.0052\n",
+      "Epoch 10/50\n",
+      "1198/1198 [==============================] - 2s 2ms/step - loss: 0.0046\n",
+      "Epoch 11/50\n",
+      "1198/1198 [==============================] - 2s 2ms/step - loss: 0.0042\n",
+      "Epoch 12/50\n",
+      "1198/1198 [==============================] - 2s 2ms/step - loss: 0.0046\n",
+      "Epoch 13/50\n",
+      "1198/1198 [==============================] - 2s 2ms/step - loss: 0.0037\n",
+      "Epoch 14/50\n",
+      "1198/1198 [==============================] - 2s 2ms/step - loss: 0.0039\n",
+      "Epoch 15/50\n",
+      "1198/1198 [==============================] - 2s 2ms/step - loss: 0.0039\n",
+      "Epoch 16/50\n",
+      "1198/1198 [==============================] - 4s 3ms/step - loss: 0.0035\n",
+      "Epoch 17/50\n",
+      "1198/1198 [==============================] - 2s 2ms/step - loss: 0.0038\n",
+      "Epoch 18/50\n",
+      "1198/1198 [==============================] - 2s 2ms/step - loss: 0.0039\n",
+      "Epoch 19/50\n",
+      "1198/1198 [==============================] - 2s 2ms/step - loss: 0.0037\n",
+      "Epoch 20/50\n",
+      "1198/1198 [==============================] - 2s 2ms/step - loss: 0.0037\n",
+      "Epoch 21/50\n",
+      "1198/1198 [==============================] - 2s 2ms/step - loss: 0.0036\n",
+      "Epoch 22/50\n",
+      "1198/1198 [==============================] - 2s 2ms/step - loss: 0.0036\n",
+      "Epoch 23/50\n",
+      "1198/1198 [==============================] - 2s 2ms/step - loss: 0.0036\n",
+      "Epoch 24/50\n",
+      "1198/1198 [==============================] - 2s 2ms/step - loss: 0.0033\n",
+      "Epoch 25/50\n",
+      "1198/1198 [==============================] - 2s 2ms/step - loss: 0.0034\n",
+      "Epoch 26/50\n",
+      "1198/1198 [==============================] - 2s 2ms/step - loss: 0.0032\n",
+      "Epoch 27/50\n",
+      "1198/1198 [==============================] - 2s 2ms/step - loss: 0.0032\n",
+      "Epoch 28/50\n",
+      "1198/1198 [==============================] - 2s 2ms/step - loss: 0.0034\n",
+      "Epoch 29/50\n",
+      "1198/1198 [==============================] - 2s 2ms/step - loss: 0.0035\n",
+      "Epoch 30/50\n",
+      "1198/1198 [==============================] - 2s 2ms/step - loss: 0.0033\n",
+      "Epoch 31/50\n",
+      "1198/1198 [==============================] - 2s 2ms/step - loss: 0.0031\n",
+      "Epoch 32/50\n",
+      "1198/1198 [==============================] - 2s 2ms/step - loss: 0.0031\n",
+      "Epoch 33/50\n",
+      "1198/1198 [==============================] - 2s 2ms/step - loss: 0.0032\n",
+      "Epoch 34/50\n",
+      "1198/1198 [==============================] - 3s 2ms/step - loss: 0.0029\n",
+      "Epoch 35/50\n",
+      "1198/1198 [==============================] - 3s 3ms/step - loss: 0.0028\n",
+      "Epoch 36/50\n",
+      "1198/1198 [==============================] - 2s 2ms/step - loss: 0.0032\n",
+      "Epoch 37/50\n",
+      "1198/1198 [==============================] - 2s 2ms/step - loss: 0.0030\n",
+      "Epoch 38/50\n",
+      "1198/1198 [==============================] - 2s 2ms/step - loss: 0.0029\n",
+      "Epoch 39/50\n",
+      "1198/1198 [==============================] - 2s 2ms/step - loss: 0.0032\n",
+      "Epoch 40/50\n",
+      "1198/1198 [==============================] - 2s 2ms/step - loss: 0.0031\n",
+      "Epoch 41/50\n",
+      "1198/1198 [==============================] - 2s 2ms/step - loss: 0.0030\n",
+      "Epoch 42/50\n",
+      "1198/1198 [==============================] - 2s 2ms/step - loss: 0.0029\n",
