Question

我有一个pandas DataFrame，其中所有值都是英文字母或空字符串“”。我的目标是a）通过将列索引作为X轴并将行索引作为Y轴（散点图）来绘制这些字母，并 b）控制X轴方向上的间距，以使它们之间的间距不大。

我已经能够在所需的坐标处绘制字形（例如，圆形），但无法绘制字母（如出现在DataFrame中的字母）。而且，由于X轴具有0、1、2、3 ...，这些圆也间隔开了。如果X轴提供了简单/更好的解决方案，则也可以将其分类，而不是整数。

import pandas as pd
from bokeh.plotting import figure
from bokeh.io import output_file, show
from bokeh.models import ColumnDataSource,Range1d #FactorRange

output_file("plot_text.html",title="plot_text")
# creating the DataFrame
d = {0:["A","A","A","D","D","C","E"],
    1:["B","","B","C","D","E","E"],
    2:["","","F","F","G","","H"],
    3:["","","","","","H","H"]}
df = pd.DataFrame(d,index=range(800,100,-100))
list1_x = []
list1_y = []
for i in range(len(df.columns)):
    for j in range(len(df.index)):
        if df.iloc[j,i]=="": # excluding the "" appearance
            continue
        else:
            list1_x.append(df.columns[i])
            list1_y.append(df.index[j])
source = ColumnDataSource(data=dict(x = list1_x,y = list1_y))
fig = figure(plot_height=500, plot_width=1100,
    tools="pan,xwheel_zoom,reset,save,crosshair,box_zoom",
    active_drag='pan',
    active_scroll='xwheel_zoom',
    x_range=Range1d(-5, 100, bounds="auto"),
    y_range=Range1d(-100, 1200, bounds="auto")
    )
fig.circle(x= 'x',y='y',color = "blue",size =10,source = source)
show(fig)

如前所述，上面的代码绘制了单个字形（在这种情况下为圆形），这不是我想要的，而且我绝对不知道如何实现对缩放的控制。

Answer 1

您需要根据要绘制的数据创建一个列表，其长度与columndatasource中其他列的长度相同，然后将其添加到源中。如果只需要字符，则可以禁用圆，否则将同时绘制两个字符，还应考虑使用悬停功能，这是向图表添加交互的一种很好的方法。我使用LabelSet来映射数据的坐标，也可以像上面提到的那样使用偏移量来调整间距。

import pandas as pd
from bokeh.plotting import figure
from bokeh.io import output_file, show, output_notebook
from bokeh.models import ColumnDataSource,Range1d, LabelSet #FactorRange
import itertools
output_notebook()

output_file("plot_text.html",title="plot_text")
# creating the DataFrame
d = {0:["A","A","A","D","D","C","E"],
    1:["B","","B","C","D","E","E"],
    2:["","","F","F","G","","H"],
    3:["","","","","","H","H"]}
#convert dict to a single list to match the length in your 
#source(ColumnDataSource)
d1 = list(d.values())
d_letters = list(itertools.chain(*d1))
#I tried to remove your nan values, but it didnt work, I did it manually but 
#here is the code to do so
d2 = [x for x in d_letters if d_letters != ''] # [x for x in d_letters if 
#d_letters != 'nan']
d_ = ['A', 'A', 'A', 'D', 'D', 'C', 'E', 'B', 'B', 'C','D', 'E', 'E', 'F', 
'F', 'G', 'H', 'H', 'H']
#len(d_) 19 as x and y


df = pd.DataFrame(d,index=range(800,100,-100))
list1_x = []
list1_y = []
for i in range(len(df.columns)):
    for j in range(len(df.index)):
        if df.iloc[j,i]=="": # excluding the "" appearance
            continue
        else:
            list1_x.append(df.columns[i])
            list1_y.append(df.index[j])
source = ColumnDataSource(data=dict(x = list1_x,y = list1_y, x1=d_))
fig = figure(plot_height=500, plot_width=1100,
    tools="pan,xwheel_zoom,reset,save,crosshair,box_zoom",
    active_drag='pan',
    active_scroll='xwheel_zoom',
    x_range=Range1d(-5, 100, bounds="auto"),
    y_range=Range1d(-100, 1200, bounds="auto")
    )
fig.circle(x= 'x',y='y',color = "blue",size =10,source = source)

#create labels
labels = LabelSet(x='x', y='y', text='x1', level='glyph',
              x_offset=5, y_offset=5, source=source, render_mode='canvas')


fig.add_layout(labels)


show(fig)

如何在散景中绘制字符

1 个答案: