def fit(self, X_train, y_train):
# intrusion
if intrusion:
X_intrusion = FeatureEngineering(
X_train[self.features],
"intrusion_cutoff").engineer_features().values
y_intrusion = X_train["intrusion_cutoff"].apply(lambda x: int(x))
self.pipe_intrusion = Pipeline(
steps=[('feature_selection', SelectFpr(
alpha=0.05)), ('sampling',
BorderlineSMOTE(k_neighbors=10)),
('classifier',
XGBClassifier(n_estimators=300, max_depth=5))])
scores = cross_val_score(self.pipe_intrusion,
X_intrusion,
y_intrusion,
scoring='f1',
cv=StratifiedKFold(5))
print(f"intrusion {sum(scores)/5}")
self.pipe_intrusion.fit(X_intrusion, y_intrusion)
# avoidance
if avoidance:
X_avoidance = FeatureEngineering(
X_train[self.features],
"avoidance_cutoff").engineer_features().values
y_avoidance = X_train["avoidance_cutoff"].apply(lambda x: int(x))
self.pipe_avoidance = Pipeline(
steps=[('feature_selection',
RFE(estimator=XGBClassifier(scale_pos_weight=5.88,
n_estimators=100),
n_features_to_select=20)),
('classifier',
BalancedRandomForestClassifier(n_estimators=300,
max_depth=10))])
scores = cross_val_score(self.pipe_avoidance,
X_avoidance,
y_avoidance,
scoring='f1',
cv=StratifiedKFold(5))
print(f"avoidance {sum(scores)/5}")
self.pipe_avoidance.fit(X_avoidance, y_avoidance)
# hypertension
if hypertension:
X_hypertension = FeatureEngineering(
X_train[self.features],
"hypertention_cutoff").engineer_features().values
y_hypertention = X_train["hypertention_cutoff"].apply(
lambda x: int(x))
self.pipe_hypertension = Pipeline(
steps=[('feature_selection',
RFE(estimator=XGBClassifier(n_estimators=100,
scale_pos_weight=3.51),
n_features_to_select=20)
), ('sampling', SMOTE(k_neighbors=10)),
('classifier',
BalancedRandomForestClassifier(n_estimators=100))])
scores = cross_val_score(self.pipe_hypertension,
X_hypertension,
y_hypertention,
scoring='f1',
cv=StratifiedKFold(5))
print(f"hypertension {sum(scores)/5}")
self.pipe_hypertension.fit(X_hypertension, y_hypertention)
# depression
if depression:
X_depression = FeatureEngineering(
X_train[self.features],
"depression_cutoff").engineer_features().values
y_depression = X_train["depression_cutoff"].apply(lambda x: int(x))
self.pipe_depression = Pipeline(
steps=[('feature_selection', SelectFdr(
alpha=0.1)), ('sampling', SMOTE(k_neighbors=5)),
('classifier',
RandomForestClassifier(n_estimators=100))])
scores = cross_val_score(self.pipe_depression,
X_depression,
y_depression,
scoring='f1',
cv=StratifiedKFold(5))
print(f"depression {sum(scores)/5}")
self.pipe_depression.fit(X_depression, y_depression)
# only_avoidance
if only_avoidance:
X_only_avoidance = FeatureEngineering(
X_train[self.features],
"only_avoidance_cutoff").engineer_features().values
y_only_avoidance = X_train["only_avoidance_cutoff"].apply(
lambda x: int(x))
self.pipe_only_avoidance = Pipeline(
steps=[('feature_selection',
RFE(XGBClassifier(n_estimators=100, max_depth=3),
n_features_to_select=10)),
('classifier',
BalancedRandomForestClassifier(n_estimators=500,
max_depth=10))])
scores = cross_val_score(self.pipe_only_avoidance,
X_only_avoidance,
y_only_avoidance,
scoring='f1',
cv=StratifiedKFold(5))
print(f"only_avoidance {sum(scores)/5}")
self.pipe_only_avoidance.fit(X_only_avoidance, y_only_avoidance)
# pcl_strict3
if PCL_Strict3:
X_PCL_Strict3 = FeatureEngineering(
X_train[self.features],
"PCL_Strict3").engineer_features().values
y_PCL_Strict3 = y_train["PCL_Strict3"].apply(lambda x: int(x))
self.pipe_PCL_Strict3 = Pipeline(
steps=[('feature_selection',
SelectKBest(k=20)), ('sampling', SMOTE(k_neighbors=5)),
('classifier',
XGBClassifier(max_depth=3, n_estimators=100))])
scores = cross_val_score(self.pipe_PCL_Strict3,
X_PCL_Strict3,
y_PCL_Strict3,
scoring='f1',
cv=StratifiedKFold(5))
