def NuSVRRegressor(X_train, X_test, y_train, y_test):
y_train1 = y_train[:, 0]
y_train2 = y_train[:, 1]
reg1 = NuSVR()
reg1.fit(X_train, y_train1)
reg2 = NuSVR()
reg2.fit(X_train, y_train2)
y_pred1 = reg1.predict(X=X_test)
y_pred2 = reg2.predict(X=X_test)
y_pred = np.hstack((y_pred1.reshape(-1, 1), y_pred2.reshape(-1, 1)))
printMetrics(y_true=y_test, y_pred=y_pred)
val_metrics = getMetrics(y_true=y_test, y_pred=y_pred)
y_pred1 = reg1.predict(X=X_train)
y_pred2 = reg2.predict(X=X_train)
y_pred = np.hstack((y_pred1.reshape(-1, 1), y_pred2.reshape(-1, 1)))
metrics = getMetrics(y_true=y_train, y_pred=y_pred)
printMetrics(y_true=y_train, y_pred=y_pred)
logSave(nameOfModel="NuSVRRegressor",
reg=[reg1, reg2],
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 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 LinearSVRRegressor(X_train, X_test, y_train, y_test):
y_train1 = y_train[:, 0]
y_train2 = y_train[:, 1]
reg1 = LinearSVR(epsilon=0.001,
max_iter=5000,
C=3,
loss='squared_epsilon_insensitive')
reg1.fit(X_train, y_train1)
reg2 = LinearSVR(epsilon=0.001,
max_iter=5000,
C=3,
loss='squared_epsilon_insensitive')
reg2.fit(X_train, y_train2)
y_pred1 = reg1.predict(X=X_test)
y_pred2 = reg2.predict(X=X_test)
y_pred = np.hstack((y_pred1.reshape(-1, 1), y_pred2.reshape(-1, 1)))
printMetrics(y_true=y_test, y_pred=y_pred)
val_metrics = getMetrics(y_true=y_test, y_pred=y_pred)
y_pred1 = reg1.predict(X=X_train)
y_pred2 = reg2.predict(X=X_train)
y_pred = np.hstack((y_pred1.reshape(-1, 1), y_pred2.reshape(-1, 1)))
metrics = getMetrics(y_true=y_train, y_pred=y_pred)
printMetrics(y_true=y_train, y_pred=y_pred)
logSave(nameOfModel="LinearSVRRegressor",
reg=[reg1, reg2],
metrics=metrics,
val_metrics=val_metrics)
def ExtraTreeGS(X_train, X_test, y_train, y_test):
reg = ExtraTreeRegressor()
grid_values = {
'criterion': ["mse", "mae"],
'max_depth': list(range(20, 25))
}
grid_reg = GridSearchCV(
reg,
param_grid=grid_values,
scoring=['neg_mean_squared_error', 'neg_mean_absolute_error', 'r2'],
refit='r2',
n_jobs=-1,
cv=2,
verbose=100)
grid_reg.fit(X_train, y_train)
reg = grid_reg.best_estimator_
reg.fit(X_train, y_train)
y_pred = reg.predict(X_test)
printMetrics(y_true=y_test, y_pred=y_pred)
val_metrics = getMetrics(y_true=y_test, y_pred=y_pred)
y_pred = reg.predict(X=X_train)
metrics = getMetrics(y_true=y_train, y_pred=y_pred)
printMetrics(y_true=y_train, y_pred=y_pred)
best_params: dict = grid_reg.best_params_
saveBestParams(nameOfModel="ExtraTreeGS", best_params=best_params)
logSave(nameOfModel="ExtraTreeGS",
reg=reg,
metrics=metrics,
val_metrics=val_metrics)
def AdaBoost(X_train, X_test, y_train, y_test):
y_train1 = y_train[:, 0]
y_train2 = y_train[:, 1]
reg1 = AdaBoostRegressor(base_estimator=LinearSVR(),
loss='exponential',
n_estimators=5)
reg1.fit(X_train, y_train1)
reg2 = AdaBoostRegressor(base_estimator=LinearSVR(),
loss='exponential',
n_estimators=5)
