pump_predictive_variables.py

# select columns that have "few" unique values
cramer_cols = [col for col in df.columns.values if (len(df[col].unique())<250)]

for col in cramer_cols:
    try:
        cm = pd.crosstab(df[col], df['status_group']).values # contingency table
        cv1 = cramers_corrected_stat(cm)
        if (cv1>=0.20):
            print(col, int(cv1*100))
    except:
        None

# Output :
# funder            25
# installer         25
# region            20
# scheme_name       20
# extraction_type   24
# quantity          30
# waterpoint_type   25
# amount_tsh_zero   22