仅显示散景图例中的主要类别

Question

我想让 bokeh 显示分类条形图数据的图例，但要控制图例中显示的类别级别。

例如使用下面的散景示例代码，我希望图例仅显示年份。所以“2015”、“2016”、“2017”，而不是现在的"Apples, 2015"等等

此外，我试图隐藏 x 轴上显示的年份，因此它只显示水果。

我已经在 bokeh 的文档中搜索了一段时间，但看不到如何执行此操作。我想我需要在创建 vbar 时将图例属性设置为某种格式字符串，但我不知道允许使用哪些格式。执行此操作的正确方法是什么？

from bokeh.io import show, output_file
from bokeh.models import ColumnDataSource, FactorRange
from bokeh.plotting import figure
from bokeh.transform import factor_cmap

output_file("bars.html")

fruits = ['Apples', 'Pears', 'Nectarines', 'Plums', 'Grapes', 'Strawberries']
years = ['2015', '2016', '2017']

data = {'fruits' : fruits,
        '2015'   : [2, 1, 4, 3, 2, 4],
        '2016'   : [5, 3, 3, 2, 4, 6],
        '2017'   : [3, 2, 4, 4, 5, 3]}

# this creates [ ("Apples", "2015"), ("Apples", "2016"), ("Apples", "2017"), ("Pears", "2015), ... ]
x = [ (fruit, year) for fruit in fruits for year in years ]
counts = sum(zip(data['2015'], data['2016'], data['2017']), ()) # like an hstack

source = ColumnDataSource(data=dict(x=x, counts=counts))

p = figure(x_range=FactorRange(*x), plot_height=250, title="Fruit Counts by Year",
           toolbar_location=None, tools="")

palette = ["Red", "Green", "Blue"]
#p.vbar(x='x', top='counts', width=0.9, source=source)
p.vbar(x='x', top='counts', width=0.9, source=source, line_color="white",
       fill_color=factor_cmap('x', palette=palette, factors=years, start=1, end=2),
       # legend='x[0]'
       legend='x',
      )


p.y_range.start = 0
p.x_range.range_padding = 0.1
p.xaxis.major_label_orientation = 1
p.xgrid.grid_line_color = None
p.legend.location = "top_right"

show(p)

Answer 1

如果您不需要层次轴标签，则需要使用用户指南Visual Dodge section of the Handling Categorical Data 章节中描述的方法。

除非我记错了，上面的例子正是你要问的：

from bokeh.core.properties import value
from bokeh.io import show, output_file
from bokeh.models import ColumnDataSource
from bokeh.plotting import figure
from bokeh.transform import dodge

output_file("dodged_bars.html")

fruits = ['Apples', 'Pears', 'Nectarines', 'Plums', 'Grapes', 'Strawberries']
years = ['2015', '2016', '2017']

data = {'fruits' : fruits,
        '2015'   : [2, 1, 4, 3, 2, 4],
        '2016'   : [5, 3, 3, 2, 4, 6],
        '2017'   : [3, 2, 4, 4, 5, 3]}

source = ColumnDataSource(data=data)

p = figure(x_range=fruits, y_range=(0, 10), plot_height=250, 
           title="Fruit Counts by Year", toolbar_location=None, tools="")

p.vbar(x=dodge('fruits', -0.25, range=p.x_range), top='2015', width=0.2, 
       source=source, color="#c9d9d3", legend=value("2015"))

p.vbar(x=dodge('fruits',  0.0,  range=p.x_range), top='2016', width=0.2, 
       source=source, color="#718dbf", legend=value("2016"))

p.vbar(x=dodge('fruits',  0.25, range=p.x_range), top='2017', width=0.2, 
       source=source, color="#e84d60", legend=value("2017"))

p.x_range.range_padding = 0.1
p.xgrid.grid_line_color = None
p.legend.location = "top_left"
p.legend.orientation = "horizontal"

show(p)

Answer 2

下面是一些动态构建图表的快速代码。单独定义increment，然后从上面的figure中提取：

def incrementer(labels, base_inc=0.25):
    num_labels = len(labels)
    midpoint = num_labels / 2 if num_labels % 2 == 0 else num_labels / 2 - 0.5
    offset = base_inc * midpoint
    even_offset = base_inc / 2 if num_labels % 2 == 0 else 0

    return [i * base_inc - offset + even_offset for i in range(num_labels)]

..... 


from bokeh.palettes import Category20

palette = Category20[20]
increments = incrementer(regions, base_inc=0.125)
for i, region in enumerate(regions):
    p.vbar(
        x=dodge('x', increments[i], range=p.x_range), top=region, width=0.1, 
           source=source, color=palette[i], legend_label=region
        )

Answer 3

这可以通过向 ColumnDataSource 添加另一列来实现，该列映射到感兴趣的类别级别。在问题代码中，将以下内容添加到 ColumnDataSource:

legend_names = [level1 for level0, level1 in x]
source = ColumnDataSource(data=dict(x=x, counts=counts, legend_name=legend_names))

然后更改 vbar 以将该字段用作图例（与普通图例参数相反）：

p.vbar(<other arguments>, legend_field='legend_name')

这样可以轻松选择任何级别用作图例。

结果：

完整代码：

from bokeh.io import show
from bokeh.models import ColumnDataSource, FactorRange
from bokeh.plotting import Figure
from bokeh.transform import factor_cmap

fruits = ['Apples', 'Pears', 'Nectarines', 'Plums', 'Grapes', 'Strawberries']
years = ['2015', '2016', '2017']

data = {'fruits': fruits,
        '2015': [2, 1, 4, 3, 2, 4],
        '2016': [5, 3, 3, 2, 4, 6],
        '2017': [3, 2, 4, 4, 5, 3]}

x = [(fruit, year) for fruit in fruits for year in years]
counts = sum(zip(data['2015'], data['2016'], data['2017']), ())
legend_names = [level1 for level0, level1 in x]
source = ColumnDataSource(data=dict(x=x, counts=counts, legend_name=legend_names))

figure = Figure(x_range=FactorRange(*x), plot_height=250, title="Fruit Counts by Year",
                toolbar_location=None, tools="")

palette = ["Red", "Green", "Blue"]
figure.vbar(x='x', top='counts', width=0.9, source=source, line_color="white",
            fill_color=factor_cmap('x', palette=palette, factors=years, start=1, end=2),
            legend_field='legend_name')

figure.y_range.start = 0
figure.x_range.range_padding = 0.1
figure.xaxis.major_label_orientation = 1
figure.xgrid.grid_line_color = None
figure.legend.location = "top_right"

show(figure)

仅显示散景图例中的主要类别

Show only major category in bokeh legend

python

bokeh