reg2.fit(X_train, y_train2)
y_pred1 = reg1.predict(X=X_test)
y_pred2 = reg2.predict(X=X_test)
y_pred = np.hstack((y_pred1.reshape(-1, 1), y_pred2.reshape(-1, 1)))
printMetrics(y_true=y_test, y_pred=y_pred)
val_metrics = getMetrics(y_true=y_test, y_pred=y_pred)
y_pred1 = reg1.predict(X=X_train)
y_pred2 = reg2.predict(X=X_train)
y_pred = np.hstack((y_pred1.reshape(-1, 1), y_pred2.reshape(-1, 1)))
metrics = getMetrics(y_true=y_train, y_pred=y_pred)
printMetrics(y_true=y_train, y_pred=y_pred)
logSave(nameOfModel="AdaBoost",
reg=[reg1, reg2],
metrics=metrics,
val_metrics=val_metrics)
def LogisticRegressionModelV2(X_train, X_test, y_train, y_test):
multi_class = True
clf = LogisticRegression(penalty='l2',
solver='lbfgs',
multi_class='multinomial',
max_iter=700,
class_weight='balanced')
grid_values = {'C': [0.01, .09, 1, 5, 25, 50, 100, 1000]}
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)
logAndSaveV2(name_of_model="LogisticRegressionModelV2GS",
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 NeuralNetGS(X_train, X_test, y_train, y_test):
reg = MLPRegressor()
grid_values = {
'hidden_layer_sizes': [(8, 16, 32, 64, 128, 64, 32, 64, 16, 8),
(8, 16, 32, 64, 32, 16, 8), (8, 16, 32, 16, 8)],
'solver': ['adam'],
'learning_rate': ['constant', 'invscaling']
}
grid_reg = GridSearchCV(
reg,
param_grid=grid_values,
scoring=['neg_mean_squared_error', 'neg_mean_absolute_error', 'r2'],
refit='r2',
n_jobs=-1,
cv=2,
verbose=100)
grid_reg.fit(X_train, y_train)
reg = grid_reg.best_estimator_
reg.fit(X_train, y_train)
y_pred = reg.predict(X_test)
printMetrics(y_true=y_test, y_pred=y_pred)
val_metrics = getMetrics(y_true=y_test, y_pred=y_pred)
y_pred = reg.predict(X=X_train)
metrics = getMetrics(y_true=y_train, y_pred=y_pred)
printMetrics(y_true=y_train, y_pred=y_pred)
best_params: dict = grid_reg.best_params_
saveBestParams(nameOfModel="NeuralNetGS", best_params=best_params)
logSave(nameOfModel="NeuralNetGS",
reg=reg,
metrics=metrics,
val_metrics=val_metrics)
def GradientBoosting(X_train, X_test, y_train, y_test):
y_train1 = y_train[:, 0]
y_train2 = y_train[:, 1]
reg1 = GradientBoostingRegressor(loss='huber')
reg1.fit(X_train, y_train1)
reg2 = GradientBoostingRegressor(loss='huber')
reg2.fit(X_train, y_train2)
y_pred1 = reg1.predict(X=X_test)
y_pred2 = reg2.predict(X=X_test)
y_pred = np.hstack((y_pred1.reshape(-1, 1), y_pred2.reshape(-1, 1)))
printMetrics(y_true=y_test, y_pred=y_pred)
val_metrics = getMetrics(y_true=y_test, y_pred=y_pred)
y_pred1 = reg1.predict(X=X_train)
y_pred2 = reg2.predict(X=X_train)
y_pred = np.hstack((y_pred1.reshape(-1, 1), y_pred2.reshape(-1, 1)))
metrics = getMetrics(y_true=y_train, y_pred=y_pred)
printMetrics(y_true=y_train, y_pred=y_pred)
logSave(nameOfModel="GradientBoosting",
reg=[reg1, reg2],
metrics=metrics,
val_metrics=val_metrics)
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 XgBoost(X_train, X_test, y_train, y_test):