+      "Epoch 43/50\n",
+      "1198/1198 [==============================] - 2s 2ms/step - loss: 0.0029\n",
+      "Epoch 44/50\n",
+      "1198/1198 [==============================] - 2s 2ms/step - loss: 0.0028\n",
+      "Epoch 45/50\n",
+      "1198/1198 [==============================] - 2s 2ms/step - loss: 0.0029\n",
+      "Epoch 46/50\n",
+      "1198/1198 [==============================] - 2s 2ms/step - loss: 0.0031\n",
+      "Epoch 47/50\n",
+      "1198/1198 [==============================] - 2s 2ms/step - loss: 0.0028\n",
+      "Epoch 48/50\n",
+      "1198/1198 [==============================] - 3s 3ms/step - loss: 0.0029\n",
+      "Epoch 49/50\n",
+      "1198/1198 [==============================] - 3s 2ms/step - loss: 0.0030\n",
+      "Epoch 50/50\n",
+      "1198/1198 [==============================] - 2s 2ms/step - loss: 0.0028\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "<keras.callbacks.History at 0x7f3211e66160>"
+      ]
+     },
+     "execution_count": 14,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# The GRU architecture\n",
+    "regressorGRU = Sequential()\n",
+    "# First GRU layer with Dropout regularisation\n",
+    "regressorGRU.add(GRU(units=50, return_sequences=True, input_shape=(X_train.shape[1],1), activation='tanh'))\n",
+    "regressorGRU.add(Dropout(0.2))\n",
+    "# Second GRU layer\n",
+    "regressorGRU.add(GRU(units=50, return_sequences=True, input_shape=(X_train.shape[1],1), activation='tanh'))\n",
+    "regressorGRU.add(Dropout(0.2))\n",
+    "# Third GRU layer\n",
+    "regressorGRU.add(GRU(units=50, return_sequences=True, input_shape=(X_train.shape[1],1), activation='tanh'))\n",
+    "regressorGRU.add(Dropout(0.2))\n",
+    "# Fourth GRU layer\n",
+    "regressorGRU.add(GRU(units=50, activation='tanh'))\n",
+    "regressorGRU.add(Dropout(0.2))\n",
+    "# The output layer\n",
+    "regressorGRU.add(Dense(units=1))\n",
+    "# Compiling the RNN\n",
+    "regressorGRU.compile(optimizer=SGD(lr=0.01, decay=1e-7, momentum=0.9, nesterov=False),loss='mean_squared_error')\n",
+    "# Fitting to the training set\n",
+    "regressorGRU.fit(X_train,y_train,epochs=50,batch_size=150)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# Getting the real stock price of 2017\n",
+    "dataset_test = pd.read_csv('Google_Stock_Price_Test.csv')\n",
+    "real_stock_price = dataset_test.iloc[:, 1:2].values\n",
+    "\n",
+    "# Getting the predicted stock price of 2017\n",
+    "dataset_total = pd.concat((dataset_train['Open'], dataset_test['Open']), axis = 0)\n",
+    "inputs = dataset_total[len(dataset_total) - len(dataset_test) - 60:].values\n",
+    "inputs = inputs.reshape(-1,1)\n",
+    "inputs = sc.transform(inputs)\n",
+    "X_test = []\n",
+    "for i in range(60, 80):\n",
+    "    X_test.append(inputs[i-60:i, 0])\n",
+    "X_test = np.array(X_test)\n",
+    "X_test = np.reshape(X_test, (X_test.shape[0], X_test.shape[1], 1))\n",
+    "predicted_stock_price = regressor.predict(X_test)\n",
+    "predicted_stock_price = sc.inverse_transform(predicted_stock_price)\n",
+    "\n",
+    "# Visualising the results\n",
+    "plt.plot(real_stock_price, color = 'red', label = 'Real Google Stock Price')\n",
+    "plt.plot(predicted_stock_price, color = 'blue', label = 'Predicted Google Stock Price')\n",
+    "plt.title('Google Stock Price Prediction')\n",
+    "plt.xlabel('Time')\n",
+    "plt.ylabel('Google Stock Price')\n",
+    "plt.legend()\n",
+    "plt.show()"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.7.3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}