print(f"PCL_Strict3 {sum(scores)/5}")
self.pipe_PCL_Strict3.fit(X_PCL_Strict3, y_PCL_Strict3)
# cutoff_33
if regression_cutoff_33:
X_regression_cutoff_33 = FeatureEngineering(
X_train[self.features],
"regression_cutoff_33").engineer_features().values
y_regression_cutoff_33 = X_train["regression_cutoff_33"].apply(
lambda x: int(x))
self.pipe_regression_cutoff_33 = Pipeline(
steps=[('feature_selection', SelectFpr(
alpha=0.033)), ('sampling', SMOTE(k_neighbors=10)),
('classifier',
RandomForestClassifier(n_estimators=100, max_depth=5)
)])
scores = cross_val_score(self.pipe_regression_cutoff_33,
X_regression_cutoff_33,
y_regression_cutoff_33,
scoring='f1',
cv=StratifiedKFold(5))
print(f"regression_cutoff_33 {sum(scores)/5}")
self.pipe_regression_cutoff_33.fit(X_regression_cutoff_33,
y_regression_cutoff_33)
# cutoff 50
if regression_cutoff_50:
X_regression_cutoff_50 = FeatureEngineering(
X_train[self.features],
"regression_cutoff_50").engineer_features().values
y_regression_cutoff_50 = X_train["regression_cutoff_50"].apply(
lambda x: int(x))
self.pipe_regression_cutoff_50 = Pipeline(
steps=[('feature_selection',
SelectKBest(k=10)), ('sampling',
SMOTE(k_neighbors=10)),
('classifier',
XGBClassifier(max_depth=2, n_estimators=100))])
scores = cross_val_score(self.pipe_regression_cutoff_50,
X_regression_cutoff_50,
y_regression_cutoff_50,
scoring='f1',
cv=StratifiedKFold(5))
print(f"regression_cutoff_50 {sum(scores)/5}")
self.pipe_regression_cutoff_50.fit(X_regression_cutoff_50,
y_regression_cutoff_50)
# tred_cutoff
if tred_cutoff:
X_tred_cutoff = FeatureEngineering(
X_train[self.features],
"tred_cutoff").engineer_features().values
y_tred_cutoff = X_train["tred_cutoff"].apply(lambda x: int(x))
self.pipe_tred_cutoff = Pipeline(
steps=[('feature_selection',
SelectKBest(k=20)), ('sampling',
SMOTE(k_neighbors=10)),
('classifier',
XGBClassifier(n_estimators=100, max_depth=2))])
scores = cross_val_score(self.pipe_tred_cutoff,
X_tred_cutoff,
y_tred_cutoff,
scoring='f1',
cv=StratifiedKFold(5))
print(f"tred_cutoff {sum(scores)/5}")
self.pipe_tred_cutoff.fit(X_tred_cutoff, y_tred_cutoff)
# target
if intrusion:
y_pred_intrusion = self.pipe_intrusion.predict(X_intrusion)
else:
y_pred_intrusion = 1
if avoidance:
y_pred_avoidance = self.pipe_avoidance.predict(X_avoidance)
else:
y_pred_avoidance = 1
if hypertension:
y_pred_hypertension = self.pipe_hypertension.predict(
X_hypertension)
else:
y_pred_hypertension = 1
if depression:
y_pred_depression = self.pipe_depression.predict(X_depression)
else:
y_pred_depression = 1
if only_avoidance:
y_pred_only_avoidance = self.pipe_only_avoidance.predict(
X_only_avoidance)
else:
y_pred_only_avoidance = 1
if PCL_Strict3:
y_pred_PCL_Strict3 = self.pipe_PCL_Strict3.predict(X_PCL_Strict3)
else:
y_pred_PCL_Strict3 = 1
if regression_cutoff_33:
y_pred_regression_cutoff_33 = self.pipe_regression_cutoff_33.predict(
X_regression_cutoff_33)
else:
y_pred_regression_cutoff_33 = 1
if regression_cutoff_50:
y_pred_regression_cutoff_50 = self.pipe_regression_cutoff_50.predict(
X_regression_cutoff_50)
else:
y_pred_regression_cutoff_50 = 1
if tred_cutoff:
y_pred_tred_cutoff = self.pipe_tred_cutoff.predict(X_tred_cutoff)
else:
y_pred_tred_cutoff = 1
y_pred = (y_pred_hypertension & y_pred_avoidance & y_pred_intrusion
& y_pred_depression & y_pred_only_avoidance
& y_pred_PCL_Strict3 & y_pred_regression_cutoff_33
& y_pred_regression_cutoff_50 & y_pred_tred_cutoff)
y_target = y_train
acc = accuracy_score(y_target, y_pred)
f1 = f1_score(y_target, y_pred)
recall = recall_score(y_target, y_pred)
precision = precision_score(y_target, y_pred)
print("training scores")
print(f"acc-{acc}, f1- {f1}, recall-{recall}, precision - {precision}")
def fit(self, X_train, y_train):
predictions_list = []
