如何使用不同的数据帧设置轴向散布参数来获得散布3D-Plot？ [英] How can get scatter 3D-plot using different dataframes to set ax.scatter parameters?

问题描述

最近，我很难使用两个不同的数据帧来演示3D散点图。我们的想法是提供一个3D散点图，包括两个图例，用于报告集群算法的结果。假设我们有主数据帧df1包含以下3个功能：

+-----+------------+----------+----------+
|   id|           x|         y|         z|
+-----+------------+----------+----------+
| row0|  -6.0776997|-2.9096103|-1.5181729|
| row1|  -1.0122601|  7.322841|-5.4424076|
| row2|   -8.297007| 6.3228936| 1.1672047|
| row3|  -3.5071216|  4.784812|-5.4449472|
| row4|   -5.122823|-3.3220499|-0.5069805|
| row5|  -2.4764006|  8.255791|  4.409478|
| row6|   7.3153954| -5.079449| -7.291215|
| row7|  -2.0167463|  9.303454|  7.095179|
| row8|  -0.2338185| -4.892681| 2.1228876|
| row9|    6.565442| -6.855994|-6.7983212|
|row10|  -5.6902847|-6.4827404|-0.9246967|
|row11|-0.017986143| 2.7632365| -8.814824|
|row12|  -6.9042625|-6.1491723|-3.5354295|
|row13|  -10.389865|  9.537853|  0.674591|
|row14|   3.9688683|-6.0467844| -5.462389|
|row15|   -7.337052|-3.7689247| -5.261122|
|row16|   -8.991589|  8.738728|  3.864116|
|row17| -0.18098584|  5.482743| -4.900118|
|row18|   3.3193955|-6.3573766| -6.978025|
|row19|  -2.0266335|-3.4171724|0.48218703|
+-----+------------+----------+----------+

现在，我以datafaramedf2的形式获得了来自集群算法的信息，如下所示：

print("==========================Short report==================================== ")

n_clusters = model.summary.k
#n_clusters
print("Number of predicted clusters: " + str(n_clusters))

cluster_Sizes = model.summary.clusterSizes
#cluster_Sizes 

col = ['size']
df2 = pd.DataFrame(cluster_Sizes, columns=col).sort_values(by=['size'], ascending=True)  #sorting
cluster_Sizes = df2["size"].unique()
print("Size of predicted clusters: " + str(cluster_Sizes))
clusterSizes

#==========================Short report==================================== 
#Number of predicted clusters: 10
#Size of predicted clusters: [ 486  496  504  529  985  998  999 1003 2000]

+-----+----------+
|     |prediction|
+-----+----------+
|    2|       486|
|    6|       496|
|    0|       504|
|    8|       529|
|    5|       985|
|    9|       998|
|    7|       999|
|    3|      1003|
|    1|      2000|
|    4|      2000|
+-----+----------+

所以这里的索引列是预测的集群标签。我可以将预测的集群标签分配到主数据帧中，但不能分配集群大小，如下所示：

+-----+----------+------------+----------+----------+
|   id|prediction|           x|         y|         z|
+-----+----------+------------+----------+----------+
| row0|         9|  -6.0776997|-2.9096103|-1.5181729|
| row1|         4|  -1.0122601|  7.322841|-5.4424076|
| row2|         1|   -8.297007| 6.3228936| 1.1672047|
| row3|         4|  -3.5071216|  4.784812|-5.4449472|
| row4|         3|   -5.122823|-3.3220499|-0.5069805|
| row5|         1|  -2.4764006|  8.255791|  4.409478|
| row6|         5|   7.3153954| -5.079449| -7.291215|
| row7|         1|  -2.0167463|  9.303454|  7.095179|
| row8|         7|  -0.2338185| -4.892681| 2.1228876|
| row9|         5|    6.565442| -6.855994|-6.7983212|
|row10|         3|  -5.6902847|-6.4827404|-0.9246967|
|row11|         4|-0.017986143| 2.7632365| -8.814824|
|row12|         9|  -6.9042625|-6.1491723|-3.5354295|
|row13|         1|  -10.389865|  9.537853|  0.674591|
|row14|         2|   3.9688683|-6.0467844| -5.462389|
|row15|         9|   -7.337052|-3.7689247| -5.261122|
|row16|         1|   -8.991589|  8.738728|  3.864116|
|row17|         4| -0.18098584|  5.482743| -4.900118|
|row18|         2|   3.3193955|-6.3573766| -6.978025|
|row19|         7|  -2.0266335|-3.4171724|0.48218703|
+-----+----------+------------+----------+----------+

现在想包括 报告3D散点图它除了通过以下功能外，还通过2个单独的图例绘制：

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

def plot_3d_transformed_data(df, title, colors="red"):
 
