Question

如何在GridSearchCV中对数据进行标准化？

这是代码。我不知道该怎么做。

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')

更新这是我尝试运行但得到错误：

print('logistic regression')
model = LogisticRegression()
pipeline = Pipeline([('scale', StandardScaler()), ('clf', model)])
parameter_grid = {'solver': ['newton-cg', 'lbfgs', 'liblinear', 'sag', 'saga']}
grid_search = GridSearchCV(pipeline, 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')

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)

Answer 2

如果您使用 refit=True，那么您可以使用来自 GridSearchCV 的最佳模型结果。您可以使用 cv_results 根据排名分数找到最佳行。使用最佳行然后可以提取参数。如果您的特征列表变大，请使用 RandomSearchCV 进行预测。

 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=0.3)

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

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

 grid_class=GridSearchCV(
    estimator=pipeline,
    param_grid=parameter_grid,
    scoring='accuracy',
    n_jobs=4, #use 4 cores
    cv=10, #10 folds
    refit=True,
    return_train_score=True)

    grid_class.fit(X_train,y_train)

    predictions=grid_class.predict(X_test)

    cv_results_df=pd.DataFrame(grid_class.cv_results_)

    best_row=cv_results_df[cv_results_df["rank_test_score"]==1]
 
    print(best_row)

    params_column = cv_results_df.loc[:, ['params']]
    print(params_column)

如何在GridSearchCV中对数据进行标准化？

2 个答案: