ashwinprasadme

import numpy as np
import matplotlib.pyplot as plt
plt.style.use('fivethirtyeight')
import pandas as pd
from sklearn.preprocessing import MinMaxScaler
from keras.models import Sequential
from keras.layers import Dense, LSTM, Dropout, GRU, Bidirectional
from keras.optimizers import SGD
import math
from sklearn.metrics import mean_squared_error

ashwinprasadme

np.sqrt(((dataY_plot[-testX.size()[0]:] - data_predict[-testX.size()[0]:] ) ** 2).mean())

ashwinprasadme

def normalize_data(df):
    min_max_scaler = sklearn.preprocessing.MinMaxScaler()
    df['open'] = min_max_scaler.fit_transform(df.open.values.reshape(-1,1))
    df['high'] = min_max_scaler.fit_transform(df.high.values.reshape(-1,1))
    df['low'] = min_max_scaler.fit_transform(df.low.values.reshape(-1,1))
    df['close'] = min_max_scaler.fit_transform(df['close'].values.reshape(-1,1))
    return df

ashwinprasadme

#Create the testing data set
#Create a new array containing scaled values from index 1543 to 2002 
test_data = scaled_data[training_data_len - 60: , :]
#Create the data sets x_test and y_test
x_test = []
y_test = dataset[training_data_len:, :]
for i in range(60, len(test_data)):
    x_test.append(test_data[i-60:i, 0])
    
# Convert the data to a numpy array

ashwinprasadme

######Prediction###############


lstm.eval()
train_predict = lstm(dataX.to(device))
data_predict = train_predict.cpu().data.numpy()
dataY_plot = dataY.data.numpy()

## Inverse Normalize 
data_predict = scaler.inverse_transform(data_predict)

ashwinprasadme

## finding all columns that have nan:

droping_list_all=[]
for j in range(0,7):
    if not df.iloc[:, j].notnull().all():
        droping_list_all.append(j)        
        #print(df.iloc[:,j].unique())
droping_list_all

ashwinprasadme

df = df[df.symbol == 'GOOG']
df.drop(['symbol'],1,inplace=True)
df.head()