python - Scikit-learn 的特征选择回归

Question

我有一个 Excel 数据文件，其中包括预测变量和目标/响应。我将目标称为“NEAR”，每个预测变量都有自己的名称。为了研究特征选择，我使用了这段代码，但出了问题，我无法意识到每个预测变量对我的目标的影响。我写的代码如下。所有帮助将不胜感激。

#importing libraries
from sklearn.datasets import load_boston
import pandas as pd
import numpy as np
import matplotlib
import matplotlib.pyplot as plt
import seaborn as sns
import statsmodels.api as sm
%matplotlib inline
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn.feature_selection import RFE
from sklearn.linear_model import RidgeCV, LassoCV, Ridge, Lasso

# reading files
x = pd.read_excel("train.xlsx")

X = x.iloc[:, 0:5]

y = x.iloc[:,5]

#Using Pearson Correlation
plt.figure(figsize=(12,10))
cor = X.corr()
sns.heatmap(cor, annot=True, cmap=plt.cm.Reds)
plt.show()
#Correlation with output variable
cor_target = abs(cor["NEAR"])
#Selecting highly correlated features
relevant_features = cor_target[cor_target > 0.5]
relevant_features 

但是我收到了这个错误

---------------------------------------------------------------------------
KeyError                                  Traceback (most recent call last)
<ipython-input-28-3468dfbea7e1> in <module>
      1 #Correlation with output variable
----> 2 cor_target = abs(cor[y])
      3 #Selecting highly correlated features
      4 relevant_features = cor_target[cor_target > 0.5]
      5 relevant_features

~\Anaconda3\lib\site-packages\pandas\core\frame.py in __getitem__(self, key)
   2984             if is_iterator(key):
   2985                 key = list(key)
-> 2986             indexer = self.loc._convert_to_indexer(key, axis=1, raise_missing=True)
   2987 
   2988         # take() does not accept boolean indexers

~\Anaconda3\lib\site-packages\pandas\core\indexing.py in _convert_to_indexer(self, obj, axis, is_setter, raise_missing)
   1283                 # When setting, missing keys are not allowed, even with .loc:
   1284                 kwargs = {"raise_missing": True if is_setter else raise_missing}
-> 1285                 return self._get_listlike_indexer(obj, axis, **kwargs)[1]
   1286         else:
   1287             try:

~\Anaconda3\lib\site-packages\pandas\core\indexing.py in _get_listlike_indexer(self, key, axis, raise_missing)
   1090 
   1091         self._validate_read_indexer(
-> 1092             keyarr, indexer, o._get_axis_number(axis), raise_missing=raise_missing
   1093         )
   1094         return keyarr, indexer

~\Anaconda3\lib\site-packages\pandas\core\indexing.py in _validate_read_indexer(self, key, indexer, axis, raise_missing)
   1175                 raise KeyError(
   1176                     "None of [{key}] are in the [{axis}]".format(
-> 1177                         key=key, axis=self.obj._get_axis_name(axis)
   1178                     )
   1179                 )

KeyError: "None of [Float64Index([-0.00398046,  0.00205926, -0.00304156,  0.00206342,  0.00797852,\n               0.00619195,  0.00368038,  0.00415858,  0.00454432,  0.00536623,\n              ...\n               0.00201033,  0.00184575,  0.00165407,  0.00148248,  0.00131221,\n               0.00103276,  0.00084394,  0.00078347,  0.00069564,  0.00058571],\n             dtype='float64', length=209076)] are in the [columns]"

Answer 1

问题所在(与您发布的代码不同)出现在以下行中:

cor_target = abs(cor[y])

您似乎已更改为:

cor_target = abs(cor["NEAR"])

代码的问题是您传递了一个变量y，它充当数据帧cor的数组。当您执行此操作时，pandas 会尝试选择值等于数组y 的列名称。这意味着它将搜索名为 -0.00398046、0.00205926、-0.00304156 等的列，这些列不存在，因此会出现错误。

鉴于目标变量是NEAR，您的新代码应该可以工作。