Feature/Variable importance after a PCA analysis

Question

I have performed a PCA analysis over my original dataset and from the compressed dataset transformed by the PCA I have also selected the number of PC I want to keep (they ex

Answer 1

# original_num_df the original numeric dataframe
# pca is the model
def create_importance_dataframe(pca, original_num_df):

    # Change pcs components ndarray to a dataframe
    importance_df  = pd.DataFrame(pca.components_)

    # Assign columns
    importance_df.columns  = original_num_df.columns

    # Change to absolute values
    importance_df =importance_df.apply(np.abs)

    # Transpose
    importance_df=importance_df.transpose()

    # Change column names again

    ## First get number of pcs
    num_pcs = importance_df.shape[1]

    ## Generate the new column names
    new_columns = [f'PC{i}' for i in range(1, num_pcs + 1)]

    ## Now rename
    importance_df.columns  =new_columns

    # Return importance df
    return importance_df

# Call function to create importance df
importance_df  =create_importance_dataframe(pca, original_num_df)

# Show first few rows
display(importance_df.head())

# Sort depending on PC of interest

## PC1 top 10 important features
pc1_top_10_features = importance_df['PC1'].sort_values(ascending = False)[:10]
print(), print(f'PC1 top 10 feautres are \n')
display(pc1_top_10_features )

## PC2 top 10 important features
pc2_top_10_features = importance_df['PC2'].sort_values(ascending = False)[:10]
print(), print(f'PC2 top 10 feautres are \n')
display(pc2_top_10_features )