def main():
x, y = make_regression(n_samples=200, n_features=1, noise=25)
x_train, x_test, y_train, y_test = train_test_split(x, y)
model = LassoRegression(reg_factor=0.05,
learing_rate=0.001,
n_iterations=1000)
model.fit(x_train, y_train)
y_pred = model.predict(x_test)
mse = mean_squared_error(y_test, y_pred)
print("Mean squared error: %s" % (mse))
# plot the results
cmap = plt.get_cmap('plasma')
y_pred_line = model.predict(x)
train = plt.scatter(400 * x_train, y_train, color=cmap(0.9), s=10)
test = plt.scatter(400 * x_test, y_test, color=cmap(0.5), s=10)
plt.plot(400 * x,
y_pred_line,
color='black',
linewidth=2,
label="Prediction")
plt.suptitle("Lasso Regression")
plt.title("MSE: %.2f" % mse, fontsize=10)
plt.xlabel('X')
plt.ylabel('Y')
plt.legend((train, test), ("Training data", "Test data"),
loc='lower right')
plt.show()
def main():
data = datasets.load_digits()
x = normalize(data.data)
y = data.target
#one-hot encoding
y = to_categorical(y)
x_train, x_test, y_train, y_test = train_test_split(x, y, seed=1)
clf = Perceptron(n_iterations=5000,
learning_rate=0.001,
loss=CrossEntropy,
activation_function=Sigmoid)
clf.fit(x_train, y_train)
y_pred = np.argmax(clf.predict(x_test), axis=1)
y_test = np.argmax(y_test, axis=1)
accuracy = accuracy_score(y_test, y_pred)
print("Accuracy:", accuracy)
Plot().plot_2d(x_test,
y_pred,
title="Perceptron",
accuracy=accuracy,
legend_label=np.unique(y))
def main():
data = datasets.load_iris()
X = normalize(data.data)
y = data.target
x_train, x_test, y_train, y_test = train_test_split(X, y, test_size=0.30)
knn = KNN(k=5)
y_pred = knn.predict(x_test, x_train, y_train)
accuracy = accuracy_score(y_test, y_pred)
print("Accuracy:", accuracy)
Plot().plot_2d(x_test,
y_pred,
title="K Nearest Neighbors",
accuracy=accuracy,
legend_label=data.target_names)
def main():
data = datasets.load_iris()
# using two class only
x = normalize(data.data[data.target != 0])
y = data.target[data.target != 0]
y[y == 1] = 0
y[y == 2] = 1
x_train, x_test, y_train, y_test = train_test_split(x, y, seed=1)
model = LogisticRegression()
model.fit(x_train, y_train)
y_pred = model.predict(x_test)
accuracy = accuracy_score(y_test, y_pred)
print ("Accuracy:", accuracy)
# plot the results
Plot().plot_2d(x_test, y_pred, title="Logistic Regression", accuracy=accuracy)
def main():
data = datasets.load_digits()
x = normalize(data.data)
y = data.target
x_train, x_test, y_train, y_test = train_test_split(x, y)
clf = NaiveBayes()
clf.fit(x_train, y_train)
y_pred = clf.predict(x_test)
accuracy = accuracy_score(y_test, y_pred)
print("Accuracy:", accuracy)
Plot().plot_2d(x_test,
y_pred,
title="Naive Bayes",
accuracy=accuracy,
legend_label=data.target_names)
def main():
print("Gradient Boosting Classification")
data = datasets.load_iris()
x = data.data
y = data.target
x_train, x_test, y_train, y_test = train_test_split(x, y)
clf = GradientBoostingClassifier()
clf.fit(x_train, y_train)
y_pred = clf.predict(x_test)
accuracy = accuracy_score(y_test, y_pred)
print("Accuracy:", accuracy)
Plot().plot_2d(x_test,
y_pred,
title="Gradient Boosting",
accuracy=accuracy,
legend_label=data.target_names)
def main():
print("XGBoost")
data = datasets.load_iris()
x = data.data
y = data.target
x_train, x_test, y_train, y_test = train_test_split(x, y, seed=1)
clf = XGBoost()
clf.fit(x_train, y_train)
y_pred = clf.predict(x_test)
accuracy = accuracy_score(y_test, y_pred)
print("Accuracy:", accuracy)
Plot().plot_2d(x_test,
y_pred,
title="XGBoost",
accuracy=accuracy,
legend_label=data.target_names)
def main():
data = datasets.load_iris()
x = data.data
y = data.target
# Three -> two classes
x = x[y != 2]
y = y[y != 2]
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.33)
lda = LDA()
lda.fit(x_train, y_train)
y_pred = lda.predict(x_test)
accuracy = accuracy_score(y_test, y_pred)
print ("Accuracy:", accuracy)
Plot().plot_2d(x_test, y_pred, title="LDA", accuracy=accuracy)
def main():
print("Random Forest")
data = datasets.load_digits()
x = data.data
y = data.target
x_train, x_test, y_train, y_test = train_test_split(x, y, seed=1)
clf = RandomForest(n_estimators=100)
clf.fit(x_train, y_train)
y_pred = clf.predict(x_test)
accuracy = accuracy_score(y_test, y_pred)
print("Accuracy:", accuracy)
Plot().plot_2d(x_test,
y_pred,
title="Random Forest",
accuracy=accuracy,
legend_label=data.target_names)
def main():
data = datasets.load_digits()
x = data.data
y = data.target
digit1 = 1
digit2 = 5
idx = np.append(np.where(y == digit1)[0], np.where(y == digit2)[0])
y = data.target[idx]
# Change labels to {-1, 1}
y[y == digit1] = -1
y[y == digit2] = 1
x = data.data[idx]
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.5)
clf = Adaboost(n_clf=5)
clf.fit(x_train, y_train)
y_pred = clf.predict(x_test)
accuracy = accuracy_score(y_test, y_pred)
print("Accuracy:", accuracy)
Plot().plot_2d(x_test, y_pred, title="Adaboost", accuracy=accuracy)
def main():
print("Gradient Boosting Regression")
x, y = make_regression(n_samples=200, n_features=1, noise=20)
x_train, x_test, y_train, y_test = train_test_split(x, y)
model = GradientBoostingRegressor()
model.fit(x_train, y_train)
y_pred = model.predict(x_test)
cmap = plt.get_cmap('plasma')
mse = mean_squared_error(y_test, y_pred)
print("Mean Squared Error:", mse)
m1 = plt.scatter(366 * x_train, y_train, color=cmap(0.9), s=10)
m2 = plt.scatter(366 * x_test, y_test, color=cmap(0.5), s=10)
m3 = plt.scatter(366 * x_test, y_pred, color='black', s=10)
plt.suptitle("Regression Tree")
plt.title("MSE: %.2f" % mse, fontsize=10)
plt.xlabel('X')
plt.ylabel('Y')
plt.legend((m1, m2, m3), ("Training data", "Test data", "Prediction"),
loc='lower right')
plt.show()