glass_correlation.py

# There are many column pairs with high correlation, thus acting as duplicates. 
# We can drop a column if there is a correlation = 1 or -1

final_columns = list(df.columns)    # maintaining a temporary list to remove columns from

for i in range(corr.shape[0]):
    for j in range(i+1, corr.shape[0]):
        #print(abs(corr.iloc[i,j]), list(df.columns)[i], list(df.columns)[j])
        if abs(corr.iloc[i, j]) > 0.98:    # if very high correlation            
            if list(df.columns)[j] in final_columns:    # if not aldready removed
                final_columns.remove(list(df.columns)[j])    # remove

df = df[final_columns]    # selecting only the required columns