python - 为 3D 绘图自动创建图例

Question

我正在尝试更新以下函数以通过图例报告集群信息:

color_names = ["red", "blue", "yellow", "black", "pink", "purple", "orange"]

def plot_3d_transformed_data(df, title, colors="red"):
 
  ax = plt.figure(figsize=(12,10)).gca(projection='3d')
  #fig = plt.figure(figsize=(8, 8))
  #ax = fig.add_subplot(111, projection='3d')
  

  if type(colors) is np.ndarray:
    for cname, class_label in zip(color_names, np.unique(colors)):
      X_color = df[colors == class_label]
      ax.scatter(X_color[:, 0], X_color[:, 1], X_color[:, 2], marker="x", c=cname, label=f"Cluster {class_label}" if type(colors) is np.ndarray else None)
  else:
      ax.scatter(df.Type, df.Length, df.Freq, alpha=0.6, c=colors, marker="x", label=str(clusterSizes)  )

  ax.set_xlabel("PC1: Type")
  ax.set_ylabel("PC2: Length")
  ax.set_zlabel("PC3: Frequency")
  ax.set_title(title)
  
  if type(colors) is np.ndarray:
    #ax.legend()
    plt.gca().legend()
    
  
  plt.legend(bbox_to_anchor=(1.04,1), loc="upper left")
  plt.show()

所以我调用我的函数来可视化集群模式:

plot_3d_transformed_data(pdf_km_pred,
                         f'Clustering rare URL parameters for data of date: {DATE_FROM}  \nMethod: KMeans over PCA \nn_clusters={n_clusters} , Distance_Measure={DistanceMeasure}',
                         colors=pdf_km_pred.prediction_km)

print(clusterSizes)

遗憾的是我无法显示图例，我必须在 3D 绘图下手动打印集群成员。这是没有图例的输出，有以下错误: No handles with labels found to put in legend.
我检查这个 post ，但我无法弄清楚正确传递集群标签列表的功能错误是什么。我想更新该函数，以便我可以通过 clusterSizes.index 演示集群标签和他们的规模通过 clusterSizes.size 预期输出:如 here建议更好地使用 legend_elements()确定要显示的有用数量的图例条目并自动返回句柄和标签的元组。
更新:正如我在预期输出中提到的，应该包含一个集群标签图例和另一个集群大小图例(每个集群中的实例数)。它也可能通过单个图例报告此信息。
请参阅下面的 2D 示例:

Answer 1

在可视化集群的函数中，您需要 ax.legend而不是 plt.legend

from matplotlib import pyplot as plt
from mpl_toolkits.mplot3d.axes3d import Axes3D
import numpy as np
import pandas as pd

color_names = ["red", "blue", "yellow", "black", "pink", "purple", "orange"]

def plot_3d_transformed_data(df, title, colors="red"):
 
  ax = plt.figure(figsize=(12,10)).gca(projection='3d')
  #fig = plt.figure(figsize=(8, 8))
  #ax = fig.add_subplot(111, projection='3d')
  

  if type(colors) is np.ndarray:
    for cname, class_label in zip(color_names, np.unique(colors)):
      X_color = df[colors == class_label]
      ax.scatter(X_color[:, 0], X_color[:, 1], X_color[:, 2], marker="x", c=cname, label=f"Cluster {class_label}" if type(colors) is np.ndarray else None)
  else:
      ax.scatter(df.Type, df.Length, df.Freq, alpha=0.6, c=colors, marker="x", label=str(clusterSizes)  )

  ax.set_xlabel("PC1: Type")
  ax.set_ylabel("PC2: Length")
  ax.set_zlabel("PC3: Frequency")
  ax.set_title(title)
  
  if type(colors) is np.ndarray:
    #ax.legend()
    plt.gca().legend()
    
  
  ax.legend(bbox_to_anchor=(.9,1), loc="upper left")
  plt.show()

clusterSizes = 10

test_df = pd.DataFrame({'Type':np.random.randint(0,5,10),
                        'Length':np.random.randint(0,20,10),
                        'Freq':np.random.randint(0,10,10),
                        'Colors':np.random.choice(color_names,10)})

plot_3d_transformed_data(test_df,
                         'Clustering rare URL parameters for data of date:haha\nMethod: KMeans over PCA \nn_clusters={n_clusters} , Distance_Measure={DistanceMeasure}',
                         colors=test_df.Colors)

运行此示例代码，您将获得预期的图例句柄