python bokeh，如何制作相关图？

Question

如何在散景中制作相关热图？

import pandas as pd
import bokeh.charts

df = pd.util.testing.makeTimeDataFrame(1000)
c = df.corr()

p = bokeh.charts.HeatMap(c) # not right

# try to make it a long form
# (and it's ugly in pandas to use 'index' in melt)

c['x'] = c.index
c = pd.melt(c, 'x', ['A','B','C','D'])

# this shows the right 4x4 matrix, but values are still wrong
p = bokeh.charts.HeatMap(c, x = 'x', y = 'variable', values = 'value') 

顺便说一句，我可以在侧面制作一个颜色条，而不是情节中的图例吗？以及如何选择颜色范围/映射，例如深蓝色（-1）到白色（0）到深红色（+1）？

Answer 1

所以我想我可以提供一个基线代码来帮助你使用上面的答案和一些额外的预处理的组合来完成你的要求。

假设您已经加载了一个数据帧df（在本例中为UCI Adult Data）并计算了相关系数（p_corr）。

import bisect
#
from math import pi
from numpy import arange
from itertools import chain
from collections import OrderedDict
#
from bokeh.palettes import RdBu as colors  # just make sure to import a palette that centers on white (-ish)
from bokeh.models import ColorBar, LinearColorMapper

colors = list(reversed(colors[9]))  # we want an odd number to ensure 0 correlation is a distinct color
labels = df.columns
nlabels = len(labels)

def get_bounds(n):
    """Gets bounds for quads with n features"""
    bottom = list(chain.from_iterable([[ii]*nlabels for ii in range(nlabels)]))
    top = list(chain.from_iterable([[ii+1]*nlabels for ii in range(nlabels)]))
    left = list(chain.from_iterable([list(range(nlabels)) for ii in range(nlabels)]))
    right = list(chain.from_iterable([list(range(1,nlabels+1)) for ii in range(nlabels)]))
    return top, bottom, left, right

def get_colors(corr_array, colors):
    """Aligns color values from palette with the correlation coefficient values"""
    ccorr = arange(-1, 1, 1/(len(colors)/2))
    color = []
    for value in corr_array:
        ind = bisect.bisect_left(ccorr, value)
        color.append(colors[ind-1])
    return color

p = figure(plot_width=600, plot_height=600,
           x_range=(0,nlabels), y_range=(0,nlabels),
           title="Correlation Coefficient Heatmap (lighter is worse)",
           toolbar_location=None, tools='')

p.xgrid.grid_line_color = None
p.ygrid.grid_line_color = None
p.xaxis.major_label_orientation = pi/4
p.yaxis.major_label_orientation = pi/4

top, bottom, left, right = get_bounds(nlabels)  # creates sqaures for plot
color_list = get_colors(p_corr.values.flatten(), colors)

p.quad(top=top, bottom=bottom, left=left,
       right=right, line_color='white',
       color=color_list)

# Set ticks with labels
ticks = [tick+0.5 for tick in list(range(nlabels))]
tick_dict = OrderedDict([[tick, labels[ii]] for ii, tick in enumerate(ticks)])
# Create the correct number of ticks for each axis 
p.xaxis.ticker = ticks
p.yaxis.ticker = ticks
# Override the labels 
p.xaxis.major_label_overrides = tick_dict
p.yaxis.major_label_overrides = tick_dict

# Setup color bar
mapper = LinearColorMapper(palette=colors, low=-1, high=1)
color_bar = ColorBar(color_mapper=mapper, location=(0, 0))
p.add_layout(color_bar, 'right')

show(p)

如果类别是整数编码的，这将导致以下图（这是一个可怕的数据示例）：