def clean_data(data):
# drop problematic row with zero for asthma_rate
data = data.drop([141, 142, 149, 153, 158])
# replacing nans with zeros
data_nas = data.fillna(0)
# print('clean_data')
# print(type(data_nas))
return data_nas
def feature_selection(data):
all_columns = [
'pm10_mean', 'pm25_mean', 'pm25non_mean', 'pm25spec_mean', 'co_mean',
'so2_mean', 'no2_mean', 'ozo_mean', 'nonox_mean', 'lead_mean',
'haps_mean', 'vocs_mean', 'smoke_adult', 'obese_adult', 'uninsured',
'pcp', 'high_sch_grad', 'unemployment', 'income_ineq',
'air_poll_partic'
]
drop_columns = [
'pm10_mean', 'pm25_mean', 'pm25non_mean', 'pm25spec_mean', 'co_mean',
'no2_mean', 'ozo_mean', 'nonox_mean', 'lead_mean', 'haps_mean',
'vocs_mean', 'pcp', 'high_sch_grad', 'income_ineq', 'co', 'ca'
]
data = data.drop(drop_columns, axis=1)
return data, data.columns
def clean_data(data):
# drop problematic row with zero for asthma_rate
data = data.drop([141, 142, 149, 153, 158])
data_nas = data.fillna(0)
return data_nas
