【Python百日进阶-数据分析】Day146 - plotly小提琴图:px.violin()/go.violin()

四、实例

4.1 Plotly Express 的小提琴图

小提琴图是数字数据的统计表示。它类似于箱线图，在每一侧都增加了一个旋转的核密度图。

用于可视化分布的小提琴图的替代方法包括直方图、箱线图、ECDF 图和条形图。

4.1.1 Plotly Express 的基本小提琴图

import plotly.express as px

df = px.data.tips()
print(df)
'''
     total_bill   tip     sex smoker   day    time  size
0         16.99  1.01  Female     No   Sun  Dinner     2
1         10.34  1.66    Male     No   Sun  Dinner     3
2         21.01  3.50    Male     No   Sun  Dinner     3
3         23.68  3.31    Male     No   Sun  Dinner     2
4         24.59  3.61  Female     No   Sun  Dinner     4
..          ...   ...     ...    ...   ...     ...   ...
239       29.03  5.92    Male     No   Sat  Dinner     3
240       27.18  2.00  Female    Yes   Sat  Dinner     2
241       22.67  2.00    Male    Yes   Sat  Dinner     2
242       17.82  1.75    Male     No   Sat  Dinner     2
243       18.78  3.00  Female     No  Thur  Dinner     2

[244 rows x 7 columns]
'''
fig = px.violin(df, y="total_bill")
fig.show()

4.1.2 带框和数据点的小提琴图

import plotly.express as px

df = px.data.tips()
print(df)
'''
     total_bill   tip     sex smoker   day    time  size
0         16.99  1.01  Female     No   Sun  Dinner     2
1         10.34  1.66    Male     No   Sun  Dinner     3
2         21.01  3.50    Male     No   Sun  Dinner     3
3         23.68  3.31    Male     No   Sun  Dinner     2
4         24.59  3.61  Female     No   Sun  Dinner     4
..          ...   ...     ...    ...   ...     ...   ...
239       29.03  5.92    Male     No   Sat  Dinner     3
240       27.18  2.00  Female    Yes   Sat  Dinner     2
241       22.67  2.00    Male    Yes   Sat  Dinner     2
242       17.82  1.75    Male     No   Sat  Dinner     2
243       18.78  3.00  Female     No  Thur  Dinner     2

[244 rows x 7 columns]
'''

fig = px.violin(df, y="total_bill", box=True, # 在小提琴内部绘制方框图
                points='all', # 可以是 'outliers', or False
               )
fig.show()

4.1.3 多个小提琴图

import plotly.express as px

df = px.data.tips()
print(df)
'''
     total_bill   tip     sex smoker   day    time  size
0         16.99  1.01  Female     No   Sun  Dinner     2
1         10.34  1.66    Male     No   Sun  Dinner     3
2         21.01  3.50    Male     No   Sun  Dinner     3
3         23.68  3.31    Male     No   Sun  Dinner     2
4         24.59  3.61  Female     No   Sun  Dinner     4
..          ...   ...     ...    ...   ...     ...   ...
239       29.03  5.92    Male     No   Sat  Dinner     3
240       27.18  2.00  Female    Yes   Sat  Dinner     2
241       22.67  2.00    Male    Yes   Sat  Dinner     2
242       17.82  1.75    Male     No   Sat  Dinner     2
243       18.78  3.00  Female     No  Thur  Dinner     2

[244 rows x 7 columns]
'''
fig = px.violin(df, y="tip", x="smoker", color="sex", box=True, points="all",
          hover_data=df.columns)
fig.show()

4.1.4 叠加的小提琴图

import plotly.express as px

df = px.data.tips()
print(df)
'''
     total_bill   tip     sex smoker   day    time  size
0         16.99  1.01  Female     No   Sun  Dinner     2
1         10.34  1.66    Male     No   Sun  Dinner     3
2         21.01  3.50    Male     No   Sun  Dinner     3
3         23.68  3.31    Male     No   Sun  Dinner     2
4         24.59  3.61  Female     No   Sun  Dinner     4
..          ...   ...     ...    ...   ...     ...   ...
239       29.03  5.92    Male     No   Sat  Dinner     3
240       27.18  2.00  Female    Yes   Sat  Dinner     2
241       22.67  2.00    Male    Yes   Sat  Dinner     2
242       17.82  1.75    Male     No   Sat  Dinner     2
243       18.78  3.00  Female     No  Thur  Dinner     2

