【发布时间】:2020-01-27 09:19:29
【问题描述】:
我正在尝试使用 pandas 数据框和散景 vbar 复制如下图表:
到目前为止,我已经设法将标签放置在其相应的高度,但现在我无法找到一种方法来访问类别 (2016,2017,2018) 位于 x 轴上的数值。这是我的结果:
My nested categorical stacked bars chart
这是我的代码。它很乱,但这是我到目前为止所管理的。那么有没有办法访问条形图 x_axis 中的数值?
def make_nested_stacked_bars(source,measurement,dimension_attr):
#dimension_attr is a list that contains the names of columns in source that will be used as categories
#measurement containes the name of the column with numeric data.
data = source.copy()
#Creates list of values of highest index
list_attr = source[dimension_attr[0]].unique()
list_stackers = list(source[dimension_attr[-1]].unique())
list_stackers.sort()
#trims labals that are too wide to fit in graph
for column in data.columns:
if data[column].dtype.name == 'object':
data[column] = np.where(data[column].apply(len) > 30, data[column].str[:30]+'...', data[column])
#Creates a list of dataframes, each grouping a specific value
list_groups = []
for item in list_attr:
list_groups.append(data[data[dimension_attr[0]] == item])
#Groups data by dimension attrs, aggregates measurement to count
#Drops highest index from dimension attr
dropped_attr = dimension_attr[0]
dimension_attr.remove(dropped_attr)
#Creates groupby by the last 2 parameters, and aggregates to count
#Calculates percentage
for index,value in enumerate(list_groups):
list_groups[index] = list_groups[index].groupby(by=dimension_attr).agg({measurement: ['count']})
list_groups[index] = list_groups[index].groupby(level=0).apply(lambda x: round(100 * x / float(x.sum()),1))
# Resets indexes
list_groups[index] = list_groups[index].reset_index()
list_groups[index] = list_groups[index].pivot(index=dimension_attr[0], columns=dimension_attr[1])
list_groups[index].index = [(x,list_attr[index]) for x in list_groups[index].index]
# Drops dimension attr as top level column
list_groups[index].columns = list_groups[index].columns.droplevel(0)
list_groups[index].columns = list_groups[index].columns.droplevel(0)
df = pd.concat(list_groups)
# Get the number of colors needed for the plot.
colors = brewer["Spectral"][len(list_stackers)]
colors.reverse()
p = figure(plot_width=800, plot_height=500, x_range=FactorRange(*df.index))
renderers = p.vbar_stack(list_stackers, x='index', width=0.3, fill_color=colors, legend=[get_item_value(x)for x in list_stackers], line_color=None, source=df, name=list_stackers,)
# Adds a different hovertool to a stacked bar
#empy dictionary with initial values set to zero
list_previous_y = {}
for item in df.index:
list_previous_y[item] = 0
#loops through bar graphs
for r in renderers:
stack = r.name
hover = HoverTool(tooltips=[
("%s" % stack, "@%s" % stack),
], renderers=[r])
#Initial value for placing label in x_axis
previous_x = 0.5
#Loops through dataset rows
for index, row in df.iterrows():
#adds value of df column to list
list_previous_y[index] = list_previous_y[index] + df[stack][index]
## adds label if value is not nan and at least 10
if not math.isnan(df[stack][index]) and df[stack][index]>=10:
p.add_layout(Label(x=previous_x, y=list_previous_y[index] -df[stack][index]/2,
text='% '+str(df[stack][index]), render_mode='css',
border_line_color='black', border_line_alpha=1.0,
background_fill_color='white', background_fill_alpha=1.0))
# increases position in x_axis
#this should be done by adding the value of next bar in x_axis
previous_x = previous_x + 0.8
p.add_tools(hover)
p.add_tools(hover)
p.legend.location = "top_left"
p.x_range.range_padding = 0.2
p.xgrid.grid_line_color = None
return p
或者有没有更简单的方法来完成这一切?
感谢您的宝贵时间!
更新:
添加了一个三级嵌套图表的附加图像,其中 x_axis 中的标签放置也应该完成
【问题讨论】: