import numpy as np # linear algebra
import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)
import matplotlib.pyplot as plt
from sklearn.preprocessing import MinMaxScaler

data_train = pd.read_csv('./Stock_Price_Train.csv')
data_train.info()

train = data_train.loc[:, ['Open']].values

scaler = MinMaxScaler(feature_range = (0, 1))
train_scaled = scaler.fit_transform(train)

plt.plot(train_scaled)
plt.show()

X_train = []
Y_train = []
timesteps = 50

for i in range(timesteps, 1250):
    X_train.append(train_scaled[i - timesteps:i, 0])
    Y_train.append(train_scaled[i, 0])
    
X_train, Y_train = np.array(X_train), np.array(Y_train)
X_train = np.reshape(X_train, (X_train.shape[0], X_train.shape[1], 1))

# ---------------------------------------------------------------------------

import keras
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import SimpleRNN
from keras.layers import Dropout

regressor = Sequential()

#Adding the first RNN layer and some Dropout regularization
regressor.add(SimpleRNN(units = 50, activation='tanh', return_sequences=True, input_shape= (X_train.shape[1],1)))
regressor.add(Dropout(0.2))

#Adding the second RNN layer and some Dropout regularization
regressor.add(SimpleRNN(units = 50, activation='tanh', return_sequences=True))
regressor.add(Dropout(0.2))

#Adding the third RNN layer and some Dropout regularization
regressor.add(SimpleRNN(units = 50, activation='tanh', return_sequences=True))
regressor.add(Dropout(0.2))

#Adding the fourth RNN layer and some Dropout regularization
regressor.add(SimpleRNN(units = 50))
regressor.add(Dropout(0.2))

#Adding the output layer
regressor.add(Dense(units = 1))

#Compile the RNN
regressor.compile(optimizer='adam', loss='mean_squared_error')

#Fitting the RNN to the Training set
callback = keras.callbacks.EarlyStopping(monitor="loss", mode="min", verbose=1, patience=10, min_delta=0.001)
history = regressor.fit(X_train, Y_train, epochs=100, batch_size=32, callbacks=[callback])

plt.plot(history.history['loss'], color='b', label="validation loss")
plt.title("Test Loss")
plt.xlabel("Number of Epochs")
plt.ylabel("Loss")
plt.legend()
plt.show()

data_test = pd.read_csv('./Stock_Price_Test.csv')
test = data_test.loc[:, ['Open']].values

#Getting the predicted stock price
data_total = pd.concat((data_train['Open'], data_test['Open']), axis=0)
inputs = data_total[len(data_total)-len(data_test) - timesteps:].values.reshape(-1,1)
inputs = scaler.transform(inputs) #minmax scaler

X_test = []
for i in range(timesteps, 70):
    X_test.append(inputs[i-timesteps:i,0])
X_test = np.array(X_test)
X_test = np.reshape(X_test, (X_test.shape[0], X_test.shape[1], 1))
predicted_stock_price = regressor.predict(X_test)
predicted_stock_price = scaler.inverse_transform(predicted_stock_price)

plt.plot(test, color='red', label='Real Google Stock Price')
plt.plot(predicted_stock_price, color='blue', label='Predicted Google Stock Price')
plt.title('Google Stock Price Prediction')
plt.xlabel('Time')
plt.ylabel('Google Stock Price')
plt.legend()
plt.show()