[244 rows x 7 columns]
'''
fig = px.violin(df, y="tip", color="sex",
                # 默认violinmode是'group'
                violinmode='overlay', # 把小提琴放在彼此的上面
                hover_data=df.columns)
fig.show()

4.2 graph_objects的小提琴图

如果Plotly Express 没有提供好的起点，您可以使用plotly.graph_objects的go.Violin所有选项go.Violin都记录在参考https://plotly.com/python/reference/violin/中

4.2.1 基本小提琴图

import plotly.graph_objects as go

import pandas as pd
# 'https://raw.githubusercontent.com/plotly/datasets/master/violin_data.csv'
df = pd.read_csv("f:/violin_data.csv")
print(df)
'''
     total_bill   tip     sex smoker   day    time  size
0         16.99  1.01  Female     No   Sun  Dinner     2
1         10.34  1.66    Male     No   Sun  Dinner     3
2         21.01  3.50    Male     No   Sun  Dinner     3
3         23.68  3.31    Male     No   Sun  Dinner     2
4         24.59  3.61  Female     No   Sun  Dinner     4
..          ...   ...     ...    ...   ...     ...   ...
239       29.03  5.92    Male     No   Sat  Dinner     3
240       27.18  2.00  Female    Yes   Sat  Dinner     2
241       22.67  2.00    Male    Yes   Sat  Dinner     2
242       17.82  1.75    Male     No   Sat  Dinner     2
243       18.78  3.00  Female     No  Thur  Dinner     2

[244 rows x 7 columns]
'''

fig = go.Figure(data=go.Violin(y=df['total_bill'], box_visible=True, line_color='black',
                               meanline_visible=True, fillcolor='lightseagreen', opacity=0.6,
                               x0='Total Bill'))

fig.update_layout(yaxis_zeroline=False)
fig.show()

4.2.2 多条小提琴迹线

import plotly.graph_objects as go

import pandas as pd
# 'https://raw.githubusercontent.com/plotly/datasets/master/violin_data.csv'
df = pd.read_csv("f:/violin_data.csv")
print(df)
'''
     total_bill   tip     sex smoker   day    time  size
0         16.99  1.01  Female     No   Sun  Dinner     2
1         10.34  1.66    Male     No   Sun  Dinner     3
2         21.01  3.50    Male     No   Sun  Dinner     3
3         23.68  3.31    Male     No   Sun  Dinner     2
4         24.59  3.61  Female     No   Sun  Dinner     4
..          ...   ...     ...    ...   ...     ...   ...
239       29.03  5.92    Male     No   Sat  Dinner     3
240       27.18  2.00  Female    Yes   Sat  Dinner     2
241       22.67  2.00    Male    Yes   Sat  Dinner     2
242       17.82  1.75    Male     No   Sat  Dinner     2
243       18.78  3.00  Female     No  Thur  Dinner     2

[244 rows x 7 columns]
'''

fig = go.Figure()

days = ['Thur', 'Fri', 'Sat', 'Sun']

for day in days:
    fig.add_trace(go.Violin(x=df['day'][df['day'] == day],
                            y=df['total_bill'][df['day'] == day],
                            name=day,
                            box_visible=True,
                            meanline_visible=True))

fig.show()

4.2.3 分组小提琴图

import plotly.graph_objects as go

import pandas as pd
# 'https://raw.githubusercontent.com/plotly/datasets/master/violin_data.csv'
df = pd.read_csv("f:/violin_data.csv")
print(df)
'''
     total_bill   tip     sex smoker   day    time  size
0         16.99  1.01  Female     No   Sun  Dinner     2
1         10.34  1.66    Male     No   Sun  Dinner     3
2         21.01  3.50    Male     No   Sun  Dinner     3
3         23.68  3.31    Male     No   Sun  Dinner     2
4         24.59  3.61  Female     No   Sun  Dinner     4
..          ...   ...     ...    ...   ...     ...   ...
239       29.03  5.92    Male     No   Sat  Dinner     3
240       27.18  2.00  Female    Yes   Sat  Dinner     2
241       22.67  2.00    Male    Yes   Sat  Dinner     2
242       17.82  1.75    Male     No   Sat  Dinner     2
243       18.78  3.00  Female     No  Thur  Dinner     2