y_train1 = y_train[:, 0]
y_train2 = y_train[:, 1]
reg1 = xg.XGBRegressor(objective='reg:squarederror')
reg1.fit(X=X_train, y=y_train1)
reg2 = xg.XGBRegressor(objective='reg:squarederror')
reg2.fit(X=X_train, y=y_train2)
y_pred1 = reg1.predict(X_test)
y_pred2 = reg2.predict(X_test)
y_pred = np.hstack((y_pred1.reshape(-1, 1), y_pred2.reshape(-1, 1)))
printMetrics(y_true=y_test, y_pred=y_pred)
val_metrics = getMetrics(y_true=y_test, y_pred=y_pred)
y_pred1 = reg1.predict(X_train)
y_pred2 = reg2.predict(X_train)
y_pred = np.hstack((y_pred1.reshape(-1, 1), y_pred2.reshape(-1, 1)))
metrics = getMetrics(y_true=y_train, y_pred=y_pred)
printMetrics(y_true=y_train, y_pred=y_pred)
logSave(nameOfModel="XgBoost",
reg=[reg1, reg2],
metrics=metrics,
val_metrics=val_metrics)
def LogisticRegressionModelV2(X_train, X_test, y_train, y_test):
multi_class = True
clf = LogisticRegression(penalty='l2',
solver='lbfgs',
multi_class='multinomial',
max_iter=700)
clf.fit(X_train, y_train)
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)
# 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")
logAndSaveV2(name_of_model="LogisticRegressionModelV2",
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 LarsRegressorGS(X_train, X_test, y_train, y_test):
reg = Lars()
grid_values = {
'n_nonzero_coefs': list(range(100, 500, 100)),
}
grid_reg = GridSearchCV(
reg,
param_grid=grid_values,
scoring=['neg_mean_squared_error', 'neg_mean_absolute_error', 'r2'],
refit='r2',
n_jobs=-1,
cv=2,
verbose=100)
grid_reg.fit(X_train, y_train)
reg = grid_reg.best_estimator_
reg.fit(X_train, y_train)
y_pred = reg.predict(X_test)
printMetrics(y_true=y_test, y_pred=y_pred)
val_metrics = getMetrics(y_true=y_test, y_pred=y_pred)
y_pred = reg.predict(X=X_train)
metrics = getMetrics(y_true=y_train, y_pred=y_pred)
printMetrics(y_true=y_train, y_pred=y_pred)
best_params: dict = grid_reg.best_params_
saveBestParams(nameOfModel="LarsRegressorGS", best_params=best_params)
logSave(nameOfModel="LarsRegressorGS",
reg=reg,
metrics=metrics,
val_metrics=val_metrics)
def RidgeRegressorGS(X_train, X_test, y_train, y_test):
reg = Ridge()
grid_values = {
'alpha': list(range(1, 3)) + [value * 0.01 for value in range(1, 3)],
'solver': ['svd', 'cholesky', 'saga']
}
grid_reg = GridSearchCV(
reg,
param_grid=grid_values,
scoring=['neg_mean_squared_error', 'neg_mean_absolute_error', 'r2'],
refit='r2',
n_jobs=-1,
cv=2,
verbose=100)
grid_reg.fit(X_train, y_train)
reg = grid_reg.best_estimator_
reg.fit(X_train, y_train)
y_pred = reg.predict(X_test)
printMetrics(y_true=y_test, y_pred=y_pred)
val_metrics = getMetrics(y_true=y_test, y_pred=y_pred)
y_pred = reg.predict(X=X_train)
metrics = getMetrics(y_true=y_train, y_pred=y_pred)
printMetrics(y_true=y_train, y_pred=y_pred)
best_params: dict = grid_reg.best_params_
saveBestParams(nameOfModel="RidgeRegressorGS", best_params=best_params)
logSave(nameOfModel="RidgeRegressorGS",
reg=reg,
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 AdaBoostGS(X_train, X_test, y_train, y_test):
y_train1 = y_train[:, 0]
y_train2 = y_train[:, 1]
reg1 = AdaBoostRegressor(base_estimator=LinearSVR(), n_estimators=3)
reg2 = AdaBoostRegressor(base_estimator=LinearSVR(), n_estimators=3)
grid_values = {
'base_estimator__epsilon': [value * 0.1 for value in range(0, 2)],
'base_estimator__C':
list(range(1, 2)),
'base_estimator__loss':
['epsilon_insensitive', 'squared_epsilon_insensitive']
}
grid_reg1 = GridSearchCV(
reg1,
param_grid=grid_values,
scoring=['neg_mean_squared_error', 'neg_mean_absolute_error', 'r2'],
refit='r2',
n_jobs=-1,
cv=2,
verbose=100)
grid_reg1.fit(X_train, y_train1)
reg1 = grid_reg1.best_estimator_
reg1.fit(X_train, y_train1)
grid_reg2 = GridSearchCV(
reg2,
param_grid=grid_values,
scoring=['neg_mean_squared_error', 'neg_mean_absolute_error', 'r2'],
refit='r2',
n_jobs=-1,
cv=2,
verbose=100)
grid_reg2.fit(X_train, y_train2)
reg2 = grid_reg1.best_estimator_
reg2.fit(X_train, y_train2)
y_pred1 = reg1.predict(X=X_test)
y_pred2 = reg2.predict(X=X_test)
y_pred = np.hstack((y_pred1.reshape(-1, 1), y_pred2.reshape(-1, 1)))
printMetrics(y_true=y_test, y_pred=y_pred)
val_metrics = getMetrics(y_true=y_test, y_pred=y_pred)
y_pred1 = reg1.predict(X=X_train)
y_pred2 = reg2.predict(X=X_train)
y_pred = np.hstack((y_pred1.reshape(-1, 1), y_pred2.reshape(-1, 1)))
metrics = getMetrics(y_true=y_train, y_pred=y_pred)
printMetrics(y_true=y_train, y_pred=y_pred)
best_params1: dict = grid_reg1.best_params_
best_params2: dict = grid_reg2.best_params_
best_params = {}
for key in best_params1.keys():
best_params[key] = [best_params1[key], best_params2[key]]
saveBestParams(nameOfModel="AdaBoostGS", best_params=best_params)
logSave(nameOfModel="AdaBoostGS",
reg=[reg1, reg2],
metrics=metrics,
val_metrics=val_metrics)
def SGD_GS(X_train, X_test, y_train, y_test):
y_train1 = y_train[:, 0]
y_train2 = y_train[:, 1]
reg1 = SGDRegressor()
reg2 = SGDRegressor()
grid_values = {
'alpha': [value * 0.001 for value in range(1, 3)],
'loss': ['squared_loss', 'huber'],
'penalty': ['l2', 'l1'],
'l1_ratio': [value * 0.1 for value in range(0, 3)]
}
grid_reg1 = GridSearchCV(
reg1,
param_grid=grid_values,
scoring=['neg_mean_squared_error', 'neg_mean_absolute_error', 'r2'],
refit='r2',
n_jobs=-1,
cv=2,
verbose=100)
grid_reg1.fit(X_train, y_train1)
reg1 = grid_reg1.best_estimator_
reg1.fit(X_train, y_train1)
grid_reg2 = GridSearchCV(
reg2,
param_grid=grid_values,
scoring=['neg_mean_squared_error', 'neg_mean_absolute_error', 'r2'],
refit='r2',
n_jobs=-1,
cv=2,
verbose=100)
grid_reg2.fit(X_train, y_train2)
reg2 = grid_reg1.best_estimator_
reg2.fit(X_train, y_train2)
y_pred1 = reg1.predict(X=X_test)
y_pred2 = reg2.predict(X=X_test)
y_pred = np.hstack((y_pred1.reshape(-1, 1), y_pred2.reshape(-1, 1)))
printMetrics(y_true=y_test, y_pred=y_pred)
