Wine 数据集 LDA 和 PCA 比较 - Python

Question

我正在尝试使用从 Internet 下载的 WINE 数据集运行此 Comparison of LDA and PCA 2D projection of Iris dataset example，但出现错误：

d:\ProgramData\Anaconda3\lib\site-packages\sklearn\utils\validation.py:760: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().   y = column_or_1d(y, warn=True)
--------------------------------------------------------------------------- IndexError                                Traceback (most recent call last) <ipython-input-44-a42b504da984> in <module>
     14 
     15 for color, i, target_name in zip(colors, [0, 1, 2], target_names):
---> 16     plt.scatter(X_r[y == i, 0], X_r[y == i, 1], color=color, alpha=.8, lw=lw,
     17                 label=target_name)
     18 plt.legend(loc='best', shadow=False, scatterpoints=1)

IndexError: too many indices for array

<Figure size 432x288 with 0 Axes>

我该如何解决？

代码：

import matplotlib.pyplot as plt

from sklearn import datasets
from sklearn.decomposition import PCA
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis

import pandas as pd

df = pd.read_csv('https://gist.githubusercontent.com/tijptjik/9408623/raw/b237fa5848349a14a14e5d4107dc7897c21951f5/wine.csv')
df.to_numpy()

X  = df.iloc[:,[1,2,3,4,5,6,7,8,9,10,11,12,13]]
X.to_numpy()
y  = df.iloc[:,[0]]
y.to_numpy()
target_names = y

pca = PCA(n_components=2)
X_r = pca.fit(X).transform(X)

lda = LinearDiscriminantAnalysis(n_components=2)
X_r2 = lda.fit(X, y).transform(X)

# Percentage of variance explained for each components
print('explained variance ratio (first two components): %s'
      % str(pca.explained_variance_ratio_))

plt.figure()
colors = ['navy', 'turquoise', 'darkorange']
lw = 2

for color, i, target_name in zip(colors, [0, 1, 2], target_names):
    plt.scatter(X_r[y == i, 0], X_r[y == i, 1], color=color, alpha=.8, lw=lw,
                label=target_name)

Answer 1

如果您查看示例脚本中的y 与y，您将看到您的y 具有多个维度，即使第二个暗淡的长度为0。您需要删除此第二个维度可以通过np.squeeze完成

y = np.squeeze(df.loc[:,['Wine']].to_numpy())

这是完整的代码

import matplotlib.pyplot as plt
import pandas as pd
import numpy as np

from sklearn import datasets
from sklearn.decomposition import PCA
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis

df = pd.read_csv('https://gist.githubusercontent.com/tijptjik/9408623/raw/b237fa5848349a14a14e5d4107dc7897c21951f5/wine.csv')

X = df.loc[:, df.columns != 'Wine'].to_numpy()
y = np.squeeze(df.loc[:,['Wine']].to_numpy())
target_names = ['first', 'sceond', 'third']

pca = PCA(n_components=2)
X_r = pca.fit(X).transform(X)

lda = LinearDiscriminantAnalysis(n_components=2)
X_r2 = lda.fit(X, y).transform(X)


lda = LinearDiscriminantAnalysis(n_components=2)
X_r2 = lda.fit(X, y).transform(X)

# Percentage of variance explained for each components
print('explained variance ratio (first two components): %s'
    % str(pca.explained_variance_ratio_))

plt.figure()
colors = ['navy', 'turquoise', 'darkorange']
lw = 2

for color, i, target_name in zip(colors, [1,2,3], target_names):
    plt.scatter(X_r[y == i, 0], X_r[y == i, 1], color=color, alpha=.8, lw=lw,
                label=target_name)
plt.legend(loc='best', shadow=False, scatterpoints=1)
plt.title('PCA of Wine dataset')

plt.figure()
for color, i, target_name in zip(colors, [1, 2, 3], target_names):
    plt.scatter(X_r2[y == i, 0], X_r2[y == i, 1], alpha=.8, color=color,
                label=target_name)
plt.legend(loc='best', shadow=False, scatterpoints=1)
plt.title('LDA of Wine dataset')

plt.show()