网格搜索GridSearchCV

网格搜索用来寻找模型最佳的超参数

环境

• python==3.7
• scikit-learn==0.24.1

---

使用方式

import numpy as np
from sklearn import datasets
from sklearn.model_selection import GridSearchCV
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler
from sklearn.svm import SVC

iris = datasets.load_iris()

X = iris["data"][:, (2, 3)]
y = (iris["target"] == 2).astype(np.float64)

poly_svm = Pipeline([
    ("preprocess", StandardScaler()),
    ("svm_clf", SVC(kernel="poly"))
])


para = {"svm_clf__degree": [3, 10],
        "svm_clf__coef0": [1],
        "svm_clf__C": [5, 10]}
gs = GridSearchCV(poly_svm, para， cv=5)
gs.fit(X, y)
print(gs.best_params_)

输出为： {‘svm_clf__C’: 10, ‘svm_clf__coef0’: 1, ‘svm_clf__degree’: 10}

这里用到了Pipeline, 对模型网格搜索时，需要在超参数名前面加模型名字+两个下划线(svm_clf__)