PCA_.py

from Packages import *
from Class_Mod.DATA_HANDLING import *


def pca_maker(data_import):
    numerical_data, categorical_data, scaled_values = col_cat(data_import)
    # Compute a 6 components PCA on scaled values
    pca = PCA(n_components=6)
    pca_fit = pca.fit(scaled_values)
    pca_data = pca_fit.transform(scaled_values)
    pca_data = pd.DataFrame(pca_data, index=numerical_data.index)
    # Set PCA column names with component number and explained variance %
    new_column_names = ["PCA_" + str(i) + ' - ' + str(round(pca_fit.explained_variance_ratio_[i-1], 3) *100) + '%' for i in range(1, len(pca_data.columns) + 1)]
    # Format the output
    column_mapper = dict(zip(list(pca_data.columns), new_column_names))
    pca_data = pca_data.rename(columns=column_mapper)
    output = pd.concat([data_import, pca_data], axis=1)
    return output, list(categorical_data.columns), new_column_names



####################################################################################################################################################################