def test_gradient_boosting_classification():
iris = datasets.load_iris()
X, y = iris.data, iris.target
print (X.shape, y.shape)
train_X, train_y, test_X, test_y = split_train_test(X, y)
print (train_X.shape, train_y.shape, test_X.shape, test_y.shape)
clf = GradientBoostingClassifier(n_estimators=100, learning_rate=0.1)
clf.fit(train_X, train_y)
preds = clf.predict(test_X)
accuracy = cal_accuracy(test_y, preds)
print ('accuracy: ', accuracy)
def main():
print("-- Gradient Boosting Classification --")
df = pd.read_csv("cancer_o.csv")
y = df.level
X = df.drop(['level', 'patient_id'], axis=1)
data_classes = ["Low", "Medium", "High"]
y = df['level'].apply(data_classes.index)
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.2,
random_state=42)
clf = GradientBoostingClassifier()
clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)
accuracy = accuracy_score(y_test, y_pred)
print("Accuracy:", accuracy)
perceptron.fit(X_train, y_train)
print ("\tRandom Forest")
random_forest.fit(X_train, y_train)
print ("\tSupport Vector Machine")
support_vector_machine.fit(X_train, rescaled_y_train)
print ("\tXGBoost")
xgboost.fit(X_train, y_train)
# .........
# PREDICT
# .........
y_pred = {}
y_pred["Adaboost"] = adaboost.predict(X_test)
y_pred["Gradient Boosting"] = gbc.predict(X_test)
y_pred["Naive Bayes"] = naive_bayes.predict(X_test)
y_pred["K Nearest Neighbors"] = knn.predict(X_test, X_train, y_train)
y_pred["Logistic Regression"] = logistic_regression.predict(X_test)
y_pred["LDA"] = lda.predict(X_test)
y_pred["Multilayer Perceptron"] = mlp.predict(X_test)
y_pred["Perceptron"] = perceptron.predict(X_test)
y_pred["Decision Tree"] = decision_tree.predict(X_test)
y_pred["Random Forest"] = random_forest.predict(X_test)
y_pred["Support Vector Machine"] = support_vector_machine.predict(X_test)
y_pred["XGBoost"] = xgboost.predict(X_test)
# ..........
# ACCURACY
# ..........
perceptron.fit(X_train, y_train)
print ("\tRandom Forest")
random_forest.fit(X_train, y_train)
print ("\tSupport Vector Machine")
support_vector_machine.fit(X_train, rescaled_y_train)
print ("\tXGBoost")
xgboost.fit(X_train, y_train)
# .........
# PREDICT
# .........
y_pred = {}
y_pred["Adaboost"] = adaboost.predict(X_test)
y_pred["Gradient Boosting"] = gbc.predict(X_test)
y_pred["Naive Bayes"] = naive_bayes.predict(X_test)
y_pred["K Nearest Neighbors"] = knn.predict(X_test, X_train, y_train)
y_pred["Logistic Regression"] = logistic_regression.predict(X_test)
y_pred["LDA"] = lda.predict(X_test)
y_pred["Multilayer Perceptron"] = mlp.predict(X_test)
y_pred["Perceptron"] = perceptron.predict(X_test)
y_pred["Decision Tree"] = decision_tree.predict(X_test)
y_pred["Random Forest"] = random_forest.predict(X_test)
y_pred["Support Vector Machine"] = support_vector_machine.predict(X_test)
y_pred["XGBoost"] = xgboost.predict(X_test)
# ..........
# ACCURACY
# ..........