Reading Data.py

# training data
train_data = pd.read_csv('train.csv', encoding = 'ISO-8859-1')
    
# test data
test_data = pd.read_csv('test.csv', encoding = 'ISO-8859-1')

# filter null label rows
train_data = train_data[(train_data['compliance']==0) | (train_data['compliance']==1)]
    
# filter null hearing dates rows
train_data = train_data[~train_data['hearing_date'].isnull()]
    
# adresses data
address_data = pd.read_csv('addresses.csv', encoding = 'ISO-8859-1')
    
# latlon data
latlons_data = pd.read_csv('latlons.csv', encoding = 'ISO-8859-1')
 
# merge address and latlon
address_latlons = address_data.set_index('address').join(latlons_data.set_index('address'),how='left')
    
# merge adress and latlon to test and train data
train_data = train_data.set_index('ticket_id').join(address_latlons.set_index('ticket_id'))
test_data = test_data.set_index('ticket_id').join(address_latlons.set_index('ticket_id'))