Python Sklearn Pipelines:值错误-预期功能数
我创建了一个管道,它基本上在模型和定标器上循环,并执行递归特征消除(RFE),如下所示:Python Sklearn Pipelines:值错误-预期功能数,python,machine-learning,scikit-learn,pipeline,feature-selection,Python,Machine Learning,Scikit Learn,Pipeline,Feature Selection,我创建了一个管道,它基本上在模型和定标器上循环,并执行递归特征消除(RFE),如下所示: def train_models(models, scalers, X_train, y_train, X_val, y_val): best_results = {'f1_score': 0} for model in models: for scaler in scalers: for n_features in list(range( len(
def train_models(models, scalers, X_train, y_train, X_val, y_val):
best_results = {'f1_score': 0}
for model in models:
for scaler in scalers:
for n_features in list(range(
len(X_train.columns),
int(len(X_train.columns)/2),
-10
)):
rfe = RFE(
estimator=model,
n_features_to_select=n_features,
step=10
)
pipe = Pipeline([
('scaler', scaler),
('selector', rfe),
('model', model)
])
pipe.fit(X_train, y_train)
y_pred = pipe.predict(X_val)
results = evaluate(y_val, y_pred) #Returns a dictionary of values
results['pipeline'] = pipe
results['y_pred'] = y_pred
if results['f1_score'] > best_results['f1_score']:
best_results = results
print("Best F1: {}".format(best_results['f1_score']))
return best_results
管道在函数内部工作良好,能够正确预测和评分结果
但是,当我在函数外部调用pipeline.predict()时,例如
best_result = train_models(models, scalers, X_train, y_train, X_val, y_val)
pipeline = best_result['pipeline']
pipeline.predict(X_val)
我得到以下错误:
以下是管道
的外观:
Pipeline(steps=[('scaler', StandardScaler()),
('selector',
RFE(estimator=LogisticRegression(C=1, max_iter=1000,
penalty='l1',
solver='liblinear'),
n_features_to_select=78, step=10)),
('model',
LogisticRegression(C=1, max_iter=1000, penalty='l1',
solver='liblinear'))])
我猜管道中的模型
期望的是48个功能,而不是78个,但我不明白数字48是从哪里来的,因为n\u features\u to\u select
在上一个RFE步骤中设置为78
任何帮助都将不胜感激 我没有你的数据。但是,根据您共享的信息进行一些计算和猜测,48似乎是嵌套循环尝试的最后一个
n_功能。这使我怀疑罪犯是个肤浅的复制品。我建议您更改以下内容:
pipe = Pipeline([
('scaler', scaler),
('selector', rfe),
('model', model)
])
到
然后再试一次(当然,在第一次执行导入拷贝之后)
pipe = Pipeline([
('scaler', scaler),
('selector', rfe),
('model', copy.deepcopy(model))
])