val_metrics = getMetrics(y_true=y_test, y_pred=y_pred)
y_pred1 = reg1.predict(X=X_train)
y_pred2 = reg2.predict(X=X_train)
y_pred = np.hstack((y_pred1.reshape(-1, 1), y_pred2.reshape(-1, 1)))
metrics = getMetrics(y_true=y_train, y_pred=y_pred)
printMetrics(y_true=y_train, y_pred=y_pred)
best_params1: dict = grid_reg1.best_params_
best_params2: dict = grid_reg2.best_params_
best_params = {}
for key in best_params1.keys():
best_params[key] = [best_params1[key], best_params2[key]]
saveBestParams(nameOfModel="SGD_GS", best_params=best_params)
logSave(nameOfModel="SGD_GS",
reg=[reg1, reg2],
metrics=metrics,
val_metrics=val_metrics)
def GradientBoostingGS(X_train, X_test, y_train, y_test):
y_train1 = y_train[:, 0]
y_train2 = y_train[:, 1]
reg1 = GradientBoostingRegressor()
reg2 = GradientBoostingRegressor()
grid_values = {
'loss': ['ls', 'huber'],
'learning_rate': [value * 0.1 for value in range(1, 3)],
'criterion': ["mse", "mae"],
'alpha': [0.25, 0.5, 0.75, 0.9],
}
grid_reg1 = GridSearchCV(
reg1,
param_grid=grid_values,
scoring=['neg_mean_squared_error', 'neg_mean_absolute_error', 'r2'],
refit='r2',
n_jobs=-1,
cv=2,
verbose=100)
grid_reg1.fit(X_train, y_train1)
reg1 = grid_reg1.best_estimator_
reg1.fit(X_train, y_train1)
grid_reg2 = GridSearchCV(
reg2,
param_grid=grid_values,
scoring=['neg_mean_squared_error', 'neg_mean_absolute_error', 'r2'],
refit='r2',
n_jobs=-1,
cv=2,
verbose=100)
grid_reg2.fit(X_train, y_train2)
reg2 = grid_reg1.best_estimator_
reg2.fit(X_train, y_train2)
y_pred1 = reg1.predict(X=X_test)
y_pred2 = reg2.predict(X=X_test)
y_pred = np.hstack((y_pred1.reshape(-1, 1), y_pred2.reshape(-1, 1)))
printMetrics(y_true=y_test, y_pred=y_pred)
val_metrics = getMetrics(y_true=y_test, y_pred=y_pred)
y_pred1 = reg1.predict(X=X_train)
y_pred2 = reg2.predict(X=X_train)
y_pred = np.hstack((y_pred1.reshape(-1, 1), y_pred2.reshape(-1, 1)))
metrics = getMetrics(y_true=y_train, y_pred=y_pred)
printMetrics(y_true=y_train, y_pred=y_pred)
best_params1: dict = grid_reg1.best_params_
best_params2: dict = grid_reg2.best_params_
best_params = {}
for key in best_params1.keys():
best_params[key] = [best_params1[key], best_params2[key]]
saveBestParams(nameOfModel="GradientBoostingGS", best_params=best_params)
logSave(nameOfModel="GradientBoostingGS",
reg=[reg1, reg2],
metrics=metrics,
val_metrics=val_metrics)
def NuSVRRegressorGS(X_train, X_test, y_train, y_test):
y_train1 = y_train[:, 0]
y_train2 = y_train[:, 1]
reg1 = NuSVR()
reg2 = NuSVR()
grid_values = {
'nu': [value * 0.1 for value in range(1, 3)],
'C': list(range(1, 3)),
'kernel': ['poly', 'rbf'],
'degree': list(range(1, 3))
}
grid_reg1 = GridSearchCV(
reg1,
param_grid=grid_values,
scoring=['neg_mean_squared_error', 'neg_mean_absolute_error', 'r2'],
refit='r2',
n_jobs=-1,
cv=2,
verbose=100)
grid_reg1.fit(X_train, y_train1)
reg1 = grid_reg1.best_estimator_
reg1.fit(X_train, y_train1)
