def prediction(data):
df = DataFrame(data, index=[0])
df.CNDTN = df.apply(applyCNDTN, axis=1)
df.GRADE = df.apply(applyGRADE, axis=1)
import category_encoders as ce
df_temp = encoder_features.transform(df.drop(
['GRADE', 'CNDTN'], axis=1)).drop([
'HEAT_0', 'AC_0', 'STYLE_0', 'STRUCT_0', 'EXTWALL_0',
'QUALIFIED_0', 'ROOF_0', 'INTWALL_0', 'ASSESSMENT_NBHD_0',
'WARD_0', 'QUADRANT_0'
],
axis=1)
df = pd.concat([df_temp, df[['GRADE', 'CNDTN']]], axis=1)
df_scaled = scaller_features.transform(df[['YR_RMDL', 'GBA', 'LANDAREA']])
df_scaled = pd.DataFrame(df_scaled, columns=['YR_RMDL', 'GBA', 'LANDAREA'])
df = pd.concat(
[df.drop(['YR_RMDL', 'GBA', 'LANDAREA'], axis=1), df_scaled], axis=1)
df = df[[
'BATHRM', 'HF_BATHRM', 'HEAT_1', 'HEAT_2', 'HEAT_3', 'HEAT_4', 'AC_1',
'NUM_UNITS', 'ROOMS', 'BEDRM', 'QUALIFIED_1', 'BLDG_NUM', 'STYLE_1',
'STYLE_2', 'STYLE_3', 'STYLE_4', 'STYLE_5', 'STRUCT_1', 'STRUCT_2',
'STRUCT_3', 'EXTWALL_1', 'EXTWALL_2', 'EXTWALL_3', 'EXTWALL_4',
'EXTWALL_5', 'ROOF_1', 'ROOF_2', 'ROOF_3', 'ROOF_4', 'INTWALL_1',
'INTWALL_2', 'INTWALL_3', 'INTWALL_4', 'KITCHENS', 'FIREPLACES',
'ASSESSMENT_NBHD_1', 'ASSESSMENT_NBHD_2', 'ASSESSMENT_NBHD_3',
'ASSESSMENT_NBHD_4', 'ASSESSMENT_NBHD_5', 'ASSESSMENT_NBHD_6',
'WARD_1', 'WARD_2', 'WARD_3', 'QUADRANT_1', 'QUADRANT_2', 'GRADE',
'CNDTN', 'YR_RMDL', 'GBA', 'LANDAREA'
]]
hasil = model.predict(df)
hasil_fix = int(hasil[0])
return hasil_fix
