python - 创建堆积条形图并用计数和百分比进行注释

Question

我有以下数据框

import pandas as pd
import matplotlib.pyplot as plt
import matplotlib 
print('matplotlib: {}'.format(matplotlib.__version__))
# 3.5.3

df=pd.DataFrame({'Type': [ 'Sentence', 'Array', 'String', '-','-', 'Sentence', 'Array', 'String', '-','-', 'Sentence'],
                 'Length': [42,21,11,6,6,42,21,11,6,6,42],
                 'label': [1,1,0,0,0,1,1,0,0,0,1],
                 })
print(df)
#       Type     Length  label
#0   Sentence      42      1
#1      Array      21      1
#2     String      11      0
#3          -       6      0
#4          -       6      0
#5   Sentence      42      1
#6      Array      21      1
#7     String      11      0
#8          -       6      0
#9          -       6      0
#10  Sentence      42      1

我想为数据框中的任意列绘制堆积条形图(数字，例如 Length 列或 categorical 例如 Type 列)并相对于 label 进行堆叠使用计数/百分比注释的列，其中还显示罕见观察值的小值。以下脚本给出了错误的结果:

ax = df.plot.bar(stacked=True)

#ax = df[["Type","label"]].plot.bar(stacked=True)
#ax = df.groupby('Type').size().plot(kind='bar', stacked=True)

ax.legend(["0: normanl", "1: Anomaly"])
for p in ax.patches:
    width, height = p.get_width(), p.get_height()
    x, y = p.get_xy() 
    ax.text(x+width/2, 
            y+height/2, 
            '{:.0f} %'.format(height), 
            horizontalalignment='center', 
            verticalalignment='center')

我可以想象，我需要以某种方式计算所选列相对于 label 的计数栏目:

## counts will be used for the labels
counts = df.apply(lambda x: x.value_counts())

## percents will be used to determine the height of each bar
percents = counts.div(counts.sum(axis=1), axis=0)

我尝试使用 df.groupby(['selcted column', 'label'] 来解决该问题不成功。我在这个Google Colab Notebook 中收集了所有可能的解决方案尽管如此，我找不到一种直接的方法来适应数据框架。

到目前为止，我已经尝试了以下受此启发的解决方案 post通过使用 df.groupby(['selcted column', 'label'] 解决问题不成功，我得到了 TypeError: unsupported operand type(s) for +: 'int' and 'str' for total = sum(dff.sum())不知道问题出在哪里？在索引中或 df转型。

顺便说一句，我在这个 Google Colab Notebook 中收集了所有可能的解决方案尽管如此，我找不到一种直接的方法来通过 Mathplotlib 适应数据帧。 。所以我正在寻找一种优雅的使用方式 Seaborn或plotly .

df = df.groupby(["Type","label"]).count()
#dfp_Type   = df.pivot_table(index='Type', columns='label', values= 'Length', aggfunc='mean') 
dfp_Type   = df.pivot_table(index='Type', columns='label', values= df.Type.size(), aggfunc='mean') 
#dfp_Length = df.pivot_table(index='Length', columns='label', values= df.Length.size(), aggfunc='mean') 

ax = dfp_Type.plot(kind='bar', stacked=True, rot=0) 

# iterate through each bar container
for c in ax.containers: labels = [v.get_height() if v.get_height() > 0 else '' for v in c]

# add the annotations
ax.bar_label(c, fmt='%0.0f%%', label_type='center')

# move the legend
ax.legend(title='Class', bbox_to_anchor=(1, 1.02), loc='upper left')

plt.show()

输出:

预期输出:

Answer 1

• 预期输出中的值与OP中的df不匹配，因此示例DataFrame已更新。

• 用 pandas.DataFrame.plot 绘图，使用 kind='bar' 和 stacked=True。 pandas 使用并导入 matplotlib 作为默认绘图后端，因此无需导入其他绘图库。

• 资源:

  • How to aggregate unique count with pandas pivot_table了解有关在 .pivot_table 中使用 aggfunc=len 的详细信息。
  • How to add value labels on a bar chart有关 .bar_label 的详细信息和示例。
  • How to add multiple annotations to a bar plot & How to create and annotate a stacked proportional bar chart用于向条形图添加计数和百分比。

