python - 名称错误 : name 'assigs' is not defined

Question

我在我的数据集上应用了 scikit-learn 形式的 kmeans 方法，然后尝试绘制数据和我的集群，但不断收到错误，并且不知道还要做什么。

这是我现在的代码:

    from sklearn.cluster import KMeans
    from sklearn.metrics import silhouette_score

    def construct_dict(list_keys, list_values):
      res = {}
      for i in range(len(list_keys)):
      k=list_keys[i]
      for v in set(list_values):
          res[k]=res.get(k,{})
          res[k][v]=res[k].get(v,0)
          res[k][list_values[i]]+=1
      return res

    def print_result(matrix, assigs, y): 
      pred=list(set(y))
      res = construct_dict(assigs,y)
      print(res, "is a clustering obtained when K=", nclusts)
      silhouette_avg = silhouette_score(matrix, assigs)  #Compute the mean 
      Silhouette Coefficient of all samples
      print("For %d clusters the average sillouette score is: %f" % (nclusts, silhouette_avg))
      return res

    def bcubed(assigs, y, calcule='precision'):
      #calcule = precision ou recall
      summatory = 0.0
      n = len(y)
      if calcule=='precision':
         list_dicts = construct_dict(assigs,y).values()
      elif calcule=='recall':
         list_dicts = construct_dict(y,assigs).values()
      for dic in list_dicts:
         values_dict= dic.values()
         n_elem_dic=sum(values_dict)
      for value in values_dict:
        summatory +=(value-1)*value/n_elem_dic
      return summatory/n


  def k_means(nclusts, matrix, y):
     kmeans = KMeans(n_clusters=nclusts, random_state=0).fit(matrix)
     assigs=list(kmeans.labels_)
     res=print_result(matrix, assigs, y)
     print('Precision BCubed:',bcubed(assigs,y))
     print('Recall BCubed:',bcubed(assigs,y,'recall'))
     return assigs

  for nclusts in [2,3,4,5,10,20,30]:
     k_means(nclusts, X_pca, y)
     print("--------------")

输出:

{0: {'ALL': 12, 'AML': 14}, 1: {'ALL': 35, 'AML': 11}} is a clustering
obtained when K= 2 For 2 clusters the average sillouette score is:
0.147925 Precision BCubed: 0.5602471200297287 Recall BCubed: 0.5528841607565012

...

    import pandas as pd
    from matplotlib import pyplot as plt
    pd.DataFrame(X_pca).T.plot()
    plt.show()

输出:情节很好。

现在给我错误的部分是:

    import pandas as pd
    k_means(5,X_pca,y)
    pd.DataFrame(assigs).T.plot()
    plt.show()

输出:

NameError: name 'assigs' is not defined

我做错了什么？

Answer 1

您似乎没有保存 kmeans 返回的内容。这有效吗？

import pandas as pd
assigs = k_means(5,X_pca,y)
pd.DataFrame(assigs).T.plot()
plt.show()