def test_kNNClassifier(self):
iris = datasets.load_iris()
X = iris['data']
y = iris['target']
X_train, y_train, X_test, y_test = train_test_split(X,
y,
test_ratio=0.2)
knn_clf = KNNClassifier(k_neighbours=3)
fit_result = knn_clf.fit(X_train, y_train)
print(fit_result)
# x = np.array([8.093607318, 3.365731514])
# X_predict = np.array(x).reshape(1, -1)
y_predict = knn_clf.predict(X_test)
print(y_predict)
print(y_test)
score = accuracy_rate(y_test, y_predict)
print(score)
print(knn_clf.score(X_test, y_test))
plt.scatter(X_train[y_train == 0, 0],
X_train[y_train == 0, 1],
color='g')
plt.scatter(X_train[y_train == 1, 0],
X_train[y_train == 1, 1],
color='b')
plt.scatter(X_train[y_train == 2, 0],
X_train[y_train == 2, 1],
color='r')
plt.show()
def test_LinearRegerssion(self):
boston = datasets.load_boston()
X = boston['data']
y = boston['target']
X = X[y < 50.0]
y = y[y < 50.0]
X_train, y_train, X_test, y_test = train_test_split(X, y)
regression = LinearRegression()
print(regression.fit_normal(X_train, y_train))
print('score={}'.format(regression.score(X_test, y_test)))
def test_StandardScaler(self):
iris = datasets.load_iris()
X = iris['data']
y = iris['target']
X_train, y_train, X_test, y_test = train_test_split(X, y)
# print(X_train)
scaler = StandardScaler()
fit = scaler.fit(X_train)
print(fit)
X_train = scaler.transform(X_train)
print(X_train)
# print(X_test)
X_test = scaler.transform(X_test)
print(X_test)
def test_stochastic_gradient_descent(self):
boston = datasets.load_boston()
X = boston['data']
y = boston['target']
X = X[y < 50.0]
y = y[y < 50.0]
X_train, y_train, X_test, y_test = train_test_split(X, y)
scaler = StandardScaler()
scaler.fit(X_train)
X_train_standard = scaler.transform(X_train)
X_test_standard = scaler.transform(X_test)
lin_reg = LinearRegression()
lin_reg.fit_stochastic_gradient_descent(X_train_standard, y_train)
print(lin_reg.score(X_test_standard, y_test))
def test_find_the_best_k(self):
iris = datasets.load_iris()
X = iris['data']
y = iris['target']
X_train, y_train, X_test, y_test = train_test_split(X, y)
best_score = 0.0
best_k = -1
for k in range(1, 11):
knn_clf = KNNClassifier(k_neighbours=k)
knn_clf.fit(X_train, y_train)
score = knn_clf.score(X_test, y_test)
if score > best_score:
best_score = score
best_k = k
print('The best K is {} and the best score is {}'.format(
best_k, best_score))
def test_MSE_RMSE_MAE_R2(self):
boston = datasets.load_boston()
print(boston['feature_names'])
X = boston['data'][:, 5] # Get the `RM`(room) data
y = boston['target']
# clean data
X = X[y < 50.0]
y = y[y < 50.0]
x_train, y_train, x_test, y_test = train_test_split(X, y)
regression = SimpleLinearRegression()
print(regression.fit(x_train, y_train))
y_predict = regression.predict(x_test)
print(mean_squared_error(y_test, y_predict))
print(root_meas_squared_error(y_test, y_predict))
print(mean_absolute_error(y_test, y_predict))
print(regression.score(x_test, y_test))
plt.scatter(x_train, y_train)
plt.plot(x_train, regression.predict(x_train), color='r')
plt.show()