共线特征及其对线性模型的影响，任务：1 Logistic Regression

Question

%matplotlib inline
import warnings
warnings.filterwarnings("ignore")
import pandas as pd
import numpy as np
from sklearn.datasets import load_iris
from sklearn.linear_model import SGDClassifier
from sklearn.model_selection import GridSearchCV
import seaborn as sns
import matplotlib.pyplot as plt`enter code here`
data = pd.read_csv('task_d.csv')
data.head()

输出

         x         y           z          x*x      2*y           2*z+3*x*x     w        target
0   -0.581066   0.841837    -1.012978   -0.604025   0.841837    -0.665927   -0.536277   0
1   -0.894309   -0.207835   -1.012978   -0.883052   -0.207835   -0.917054   -0.522364   0
2   -1.207552   0.212034    -1.082312   -1.150918   0.212034    -1.166507   0.205738    0
3   -1.364174   0.002099    -0.943643   -1.280666   0.002099    -1.266540   -0.665720   0
4   -0.737687   1.051772    -1.012978   -0.744934   1.051772    -0.792746   -0.735054   0
X = data.drop(['target'], axis=1).values
Y = data['target'].values

做扰动测试来检查共线性的存在 任务：1 个逻辑回归¶

data.corr()['target']

输出

x            0.728290
y           -0.690684
z            0.969990
x*x          0.719570
2*y         -0.690684
2*z+3*x*x    0.764729
w            0.641750
target       1.000000
Name: target, dtype: float64

corr = X.corr()
ax = sns.heatmap(corr,vmin=-1, vmax=1, center=0,cmap=sns.diverging_palette(20, 220, n=200),square=True)
ax.set_xticklabels(ax.get_xticklabels(),rotation=45,horizontalalignment='right');

输出

AttributeError                            Traceback (most recent call last)
<ipython-input-42-749cdea8ad1a> in <module>
      1 ##correlation matrix using seaborn heatmap##https://towardsdatascience.com/better-heatmapscorr = X.corr()
----> 2 corr = X.corr()
      3 ax = sns.heatmap(corr,vmin=-1, vmax=1, center=0,cmap=sns.diverging_palette(20, 220, n=200),square=True)
      4 ax.set_xticklabels(ax.get_xticklabels(),rotation=45,horizontalalignment='right');

AttributeError: 'numpy.ndarray' object has no attribute 'corr'

我该如何解决这个问题？

Answer 1

而不是 X 直接调用数据集

这会有所帮助：

corr = data.corr()
ax = sns.heatmap(corr,vmin=-1, vmax=1, center=0,cmap=sns.diverging_palette(20, 220, n=200),square=True)
ax.set_xticklabels(ax.get_xticklabels(),rotation=45,horizontalalignment='right')

Answer 2

为什么在创建 X 时使用 .values()？这将返回一个 numpy 数组。

如果您删除 .values()，您的 X 将保留为 pandas DataFrame，它具有 .corr() 方法。然后您的代码将按照您的预期运行。