  # Imports.
  import matplotlib as mpl
  import matplotlib.pyplot as plt
  from mpl_toolkits.mplot3d import Axes3D
  import pandas as pd
  import numpy as np
  import plotly.express as px
  import matplotlib.cm as cm

  # Figure.
  figure = plt.figure(figsize=(12, 10))
  ax = figure.add_subplot(projection="3d")
  ax.set_xlabel("PC1: x")
  ax.set_ylabel("PC2: y")
  ax.set_zlabel("PC3: z")
  ax.set_title("scatter 3D legend") 

  # Data and 3D scatter.
  #colors = ["red", "blue", "yellow", "black", "pink", "purple", "orange", "black", "red" ,"blue"]
  colors = cm.rainbow(np.linspace(0, 1, len(cluster_Sizes)))

  # Create your plot
  #px.scatter(df1, x='x', y='y', size=df2['size'], color='jet')
  sc = ax.scatter(df1.x, df1.y, df1.z, alpha=0.6, c=colors, sizes=df2['size'], marker="o")

  # Legend 1.
  handles, labels = sc.legend_elements(prop="sizes", alpha=0.6)
  legend1 = ax.legend(handles, labels, bbox_to_anchor=(1, 1), loc="upper right", title="Sizes")
  ax.add_artist(legend1) # <- this is important.

  # Legend 2.
  unique_colors = set(colors)
  handles = []
  labels = []
  for n, color in enumerate(unique_colors, start=1):
      artist = mpl.lines.Line2D([], [], color=color, lw=0, marker="o")
      handles.append(artist)
      labels.append(str(n))
  legend2 = ax.legend(handles, labels, bbox_to_anchor=(0.05, 0.05), loc="lower left", title="Classes")

  figure.show() 

问题是创建合适的色彩映射表支持簇号(避免ValueError: 'c' argument has 9 elements, which is inconsistent with 'x' and 'y' with size 10000.)，并找到两个数据帧之间大小不匹配的解决方案(避免ValueError: s must be a scalar, or the same size as x and y)以用于：

sc = ax.scatter(df1.x,
                df1.y,
                df1.z,
                alpha=0.6,
                c=colors,   #colors=cm.rainbow(np.linspace(0, 1, len(cluster_Sizes)))
                s=df2['size'],
                marker="o")

所以有一个想法是，我将df2['size']赋给df1，但这很昂贵，而且不是一个好主意。所以我想知道是否有一种很好的方法来更新def plot_3d_transformed_data()，并使用它来更好地可视化可以通过一个曲线图来指示预测的星团标签和星团大小。为了快速调试，我提供了一个colab notebook。

预期产量如下：

推荐答案

我尝试使用更新的Colab仅复制绘图部分。我追踪了你的代码，注意到了一些东西。我认为运行函数的错误是因为颜色的数量与数据的数量不匹配。通过仅从代码中剪切重要数据，可以将图表创建为20个数据。

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

def plot_3d_transformed_data(df, title, colors="red"):

  # Imports.
  import matplotlib as mpl
  import matplotlib.pyplot as plt
  from mpl_toolkits.mplot3d import Axes3D
  import pandas as pd
  import numpy as np
  import plotly.express as px
  import matplotlib.cm as cm

  #clusterSizes = pd.read_csv(io.StringIO(data1), delim_whitespace=True)

  #pddf_pred = df_pred.set_index('id')
  cluster_Sizes = clusterSizes["size"].unique()
  #x_train = np.random.randint(20,500,(20,))

  # Figure.
  figure = plt.figure(figsize=(12, 10))
  ax = figure.add_subplot(projection="3d")
  ax.set_xlabel("PC1: x")
  ax.set_ylabel("PC2: y")
  ax.set_zlabel("PC3: z")
  ax.set_title("scatter 3D legend") 

  colors2 = ["red", "blue", "yellow", "black", "pink", "purple", "orange", "black", "red" ,"blue"]
  colors = cm.rainbow(np.linspace(0, 1, 20))

  # Create 3D scatter plot
  sc = ax.scatter(pddf_pred.x.values, pddf_pred.y.values, pddf_pred.z.values, alpha=0.6, s=x_train, c=colors, marker="o")

  # Legend 1.
  handles, labels = sc.legend_elements(prop="sizes", alpha=0.6)
  legend1 = ax.legend(handles, labels, bbox_to_anchor=(1.2, 1), loc="upper right", title="Sizes")
  ax.add_artist(legend1)

  # Legend 2.
  unique_colors = set(colors2)
  handles = []
  labels = []
  for n, color in enumerate(unique_colors, start=1):
      artist = mpl.lines.Line2D([], [], color=color, lw=0, marker="o")
      handles.append(artist)
      labels.append(str(n))
  legend2 = ax.legend(handles, labels, bbox_to_anchor=(-0.05, 0.05), loc="lower left", title="Classes")

  plt.show()

这篇关于如何使用不同的数据帧设置轴向散布参数来获得散布3D-Plot？的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！