def NeuralNetworkModel(splitData, X_train, X_test, y_train, y_test):
clf = MLPClassifier(alpha=1e-4, max_iter=1000)
layers = [(4, 6), (5, 7), (8, 10)]
grid_values = {
'hidden_layer_sizes': layers,
'activation': ['tanh', 'relu'],
'learning_rate': ['constant', 'invscaling']
}
grid_clf_acc = GridSearchCV(clf,
param_grid=grid_values,
scoring=['roc_auc', 'f1', 'accuracy'],
refit='roc_auc')
grid_clf_acc.fit(X_train, y_train.ravel())
clf = grid_clf_acc.best_estimator_
if splitData:
y_preds = clf.predict(X_test)
# printMetrics(y_test, y_preds)
val_acc, val_pre, val_recall, val_auc, val_f1 = getMetrics(
y_test, y_preds)
else:
val_acc, val_pre, val_recall, val_auc, val_f1 = 0, 0, 0, 0, 0
y_preds = clf.predict(X_train)
acc, pre, recall, auc, f1 = getMetrics(y_train, y_preds)
val_metrics = (val_acc, val_pre, val_recall, val_auc, val_f1)
metrics = (acc, pre, recall, auc, f1)
# print("acc-" + str(acc) + "\tprecision-" + str(pre) + "\trecall-" + str(recall) + "\tauc-" + str(auc) + "\tf1-" + str(f1) + "\tval_accuracy-" + str(val_acc) + "\tval_precision-" + str(val_pre) + "\tval_recall-" + str(val_recall) + "\tval_auc-" + str(val_auc) + "\tval_f1-" + str(val_f1) + "\n")
logAndSave(name_of_model="NeuralNetworkGS",
clf=clf,
metrics=metrics,
val_metrics=val_metrics)
def LogisticRegressionModel(splitData, X_train, X_test, y_train, y_test):
clf = LogisticRegression(solver='liblinear',
multi_class='ovr',
class_weight={
0: 0.7,
1: 1.5
})
grid_values = {
'penalty': ['l1', 'l2'],
'C': [0.01, .09, 1, 5, 25, 50, 100]
}
grid_clf_acc = GridSearchCV(clf,
param_grid=grid_values,
scoring=['roc_auc', 'f1', 'accuracy'],
refit='roc_auc')
grid_clf_acc.fit(X_train, y_train.ravel())
clf = grid_clf_acc.best_estimator_
if splitData:
y_preds = clf.predict(X_test)
# printMetrics(y_test, y_preds)
val_acc, val_pre, val_recall, val_auc, val_f1 = getMetrics(
y_test, y_preds)
else:
val_acc, val_pre, val_recall, val_auc, val_f1 = 0, 0, 0, 0, 0
y_preds = clf.predict(X_train)
acc, pre, recall, auc, f1 = getMetrics(y_train, y_preds)
val_metrics = (val_acc, val_pre, val_recall, val_auc, val_f1)
metrics = (acc, pre, recall, auc, f1)
# print("acc-" + str(acc) + "\tprecision-" + str(pre) + "\trecall-" + str(recall) + "\tauc-" + str(auc) + "\tf1-" + str(f1) + "\tval_accuracy-" + str(val_acc) + "\tval_precision-" + str(val_pre) + "\tval_recall-" + str(val_recall) + "\tval_auc-" + str(val_auc) + "\tval_f1-" + str(val_f1) + "\n")
logAndSave(name_of_model="LogisticRegressionGS",
clf=clf,
metrics=metrics,
val_metrics=val_metrics)
def AdaBoostModel(splitData, X_train, X_test, y_train, y_test):
svc = SVC()
clf = AdaBoostClassifier(base_estimator=svc, algorithm='SAMME')
grid_values = {
'base_estimator__kernel': ['linear', 'poly', 'rbf', 'sigmoid'],
'base_estimator__C': [x / 10 for x in range(1, 11)],
'base_estimator__degree': list(range(3, 5))
}
grid_clf_acc = GridSearchCV(clf,
param_grid=grid_values,
scoring=['roc_auc', 'f1', 'accuracy'],
refit='roc_auc')
grid_clf_acc.fit(X_train, y_train.ravel())
clf = grid_clf_acc.best_estimator_
if splitData:
y_preds = clf.predict(X_test)
