def __init__(self,
base_estimator=None,
n_estimators=10,
learning_rate=1.0):
"""
:param base_estimator: 基学习器，允许异质；异质的情况下使用列表传入比如[estimator1,estimator2,...,estimator10],这时n_estimators会失效；
同质的情况，单个estimator会被copy成n_estimators份
:param n_estimators: 基学习器迭代数量
:param learning_rate: 学习率，降低后续基学习器的权重，避免过拟合
"""
self.base_estimator = base_estimator
self.n_estimators = n_estimators
self.learning_rate = learning_rate
if self.base_estimator is None:
# 默认使用决策树桩
self.base_estimator = CARTRegressor(max_depth=2)
# 同质分类器
if type(base_estimator) != list:
estimator = self.base_estimator
self.base_estimator = [
copy.deepcopy(estimator) for _ in range(0, self.n_estimators)
]
# 异质分类器
else:
self.n_estimators = len(self.base_estimator)
# 记录estimator权重
self.estimator_weights = []
# 记录最终中位数值弱学习器的index
self.median_index = None
def __init__(self,
base_estimator=None,
n_estimators=10,
learning_rate=1.0,
loss='ls',
huber_threshold=1e-1,
quantile_threshold=0.5):
"""
:param base_estimator: 基学习器，允许异质；异质的情况下使用列表传入比如[estimator1,estimator2,...,estimator10],这时n_estimators会失效；
同质的情况，单个estimator会被copy成n_estimators份
:param n_estimators: 基学习器迭代数量
:param learning_rate: 学习率，降低后续基学习器的权重，避免过拟合
:param loss:表示损失函数ls表示平方误差,lae表示绝对误差,huber表示huber损失,quantile表示分位数损失
:param huber_threshold:huber损失阈值，只有在loss=huber时生效
:param quantile_threshold损失阈值，只有在loss=quantile时生效
"""
self.base_estimator = base_estimator
self.n_estimators = n_estimators
self.learning_rate = learning_rate
if self.base_estimator is None:
# 默认使用决策树桩
self.base_estimator = CARTRegressor(max_depth=2)
# 同质分类器
if type(base_estimator) != list:
estimator = self.base_estimator
self.base_estimator = [
copy.deepcopy(estimator) for _ in range(0, self.n_estimators)
]
# 异质分类器
else:
self.n_estimators = len(self.base_estimator)
self.loss = loss
self.huber_threshold = huber_threshold
self.quantile_threshold = quantile_threshold
def __init__(self,
base_estimator=None,
n_estimators=10,
feature_sample=0.66):
"""
:param base_estimator: 基学习器，允许异质；异质的情况下使用列表传入比如[estimator1,estimator2,...,estimator10],这时n_estimators会失效；
同质的情况，单个estimator会被copy成n_estimators份
:param n_estimators: 基学习器迭代数量
:param feature_sample:特征抽样率
"""
self.base_estimator = base_estimator
self.n_estimators = n_estimators
if self.base_estimator is None:
# 默认使用决策树
self.base_estimator = CARTRegressor()
# 同质
if type(base_estimator) != list:
estimator = self.base_estimator
self.base_estimator = [
copy.deepcopy(estimator) for _ in range(0, self.n_estimators)
]
# 异质
else:
self.n_estimators = len(self.base_estimator)
self.feature_sample = feature_sample
# 记录每个基学习器选择的特征
self.feature_indices = []
def __init__(self, base_estimator=None, n_estimators=10, dropout=0.5):
"""
:param base_estimator: 基学习器，允许异质；异质的情况下使用列表传入比如[estimator1,estimator2,...,estimator10],这时n_estimators会失效；
同质的情况，单个estimator会被copy成n_estimators份
:param n_estimators: 基学习器迭代数量
:param dropout: dropout概率
"""
self.base_estimator = base_estimator
self.n_estimators = n_estimators
self.dropout = dropout
if self.base_estimator is None:
# 默认使用决策树桩
self.base_estimator = CARTRegressor(max_depth=2)
# 同质分类器
if type(base_estimator) != list:
estimator = self.base_estimator
self.base_estimator = [
copy.deepcopy(estimator) for _ in range(0, self.n_estimators)
]
# 异质分类器
else:
self.n_estimators = len(self.base_estimator)
# 扩展class_num组分类器
self.expand_base_estimators = []
# 记录权重
self.weights = None
def __init__(self, base_estimator=None, n_estimators=10):
"""
:param base_estimator: 基学习器，允许异质；异质的情况下使用列表传入比如[estimator1,estimator2,...,estimator10],这时n_estimators会失效；
同质的情况，单个estimator会被copy成n_estimators份
:param n_estimators: 基学习器迭代数量
"""
self.base_estimator = base_estimator
self.n_estimators = n_estimators
if self.base_estimator is None:
# 默认使用决策树
self.base_estimator = CARTRegressor()
# 同质
if type(base_estimator) != list:
estimator = self.base_estimator
self.base_estimator = [copy.deepcopy(estimator) for _ in range(0, self.n_estimators)]
# 异质
else:
self.n_estimators = len(self.base_estimator)
import numpy as np
import os
os.chdir('../')
import matplotlib.pyplot as plt
from ml_models.tree import CARTRegressor
from ml_models.linear_model import LinearRegression
data = np.linspace(1, 10, num=100)
target = np.sin(data) + np.random.random(size=100) # 添加噪声
data = data.reshape((-1, 1))
from ml_models.ensemble import DARTRegressor
model = DARTRegressor(base_estimator=CARTRegressor())
model.fit(data, target)
plt.scatter(data, target)
plt.plot(data, model.predict(data), color='r')
plt.show()
import numpy as np
import os
os.chdir('../')
import matplotlib.pyplot as plt
from ml_models.tree import CARTRegressor
from ml_models.linear_model import LinearRegression
data = np.linspace(1, 10, num=100)
target = np.sin(data) + np.random.random(size=100) # 添加噪声
data = data.reshape((-1, 1))
from ml_models.ensemble import RandomForestRegressor
model = RandomForestRegressor(