[244 rows x 7 columns]
'''

fig = go.Figure()

fig.add_trace(go.Violin(x=df['day'][ df['sex'] == 'Male' ],
                        y=df['total_bill'][ df['sex'] == 'Male' ],
                        legendgroup='M', scalegroup='M', name='M',
                        line_color='blue')
             )
fig.add_trace(go.Violin(x=df['day'][ df['sex'] == 'Female' ],
                        y=df['total_bill'][ df['sex'] == 'Female' ],
                        legendgroup='F', scalegroup='F', name='F',
                        line_color='orange')
             )

fig.update_traces(box_visible=True, meanline_visible=True)
fig.update_layout(violinmode='group')

fig.show()

4.2.4 分裂小提琴图

import plotly.graph_objects as go

import pandas as pd
# 'https://raw.githubusercontent.com/plotly/datasets/master/violin_data.csv'
df = pd.read_csv("f:/violin_data.csv")
print(df)
'''
     total_bill   tip     sex smoker   day    time  size
0         16.99  1.01  Female     No   Sun  Dinner     2
1         10.34  1.66    Male     No   Sun  Dinner     3
2         21.01  3.50    Male     No   Sun  Dinner     3
3         23.68  3.31    Male     No   Sun  Dinner     2
4         24.59  3.61  Female     No   Sun  Dinner     4
..          ...   ...     ...    ...   ...     ...   ...
239       29.03  5.92    Male     No   Sat  Dinner     3
240       27.18  2.00  Female    Yes   Sat  Dinner     2
241       22.67  2.00    Male    Yes   Sat  Dinner     2
242       17.82  1.75    Male     No   Sat  Dinner     2
243       18.78  3.00  Female     No  Thur  Dinner     2

[244 rows x 7 columns]
'''

fig = go.Figure()

fig.add_trace(go.Violin(x=df['day'][ df['smoker'] == 'Yes' ],
                        y=df['total_bill'][ df['smoker'] == 'Yes' ],
                        legendgroup='Yes', scalegroup='Yes', name='Yes',
                        side='negative',
                        line_color='blue')
             )
fig.add_trace(go.Violin(x=df['day'][ df['smoker'] == 'No' ],
                        y=df['total_bill'][ df['smoker'] == 'No' ],
                        legendgroup='No', scalegroup='No', name='No',
                        side='positive',
                        line_color='orange')
             )
fig.update_traces(meanline_visible=True)
fig.update_layout(violingap=0, violinmode='overlay')

fig.show()

4.2.5 高级小提琴图

import plotly.graph_objects as go

import pandas as pd
# 'https://raw.githubusercontent.com/plotly/datasets/master/violin_data.csv'
df = pd.read_csv("f:/violin_data.csv")
print(df)
'''
     total_bill   tip     sex smoker   day    time  size
0         16.99  1.01  Female     No   Sun  Dinner     2
1         10.34  1.66    Male     No   Sun  Dinner     3
2         21.01  3.50    Male     No   Sun  Dinner     3
3         23.68  3.31    Male     No   Sun  Dinner     2
4         24.59  3.61  Female     No   Sun  Dinner     4
..          ...   ...     ...    ...   ...     ...   ...
239       29.03  5.92    Male     No   Sat  Dinner     3
240       27.18  2.00  Female    Yes   Sat  Dinner     2
241       22.67  2.00    Male    Yes   Sat  Dinner     2
242       17.82  1.75    Male     No   Sat  Dinner     2
243       18.78  3.00  Female     No  Thur  Dinner     2

