Boosting
1
2
| import numpy as np
import matplotlib.pyplot as plt
|
1
2
3
| from sklearn import datasets
X, y = datasets.make_moons(n_samples=500, noise=0.3, random_state=666)
|
1
2
3
| plt.scatter(X[y==0,0], X[y==0,1])
plt.scatter(X[y==1,0], X[y==1,1])
plt.show()
|
1
2
3
| from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=666)
|
AdaBoosting
1
2
3
4
5
6
| from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import AdaBoostClassifier
ada_clf = AdaBoostClassifier(
DecisionTreeClassifier(max_depth=2), n_estimators=500)
ada_clf.fit(X_train, y_train)
|
AdaBoostClassifier(algorithm='SAMME.R',
base_estimator=DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=2,
max_features=None, max_leaf_nodes=None,
min_impurity_decrease=0.0, min_impurity_split=None,
min_samples_leaf=1, min_samples_split=2,
min_weight_fraction_leaf=0.0, presort=False, random_state=None,
splitter='best'),
learning_rate=1.0, n_estimators=500, random_state=None)
1
| ada_clf.score(X_test, y_test)
|
0.85599999999999998
Gradient Boosting
1
2
3
4
| from sklearn.ensemble import GradientBoostingClassifier
gb_clf = GradientBoostingClassifier(max_depth=2, n_estimators=30)
gb_clf.fit(X_train, y_train)
|
GradientBoostingClassifier(criterion='friedman_mse', init=None,
learning_rate=0.1, loss='deviance', max_depth=2,
max_features=None, max_leaf_nodes=None,
min_impurity_decrease=0.0, min_impurity_split=None,
min_samples_leaf=1, min_samples_split=2,
min_weight_fraction_leaf=0.0, n_estimators=30,
presort='auto', random_state=None, subsample=1.0, verbose=0,
warm_start=False)
1
| gb_clf.score(X_test, y_test)
|
0.90400000000000003
Boosting 解决回归问题
1
2
| from sklearn.ensemble import AdaBoostRegressor
from sklearn.ensemble import GradientBoostingRegressor
|
