EEG上k-means的一次实验

数据读取

data=np.loadtxt("/Users/rain/Downloads/EEG/DEAP/EEG_feature.txt")
#我们读入所有的可能的
label1=np.loadtxt("/Users/rain/Downloads/EEG/DEAP/valence_arousal_label.txt")
label2=np.loadtxt("/Users/rain/Downloads/EEG/DEAP/subject_video.txt")

计算欧式距离

def distEclud(x,y):
    return np.sqrt(np.sum((x-y)**2))

产生随机的聚类中心

def randCent(dataSet,k):
    m,n = dataSet.shape
    #先将中心全置为0
    centroids = np.zeros((k,n))
    for i in range(k):
        index = int(np.random.uniform(0,m)) #随机生成中心
        centroids[i,:] = dataSet[index,:]
    return centroids

进行聚类

def KMeans(dataSet,k):
    m = np.shape(dataSet)[0]  #行的数目
    # 第一列存样本属于哪一簇
    # 第二列存样本的到簇的中心点的误差
    clusterAssment = np.mat(np.zeros((m,2)))
    clusterChange = True
    # 第1步 初始化centroids
    centroids = randCent(dataSet,k)
    while clusterChange:
        clusterChange = False
        # 遍历所有的样本（行数）
        for i in range(m):
            minDist = 100000.0
            minIndex = -1
            # 遍历所有的聚类中心
            #第2步 找出最近的聚类中心
            for j in range(k):
                # 计算该样本到质心的欧式距离
                distance = distEclud(centroids[j,:],dataSet[i,:])
                if distance < minDist:
                    minDist = distance
                    minIndex = j
            # 第 3 步：更新每一行样本所属的类
            if clusterAssment[i,0] != minIndex:
                clusterChange = True
                clusterAssment[i,:] = minIndex,minDist**2
        #第 4 步：更新聚类中心
        for j in range(k):
            pointsInCluster = dataSet[np.nonzero(clusterAssment[:,0].A == j)[0]]  # 获取类所有的点
            centroids[j,:] = np.mean(pointsInCluster,axis=0)   
            		# 对矩阵的行求均值
    print("Cluster complete!")
    #返回聚类中心和聚类结果（包括分类和最小距离）
    return centroids,clusterAssment

进行k-means分类
对k=2进行聚类

k=2
centroids,clusterAssment = KMeans(data,k)
kind=clusterAssment[:,0:1]
kind=np.reshape(kind,-1)
kind

kind[0,0:100]
matrix([[0.,0.,0.,0.,0.,0.,0.,0.,0.,0.,0.,0.,0.,0.,0.,0.,
         0.,0.,0.,0.,0.,0.,0.,0.,0.,0.,0.,0.,0.,0.,0.,0.,
         0.,0.,0.,0.,0.,0.,0.,0.,0.,0.,0.,0.,0.,0.,0.,0.,
         0.,0.,0