junte/Model
1
0
Fork 0
mirror of https://github.com/Hestia-Homes/Model.git synced 2026-06-30 13:10:47 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

investigating dropping variables

Browse source
This commit is contained in:
Khalim Conn-Kowlessar 2023-07-04 16:13:40 +01:00
parent ccfdb7cc8c
commit 58edd9a255
1 changed files with 8 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

10
model_data/analysis/SapModel.py
View file

@ -282,9 +282,13 @@ class SapModel:
train_x = train_x.drop(columns=["idx"]) train_x = train_x.drop(columns=["idx"])
test_x = test_x.drop(columns=["idx"]) test_x = test_x.drop(columns=["idx"])
importance_df = self.make_importance(train_x) # importance_df = self.make_importance(train_x)
# Test dropping the least important features # Test dropping the least important features
to_drop = importance_df.tail(1)["Feature"].values # to_drop = importance_df.tail(2)["Feature"].values
# Dropping this is a good idea
to_drop = [
"hotwater-description_Electric immersion, off-peak",
]
train_x = train_x.drop(columns=to_drop) train_x = train_x.drop(columns=to_drop)
test_x = test_x[train_x.columns] test_x = test_x[train_x.columns]
@ -353,6 +357,8 @@ class SapModel:
fit_success = check_successes(self.fit_error, best_fit) fit_success = check_successes(self.fit_error, best_fit)
predict_success = check_successes(self.predict_error, best_predict) predict_success = check_successes(self.predict_error, best_predict)
print(self.results.summary())
self.model_data['fit'] = self.results.fittedvalues self.model_data['fit'] = self.results.fittedvalues
# The worst errors over index heavily for flats # The worst errors over index heavily for flats
self.worst["x"] = self.model_data[self.model_data.index.isin(self.worst["errors"].index)] self.worst["x"] = self.model_data[self.model_data.index.isin(self.worst["errors"].index)]