Python: 在数据集中每个类别中随机抽取两个样本

'''
auther: DeniuHe
date:2020-08-01
'''
import numpy as np
from sklearn import datasets
from scipy.spatial.distance import pdist,squareform
from sklearn.model_selection import train_test_split
from collections import OrderedDict
from itertools import combinations,product

def initLabeled(y):
    ## random selected the labeled instances' index
    labeledIndex = []
    labelDict = OrderedDict()
    for label in np.unique(y):
        labelDict[label] = []
    for i,label in enumerate(y):
        labelDict[label].append(i)
    for value in labelDict.values():
        for idx in np.random.choice(value,size=2,replace=False,p=None):
            labeledIndex.append(idx)
    return labeledIndex




if __name__ == '__main__':

    data, target = datasets.load_iris(return_X_y=True)
    X, X_test, y, y_test = train_test_split(data, target, test_size=0.1, random_state=0)
    ####------初始化已标记数据-----###
    print(y[initLabeled(y)])