LDA降维

feature_dict = {i:label for i,label in zip(range(4),('spepal length in cm','spepal width in cm','petal length in cm','petal width in cm'))}

import pandas as pd

df = pd.io.parsers.read_csv(filepath_or_buffer='链接（省略）',header=None,sep=',',)
df columns = [l for i,l in sorted(feature_dict.items())] + ['class label']
df.dropna(how="all",inplace=True)

df.tail()

映射：将y变成可衡量的数据格式

from sklearn.preprocessing import LabelEncoder

X = df[['spepal length in cm','spepal width in cm','petal length in cm','petal width in cm']].values
y = df['class label'].values

enc = LabelEncoder()
label_encoder = enc.fit(y)
y = label_encoder.transform(y) + 1

转化后的结果：

每类样例的均值：
import numpy as np
np.set_printoptions(precision=4)

mean_vectors = []
for c1 in range(1,4):
  mean_vectors.append(np.mean(X[y==c1],axis=0)
  print('Mean vector class %s:%s\n'%(c1,mean_vectors[c1-1]))