def test_classifier(dataset):
return
X_train, X_test, y_train, y_test = dataset
my_classifier = GradientBoostingClassifier(max_depth=10, n_estimators=55)
my_classifier.fit(X_train, y_train, X_test, y_test)
print(my_classifier.score(X_test, y_test))
classifier = SklearnGradientBoostingClassifier(max_depth=10,
n_estimators=55)
classifier.fit(X_train, y_train)
print(classifier.score(X_test, y_test))
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 test_real_data(dataset):
# X_train, X_valid, X_test, y_train, y_valid, y_test = DataLoader().load()
X_train, X_test, y_train, y_test = DataLoader().load()
# X_train, X_test, y_train, y_test = dataset
#X_train_ = np.copy(X_train)
#y_train_ = np.copy(y_train)
#X_test_ = np.copy(X_test)
#y_test_ = np.copy(y_test)
n_estimators = 300
model = GradientBoostingClassifier(
n_estimators=n_estimators,
max_depth=1,
min_samples_split=20,
subsample=0.5,
learning_rate=0.2,
#max_features=0.8,
min_samples_leaf=10)
model.fit(X_train, y_train.reshape(-1))
prediction = model.staged_predict_proba(X_test)
y = loss(y_test.reshape(-1), prediction)
board = DashBoard()
board.init_graph(name="my_one",
title="my_one",
line_type="default",
c="r",
y=y.reshape(-1))
model = SklearnGradientBoostingClassifier(
n_estimators=n_estimators,
max_depth=1,
criterion="mse",
min_samples_split=20,
min_samples_leaf=10,
subsample=0.5,
learning_rate=0.1,
#max_features=0.1,
init="zero")
model.fit(X_train, y_train)
prediction = np.empty([n_estimators, X_test.shape[0]])
for i, proba in enumerate(model.staged_predict_proba(X_test)):
prediction[i] = proba[:, 1]
print(y_test.shape, prediction.shape)
# assert 0
y = loss(y_test.reshape(-1), prediction)
board.init_graph(name="baseline",
title="sklearn",
line_type="baseline",
c="g",
y=y.reshape(-1))
board.make_plot()
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)
rescaled_y_test = 2*y_test - np.ones(np.shape(y_test))
# .......
# SETUP
# .......
adaboost = Adaboost(n_clf = 8)
naive_bayes = NaiveBayes()
knn = KNN(k=4)
logistic_regression = LogisticRegression()
mlp = MultilayerPerceptron(n_hidden=20)
perceptron = Perceptron()
decision_tree = ClassificationTree()
random_forest = RandomForest(n_estimators=50)
support_vector_machine = SupportVectorMachine()
lda = LDA()
gbc = GradientBoostingClassifier(n_estimators=20, learning_rate=1)
xgboost = XGBoost()
# ........
# TRAIN
# ........
print ("Training:")
print ("\tAdaboost")
adaboost.fit(X_train, rescaled_y_train)
print ("\tDecision Tree")
decision_tree.fit(X_train, y_train)
print ("\tGradient Boosting")
gbc.fit(X_train, y_train)
print ("\tLDA")
lda.fit(X_train, y_train)
print ("\tLogistic Regression")
# .......
# SETUP
# .......
adaboost = Adaboost(n_clf=8)
naive_bayes = NaiveBayes()
knn = KNN(k=4)
logistic_regression = LogisticRegression()
mlp = MultilayerPerceptron(n_hidden=20, n_iterations=20000, learning_rate=0.1)
perceptron = Perceptron()
decision_tree = ClassificationTree()
random_forest = RandomForest(n_estimators=50)
support_vector_machine = SupportVectorMachine()
lda = LDA()
gbc = GradientBoostingClassifier(n_estimators=50,
learning_rate=.9,
max_depth=2)
xgboost = XGBoost(n_estimators=50, learning_rate=0.5, max_depth=2)
# ........
# TRAIN
# ........
print("Training:")
print("\tAdaboost")
adaboost.fit(X_train, rescaled_y_train)
print("\tDecision Tree")
decision_tree.fit(X_train, y_train)
print("\tGradient Boosting")
gbc.fit(X_train, y_train)
print("\tLDA")
lda.fit(X_train, y_train)
rescaled_y_test = 2*y_test - np.ones(np.shape(y_test))
# .......
# SETUP
# .......
adaboost = Adaboost(n_clf = 8)
naive_bayes = NaiveBayes()
knn = KNN(k=4)
logistic_regression = LogisticRegression()
mlp = MultilayerPerceptron(n_hidden=20, n_iterations=20000, learning_rate=0.1)
perceptron = Perceptron()
decision_tree = ClassificationTree()
random_forest = RandomForest(n_estimators=50)
support_vector_machine = SupportVectorMachine()
lda = LDA()
gbc = GradientBoostingClassifier(n_estimators=50, learning_rate=.9, max_depth=2)
xgboost = XGBoost(n_estimators=50, learning_rate=0.5)
# ........
# TRAIN
# ........
print ("Training:")
print ("\tAdaboost")
adaboost.fit(X_train, rescaled_y_train)
print ("\tDecision Tree")
decision_tree.fit(X_train, y_train)
print ("\tGradient Boosting")
gbc.fit(X_train, y_train)
print ("\tLDA")
lda.fit(X_train, y_train)
print ("\tLogistic Regression")
rescaled_y_test = 2 * y_test - np.ones(np.shape(y_test))
# .......
# SETUP
# .......
adaboost = Adaboost(n_clf=8)
naive_bayes = NaiveBayes()
knn = KNN(k=4)
logistic_regression = LogisticRegression()
mlp = MultilayerPerceptron(n_hidden=20)
perceptron = Perceptron()
decision_tree = ClassificationTree()
random_forest = RandomForest(n_estimators=150)
support_vector_machine = SupportVectorMachine()
lda = LDA()
gbc = GradientBoostingClassifier()
# ........
# TRAIN
# ........
print("Training:")
print("\tAdaboost")
adaboost.fit(X_train, rescaled_y_train)
print("\tDecision Tree")
decision_tree.fit(X_train, y_train)
print("\tGradient Boosting")
gbc.fit(X_train, y_train)
print("\tLDA")
lda.fit(X_train, y_train)
print("\tLogistic Regression")
logistic_regression.fit(X_train, y_train)