Entfernen von Komponenten mit geringer Varianz mit scikit-learn

import numpy as np
import pandas as pd
from sklearn.feature_selection import VarianceThreshold

# Just make a convenience function; this one wraps the VarianceThreshold
# transformer but you can pass it a pandas dataframe and get one in return

def get_low_variance_columns(dframe=None, columns=None,
                             skip_columns=None, thresh=0.0,
                             autoremove=False):
    """
    Wrapper for sklearn VarianceThreshold for use on pandas dataframes.
    """
    print("Finding low-variance features.")
    try:
        # get list of all the original df columns
        all_columns = dframe.columns

        # remove `skip_columns`
        remaining_columns = all_columns.drop(skip_columns)

        # get length of new index
        max_index = len(remaining_columns) - 1

        # get indices for `skip_columns`
        skipped_idx = [all_columns.get_loc(column)
                       for column
                       in skip_columns]

        # adjust insert location by the number of columns removed
        # (for non-zero insertion locations) to keep relative
        # locations intact
        for idx, item in enumerate(skipped_idx):
            if item > max_index:
                diff = item - max_index
                skipped_idx[idx] -= diff
            if item == max_index:
                diff = item - len(skip_columns)
                skipped_idx[idx] -= diff
            if idx == 0:
                skipped_idx[idx] = item

        # get values of `skip_columns`
        skipped_values = dframe.iloc[:, skipped_idx].values

        # get dataframe values
        X = dframe.loc[:, remaining_columns].values

        # instantiate VarianceThreshold object
        vt = VarianceThreshold(threshold=thresh)

        # fit vt to data
        vt.fit(X)

        # get the indices of the features that are being kept
        feature_indices = vt.get_support(indices=True)

        # remove low-variance columns from index
        feature_names = [remaining_columns[idx]
                         for idx, _
                         in enumerate(remaining_columns)
                         if idx
                         in feature_indices]

        # get the columns to be removed
        removed_features = list(np.setdiff1d(remaining_columns,
                                             feature_names))
        print("Found {0} low-variance columns."
              .format(len(removed_features)))

        # remove the columns
        if autoremove:
            print("Removing low-variance features.")
            # remove the low-variance columns
            X_removed = vt.transform(X)

            print("Reassembling the dataframe (with low-variance "
                  "features removed).")
            # re-assemble the dataframe
            dframe = pd.DataFrame(data=X_removed,
                                  columns=feature_names)

            # add back the `skip_columns`
            for idx, index in enumerate(skipped_idx):
                dframe.insert(loc=index,
                              column=skip_columns[idx],
                              value=skipped_values[:, idx])
            print("Succesfully removed low-variance columns.")

        # do not remove columns
        else:
            print("No changes have been made to the dataframe.")

    except Exception as e:
        print(e)
        print("Could not remove low-variance features. Something "
              "went wrong.")
        pass

    return dframe, removed_features