grid_reg2 = GridSearchCV(
reg2,
param_grid=grid_values,
scoring=['neg_mean_squared_error', 'neg_mean_absolute_error', 'r2'],
refit='r2',
n_jobs=-1,
cv=2,
verbose=100)
grid_reg2.fit(X_train, y_train2)
reg2 = grid_reg1.best_estimator_
reg2.fit(X_train, y_train2)
y_pred1 = reg1.predict(X=X_test)
y_pred2 = reg2.predict(X=X_test)
y_pred = np.hstack((y_pred1.reshape(-1, 1), y_pred2.reshape(-1, 1)))
printMetrics(y_true=y_test, y_pred=y_pred)
val_metrics = getMetrics(y_true=y_test, y_pred=y_pred)
y_pred1 = reg1.predict(X=X_train)
y_pred2 = reg2.predict(X=X_train)
y_pred = np.hstack((y_pred1.reshape(-1, 1), y_pred2.reshape(-1, 1)))
metrics = getMetrics(y_true=y_train, y_pred=y_pred)
printMetrics(y_true=y_train, y_pred=y_pred)
best_params1: dict = grid_reg1.best_params_
best_params2: dict = grid_reg2.best_params_
best_params = {}
for key in best_params1.keys():
best_params[key] = [best_params1[key], best_params2[key]]
saveBestParams(nameOfModel="NuSVRRegressorGS", best_params=best_params)
logSave(nameOfModel="NuSVRRegressorGS",
reg=[reg1, reg2],
metrics=metrics,
val_metrics=val_metrics)
def XgBoostGS(X_train, X_test, y_train, y_test):
y_train1 = y_train[:, 0]
y_train2 = y_train[:, 1]
reg1 = xg.XGBRegressor(objective='reg:squarederror')
reg2 = xg.XGBRegressor(objective='reg:squarederror')
grid_values = {
'learning_rate': [x / 10 for x in range(1, 5)],
'max_depth': list(range(11, 15))
}
grid_reg1 = GridSearchCV(
reg1,
param_grid=grid_values,
scoring=['neg_mean_squared_error', 'neg_mean_absolute_error', 'r2'],
refit='r2',
n_jobs=-1,
cv=2,
verbose=100)
grid_reg1.fit(X_train, y_train1)
reg1 = grid_reg1.best_estimator_
reg1.fit(X_train, y_train1)
grid_reg2 = GridSearchCV(
reg2,
param_grid=grid_values,
scoring=['neg_mean_squared_error', 'neg_mean_absolute_error', 'r2'],
refit='r2',
n_jobs=-1,
cv=2,
verbose=100)
grid_reg2.fit(X_train, y_train2)
reg2 = grid_reg1.best_estimator_
reg2.fit(X_train, y_train2)
y_pred1 = reg1.predict(X_test)
y_pred2 = reg2.predict(X_test)
y_pred = np.hstack((y_pred1.reshape(-1, 1), y_pred2.reshape(-1, 1)))
printMetrics(y_true=y_test, y_pred=y_pred)
val_metrics = getMetrics(y_true=y_test, y_pred=y_pred)
y_pred1 = reg1.predict(X_train)
y_pred2 = reg2.predict(X_train)
y_pred = np.hstack((y_pred1.reshape(-1, 1), y_pred2.reshape(-1, 1)))
metrics = getMetrics(y_true=y_train, y_pred=y_pred)
printMetrics(y_true=y_train, y_pred=y_pred)
best_params1: dict = grid_reg1.best_params_
best_params2: dict = grid_reg2.best_params_
best_params = {}
for key in best_params1.keys():
best_params[key] = [best_params1[key], best_params2[key]]
saveBestParams(nameOfModel="XgBoostGS", best_params=best_params)
logSave(nameOfModel="XgBoostGS",
reg=[reg1, reg2],
metrics=metrics,
val_metrics=val_metrics)