for target in self.targets_list:
if self.use_feature_engineering:
X = FeatureEngineering(X_train[self.features], target).engineer_features().values
else:
X = X_train[self.features].values
if target == "PCL_Strict3":
y = y_train[target].apply(lambda x: int(x))
else:
y = X_train[target].apply(lambda x: int(x))
pipeline = pipeline_per_target[target]
scores = cross_val_score(pipeline, X, y, scoring='f1', cv=StratifiedKFold(5))
print(f"{target} - {sum(scores)/len(scores)}")
if self.train_on_partial_prediction:
combined_y = pd.DataFrame(y, columns=[target])
if target != "PCL_Strict3":
combined_y["PCL_Strict3"] = y_train["PCL_Strict3"].apply(lambda x: int(x))
_X_train, _X_test, _y_train, _y_test = \
train_test_split(X, combined_y, test_size=0.25)
self.trained_pipelines[target] = pipeline.fit(_X_train, _y_train[target])
y_pred = self.trained_pipelines[target].predict(_X_test)
predictions_list.append(self.trained_pipelines[target].predict_proba(_X_test)[:, 0])
print("test f1", target, f1_score(_y_test[target], y_pred))
self.trained_pipelines[target] = pipeline.fit(X, y)
y = _y_test["PCL_Strict3"]
else:
self.trained_pipelines[target] = pipeline.fit(X, y)
predictions_list.append([self.trained_pipelines[target].predict(X)])
y = y_train["PCL_Strict3"]
if self.check_on_test_set:
if target == "PCL_Strict3":
y_test = self.y_test[target].apply(lambda x: int(x))
else:
y_test = X_train[target].apply(lambda x: int(x))
if self.use_feature_engineering:
X_test = FeatureEngineering(self.X_test[self.features], target).engineer_features().values
else:
X_test = self.X_test[self.features].values
model = self.trained_pipelines[target]
y_pred = model.predict(X_test)
s_f = f1_score(self.y_test, y_pred)
s_p = precision_score(self.y_test, y_pred)
s_r = recall_score(self.y_test, y_pred)
print(f"test f1 {target}", s_f)
print(f"test recall {target}", s_r)
print(f"test precision {target}", s_p)
#pipe = Pipeline(steps=[
# ('scaling', StandardScaler()),
# ('sampling', SMOTE()),
# ('classifier', LogisticRegression(penalty='l1'))])
#c = ((len(y) - sum(y)) / sum(y))
if not self.use_and_func:
c = 2
pipe = Pipeline(steps=[
('clf', XGBClassifier(scale_pos_weight=c))])
X = predictions_list
self.combined_model = pipe.fit(np.array(X).reshape(-1, len(predictions_list)), y)
def predict(self, X_test):
if intrusion:
X_test_intrusion_cutoff = FeatureEngineering(
X_test[self.features],
"intrusion_cutoff").engineer_features().values
y_pred_intrusion = self.pipe_intrusion.predict(
X_test_intrusion_cutoff)
else:
y_pred_intrusion = 1
if avoidance:
X_test_avoidance_cutoff = FeatureEngineering(
X_test[self.features],
"avoidance_cutoff").engineer_features().values
y_pred_avoidance = self.pipe_avoidance.predict(
X_test_avoidance_cutoff)
else:
y_pred_avoidance = 1
if hypertension:
X_test_hypertention_cutoff = FeatureEngineering(
X_test[self.features],
"hypertention_cutoff").engineer_features().values
y_pred_hypertension = self.pipe_hypertension.predict(
X_test_hypertention_cutoff)
else:
y_pred_hypertension = 1
if depression:
X_test_depression_cutoff = FeatureEngineering(
X_test[self.features],
"depression_cutoff").engineer_features().values
y_pred_depression = self.pipe_depression.predict(
X_test_depression_cutoff)
else:
y_pred_depression = 1
if only_avoidance:
X_test_only_avoidance_cutoff = FeatureEngineering(
X_test[self.features],
"only_avoidance_cutoff").engineer_features().values
y_pred_only_avoidance = self.pipe_only_avoidance.predict(
X_test_only_avoidance_cutoff)
else:
y_pred_only_avoidance = 1
if PCL_Strict3:
X_test_PCL_Strict3 = FeatureEngineering(
X_test[self.features],
"PCL_Strict3").engineer_features().values
y_pred_PCL_Strict3 = self.pipe_PCL_Strict3.predict(
X_test_PCL_Strict3)
else:
y_pred_PCL_Strict3 = 1
