def wine_example():
x, y = get_wine()
x = x[(y == 0) | (y == 1)]
y = y[(y == 0) | (y == 1)]
_filter = Filter(FilterType.corr, 3)
x_filter = _filter.fit_transform(x, y)
print(x_filter.shape)
_filter = Filter(FilterType.var, 3)
x_filter = _filter.fit_transform(x, y)
print(x_filter.shape)
_filter = Filter(FilterType.entropy, 3)
x_filter = _filter.fit_transform(x, y)
print(x_filter.shape)
embedded = Embedded(3, EmbeddedType.Lasso)
x_embedded = embedded.fit_transform(x, y)
print(x_embedded.shape) # lasso后稀疏到只有两个值非0，因此只输出了两个特征
# GBDT暂时只支持离散特征
embedded = Embedded(3, EmbeddedType.GBDT)
x = np.random.choice([0, 1], 50).reshape(10, 5)
y = np.random.rand(10)
x_embedded = embedded.fit_transform(x, y)
print(x_embedded, y)
def wine_example():
x, y = get_wine()
x = x[(y == 0) | (y == 1)]
y = y[(y == 0) | (y == 1)]
x_train, y_train, x_test, y_test = train_test_split(x, y, 0.3, 918)
# 贝叶斯最小错误率
bme = BayesMinimumError()
bme.fit(x_train, y_train)
print(bme.score(x_test, y_test))
bme.classify_plot(x_test, y_test)
# 贝叶斯最小风险，需要给定风险矩阵
# 风险矩阵 [[0,100], [10,0]] 表示把0分为1（存伪）的损失为100，把1分为0（弃真）的损失为10
bmr = BayesMinimumRisk(np.array([[0, 100], [10, 0]]))
bmr.fit(x_train, y_train)
bmr.predict(x_test)
print(bmr.score(x_test, y_test))
bmr.classify_plot(x_test, y_test)
# 朴素贝叶斯
nb = NaiveBayes()
nb.fit(x_train, y_train)
nb.predict(x_test)
print(nb.score(x_test, y_test))
nb.classify_plot(x_test, y_test)
def moon_example():
"""
AdaBoost的例子，以月亮数据集为例
:return:
"""
x, y = get_wine()
x = x[(y == 0) | (y == 1)]
y = y[(y == 0) | (y == 1)]
x_train, y_train, x_test, y_test = train_test_split(x, y, 0.3, 918)
# 采用Logistic回归作为子分类器的AdaBoost
ada = AdaBoost(classifier=ClassifierType.LR)
ada.fit(x_train, y_train)
print(ada.score(x_test, y_test))
ada.classify_plot(x_test, y_test, ", LR")
# 采用KNN作为子分类器的AdaBoost
ada = AdaBoost(classifier=ClassifierType.KNN)
ada.fit(x_train, y_train)
print(ada.score(x_test, y_test))
ada.classify_plot(x_test, y_test, ", KNN")
# 采用CART树为子分类器的AdaBoost
ada = AdaBoost(classifier=ClassifierType.CART)
ada.fit(x_train, y_train)
print(ada.score(x_test, y_test))
ada.classify_plot(x_test, y_test, ", CART")
def watermelon_example():
"""
GBDT的例子，以西瓜数据集为例
GBDT暂时只支持回归操作，不支持分类
:return:
"""
x, y = get_watermelon()
y = x[:, -1] # y为连续标签
x = x[:, :-1] # x为离散标签
x_train, y_train, x_test, y_test = train_test_split(x, y, 0.3, 918)
gbdt = GBDT(learning_rate=1)
gbdt.fit(x_train, y_train)
print(gbdt.predict(x_test), y_test)
print("R square: %.4f" % gbdt.score(x_test, y_test))
x, y = get_wine()
y = x[:, -1] # y为连续标签
x = x[:, :-1] # x为离散标签
x_train, y_train, x_test, y_test = train_test_split(x, y, 0.3, 918)
gbdt = GBDT(learning_rate=1)
gbdt.fit(x_train, y_train)
print(gbdt.predict(x_test), y_test)
print("R square: %.4f" % gbdt.score(x_test, y_test))
def random_forest_example():
x, y = get_wine()
# x = x[(y == 0) | (y == 1)]
# y = y[(y == 0) | (y == 1)]
x_train, y_train, x_test, y_test = train_test_split(x, y, 0.3, 918)
rf = RandomForest(4, 50)
rf.fit(x_train, y_train)
print(rf.score(x_test, y_test))
rf.classify_plot(x_test, y_test)
def AdaBoost_multi_class_example():
x, y = get_wine()
x_train, y_train, x_test, y_test = train_test_split(x, y, 0.3, 918)
ada = AdaBoost(classifier=ClassifierType.LR)
ada.fit(x_train, y_train)
print(ada.predict(x_test))
ada.classify_plot(x_test, y_test, ", LR")
ada = AdaBoost(classifier=ClassifierType.CART)
ada.fit(x_train, y_train)
print(ada.predict(x_test))
ada.classify_plot(x_test, y_test, ", CART")
ada = AdaBoost(classifier=ClassifierType.KNN)
ada.fit(x_train, y_train)
print(ada.predict(x_test))
ada.classify_plot(x_test, y_test, ", CART")
def wine_example():
x, y = get_wine()
#x = x[(y == 0) | (y == 1)]
#y = y[(y == 0) | (y == 1)]
x_train, y_train, x_test, y_test = train_test_split(x, y, 0.3, 918)
cart = CART()
cart.fit(x_train, y_train)
print(cart.score(x_test, y_test))
cart.classify_plot(x_test, y_test)
y = x[:, -1]
x = x[:, :-1]
x_train, y_train, x_test, y_test = train_test_split(x, y, 0.3, 918)
cart = CART()
cart.fit(x_train, y_train)
print(cart.score(x_test, y_test))
def wine_example():
x, y = get_wine()
x = x[(y == 0) | (y == 1)]
y = y[(y == 0) | (y == 1)]
x_train, y_train, x_test, y_test = train_test_split(x, y, 0.3, 918)
logistic = BaseLogisticRegression(has_intercept=False)
logistic.fit(x_train, y_train)
print(logistic.w)
logistic.classify_plot(x_test, y_test)
logistic.auc_plot(x_test, y_test)
lasso = Lasso()
lasso.fit(x_train, y_train)
print(lasso.w)
lasso.classify_plot(x_test, y_test)
ridge = Ridge()
ridge.fit(x_train, y_train)
print(ridge.w)
ridge.classify_plot(x_test, y_test)