Question

我的Python代码中有一个自定义类，用于处理k-means聚类。该类采用一些自定义群集的参数，但是从传递给该类的列表中减去两个值时，出现以下错误：

    Traceback (most recent call last):
  File "/home/dev/PycharmProjects/KMeans/KMeansApplication.py", line 22, in <module>
    application()
  File "/home/dev/PycharmProjects/KMeans/KMeansApplication.py", line 16, in application
    opt_num_clusters = cluster_calculator.calculate_optimum_clusters()
  File "/home/dev/PycharmProjects/KMeans/ClusterCalculator.py", line 19, in calculate_optimum_clusters
    self.init_opt_line()
  File "/home/dev/PycharmProjects/KMeans/ClusterCalculator.py", line 33, in init_opt_line
    self. m = (self.sum_squared_dist[0] - self.sum_squared_dist[1]) / (1 - self.calc_border)
TypeError: unsupported operand type(s) for -: 'KMeans' and 'KMeans'

这是我的自定义类的代码：

import KMeansClusterer
from math import sqrt, fabs
from matplotlib import pyplot as plp

class ClusterCalculator:
    m = 0
    b = 0
    sum_squared_dist = []
    derivates = []
    distances = []
    line_coordinates = []

    def __init__(self, calc_border, data):
        self.calc_border = calc_border
        self.data = data

    def calculate_optimum_clusters(self):
        self.calculate_squared_dist()
        self.init_opt_line()
        self.calc_distances()
        self.calc_line_coordinates()
        opt_clusters = self.get_optimum_clusters()
        print("Evaluated", opt_clusters, "as optimum number of clusters")
        return opt_clusters


    def calculate_squared_dist(self):
        for k in range(1, self.calc_border):
            kmeans = KMeansClusterer.KMeansClusterer(k, self.data)
            self.sum_squared_dist.append(kmeans.calc_custom_params(self.data, k))

    def init_opt_line(self):
        #here the error is thrown
        self. m = (self.sum_squared_dist[0] - self.sum_squared_dist[1]) / (1 - self.calc_border)
        self.b = (1 * self.sum_squared_dist[0] - self.calc_border*self.sum_squared_dist[0]) / (1 - self.calc_border)

    def calc_y_value(self, x_calc):
        return self.m * x_calc + self.b

    def calc_line_coordinates(self):
        for i in range(1, self.calc_border):
            self.line_coordinates.append(self.calc_y_value(i))

    def calc_distances(self):
        for i in range(1, self.calc_border):
            self.distances.append(sqrt(fabs(self.calc_y_value(i))))
        print("For border", self.calc_border, ", calculated the following distances: \n", self.distances)

    def get_optimum_clusters(self):
        return self.distances.index((max(self.distances)))

    def plot_results(self):
        plp.plot(range(1, self.calc_border), self.sum_squared_dist, "bx-")
        plp.plot(range(1, self.calc_border), self.line_coordinates, "bx-")
        plp.xlabel("Number of clusters")
        plp.ylabel("Sum of squared distances")
        plp.show()

我还附加了KMeansClusterer，因为sum_squared_dist在那里填充了值：

from sklearn.cluster import KMeans
from matplotlib import pyplot as plp
class KMeansClusterer:
    def __init__(self, clusters, data):
        self.clusters = clusters
        self.data = data

    def cluster(self):
        kmeans = KMeans(n_clusters=self.cluster(), random_state=0).fit(self.data)
        print("Clustered", len(kmeans.labels_), "GTINs")
        for i, cluster_center in enumerate(kmeans.cluster_centers_):
            plp.plot(cluster_center, label="Center {0}".format(i))
        plp.legend(loc="best")
        plp.show()

    def calc_custom_params(self, data_frame, clusters):
        kmeans = KMeans(n_clusters=clusters, random_state=0).fit(data_frame)
        return kmeans

    def cluster_without_plot(self):
        return KMeans(n_clusters=self.cluster(), random_state=0).fit(self.data)

我无法想象为什么不支持'-'，我试图减去两个整数类型和1的列表值和一个整数变量。

Answer 1

KMeans.fit()返回一个类实例，这意味着calc_custom_params()返回一个类实例，因此您的列表sum_squared_dist不包含整数，元素是sklearn.cluster.KMeans类的对象

Answer 2

Python无法自动减去类。您需要在您的类上实现__sub__方法，以便python知道如何处理减去这些类。您可以在https://docs.python.org/3/library/operator.html

中找到完整的参考

Python未知操作数类型-用于自定义类

2 个答案: