各个基础学习模型超参数调节

1.随机森林

# 采用GridSearchCV进行超参数的设定
from sklearn.model_selection import GridSearchCV,StratifiedKFold
RF1=RandomForestClassifier()
parameter_grid={"n_estimators":[5,10,25,50,100],
                "max_features":[1,2,3,4,5,6,8,10],
                "warm_start":[True,False],
   　　　　　　　　#"max_depth":[1,2,3,5,7]
}
# 交叉验证StratifiedKFold默认是3
cross_validatin=StratifiedKFold(n_splits=3, random_state=None, shuffle=False)
grid_search=GridSearchCV(RF1,param_grid=parameter_grid,score="f1",cv=cross_validatin)
grid_search.fit(X_train,y_train)
print(grid_search.best_params_)
print(grid_search.best_score_)
#获取到最佳参数之后，重新进行预测
RF2=RandomForestClassifier(max_features=8,n_estimators=25,warm_start=True)
RF2.fit(X_train,y_train)

 2.逻辑回归

from sklearn.linear_model import LogisticRegression
tuned_parameters=[{'penalty':['l1','l2'],
                   'C':[0.01,0.05,0.1,0.5,1,5,10,50,100],
                    'solver':['liblinear'],
                    'multi_class':['ovr']},
                {'penalty':['l2'],
                 'C':[0.01,0.05,0.1,0.5,1,5,10,50,100],
                'solver':['lbfgs'],
                'multi_class':['ovr','multinomial']}]
grid_logist = GridSearchCV(LogisticRegression(class_weight="balanced"), cv=3, n_jobs=-1, param_grid=tuned_parameters)

 3.KNN

from sklearn.neighbors import KNeighborsClassifier
knn = KNeighborsClassifier()
param_grid = [
    {
        'weights':['uniform'],
        'n_neighbors':[1,3,5,7,9]
    },
    {
        'weights':['distance'],
        'n_neighbors':[1,3,5,7,9],
        'p':[1,3,4,5,7]
    }
]
grid_search = GridSearchCV(knn,param_grid,n_jobs=-1,verbose=2)