• 在python 3.10、pandas 1.4.3、matplotlib 3.5.1中测试

import pandas as pd

# sample dataframe
df = pd.DataFrame({'Type': [ 'Sentence', 'Array', 'String', '-','-', 'Sentence', 'Array', 'String', '-','-', 'Sentence'],
                   'Length': [42, 21, 11, 6, 6, 42, 21, 11, 6, 6, 42],
                   'label': [1, 1, 0, 0, 0, 1, 1, 0, 0, 1, 0]})

# pivot the dataframe and get len
dfp = df.pivot_table(index='Type', columns='label', values='Length', aggfunc=len) 

# get the total for each row
total = dfp.sum(axis=1)

# calculate the percent for each row
per = dfp.div(total, axis=0).mul(100).round(2)

# plot the pivoted dataframe
ax = dfp.plot(kind='bar', stacked=True, figsize=(10, 8), rot=0)

# set the colors for each Class
segment_colors = {'0': 'white', '1': 'black'}

# iterate through the containers
for c in ax.containers:
    
    # get the current segment label (a string); corresponds to column / legend
    label = c.get_label()
    
    # create custom labels with the bar height and the percent from the per column
    # the column labels in per and dfp are int, so convert label to int
    labels = [f'{v.get_height()}\n({row}%)' if v.get_height() > 0 else '' for v, row in zip(c, per[int(label)])]
    
    # add the annotation
    ax.bar_label(c, labels=labels, label_type='center', fontweight='bold', color=segment_colors[label])
    
# move the legend
_ = ax.legend(title='Class', bbox_to_anchor=(1, 1.01), loc='upper left')

---

评论更新

• 如果数据中没有'Array'，如何始终为其提供位置:
  • 如果 'Array' 不在 dfp.index 中，请将其添加到 dfp 中。
  • df.Type = pd.Categorical(df.Type, ['-', 'Array', 'Sentence', 'String'],ordered=True) 不能确保缺失的类别已绘制。
• 如何拥有所有注释，即使它们很小:
  • 不要堆叠条形图，并设置 logy=True。
• 这使用链接中提供的完整数据。

# pivot the dataframe and get len
dfp = df.pivot_table(index='Type', columns='label', values='Length', aggfunc=len) 

# append Array if it's not included
if 'Array' not in dfp.index:
    dfp = pd.concat([dfp, pd.DataFrame({0: [np.nan], 1: [np.nan]}, index=['Array'])])
    
# order the index
dfp = dfp.loc[['-', 'Array', 'Sentence', 'String'], :]

# calculate the percent for each row
per = dfp.div(dfp.sum(axis=1), axis=0).mul(100).round(2)

# plot the pivoted dataframe
ax = dfp.plot(kind='bar', stacked=False, figsize=(10, 8), rot=0, logy=True, width=0.75)

# iterate through the containers
for c in ax.containers:
    
    # get the current segment label (a string); corresponds to column / legend
    label = c.get_label()
    
    # create custom labels with the bar height and the percent from the per column
    # the column labels in per and dfp are int, so convert label to int
    labels = [f'{v.get_height()}\n({row}%)' if v.get_height() > 0 else '' for v, row in zip(c, per[int(label)])]
    
    # add the annotation
    ax.bar_label(c, labels=labels, label_type='edge', fontsize=10, fontweight='bold')
    
# move the legend
ax.legend(title='Class', bbox_to_anchor=(1, 1.01), loc='upper left')

# pad the spacing between the number and the edge of the figure
_ = ax.margins(y=0.1)

---

数据帧 View

• 基于 OP 中的示例数据

df

        Type  Length  label
0   Sentence      42      1
1      Array      21      1
2     String      11      0
3          -       6      0
4          -       6      0
5   Sentence      42      1
6      Array      21      1
7     String      11      0
8          -       6      0
9          -       6      1
10  Sentence      42      0

dfp

label       0    1
Type              
-         3.0  1.0
Array     NaN  2.0
Sentence  1.0  2.0
String    2.0  NaN

总计

Type
-           4.0
Array       2.0
Sentence    3.0
String      2.0
dtype: float64

每

label          0       1
Type                    
-          75.00   25.00
Array        NaN  100.00
Sentence   33.33   66.67
String    100.00     NaN