def KNN_smote_PCA(self):
train, test = self.process_and_split_data()
x_train = np.delete(train, obj=8, axis=1)
y_train = train[:, 8]
x_test = np.delete(test, obj=8, axis=1)
y_test = test[:, 8]
new_col = pd.get_dummies(x_train[:, 0])
new_col2 = pd.get_dummies(x_test[:, 0])
#create new columns for sex class
new_col = np.array(new_col)
new_col2 = np.array(new_col2)
#add the new columns to features
features_train = np.column_stack([x_train, new_col])
features_test = np.column_stack([x_test, new_col2])
#delete sex column
features_train = np.delete(features_train, obj=0, axis=1)
features_test = np.delete(features_test, obj=0, axis=1)
#Handle imbalance
features_train, y_train = self.smote(features_train, y_train)
#standardize data
preprocess = Preprocessing()
features_train = preprocess.standardize_data(features_train)
features_test = preprocess.standardize_data(features_test)
knn = KNeighborsClassifier(n_neighbors=7)
knn.fit(features_train, y_train)
pred = knn.predict(features_test)
#PCA
features_train = self.PCA(features_train, 5)
features_test = self.PCA(features_test, 5)
print()
print("KNN - Accuracy smote with PCA")
metrics = self.metrics(pred, y_test)
print()
features = np.vstack((features_train, features_test))
labels = np.vstack((y_train[:, None], y_test[:, None]))
cross_val_acc = self.cross_validation(knn, features, labels)
return cross_val_acc, y_test, pred, metrics
def logistic_regression_oversampled_PCA(self):
train, test = self.process_and_split_data()
train_oversampled = self.pre_process_oversample(
1219, "positive", train)
x_train = np.delete(train_oversampled, obj=8, axis=1)
y_train = train_oversampled[:, 8]
x_test = np.delete(test, obj=8, axis=1)
y_test = test[:, 8]
new_col = pd.get_dummies(x_train[:, 0])
new_col2 = pd.get_dummies(x_test[:, 0])
#create new columns for sex class
new_col = np.array(new_col)
new_col2 = np.array(new_col2)
#add the new columns to features
features_train = np.column_stack([x_train, new_col])
features_test = np.column_stack([x_test, new_col2])
#delete sex column
features_train = np.delete(features_train, obj=0, axis=1)
features_test = np.delete(features_test, obj=0, axis=1)
#standardize data
preprocess = Preprocessing()
features_train = preprocess.standardize_data(features_train)
features_test = preprocess.standardize_data(features_test)
#PCA
features_train = self.PCA(features_train, 5)
features_test = self.PCA(features_test, 5)
reg = LogisticRegression()
reg.fit(features_train, y_train)
pred = reg.predict(features_test)
print()
print("Logisitic Regression - Accuracy over sampled data after PCA")
metrics = self.metrics(pred, y_test)
features = np.vstack((features_train, features_test))
labels = np.vstack((y_train[:, None], y_test[:, None]))
cross_val_acc = self.cross_validation(reg, features, labels)
return cross_val_acc, y_test, pred, metrics
def decision_tree_undersampled_PCA(self):
train, test = self.process_and_split_data()
train_undersampled = self.pre_process_undersample(
1219, "negative", train)
x_train = np.delete(train_undersampled, obj=8, axis=1)
y_train = train_undersampled[:, 8]
x_test = np.delete(test, obj=8, axis=1)
y_test = test[:, 8]
new_col = pd.get_dummies(x_train[:, 0])
new_col2 = pd.get_dummies(x_test[:, 0])
#create new encoded columns for sex class
new_col = np.array(new_col)
new_col2 = np.array(new_col2)
#add the new columns to features
features_train = np.column_stack([x_train, new_col])
features_test = np.column_stack([x_test, new_col2])
#delete sex column
features_train = np.delete(features_train, obj=0, axis=1)
features_test = np.delete(features_test, obj=0, axis=1)
#standardize data
preprocess = Preprocessing()
features_train = preprocess.standardize_data(features_train)
features_test = preprocess.standardize_data(features_test)
#PCA
features_train = self.PCA(features_train, 5)
features_test = self.PCA(features_test, 5)
tree = DecisionTreeClassifier()
tree.fit(features_train, y_train)
pred = tree.predict(features_test)
print()
print("Decision tree - Accuracy under sampled data with PCA")
metrics = self.metrics(pred, y_test)
features = np.vstack((features_train, features_test))
labels = np.vstack((y_train[:, None], y_test[:, None]))
cross_val_acc = self.cross_validation(tree, features, labels)
return cross_val_acc, y_test, pred, metrics
def decision_tree_smote(self):
train, test = self.process_and_split_data()
x_train = np.delete(train, obj=8, axis=1)
y_train = train[:, 8]
x_test = np.delete(test, obj=8, axis=1)
y_test = test[:, 8]
new_col = pd.get_dummies(x_train[:, 0])
new_col2 = pd.get_dummies(x_test[:, 0])
#create new columns for sex class
new_col = np.array(new_col)
new_col2 = np.array(new_col2)
#add the new columns to features
features_train = np.column_stack([x_train, new_col])
features_test = np.column_stack([x_test, new_col2])
#delete sex column
features_train = np.delete(features_train, obj=0, axis=1)
features_test = np.delete(features_test, obj=0, axis=1)
#Handle imbalance
features_train, y_train = self.smote(features_train, y_train)
#standardize data
preprocess = Preprocessing()
features_train = preprocess.standardize_data(features_train)
features_test
tree = DecisionTreeClassifier()
tree.fit(features_train, y_train)
pred = tree.predict(features_test)
knn = KNeighborsClassifier(n_neighbors=7)
knn.fit(features_train, y_train)
pred = knn.predict(features_test)
accuracy = metrics.accuracy_score(y_test, pred)
print("Decision tree - Accuracy smote data without PCA: ", accuracy)
print()
features = np.vstack((features_train, features_test))
labels = np.vstack((y_train[:, None], y_test[:, None]))
cross_val_acc = self.cross_validation(tree, features, labels)
return cross_val_acc, y_test, pred, metrics
def KNN_oversampled(self):
train, test = self.process_and_split_data()
train_oversampled = self.pre_process_oversample(
1219, "positive", train)
x_train = np.delete(train_oversampled, obj=8, axis=1)
y_train = train_oversampled[:, 8]
x_test = np.delete(test, obj=8, axis=1)
y_test = test[:, 8]
new_col = pd.get_dummies(x_train[:, 0])
new_col2 = pd.get_dummies(x_test[:, 0])
#create new columns for sex class
new_col = np.array(new_col)
new_col2 = np.array(new_col2)
#add the new columns to features
features_train = np.column_stack([x_train, new_col])
features_test = np.column_stack([x_test, new_col2])
#delete sex column
features_train = np.delete(features_train, obj=0, axis=1)
features_test = np.delete(features_test, obj=0, axis=1)
#standardize data
preprocess = Preprocessing()
features_train = preprocess.standardize_data(features_train)
features_test
knn = KNeighborsClassifier(n_neighbors=7)
knn.fit(features_train, y_train)
pred = knn.predict(features_test)
print()
print("KNN - Accuracy over sampled data without PCA")
metrics = self.metrics(pred, y_test)
features = np.vstack((features_train, features_test))
labels = np.vstack((y_train[:, None], y_test[:, None]))
cross_val_acc = self.cross_validation(knn, features, labels)
return cross_val_acc, y_test, pred, metrics