def main():
@run_time
def batch():
print("Tesing the accuracy of LinearRegression(batch)...")
# Train model
reg = LinearRegression()
reg.fit(X=X_train, y=y_train, lr=0.02, epochs=5000)
# Model accuracy
get_r2(reg, X_test, y_test)
@run_time
def stochastic():
print("Tesing the accuracy of LinearRegression(stochastic)...")
# Train model
reg = LinearRegression()
reg.fit(X=X_train, y=y_train, lr=0.001, epochs=1000,
method="stochastic", sample_rate=0.5)
# Model accuracy
get_r2(reg, X_test, y_test)
# Load data
X, y = load_boston_house_prices()
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()
stochastic()
def main():
# Load data
X, y = load_tagged_speech()
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=40)
# Train model
model = HMM()
model.fit(X_train, y_train)
# Model infomation.
print("There are %d unique observations!" % len(model.observations))
print("There are %d unique states!" % len(model.states))
# Correctness test.
tolerance = 1e-6
start_probs_check = abs(sum(model.start_probs.values()) - 1) < tolerance
assert start_probs_check, "Start probs incorrect!"
trans_probs_check = all(
abs(sum(dic.values()) - 1) < tolerance
for dic in model.trans_probs.values())
assert trans_probs_check, "Trans probs incorrect!"
emit_probs_check = all(
abs(sum(dic.values()) - 1) < tolerance
for dic in model.emit_probs.values())
assert emit_probs_check, "Emit probs incorrect!"
print("Correctness test passed!")
# Model accuracy.
predictions = model.predict(X_test)
numerator = sum(
prediction == yi
for prediction, yi in zip(chain(*predictions), chain(*y_test)))
denominator = sum(map(len, y_test))
acc = numerator / denominator
print("Test accuracy is %.3f%%!" % (acc * 100))
def main():
@run_time
def batch():
print("Tesing the accuracy of LogisticRegression(batch)...")
# Train model
clf = LogisticRegression()
clf.fit(X=X_train, y=y_train, lr=0.05, epochs=200)
# Model accuracy
get_acc(clf, X_test, y_test)
@run_time
def stochastic():
print("Tesing the accuracy of LogisticRegression(stochastic)...")
# Train model
clf = LogisticRegression()
clf.fit(X=X_train,
y=y_train,
lr=0.01,
epochs=200,
method="stochastic",
sample_rate=0.5)
# Model accuracy
get_acc(clf, X_test, y_test)
# 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()
stochastic()
def main():
print("Tesing the accuracy of KNN 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 = KNeighborsClassifier()
clf.fit(X_train, y_train, k_neighbors=21)
# Model accuracy
get_acc(clf, X_test, y_test)
def main():
print("Tesing the accuracy 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 accuracy
get_acc(clf, X_test, y_test)
def main():
print("Tesing the accuracy of KNN regressor...")
# Load data
X, y = load_boston_house_prices()
# 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
reg = KNeighborsRegressor()
reg.fit(X=X_train, y=y_train, k_neighbors=3)
# Model accuracy
get_r2(reg, X_test, y_test)
def main():
print("Tesing the accuracy 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 accuracy
get_acc(rf, X_test, y_test)
def main():
print("Tesing the accuracy 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 accuracy
get_acc(clf, X_test, y_test)
def main():
print("Tesing the accuracy of RegressionTree...")
# Load data
X, y = load_boston_house_prices()
# 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
reg = RegressionTree()
reg.fit(X=X_train, y=y_train, max_depth=5)
# Show rules
reg.rules
# Model accuracy
get_r2(reg, X_test, y_test)
def main():
print("Tesing the accuracy of GBDT regressor...")
# Load data
X, y = load_boston_house_prices()
# 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
reg = GradientBoostingRegressor()
reg.fit(X=X_train,
y=y_train,
n_estimators=4,
lr=0.5,
max_depth=2,
min_samples_split=2)
# Model accuracy
get_r2(reg, X_test, y_test)
def main():
print("Tesing the accuracy 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 accuracy
get_acc(clf, X_test, y_test)
def main():
print("Tesing the accuracy of Ridge Regressor(stochastic)...")
# Load data
X, y = load_boston_house_prices()
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)
# Train model
reg = Ridge()
reg.fit(X=X_train,
y=y_train,
lr=0.001,
epochs=1000,
method="stochastic",
sample_rate=0.5,
alpha=1e-7)
# Model accuracy
get_r2(reg, X_test, y_test)