Question

 import numpy as np
 import matplotlib.pyplot as plt
 from matplotlib import style
 import pandas as pd 
 import time

 start_time = time.time()

 style.use('ggplot')

 class K_Means:
      def __init__(self, k =3, tolerance = 0.0001, max_iterations = 500):
      self.k = k
    self.tolerance = tolerance
    self.max_iterations = max_iterations

    def fit(self, data):

    self.centroids = {}

    #initialize the centroids, the first 'k' elements in the dataset will be our initial centroids
    for i in range(self.k):
        self.centroids[i] = data[i]

    #begin iterations
    for i in range(self.max_iterations):
        self.classes = {}
        for i in range(self.k):
            self.classes[i] = []

        #find the distance between the point and cluster; choose the nearest centroid
        for features in data:
            distances = [np.linalg.norm(features - self.centroids[centroid]) for centroid in self.centroids]
            classification = distances.index(min(distances))
            self.classes[classification].append(features)

        previous = dict(self.centroids)

        #average the cluster datapoints to re-calculate the centroids
        for classification in self.classes:
            self.centroids[classification] = np.average(self.classes[classification], axis = 0)

        isOptimal = True

        for centroid in self.centroids:

            original_centroid = previous[centroid]
            curr = self.centroids[centroid]

            if np.sum((curr - original_centroid)/original_centroid * 100.0) > self.tolerance:
                isOptimal = False

        #break out of the main loop if the results are optimal, ie. the centroids don't change their positions much(more than our tolerance)
        if isOptimal:
            break

def pred(self, data):
    distances = [np.linalg.norm(data - self.centroids[centroid]) for centroid in self.centroids]
    classification = distances.index(min(distances))
    return classification

def main():


#df = pd.read_csv(r"ipl.csv")
df = pd.read_csv(r"CustomerData4.csv",nrows=200)
#df = df[['one', 'two']]
df=df[['MRank','FRank','RRank']]
dataset = df.astype(float).values.tolist()
X = df.values 

#df 
dataset = df.astype(float).values.tolist()
X = df.values #returns a numpy array

km = K_Means(5)

km.fit(X)
#y_kmeansP=km.fit(X)

# Plotting starts here
colors = 10*["r", "g", "c", "b", "k"]
#prediction = pd.DataFrame(km.fit(X), columns=['predictions']).to_csv('prediction.csv')

for centroid in km.centroids:
    plt.scatter(km.centroids[centroid][0], km.centroids[centroid][1], s = 130, marker = "x")




for classification in km.classes:
    color = colors[classification]
    for features in km.classes[classification]:
        print(classification)
        df['Cluster'] = classification
        plt.scatter(features[0], features[1], color = color,s = 30)


df.to_csv("clusteringfromscrtach.csv")
#plt.show()
print("--- %s seconds ---" % (time.time() - start_time))

  if __name__ == "__main__":
     main()

这是从头开始进行K均值聚类的代码我想导出添加了一列的数据框，该列是集群，我使用那一行tdf ['Cluster'] =分类将名为Cluster的新列添加到我的数据框，但只添加了一个集群'4' 其他集群是0 1 2 3 解决此问题的任何方法

Answer 1

df['Cluster'] = classification

很显然，您已将该列覆盖了k次。

相反，将结果合并为一列。

还将代码标记在更大的数据上...

从头开始进行K均值聚类（Python）

1 个答案: