Discussing the article: "Developing a robot in Python and MQL5 (Part 1): Data preprocessing" - page 8

New comment
 
MetaQuotes:

The new article Development of a robot in Python and MQL5 (Part 1): Data preprocessing has been published:

Author: Yevgeniy Koshtenko

Great article
 

In this function

def cluster_features_by_gmm(data, n_components=4):
    X = data.drop(['label', 'labels'], axis=1)

there are two "label" to be dropped, i dont catch why since we have marked up the data with only one column: labels with the function label data

 
Why have we designed more than 200 features that we use not? I dont see a place where these features are used
12345678
New comment