[244 rows x 7 columns]
'''

fig = go.Figure()

pointpos_male = [-0.9,-1.1,-0.6,-0.3]
pointpos_female = [0.45,0.55,1,0.4]
show_legend = [True,False,False,False]

fig = go.Figure()

for i in range(0,len(pd.unique(df['day']))):
    fig.add_trace(go.Violin(x=df['day'][(df['sex'] == 'Male') &
                                        (df['day'] == pd.unique(df['day'])[i])],
                            y=df['total_bill'][(df['sex'] == 'Male')&
                                               (df['day'] == pd.unique(df['day'])[i])],
                            legendgroup='M', scalegroup='M', name='M',
                            side='negative',
                            pointpos=pointpos_male[i], # 在哪里定位点
                            line_color='lightseagreen',
                            showlegend=show_legend[i])
             )
    fig.add_trace(go.Violin(x=df['day'][(df['sex'] == 'Female') &
                                        (df['day'] == pd.unique(df['day'])[i])],
                            y=df['total_bill'][(df['sex'] == 'Female')&
                                               (df['day'] == pd.unique(df['day'])[i])],
                            legendgroup='F', scalegroup='F', name='F',
                            side='positive',
                            pointpos=pointpos_female[i],
                            line_color='mediumpurple',
                            showlegend=show_legend[i])
             )

# 更新所有跟踪共享的特征
fig.update_traces(meanline_visible=True,
                  points='all', # 显示所有要点
                  jitter=0.05,  # 在点上添加一些抖动以获得更好的可见性
                  scalemode='count') # 用总计数缩放绘图区域
fig.update_layout(
    title_text="总账单分配<br><i>按每个性别的账单数量缩放",
    violingap=0, violingroupgap=0, violinmode='overlay')

fig.show()

4.2.6 脊线图

脊线图（以前称为 Joy Plot）显示了几个组的数值分布。它们可用于可视化分布随时间或空间的变化。

import plotly.graph_objects as go
from plotly.colors import n_colors
import numpy as np
np.random.seed(1)

# 12组正态分布的随机数据，平均值和标准差都在增加
data = (np.linspace(1, 2, 12)[:, np.newaxis] * np.random.randn(12, 200) +
            (np.arange(12) + 2 * np.random.random(12))[:, np.newaxis])

colors = n_colors('rgb(5, 200, 200)', 'rgb(200, 10, 10)', 12, colortype='rgb')

fig = go.Figure()
for data_line, color in zip(data, colors):
    fig.add_trace(go.Violin(x=data_line, line_color=color))

fig.update_traces(orientation='h', side='positive', width=3, points=False)
fig.update_layout(xaxis_showgrid=False, xaxis_zeroline=False)
fig.show()

4.2.7 只有点的小提琴图

条形图就像一个带有点的小提琴图，没有小提琴：

import plotly.express as px
df = px.data.tips()
print(df)
'''
     total_bill   tip     sex smoker   day    time  size
0         16.99  1.01  Female     No   Sun  Dinner     2
1         10.34  1.66    Male     No   Sun  Dinner     3
2         21.01  3.50    Male     No   Sun  Dinner     3
3         23.68  3.31    Male     No   Sun  Dinner     2
4         24.59  3.61  Female     No   Sun  Dinner     4
..          ...   ...     ...    ...   ...     ...   ...
239       29.03  5.92    Male     No   Sat  Dinner     3
240       27.18  2.00  Female    Yes   Sat  Dinner     2
241       22.67  2.00    Male    Yes   Sat  Dinner     2
242       17.82  1.75    Male     No   Sat  Dinner     2
243       18.78  3.00  Female     No  Thur  Dinner     2

[244 rows x 7 columns]
'''
fig = px.strip(df, x='day', y='tip')
fig.show()

4.2.8 Dash中的应用

import plotly.graph_objects as go # or plotly.express as px
fig = go.Figure() # or any Plotly Express function e.g. px.bar(...)
# fig.add_trace( ... )
# fig.update_layout( ... )

import dash
import dash_core_components as dcc
import dash_html_components as html

app = dash.Dash()
app.layout = html.Div([
    dcc.Graph(figure=fig)
])

app.run_server(debug=True, use_reloader=False)  # Turn off reloader if inside Jupyter