if regression_cutoff_33:
X_test_regression_cutoff_33 = FeatureEngineering(
X_test[self.features],
"regression_cutoff_33").engineer_features().values
y_pred_regression_cutoff_33 = self.pipe_regression_cutoff_33.predict(
X_test_regression_cutoff_33)
else:
y_pred_regression_cutoff_33 = 1
if regression_cutoff_50:
X_test_regression_cutoff_50 = FeatureEngineering(
X_test[self.features],
"regression_cutoff_50").engineer_features().values
y_pred_regression_cutoff_50 = self.pipe_regression_cutoff_50.predict(
X_test_regression_cutoff_50)
else:
y_pred_regression_cutoff_50 = 1
if tred_cutoff:
X_test_tred_cutoff = FeatureEngineering(
X_test[self.features],
"tred_cutoff").engineer_features().values
y_pred_tred_cutoff = self.pipe_tred_cutoff.predict(
X_test_tred_cutoff)
else:
y_pred_tred_cutoff = 1
y_pred = (y_pred_hypertension & y_pred_avoidance & y_pred_intrusion
& y_pred_depression & y_pred_only_avoidance
& y_pred_PCL_Strict3 & y_pred_regression_cutoff_33
& y_pred_regression_cutoff_50 & y_pred_tred_cutoff)
return y_pred
def predict(self, X_test):
if intrusion:
X_test_intrusion_cutoff = FeatureEngineering(X_test[self.features],
"intrusion_cutoff").engineer_features().values
y_pred_intrusion = self.pipe_intrusion.predict(X_test_intrusion_cutoff)
else:
y_pred_intrusion = 1
if avoidance:
X_test_avoidance_cutoff = FeatureEngineering(X_test[self.features],
"avoidance_cutoff").engineer_features().values
y_pred_avoidance = self.pipe_avoidance.predict(X_test_avoidance_cutoff)
else:
y_pred_avoidance = 1
if hypertension:
X_test_hypertention_cutoff = FeatureEngineering(X_test[self.features],
"hypertention_cutoff").engineer_features().values
y_pred_hypertension = self.pipe_hypertension.predict(X_test_hypertention_cutoff)
else:
y_pred_hypertension = 1
if depression:
X_test_depression_cutoff = FeatureEngineering(X_test[self.features],
"depression_cutoff").engineer_features().values
y_pred_depression = self.pipe_depression.predict(X_test_depression_cutoff)
else:
y_pred_depression = 1
if only_avoidance:
X_test_only_avoidance_cutoff = FeatureEngineering(X_test[self.features],
"only_avoidance_cutoff").engineer_features().values
y_pred_only_avoidance = self.pipe_only_avoidance.predict(X_test_only_avoidance_cutoff)
else:
y_pred_only_avoidance = 1
if PCL_Strict3:
X_test_PCL_Strict3 = FeatureEngineering(X_test[self.features], "PCL_Strict3").engineer_features().values
y_pred_PCL_Strict3 = self.pipe_PCL_Strict3.predict(X_test_PCL_Strict3)
else:
y_pred_PCL_Strict3 = 1
if regression_cutoff_33:
X_test_regression_cutoff_33 = FeatureEngineering(X_test[self.features],
"regression_cutoff_33").engineer_features().values
y_pred_regression_cutoff_33 = self.pipe_regression_cutoff_33.predict(X_test_regression_cutoff_33)
else:
y_pred_regression_cutoff_33 = 1
if regression_cutoff_50:
X_test_regression_cutoff_50 = FeatureEngineering(X_test[self.features],
"regression_cutoff_50").engineer_features().values
y_pred_regression_cutoff_50 = self.pipe_regression_cutoff_50.predict(X_test_regression_cutoff_50)
else:
y_pred_regression_cutoff_50 = 1
if tred_cutoff:
X_test_tred_cutoff = FeatureEngineering(X_test[self.features], "tred_cutoff").engineer_features().values
y_pred_tred_cutoff = self.pipe_tred_cutoff.predict(X_test_tred_cutoff)
else:
y_pred_tred_cutoff = 1
y_pred = (y_pred_hypertension & y_pred_avoidance & y_pred_intrusion & y_pred_depression &
y_pred_only_avoidance & y_pred_PCL_Strict3 & y_pred_regression_cutoff_33 &
y_pred_regression_cutoff_50 & y_pred_tred_cutoff)
preds = ["y_pred_hypertension", "y_pred_avoidance", "y_pred_intrusion", "y_pred_regression"]
X_combined = X_test[['q6.11_NUMB_pcl2', 'q6.13_SLEEP_pcl1', 'intrusion_pcl2', 'phq2'] + preds].values
y_pred = self.pipe_combined.predict(X_combined)
return y_pred