def LassoRegressor(X_train, X_test, y_train, y_test): reg = Lasso(alpha=0.01) reg.fit(X_train, y_train) y_pred = reg.predict(X_test) printMetrics(y_true=y_test, y_pred=y_pred) val_metrics = getMetrics(y_true=y_test, y_pred=y_pred) y_pred = reg.predict(X=X_train) metrics = getMetrics(y_true=y_train, y_pred=y_pred) printMetrics(y_true=y_train, y_pred=y_pred) logSave(nameOfModel="LassoRegressor", reg=reg, metrics=metrics, val_metrics=val_metrics)
def ElasticNetRegressor(X_train, X_test, y_train, y_test):
reg = ElasticNet(alpha=10, l1_ratio=0.2)
reg.fit(X_train, y_train)
y_pred = reg.predict(X_test)
printMetrics(y_true=y_test, y_pred=y_pred)
val_metrics = getMetrics(y_true=y_test, y_pred=y_pred)
y_pred = reg.predict(X=X_train)
metrics = getMetrics(y_true=y_train, y_pred=y_pred)
printMetrics(y_true=y_train, y_pred=y_pred)
logSave(nameOfModel="ElasticNetRegressor",
reg=reg,
metrics=metrics,
val_metrics=val_metrics)
def NeuralNet(X_train, X_test, y_train, y_test):
reg = MLPRegressor(hidden_layer_sizes=(32, 64, 128, 256, 128, 64))
reg.fit(X_train, y_train)
y_pred = reg.predict(X_test)
printMetrics(y_true=y_test, y_pred=y_pred)
val_metrics = getMetrics(y_true=y_test, y_pred=y_pred)
y_pred = reg.predict(X=X_train)
metrics = getMetrics(y_true=y_train, y_pred=y_pred)
printMetrics(y_true=y_train, y_pred=y_pred)
logSave(nameOfModel="NeuralNet",
reg=reg,
metrics=metrics,
val_metrics=val_metrics)
def RidgeRegressor(X_train, X_test, y_train, y_test):
reg = Ridge()
reg.fit(X_train, y_train)
y_pred = reg.predict(X_test)
printMetrics(y_true=y_test, y_pred=y_pred)
val_metrics = getMetrics(y_true=y_test, y_pred=y_pred)
y_pred = reg.predict(X=X_train)
metrics = getMetrics(y_true=y_train, y_pred=y_pred)
printMetrics(y_true=y_train, y_pred=y_pred)
logSave(nameOfModel="RidgeRegressor",
reg=reg,
metrics=metrics,
val_metrics=val_metrics)
def AdaBoostModelV2(X_train, X_test, y_train, y_test):
multi_class = True
clf = AdaBoostClassifier(base_estimator=RandomForestClassifier(), n_estimators=200, algorithm='SAMME')
clf.fit(X_train, y_train)
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)
# 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")
logAndSaveV2(name_of_model="AdaBoostModelV2", clf=clf, metrics=metrics, val_metrics=val_metrics)
def DecisionTree(X_train, X_test, y_train, y_test):
reg = DecisionTreeRegressor()
reg.fit(X_train, y_train)
y_pred1 = reg.predict(X_test)
printMetrics(y_true=y_test, y_pred=y_pred1)
val_metrics = getMetrics(y_true=y_test, y_pred=y_pred1)
y_pred = reg.predict(X=X_train)
metrics = getMetrics(y_true=y_train, y_pred=y_pred)
printMetrics(y_true=y_train, y_pred=y_pred)
logSave(nameOfModel="DecisionTree",
reg=reg,
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 RandomForestModelV2(X_train, X_test, y_train, y_test):
multi_class = True
clf = RandomForestClassifier()
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_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)
logAndSaveV2(name_of_model="RandomForestModelV2GS", clf=clf, metrics=metrics, val_metrics=val_metrics)