# printMetrics(y_test, y_preds)
val_acc, val_pre, val_recall, val_auc, val_f1 = getMetrics(
y_test, y_preds)
else:
val_acc, val_pre, val_recall, val_auc, val_f1 = 0, 0, 0, 0, 0
y_preds = clf.predict(X_train).reshape(-1, 1)
acc, pre, recall, auc, f1 = getMetrics(y_train, y_preds)
val_metrics = (val_acc, val_pre, val_recall, val_auc, val_f1)
metrics = (acc, pre, recall, auc, f1)
# print("acc-" + str(acc) + "\tprecision-" + str(pre) + "\trecall-" + str(recall) + "\tauc-" + str(auc) + "\tf1-" + str(f1) + "\tval_accuracy-" + str(val_acc) + "\tval_precision-" + str(val_pre) + "\tval_recall-" + str(val_recall) + "\tval_auc-" + str(val_auc) + "\tval_f1-" + str(val_f1) + "\n")
logAndSave(name_of_model="AdaBoostGS",
clf=clf,
metrics=metrics,
val_metrics=val_metrics)
def LogisticRegressionModel(splitData, X_train, X_test, y_train, y_test):
clf = LogisticRegression(penalty='l1',
solver='liblinear',
multi_class='ovr',
class_weight={
0: 0.7,
1: 1.5
})
clf.fit(X_train, y_train.ravel())
if splitData:
y_preds = clf.predict(X_test)
printMetrics(y_test, y_preds)
val_acc, val_pre, val_recall, val_auc, val_f1 = getMetrics(
y_test, y_preds)
else:
val_acc, val_pre, val_recall, val_auc, val_f1 = 0, 0, 0, 0, 0
y_preds = clf.predict(X_train)
acc, pre, recall, auc, f1 = getMetrics(y_train, y_preds)
val_metrics = (val_acc, val_pre, val_recall, val_auc, val_f1)
metrics = (acc, pre, recall, auc, f1)
# print("acc-" + str(acc) + "\tprecision-" + str(pre) + "\trecall-" + str(recall) + "\tauc-" + str(auc) + "\tf1-" + str(f1) + "\tval_accuracy-" + str(val_acc) + "\tval_precision-" + str(val_pre) + "\tval_recall-" + str(val_recall) + "\tval_auc-" + str(val_auc) + "\tval_f1-" + str(val_f1) + "\n")
logAndSave(name_of_model="LogisticRegression",
clf=clf,
metrics=metrics,
val_metrics=val_metrics)
def XGBClassifierModelV2(X_train, X_test, y_train, y_test):
multi_class = True
clf = xgb.XGBClassifier(objective="multi:softmax", eval_metric="mlogloss")
grid_values = {
'learning_rate': [x / 10 for x in range(1, 5)],
'max_depth': list(range(10, 21, 1))
}
grid_clf_acc = GridSearchCV(
clf,
param_grid=grid_values,
scoring=['roc_auc_ovr_weighted', 'f1_weighted', 'accuracy'],
refit='f1_weighted',
n_jobs=2,
verbose=0)
grid_clf_acc.fit(X_train, y_train)
clf = grid_clf_acc.best_estimator_
# print(clf)
y_preds = clf.predict(X_test)
# printMetrics(y_test, y_preds, multi_class=multi_class)
val_acc, val_pre, val_recall, val_auc, val_f1 = getMetrics(
y_test, y_preds, multi_class=multi_class)
y_preds = clf.predict(X_train)
# printMetrics(y_train, y_preds, multi_class=multi_class)
acc, pre, recall, auc, f1 = getMetrics(y_train,
y_preds,
multi_class=multi_class)
val_metrics = (val_acc, val_pre, val_recall, val_auc, val_f1)
metrics = (acc, pre, recall, auc, f1)
logAndSave(name_of_model="XGBClassifierModelV2GS",
clf=clf,
metrics=metrics,
val_metrics=val_metrics)
def XGBClassifierModel(splitData, X_train, X_test, y_train, y_test):
clf = xgb.XGBClassifier(objective="binary:logistic", eval_metric="auc")
grid_values = {
'learning_rate': [x / 10 for x in range(1, 11)],
