test_df = as_category(test_df)
test_X = test_df.drop(['CONTACT_DATE', 'SNAP_DATE'], axis=1)
if clf_name != 'FeaturePredictor':
cols = list(set(test_X.columns).difference(test_X.select_dtypes(include='category').columns))
test_X.loc[:, cols] = test_X.loc[:, cols].fillna(0).replace([np.inf, -np.inf], 0)
for c in test_X.select_dtypes(include='category').columns:
test_X.loc[:, c] = test_X.loc[:, c].cat.codes
adv_auc = 0
adv_train_x, adv_train_y, adv_test_x, adv_test_y = adversial_train_test_split(train_X.loc[:, features], train_y,
test_X.loc[:, features],
topK=1000)
bayes_cv_tuner._fit_best_model(adv_train_x, adv_train_y)
adv_pred_y = bayes_cv_tuner.predict_proba(adv_test_x)[:, 1]
adv_auc = roc_auc_score(adv_test_y, adv_pred_y)
print(f'Adversial AUC = {adv_auc} by {len(adv_test_y)} samples')
bayes_cv_tuner._fit_best_model(train_X, train_y)
test_y = bayes_cv_tuner.predict_proba(test_X)
df = pd.DataFrame(test_y[:, 1])
df.to_csv(f"submits/"
f"{best_estimator.__class__.__name__}"
f"_{datetime.now().strftime('%d_%H_%M')}"
f"_{bayes_cv_tuner.best_score_:0.4f}"
f"_{adv_auc:0.4f}.csv",
header=None,
index=None)
cv_folds = [train_test_split(range(len(X)), train_size=0.666)]
model = BayesSearchCV(estimator=pipe,
search_spaces={
'model__latent_dim': (2, 20),
'model__intermediate_dim': (8, 128),
'model__epochs': (8, 128),
'model__D': (1e-3, 1e+3, 'log-uniform'),
'model__lr': (1e-4, 1e-2, 'log-uniform'),
},
n_iter=32,
cv=cv_folds,
refit=False,
error_score=-1.0)
model.on_step = lambda x: print(
(x, model.total_iterations(), model.best_score_))
model.fit(X, Y)
model.refit = True
model._fit_best_model(X, Y)
print(model.best_params_)
print(model.score(X, Y))
"""
model = pipe
model.set_params(**{'model__D': 5.1964624423233898, 'model__lr': 0.00010138257365940301,
'model__epochs': 26, 'model__intermediate_dim': 125, 'model__latent_dim': 2})
model.fit(X, Y)
print(model.predict(X, Y))
"""