小编pca*_*pca的帖子

我的代码:

from numpy import *

def pca(orig_data):
    data = array(orig_data)
    data = (data - data.mean(axis=0)) / data.std(axis=0)
    u, s, v = linalg.svd(data)
    print s #should be s**2 instead!
    print v

def load_iris(path):
    lines = []
    with open(path) as input_file:
        lines = input_file.readlines()
    data = []
    for line in lines:
        cur_line = line.rstrip().split(',')
        cur_line = cur_line[:-1]
        cur_line = [float(elem) for elem in cur_line]
        data.append(array(cur_line))
    return array(data)

if __name__ == '__main__':
    data = load_iris('iris.data')
    pca(data)

虹膜数据集:http://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data

输出:

[ 20.89551896 …