Loves learning, sharing and discovering myself. Retail SME and passionate about Machine Learning

Hey Arjun,

To save the generated model , please refer to my article- https://medium.com/datadriveninvestor/machine-learning-how-to-save-and-load-scikit-learn-models-d7b99bc32c27

Thanks

Hi Youcef,

For creating time series dataset with 36 columns , less or more refer to my article on GRU

Hope this will help

Hello Prithiv,

I compiled the code in one block.

I tried this and it worked. Please ensure you are using Python 3 or above

import numpy as np import pandas as pddataset= [10,12,12,13,12,11,14,13,15,10,10,10,100,12,14,13, 12,10…

Thanks Jason for the feedback. Appreciate it

The label of one for the noised input of the Generator is to trick it as real data.

I hope the explanation helps.

Thanks,

Hi Nischal,

As you mentioned Stock prices are random walk.

Random walks are unpredictable and cannot be reasonably predicted.

For random walk prediction, we can use observations at the previous and the next time step. The next time step is a function of the prior time step.

Thank you very much Sahana.

Appreciate your comments.

Feedback is how I learn what I am doing right and what I need to correct.

Ayan,

This is a multivariate time series as it involves two variables volume and average stock price

Marco,

Thanks for catching the issue.

I have modified the code.

Hello Lohith,

To convert the scaled predicted values to normal values, we use inverse_transform.

Code can be modified as below to get the normal values.

First scaling individual features with different scalers as MinMax scalers should not be fitted twice

Thanks Can. Updated the error