base_estimator=[LinearRegression(), CARTRegressor()], n_estimators=10)
model.fit(data, target)
plt.scatter(data, target)
plt.plot(data, model.predict(data), color='r')
plt.show()
import matplotlib.pyplot as plt
import numpy as np
import os
os.chdir('../')
from sklearn.datasets import make_regression
# data, target = make_regression(n_samples=100, n_features=1, random_state=44, bias=0.5, noise=2)
data = np.linspace(1, 10, num=100)
target = np.sin(data) + np.random.random(size=100)
data = data.reshape((-1, 1))
# indices = np.argsort(target)
#
# data = data[indices]
# target = target[indices]
from ml_models.tree import CARTRegressor
tree = CARTRegressor(max_bins=50)
tree.fit(data, target)
tree.prune(10000)
plt.scatter(data, target)
plt.plot(data, tree.predict(data), color='r')
plt.show()
import numpy as np
import os
os.chdir('../')
import matplotlib.pyplot as plt
from ml_models.tree import CARTRegressor
from ml_models.linear_model import LinearRegression
data = np.linspace(1, 10, num=100)
target = np.sin(data) + np.random.random(size=100) # 添加噪声
data = data.reshape((-1, 1))
from ml_models.ensemble import AdaBoostRegressor
model = AdaBoostRegressor(base_estimator=[LinearRegression(), CARTRegressor()], n_estimators=10)
model.fit(data, target)
plt.scatter(data, target)
plt.plot(data, model.predict(data), color='r')
plt.show()
import numpy as np
import os
os.chdir('../')
import matplotlib.pyplot as plt
from ml_models.tree import CARTRegressor
from ml_models.linear_model import LinearRegression
data = np.linspace(1, 10, num=100)
target = np.sin(data) + np.random.random(size=100) # 添加噪声
data = data.reshape((-1, 1))
from ml_models.ensemble import GradientBoostingRegressor
model = GradientBoostingRegressor(base_estimator=CARTRegressor(), loss='quantile', quantile_threshold=0.6, learning_rate=1.0)
model.fit(data, target)
plt.scatter(data, target)
plt.plot(data, model.predict(data), color='r')
plt.show()
from sklearn.datasets import make_classification
from ml_models import utils
from ml_models.linear_model import LogisticRegression
from ml_models.tree import CARTRegressor
from ml_models.svm import SVC
data, target = make_classification(n_samples=100,
n_features=2,
n_classes=2,
n_informative=1,
n_redundant=0,
n_repeated=0,
n_clusters_per_class=1,
class_sep=0.5)
X_train, X_test, y_train, y_test = model_selection.train_test_split(
data, target, test_size=0.1)
from ml_models.ensemble import GradientBoostingClassifier
classifier = GradientBoostingClassifier(base_estimator=CARTRegressor(),
n_estimators=10,
learning_rate=0.5)
classifier.fit(X_train, y_train)
# # 计算F1
from sklearn.metrics import f1_score
print(f1_score(y_test, classifier.predict(X_test)))
print(np.sum(np.abs(y_test - classifier.predict(X_test))))
#
utils.plot_decision_function(X_train, y_train, classifier)
utils.plt.show()
from sklearn.datasets import make_classification
from ml_models import utils
from ml_models.linear_model import LogisticRegression
from ml_models.tree import CARTRegressor
from ml_models.svm import SVC
data, target = make_classification(n_samples=100,
n_features=2,
n_classes=2,
n_informative=1,
n_redundant=0,
n_repeated=0,
n_clusters_per_class=1,
class_sep=0.5)
X_train, X_test, y_train, y_test = model_selection.train_test_split(
data, target, test_size=0.1)
from ml_models.ensemble import DARTClassifier
classifier = DARTClassifier(base_estimator=CARTRegressor(), n_estimators=10)
classifier.fit(X_train, y_train)
# # 计算F1
from sklearn.metrics import f1_score
print(f1_score(y_test, classifier.predict(X_test)))
print(np.sum(np.abs(y_test - classifier.predict(X_test))))
#
utils.plot_decision_function(X_train, y_train, classifier)
utils.plt.show()
import numpy as np
import os
os.chdir('../')
import matplotlib.pyplot as plt
from ml_models.tree import CARTRegressor
from ml_models.linear_model import LinearRegression
data = np.linspace(1, 10, num=100)
target = np.sin(data) + np.random.random(size=100) # 添加噪声
data = data.reshape((-1, 1))
from ml_models.ensemble import AdaBoostRegressor
model = AdaBoostRegressor(base_estimator=[LinearRegression(),
CARTRegressor()],
n_estimators=10)
model.fit(data, target)
plt.scatter(data, target)
plt.plot(data, model.predict(data), color='r')
plt.show()
import numpy as np
import os
os.chdir('../')
import matplotlib.pyplot as plt
from ml_models.tree import CARTRegressor
from ml_models.linear_model import LinearRegression
data = np.linspace(1, 10, num=100)
target = np.sin(data) + np.random.random(size=100) # 添加噪声
data = data.reshape((-1, 1))
from ml_models.ensemble import GradientBoostingRegressor
model = GradientBoostingRegressor(base_estimator=CARTRegressor(),
loss='quantile',
quantile_threshold=0.6,
learning_rate=1.0)
model.fit(data, target)
plt.scatter(data, target)
plt.plot(data, model.predict(data), color='r')
plt.show()