def main():
print("Tesing the performance of Kmeans...")
# Load data
X, y = load_breast_cancer()
X = min_max_scale(X)
# Train model
est = KMeans()
k = 2
est.fit(X, k)
print()
# Model performance
prob_pos = sum(y) / len(y)
print("Positive probability of X is:%.1f%%.\n" % (prob_pos * 100))
y_hat = est.predict(X)
cluster_pos_tot_cnt = {i: [0, 0] for i in range(k)}
for yi_hat, yi in zip(y_hat, y):
cluster_pos_tot_cnt[yi_hat][0] += yi
cluster_pos_tot_cnt[yi_hat][1] += 1
cluster_prob_pos = {k: v[0] / v[1] for k, v in cluster_pos_tot_cnt.items()}
for i in range(k):
tot_cnt = cluster_pos_tot_cnt[i][1]
prob_pos = cluster_prob_pos[i]
print("Count of elements in cluster %d is:%d." %
(i, tot_cnt))
print("Positive probability of cluster %d is:%.1f%%.\n" %
(i, prob_pos * 100))
def main():
"""Tesing the performance of LogisticRegression.
"""
@run_time
def batch():
print("Tesing the performance of LogisticRegression(batch)...")
# Train model
clf = LogisticRegression()
clf.fit(data=data_train, label=label_train, learning_rate=0.1, epochs=1000)
# Model evaluation
model_evaluation(clf, data_test, label_test)
print(clf)
@run_time
def stochastic():
print("Tesing the performance of LogisticRegression(stochastic)...")
# Train model
clf = LogisticRegression()
clf.fit(data=data_train, label=label_train, learning_rate=0.01, epochs=100,
method="stochastic", sample_rate=0.8)
# Model evaluation
model_evaluation(clf, data_test, label_test)
print(clf)
# Load data
data, label = load_breast_cancer()
data = min_max_scale(data)
# Split data randomly, train set rate 70%
data_train, data_test, label_train, label_test = train_test_split(
data, label, random_state=10)
batch()
print()
stochastic()
def main():
@run_time
def batch():
print("Tesing the performance of LogisticRegression(batch)...")
# Train model
clf = LogisticRegression()
clf.fit(X=X_train, y=y_train, lr=0.1, epochs=1000)
# Model evaluation
model_evaluation(clf, X_test, y_test)
print(clf)
@run_time
def stochastic():
print("Tesing the performance of LogisticRegression(stochastic)...")
# Train model
clf = LogisticRegression()
clf.fit(X=X_train, y=y_train, lr=0.01, epochs=100,
method="stochastic", sample_rate=0.8)
# Model evaluation
model_evaluation(clf, X_test, y_test)
print(clf)
# Load data
X, y = load_breast_cancer()
X = min_max_scale(X)
# Split data randomly, train set rate 70%
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=10)
batch()
print()
stochastic()
def main():
print("Tesing the performance of RandomForest...")
# Load data
X, y = load_breast_cancer()
# Split data randomly, train set rate 70%
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=40)
# Train model
rf = RandomForest()
rf.fit(X_train, y_train, n_samples=300, max_depth=3, n_estimators=20)
# Model evaluation
model_evaluation(rf, X_test, y_test)
def main():
print("Tesing the performance of KNN classifier...")
# Load data
X, y = load_breast_cancer()
X = min_max_scale(X)
# Split data randomly, train set rate 70%
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=20)
# Train model
clf = KNeighborsClassifier()
clf.fit(X_train, y_train, k_neighbors=21)
# Model evaluation
model_evaluation(clf, X_test, y_test)
def main():
print("Tesing the performance of Gaussian NaiveBayes...")
# Load data
X, y = load_breast_cancer()
# Split data randomly, train set rate 70%
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=10)
# Train model
clf = GaussianNB()
clf.fit(X_train, y_train)
# Model evaluation
y_hat = clf.predict(X_test)
acc = _get_acc(y_test, y_hat)
print("Accuracy is %.3f" % acc)
def main():
print("Tesing the performance of DecisionTree...")
# Load data
X, y = load_breast_cancer()
# Split data randomly, train set rate 70%
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=10)
# Train model
clf = DecisionTree()
clf.fit(X_train, y_train, max_depth=3)
# Show rules
clf.rules
# Model evaluation
model_evaluation(clf, X_test, y_test)
def main():
"""Tesing the performance of DecisionTree
"""
print("Tesing the performance of DecisionTree...")
# Load data
data, label = load_breast_cancer()
# Split data randomly, train set rate 70%
data_train, data_test, label_train, label_test = train_test_split(
data, label, random_state=10)
# Train model
clf = DecisionTree()
clf.fit(data_train, label_train, max_depth=4)
# Show rules
print(clf)
# Model evaluation
model_evaluation(clf, data_test, label_test)
def main():
print("Tesing the performance of GBDT classifier...")
# Load data
X, y = load_breast_cancer()
# Split data randomly, train set rate 70%
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=20)
# Train model
clf = GradientBoostingClassifier()
clf.fit(X_train,
y_train,
n_estimators=2,
lr=0.8,
max_depth=3,
min_samples_split=2)
# Model evaluation
model_evaluation(clf, X_test, y_test)
def main():
"""Tesing the performance of Gaussian NaiveBayes.
"""
print("Tesing the performance of Gaussian NaiveBayes...")
# Load data
data, label = load_breast_cancer()
# Split data randomly, train set rate 70%
data_train, data_test, label_train, label_test = train_test_split(data, label, random_state=100)
# Train model
clf = GaussianNB()
clf.fit(data_train, label_train)
# Model evaluation
y_hat = clf.predict(data_test)
acc = _get_acc(label_test, y_hat)
print("Accuracy is %.3f" % acc)
def main():
"""Tesing the performance of RandomForest...
"""
print("Tesing the performance of RandomForest...")
# Load data
data, label = load_breast_cancer()
# Split data randomly, train set rate 70%
data_train, data_test, label_train, label_test = train_test_split(
data, label, random_state=40)
# Train model
clf = RandomForest()
clf.fit(data_train,
label_train,
n_estimators=50,
max_depth=5,
random_state=10)
# Model evaluation
model_evaluation(clf, data_test, label_test)
def main():
"""Tesing the performance of GBDT classifier"""
print("Tesing the performance of GBDT classifier...")
# Load data
data, label = load_breast_cancer()
# Split data randomly, train set rate 70%
data_train, data_test, label_train, label_test = train_test_split(
data, label, random_state=20)
# Train model
clf = GradientBoostingClassifier()
clf.fit(data_train,
label_train,
n_estimators=2,
learning_rate=0.8,
max_depth=3,
min_samples_split=2)
# Model evaluation
model_evaluation(clf, data_test, label_test)