'max_depth': list(range(10, 21, 1)),
'gamma ': [x / 10 for x in range(1, 11)]
}
grid_clf_acc = GridSearchCV(clf,
param_grid=grid_values,
scoring=['roc_auc', 'f1', 'accuracy'],
refit='roc_auc')
grid_clf_acc.fit(X_train, y_train.ravel())
clf = grid_clf_acc.best_estimator_
if splitData:
y_preds = clf.predict(X_test)
# printMetrics(y_test, y_preds)
val_acc, val_pre, val_recall, val_auc, val_f1 = getMetrics(
y_test, y_preds)
else:
val_acc, val_pre, val_recall, val_auc, val_f1 = 0, 0, 0, 0, 0
y_preds = clf.predict(X_train)
acc, pre, recall, auc, f1 = getMetrics(y_train, y_preds)
val_metrics = (val_acc, val_pre, val_recall, val_auc, val_f1)
metrics = (acc, pre, recall, auc, f1)
# print("acc-" + str(acc) + "\tprecision-" + str(pre) + "\trecall-" + str(recall) + "\tauc-" + str(auc) + "\tf1-" + str(f1) + "\tval_accuracy-" + str(val_acc) + "\tval_precision-" + str(val_pre) + "\tval_recall-" + str(val_recall) + "\tval_auc-" + str(val_auc) + "\tval_f1-" + str(val_f1) + "\n")
logAndSave(name_of_model="XGBClassifierGS",
clf=clf,
metrics=metrics,
val_metrics=val_metrics)
def AdaBoostModel(splitData, X_train, X_test, y_train, y_test):
svc = SVC()
clf = AdaBoostClassifier(base_estimator=svc, n_estimators=100, algorithm='SAMME')
clf.fit(X_train, y_train.ravel())
if splitData:
y_preds = clf.predict(X_test)
printMetrics(y_test, y_preds)
val_acc, val_pre, val_recall, val_auc, val_f1 = getMetrics(y_test, y_preds)
else:
val_acc, val_pre, val_recall, val_auc, val_f1 = 0, 0, 0, 0, 0
y_preds = clf.predict(X_train).reshape(-1, 1)
acc, pre, recall, auc, f1 = getMetrics(y_train, y_preds)
val_metrics = (val_acc, val_pre, val_recall, val_auc, val_f1)
metrics = (acc, pre, recall, auc, f1)
# print("acc-" + str(acc) + "\tprecision-" + str(pre) + "\trecall-" + str(recall) + "\tauc-" + str(auc) + "\tval_accuracy-" + str(val_acc) + "\tval_precision-" + str(val_pre) + "\tval_recall-" + str(val_recall) + "\tval_auc-" + str(val_auc) + "\n")
logAndSave(name_of_model="AdaBoost", clf=clf, metrics=metrics, val_metrics=val_metrics)
def RandomForestModel(splitData, X_train, X_test, y_train, y_test):
clf = RandomForestClassifier(n_estimators=100, max_depth=11)
grid_values = {'n_estimators': list(range(100, 501, 50)), 'criterion': ['gini', 'entropy'], 'max_depth': list(range(10, 21, 1))}
grid_clf_acc = GridSearchCV(clf, param_grid=grid_values, scoring=['roc_auc', 'f1', 'accuracy'], refit='roc_auc')
grid_clf_acc.fit(X_train, y_train.ravel())
clf = grid_clf_acc.best_estimator_
if splitData:
y_preds = clf.predict(X_test)
# printMetrics(y_test, y_preds)
val_acc, val_pre, val_recall, val_auc, val_f1 = getMetrics(y_test, y_preds)
else:
val_acc, val_pre, val_recall, val_auc, val_f1 = 0, 0, 0, 0, 0
y_preds = clf.predict(X_train)
acc, pre, recall, auc, f1 = getMetrics(y_train, y_preds)
val_metrics = (val_acc, val_pre, val_recall, val_auc, val_f1)
metrics = (acc, pre, recall, auc, f1)
# print("acc-" + str(acc) + "\tprecision-" + str(pre) + "\trecall-" + str(recall) + "\tauc-" + str(auc) + "\tf1-" + str(f1) + "\tval_accuracy-" + str(val_acc) + "\tval_precision-" + str(val_pre) + "\tval_recall-" + str(val_recall) + "\tval_auc-" + str(val_auc) + "\tval_f1-" + str(val_f1) + "\n")
logAndSave(name_of_model="RandomForestClassifierGS", clf=clf, metrics=metrics, val_metrics=val_metrics)
