import xgboost as xgb
from sklearn.model_selection import train_test_split
from sklearn.datasets import load_breast_cancer
from sklearn.model_selection import GridSearchCV
cancer = load_breast_cancer()
x = cancer.data[:50]
y = cancer.target[:50]
train_x, valid_x, train_y, valid_y = train_test_split(x, y, test_size=0.333, random_state=0) # 分训练集和验证集
# 这里不需要Dmatrix
parameters = {
'max_depth': [5, 10, 15, 20, 25],
'learning_rate': [0.01, 0.02, 0.05, 0.1, 0.15],
'n_estimators': [50, 100, 200, 300, 500],
'min_child_weight': [0, 2, 5, 10, 20],
'max_delta_step': [0, 0.2, 0.6, 1, 2],
'subsample': [0.6, 0.7, 0.8, 0.85, 0.95],
'colsample_bytree': [0.5, 0.6, 0.7, 0.8, 0.9],
'reg_alpha': [0, 0.25, 0.5, 0.75, 1],
'reg_lambda': [0.2, 0.4, 0.6, 0.8, 1],
'scale_pos_weight': [0.2, 0.4, 0.6, 0.8, 1]
}
xlf = xgb.XGBClassifier(max_depth=10,
learning_rate=0.01,
n_estimators=2000,
silent=True,
objective='binary:logistic',
nthread=-1,
gamma=0,
min_child_weight=1,
max_delta_step=0,
subsample=0.85,
colsample_bytree=0.7,
colsample_bylevel=1,
reg_alpha=0,
reg_lambda=1,
scale_pos_weight=1,
seed=1440,
missing=None)
# 有了gridsearch我们便不需要fit函数
gsearch = GridSearchCV(xlf, param_grid=parameters, scoring='accuracy', cv=3)
gsearch.fit(train_x, train_y)
print("Best score: %0.3f" % gsearch.best_score_)
print("Best parameters set:")
best_parameters = gsearch.best_estimator_.get_params()
for param_name in sorted(parameters.keys()):
print("\t%s: %r" % (param_name, best_parameters[param_name]))
#极其耗费时间,电脑没执行完
