'int' 对象没有属性 'flatten'

Question

我正在编写一个代码，这给了我一个错误提示 'int' object has no attribute 'flatten'。我正在使用 k=2 的 kmean 算法对我的数据进行聚类（作为数据点列表传递）。

import csv
import numpy as np
k=2
data=[23,43,67,89,1,10,101,243,34]
clusters = [[] for i in range(k)]
def kmeans(data, k):
    centroids = []
    centroids = randomize_centroids(data, centroids, k)  
    old_centroids = [[] for i in range(k)] 
    iterations = 0
    while not (has_converged(centroids, old_centroids, iterations)):
        iterations += 1
        clusters = euclidean_dist(data, centroids, clusters) # assign data points to clusters
        index =0   # recalculate centroids
        for cluster in clusters:
            old_centroids[index] = centroids[index]
            centroids[index] = np.mean(cluster, axis=0).tolist()
            index += 1
    print("The total number of data instances is: " + str(len(data)))
    print("The total number of iterations necessary is: " + str(iterations))
    print("The means of each cluster are: " + str(centroids))
    print("The clusters are as follows:")
    for cluster in clusters:
        print("Cluster with a size of " + str(len(cluster)) + " starts here:")
        print(np.array(cluster).tolist())
        print("Cluster ends here.")
# Calculates euclidean distance between
# a data point and all the available cluster
# centroids.    
def euclidean_dist(data, centroids, clusters):
    for instance in data:   # Find which centroid is the closestto the given data point.
        print("hello")
        mu_index = min([(i[0], np.linalg.norm(instance-centroids[i[0]])) \
                            for i in enumerate(centroids)], key=lambda t:t[1])[0]
        try:
            clusters[mu_index].append(instance)
        except KeyError:
            clusters[mu_index] = [instance]

    # If any cluster is empty then assign one point
    # from data set randomly so as to not have empty
    # clusters and 0 means.        
    for cluster in clusters:
        if not cluster:
           cluster.append(data[np.random.randint(0, len(data), size=1)].flatten().tolist())
    return clusters


# randomize initial centroids
def randomize_centroids(data, centroids, k):
    for cluster in range(0, k):
        print("hello")
        centroids.append(data[np.random.randint(0, len(data), size=1)].flatten().tolist())
    return centroids


# check if clusters have converged    
def has_converged(centroids, old_centroids, iterations):
    MAX_ITERATIONS = 1000
    if iterations > MAX_ITERATIONS:
        return True
    return old_centroids == centroids


if __name__=='__main__' :
    kmeans([23,43,67,89,1,10,101,243,34],2)
    print("hello")

Traceback（最近一次调用最后一次）：

文件“C:\Users\shri ram\Desktop\summer_code_files\ddpcr_analysis.py”，第 66 行，在 kmeans([23,43,7,89,1,10,101,243,34,2],2) 文件“C:\Users\shri ram\Desktop\summer_code_files\ddpcr_analysis.py”，第 13 行，kmeans

clusters = euclidean_dist(data, centroids, clusters) # 将数据点分配给集群

UnboundLocalError: 赋值前引用了局部变量“clusters”

Answer 1

如 cmets 中所述，您尝试将 flatten 应用于一个 int 元素（而不是 numpy 数组）。试试

centroids.append([data[np.random.randint(0, len(data), size=1)]])

而不是

centroids.append(data[np.random.randint(0, len(data), size=1)].flatten().tolist())

另外，您应该将 clusters 初始化移动到 kmeans 函数

...
def kmeans(data, k):
    clusters = [[] for i in range(k)]
    centroids = []
    centroids = randomize_centroids(data, centroids, k)  
    ...