gridSearchCV（网格搜索）的参数、方法及示例¶

class sklearn.model_selection.GridSearchCV(estimator, param_grid, scoring=None, fit_params=None, n_jobs=1, iid=True, refit=True, cv=None, verbose=0, pre_dispatch=‘2*n_jobs’, error_score=’raise’, return_train_score=’warn’)

estimator=RandomForestClassifier(min_samples_split=100,min_samples_leaf=20,max_depth=8,max_features='sqrt',random_state=10)

param_grid = {'n_estimators':range(10,71,10)}

gbm = LGBMRegressor(boosting_type='gbdt', 
                    num_leaves=20, # Maximum tree leaves for base learners.
                    max_depth=2, # Maximum tree depth for base learners, <=0 means no limit.
                    learning_rate=0.1, n_estimators=30,
                    subsample_for_bin=200000, objective='regression_l1', class_weight=None,
                    min_split_gain=0., min_child_weight=1e-3, 
                    min_child_samples=20,  #Minimum number of data needed in a child (leaf).
                    subsample=1., 
                    subsample_freq=0, # 0 means disable bagging; k means perform bagging at every k iteration
                    colsample_bytree=1., # <1 means LightGBM will randomly select part of features on each iteration (tree)
                    reg_alpha=0., # L1 regularization term on weights.
                    reg_lambda=0.,# L2 regularization term on weights.
                    random_state=2019,
                    n_jobs=-1, silent=True, 
                    importance_type='gain' # The type of feature importance to be filled into feature_importances_. If ‘split’, result contains numbers of times the feature is used in a model. If ‘gain’, result contains total gains of splits which use the feature.
                    )

# 网格搜索
parameters = {
        'objective': ['regression', 'regression_l1'],
        'max_depth': [2,3,4,5],
#        'num_leaves': [20,25,30,35],
#        'n_estimators': [20,25,30,35],
#        'min_child_samples': [15,20,25,30],
#        'subsample_freq': [0,2,5],
#        'subsample': [0.7,0.8,0.9,1],
#        'colsample_bytree': [0.8,0.9,1]
        }
tridx = -np.ones(x_train.shape[0])
vaidx = np.zeros(x_val.shape[0])

def mape_my(t, p):
    return np.abs((t - p)/t).mean()
scorer = make_scorer(mape_my, greater_is_better=False)

# tridx所有元素=-1表示用来训练的, vaidx所有元素=0表示用来验证的. tridx和vaidx对应下面的x_search(y_search)
# tridx值=-1表示肯定参与训练
# 参与验证的元素vaidx必须>=0
# =0表示第一次cross validation的验证集, 其他不等于0的为训练集
# =1表示第二次cross validation的验证集, 其他不等于1的为训练集, 以此类推
ps = PredefinedSplit(test_fold=np.hstack([tridx, vaidx]))
gsearch = GridSearchCV(gbm, param_grid=parameters, # 前面已经用预定义了一些参数来初始化gbm, 这里只搜索'objective'和'max_depth'
                       scoring=scorer, 
                       cv=ps, verbose=10,
                       refit=False # You need to set refit=False (not a default option), otherwise the grid search will refit the estimator on the whole dataset (ignoring cv) after the grid search completes.
                       )
x_search = np.vstack([x_train, x_val])
y_search = np.concatenate([train_y, val_y],0)
gsearch.fit(x_search, y_search) # 搜索最优参数

print('参数的最佳取值:{0}'.format(gsearch.best_params_))
print('最佳模型得分:{0}'.format(gsearch.best_score_))

default_params = gbm.get_params() # 得到前面预定义的参数
default_params.update(gsearch.best_params_) # 更新最优的参数
gbm = LGBMRegressor(**default_params)
raise ValueError
"""
---------------------------------
接下来可以只用train set而不用val set拟合1个模型
gbm.fit(x_train, train_y,
        verbose=True
        )
"""

param_test1 ={'n_estimators':range(10,71,10)}
gsearch1= GridSearchCV(estimator =RandomForestClassifier(min_samples_split=100,
                                 min_samples_leaf=20,max_depth=       8,max_features='sqrt',random_state=10), 
                       param_grid =param_test1,scoring='roc_auc',cv=5)
gsearch1.fit(X,y)
gsearch1.grid_scores_, gsearch1.best_params_, gsearch1.best_score_

([mean: 0.80681, std:0.02236, params: {'n_estimators': 10},
  mean: 0.81600, std: 0.03275, params:{'n_estimators': 20},
  mean: 0.81818, std: 0.03136, params:{'n_estimators': 30},
  mean: 0.81838, std: 0.03118, params:{'n_estimators': 40},
  mean: 0.82034, std: 0.03001, params:{'n_estimators': 50},
  mean: 0.82113, std: 0.02966, params:{'n_estimators': 60},
  mean: 0.81992, std: 0.02836, params:{'n_estimators': 70}],
{'n_estimators': 60},
0.8211334476626017)

pipeline= Pipeline([("features", combined_features), ("svm", svm)])
param_grid= dict(features__pca__n_components=[1, 2, 3],
                  features__univ_select__k=[1,2],
                  svm__C=[0.1, 1, 10])

grid_search= GridSearchCV(pipeline, param_grid=param_grid, verbose=10)
grid_search.fit(X,y)
print(grid_search.best_estimator_)