Thanks for catching the issue.

I have modified the code.

  • Updated the logic to create the time series dataset
  • Updated the test data
  • Increased epochs from 100 to 200
  • Updated the dataset to plot the actual values

If I use the updated logic to create the time series before scaling the values and where lookback is just 1 step

First looking at the raw data

Image for post

Then applying the updated logic

# time series with two inputs
lookback= 1
test_size=int(.3 * len(stock_data))
for i in range(len(stock_data)-lookback-1):
for j in range(0,lookback):

t.append(input_data[[(i+j)], :])
y.append(input_data[i+ lookback,1])

and then just printing first 5 values

for i in range(5):

print(str(X[i]) + " " + str(y[i]))

the output is

Image for post

Please let me know if that fixes the problem


Written by

Loves learning, sharing, and discovering myself. Passionate about Machine Learning and Deep Learning

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store