如何对GridSearchCV中的数据进行标准化？

Question

如何对GridSearchCV中的数据进行标准化？在

这是密码。我不知道怎么做。在

import dataset
import warnings
warnings.filterwarnings("ignore")

import pandas as pd
dataset = pd.read_excel('../dataset/dataset_experiment1.xlsx')
X = dataset.iloc[:,1:-1].values
y = dataset.iloc[:,66].values

from sklearn.model_selection import GridSearchCV
#from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler
stdizer = StandardScaler()

print('===Grid Search===')

print('logistic regression')
model = LogisticRegression()
parameter_grid = {'solver': ['newton-cg', 'lbfgs', 'liblinear', 'sag', 'saga']}
grid_search = GridSearchCV(model, param_grid=parameter_grid, cv=kfold, scoring = scoring3)
grid_search.fit(X, y)
print('Best score: {}'.format(grid_search.best_score_))
print('Best parameters: {}'.format(grid_search.best_params_))
print('\n')

更新 这是我试图运行但得到的错误：

^{pr2}$

Answer 1

使用sklearn.pipeline.Pipeline

演示：

from sklearn.pipeline import Pipeline
from sklearn.model_selection import train_test_split

X_train, X_test, y_train, y_test = \
        train_test_split(X, y, test_size=0.33)

pipe = Pipeline([
    ('scale', StandardScaler()),
    ('clf', LogisticRegression())
])

param_grid = [
    {
        'clf__solver': ['newton-cg', 'lbfgs', 'liblinear', 'sag', 'saga'],
        'clf__C': np.logspace(-3, 1, 5),
    },
]

grid = GridSearchCV(pipe, param_grid=param_grid, cv=3, n_jobs=-1, verbose=2)
grid.fit(X_train, y_train)