def main():
cat_cols = ['GRADELEVEL', 'EDUCATION_LEVEL', 'LEAVING', 'AGENCY']
data = munge_funcs.import_data()
data_fm = munge_funcs.df_clean(data, cat_cols,
'Financial Management Satisfaction')
data_hr = munge_funcs.df_clean(data, cat_cols,
'Human Capital Satisfaction')
data_it = munge_funcs.df_clean(data, cat_cols, 'IT Function Satisfaction')
data_acq = munge_funcs.df_clean(
data, cat_cols, 'Contracting Function Quality of Support Satisfaction')
#return data_fm,data_hr,data_it,data_acq
data_fm.to_csv('fm_data.csv')
data_hr.to_csv('hr_data.csv')
data_it.to_csv('it_data.csv')
data_acq.to_csv('acq_data.csv')
def test_target_names_acq(self):
target = 'Contracting Function Quality of Support Satisfaction'
result = munge_funcs.df_clean(self.test_df,self.cat_cols,target)
expected_cols = ['TELEWORK', 'YRSAGENCY2', 'SUP_STATUS', 'AGE',
target, 'GRADELEVEL_GS-12', 'GRADELEVEL_GS-13',
'EDUCATION_LEVEL_High School Diploma, GED, or Equivalent',
'EDUCATION_LEVEL_Master\'s Degree', 'LEAVING_No',
'LEAVING_Yes - to take another job', 'AGENCY_Department of Justice',
'AGENCY_Department of Veterans Affairs', 'intercept']
self.assertEqual(list(result.columns).sort(),list(expected_cols).sort())