选择KBest错误：ValueError：未知标签类型:(数组（[0.55,0.84,0.72,0.54,0.59,0.77,0.85,1.03,1.62,3.04,3.6]），）

Posted 2021-05-03

import pandas as pd
import numpy as np
from sklearn.feature_selection import SelectKBest ,chi2 

label_ds=pd.read_csv("D:/intern/bll_beijing.csv")  
array = label_ds.values

label_X  = array[:,1:]
label_y = array[:,0]

test = SelectKBest(score_func=chi2, k=4)
fit = test.fit(label_X, label_y)

我收到了这个：

Traceback (most recent call last):

    fit = test.fit(label_X, label_y)
  File "C:UsersTOSHIBAAppDataLocalProgramsPythonPython35libsite-packagessklearnfeature_selectionunivariate_selection.py", line 349, in fit
    score_func_ret = self.score_func(X, y)
  File "C:UsersTOSHIBAAppDataLocalProgramsPythonPython35libsite-packagessklearnfeature_selectionunivariate_selection.py", line 217, in chi2
    Y = LabelBinarizer().fit_transform(y)
  File "C:UsersTOSHIBAAppDataLocalProgramsPythonPython35libsite-packagessklearnpreprocessinglabel.py", line 307, in fit_transform
    return self.fit(y).transform(y)
  File "C:UsersTOSHIBAAppDataLocalProgramsPythonPython35libsite-packagessklearnpreprocessinglabel.py", line 284, in fit
    self.classes_ = unique_labels(y)
  File "C:UsersTOSHIBAAppDataLocalProgramsPythonPython35libsite-packagessklearnutilsmulticlass.py", line 97, in unique_labels
    raise ValueError("Unknown label type: %s" % repr(ys))

ValueError: Unknown label type: (array([0.55, 0.84, 0.72, 0.54, 0.59, 0.77, 0.85, 1.03, 1.62, 3.04, 3.6 ]),)

[Finished in 3.4s]

[ 0.55, 0.84, 0.72, 0.54, 0.59, 0.77, 0.85, 1.03, 1.62, 3.04, 3.6 ]是csv文档的第一列。

它出什么问题了？

答案

这个label_y有连续的价值观。

但是您已将评分函数指定为chi2。根据documentation of chi2，这仅适用于分类任务。

计算每个非负特征和类之间的卡方统计量。

对于回归任务，您可以使用以下内容：

• f_regression
• mutual_info_regression