def XGBClassifierModel(splitData, X_train, X_test, y_train, y_test):
clf = xgb.XGBClassifier(objective="binary:logistic", eval_metric="auc")
clf.fit(X_train, y_train.ravel())
if splitData:
y_preds = clf.predict(X_test)
printMetrics(y_test, y_preds)
val_acc, val_pre, val_recall, val_auc, val_f1 = getMetrics(
y_test, y_preds)
else:
val_acc, val_pre, val_recall, val_auc, val_f1 = 0, 0, 0, 0, 0
y_preds = clf.predict(X_train)
acc, pre, recall, auc, f1 = getMetrics(y_train, y_preds)
val_metrics = (val_acc, val_pre, val_recall, val_auc, val_f1)
metrics = (acc, pre, recall, auc, f1)
# print("acc-" + str(acc) + "\tprecision-" + str(pre) + "\trecall-" + str(recall) + "\tauc-" + str(auc) + "\tval_accuracy-" + str(val_acc) + "\tval_precision-" + str(val_pre) + "\tval_recall-" + str(val_recall) + "\tval_auc-" + str(val_auc) + "\n")
logAndSave(name_of_model="XGBClassifier",
clf=clf,
metrics=metrics,
val_metrics=val_metrics)
def RandomForestModel(splitData, X_train, X_test, y_train, y_test):
clf = RandomForestClassifier(max_depth=14)
clf.fit(X_train, y_train.ravel())
if splitData:
y_preds = clf.predict(X_test)
printMetrics(y_test, y_preds)
val_acc, val_pre, val_recall, val_auc, val_f1 = getMetrics(
y_test, y_preds)
else:
val_acc, val_pre, val_recall, val_auc, val_f1 = 0, 0, 0, 0, 0
y_preds = clf.predict(X_train)
acc, pre, recall, auc, f1 = getMetrics(y_train, y_preds)
val_metrics = (val_acc, val_pre, val_recall, val_auc, val_f1)
metrics = (acc, pre, recall, auc, f1)
# print("acc-" + str(acc) + "\tprecision-" + str(pre) + "\trecall-" + str(recall) + "\tauc-" + str(auc) + "\tf1-" + str(f1) + "\tval_accuracy-" + str(val_acc) + "\tval_precision-" + str(val_pre) + "\tval_recall-" + str(val_recall) + "\tval_auc-" + str(val_auc) + "\tval_f1-" + str(val_f1) + "\n")
logAndSave(name_of_model="RandomForestClassifier",
clf=clf,
metrics=metrics,
val_metrics=val_metrics)
min_samples_leaf=9,
min_samples_split=18,
n_estimators=100)),
StackingEstimator(
estimator=MLPClassifier(alpha=0.001, learning_rate_init=1.0)),
StackingEstimator(
estimator=GradientBoostingClassifier(learning_rate=0.5,
max_depth=4,
max_features=0.6500000000000001,
min_samples_leaf=9,
min_samples_split=19,
n_estimators=100,
subsample=0.9500000000000001)),
BernoulliNB(alpha=10.0, fit_prior=False))
# Fix random state for all the steps in exported pipeline
set_param_recursive(exported_pipeline.steps, 'random_state', 101)
exported_pipeline.fit(X_train, y_train)
y_preds = exported_pipeline.predict(X_train)
acc, pre, recall, auc, f1 = getMetrics(y_train, y_preds)
y_preds = exported_pipeline.predict(X_test)
val_acc, val_pre, val_recall, val_auc, val_f1 = getMetrics(y_test, y_preds)
val_metrics = (val_acc, val_pre, val_recall, val_auc, val_f1)
metrics = (acc, pre, recall, auc, f1)
logAndSave(name_of_model="TPOT_Classifier",
clf=exported_pipeline,
metrics=metrics,
val_metrics=val_metrics)