如何在 Python 中多轴可视化二进制数据？

Question

我有一个如下示例 Pandas 数据框：

Action    Comedy    Crime    Thriller    SciFi    
1         0         1         1          0        
0         1         0         0          1        
0         1         0         1          0        
0         0         1         0          1        
1         1         0         0          0        

我想使用 Python（最好使用 matplotlib）绘制数据集，使每一列都是一个单独的轴。因此，在这种情况下，将有 5 个轴（动作、喜剧、犯罪...）和 5 个数据点（因为它有 5 行）。 是否可以使用 python matplotlib 绘制这种多轴数据？如果不可能，将这些数据可视化的最佳解决方案是什么？

Answer 1

这是一个不错的简单可视化，您可以通过一些数据操作和Seaborn 获得。

import seaborn as sns

# df is a Pandas DataFrame with the following content:
#   Action    Comedy    Crime    Thriller    SciFi
#   1         0         1         1          0
#   0         1         0         0          1
#   0         1         0         1          0
#   0         0         1         0          1
#   1         1         0         0          0
df = ...

# Give name to the indices for convenience
df.index.name = "Index"
df.columns.name = "Genre"

# Get a data frame containing the relevant genres and indices
df2 = df.unstack()
df2 = df2[df2 > 0].reset_index()

# Plot it
ax = sns.stripplot(x="Genre", y="Index", data=df2)
ax.set_yticks(df.index)

你会得到：

对于微调，您可以查看sns.stripplot 的文档。

Answer 2

雷达图

使用 RadarChart 可以实现多个轴。您可以根据自己的需要调整Radar Chart example。

u = u"""Action    Comedy    Crime    Thriller    SciFi    
1         0         1         1          0        
0         1         0         0          1        
0         1         0         1          0        
0         0         1         0          1        
1         1         0         0          0"""

import io
import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
from matplotlib.path import Path
from matplotlib.spines import Spine
from matplotlib.projections.polar import PolarAxes
from matplotlib.projections import register_projection


def radar_factory(num_vars, frame='circle'):
    theta = np.linspace(0, 2*np.pi, num_vars, endpoint=False)
    theta += np.pi/2

    def draw_poly_patch(self):
        verts = unit_poly_verts(theta)
        return plt.Polygon(verts, closed=True, edgecolor='k')

    def draw_circle_patch(self):
        return plt.Circle((0.5, 0.5), 0.5)

    patch_dict = {'polygon': draw_poly_patch, 'circle': draw_circle_patch}

    def unit_poly_verts(theta):
        x0, y0, r = [0.5] * 3
        verts = [(r*np.cos(t) + x0, r*np.sin(t) + y0) for t in theta]
        return verts

    class RadarAxes(PolarAxes):

        name = 'radar'
        RESOLUTION = 1
        draw_patch = patch_dict[frame]

        def fill(self, *args, **kwargs):
            """Override fill so that line is closed by default"""
            closed = kwargs.pop('closed', True)
            return super(RadarAxes, self).fill(closed=closed, *args, **kwargs)

        def plot(self, *args, **kwargs):
            """Override plot so that line is closed by default"""
            lines = super(RadarAxes, self).plot(*args, **kwargs)
            for line in lines:
                self._close_line(line)

        def _close_line(self, line):
            x, y = line.get_data()
            if x[0] != x[-1]:
                x = np.concatenate((x, [x[0]]))
                y = np.concatenate((y, [y[0]]))
                line.set_data(x, y)

        def set_varlabels(self, labels):
            self.set_thetagrids(np.degrees(theta), labels)

        def _gen_axes_patch(self):
            return self.draw_patch()

        def _gen_axes_spines(self):
            if frame == 'circle':
                return PolarAxes._gen_axes_spines(self)
            spine_type = 'circle'
            verts = unit_poly_verts(theta)
            # close off polygon by repeating first vertex
            verts.append(verts[0])
            path = Path(verts)

            spine = Spine(self, spine_type, path)
            spine.set_transform(self.transAxes)
            return {'polar': spine}

    register_projection(RadarAxes)
    return theta


df = pd.read_csv(io.StringIO(u), delim_whitespace=True)

N = 5
theta = radar_factory(N, frame='polygon')

fig, ax = plt.subplots(subplot_kw=dict(projection='radar'))

colors = ['b', 'r', 'g', 'm', 'y']
markers = ["s", "o","P", "*", "^"]
ax.set_rgrids([1])

for i,(col, row) in enumerate(df.iterrows()):
    ax.scatter(theta, row, c=colors[i], marker=markers[i], label=col)
    ax.fill(theta, row, facecolor=colors[i], alpha=0.25)
ax.set_varlabels(df.columns)

labels = ["Book {}".format(i+1) for i in range(len(df))]
ax.legend(labels*2, loc=(0.97, .1), labelspacing=0.1, fontsize='small')

plt.show()

热图

显示数据的一种简单且可能更具可读性的方法是热图。

u = u"""Action    Comedy    Crime    Thriller    SciFi    
1         0         1         1          0        
0         1         0         0          1        
0         1         0         1          0        
0         0         1         0          1        
1         1         0         0          0"""

import io
import pandas as pd
import matplotlib.pyplot as plt

df = pd.read_csv(io.StringIO(u), delim_whitespace=True)
print df

plt.matshow(df, cmap="gray")
plt.xticks(range(len(df.columns)), df.columns)
plt.yticks(range(len(df)), range(1,len(df)+1))
plt.ylabel("Book number")     
plt.show()