verbose=False)
else:
print("wrong fuzzy option")
# grid search results data frame:
gs_results_df = training_utils.get_gs_results(clf_gs)
# best parameters from grid search:
best_param_df = pd.DataFrame(clf_gs.best_params_, index=[0])
# evaluation:
clf_for_eval.set_params(**clf_gs.best_params_)
metrics, std = training_utils.evaluate_on_cv(training_data,
train_X_all,
clf_for_eval,
fuzzy_option,
fuzzy_dist_column,
fuzzy_err_column,
xgb_flag=True)
pr_curve = training_utils.predict_and_pr_curve_on_cv(training_data,
train_X_all,
clf_for_eval,
fuzzy_option,
fuzzy_dist_column,
fuzzy_err_column,
xgb_flag=True)
# best model from grid search:
clf_best = clf_gs.best_estimator_
# generalization:
train_X = training_data[features].values
general_X = general_data[features].values
for fuzzy_option in fuzzy_options:
print(fuzzy_option)
clf = ExtraTreesClassifier(n_estimators=500,
criterion='gini',
class_weight='balanced',
bootstrap=True,
random_state=476,
n_jobs=-1)
metrics, std = training_utils.evaluate_on_cv(training_data, train_X, clf,
fuzzy_option,
fuzzy_dist_column,
fuzzy_err_column)
pr_curve = training_utils.predict_and_pr_curve_on_cv(
training_data, train_X, clf, fuzzy_option, fuzzy_dist_column,
fuzzy_err_column)
# fit to the data:
if fuzzy_option == "normal":
clf.fit(X=train_X, y=training_data["Y"])
elif fuzzy_option == "fuzzy_dist":
clf.fit(X=train_X,
y=training_data["Y"],
sample_weight=training_data[fuzzy_dist_column].values.T[0])
elif fuzzy_option == "fuzzy_err":
clf.fit(X=train_X,
y=training_data["Y"],