如何在使用 matplotlib 时按时绘制事件

Question

我有 3 个列表，每个列表都包含数字，代表一个时间。时间代表事件的发生。例如，在这个A 中，我为每个事件A 的发生都有一个编号。我想在图表上表示这些数据。以下两种方式之一：

1)

aabaaabbccacac

2)

a-> xx xxx    x x
b->   x   xx  
c->         xx x x

Answer 1

你可以使用plt.hlines:

import matplotlib.pyplot as plt
import random
import numpy as np
import string

def generate_data(N = 20):
    data = [random.randrange(3) for x in range(N)]
    A = [i for i, x in enumerate(data) if x == 0]
    B = [i for i, x in enumerate(data) if x == 1]
    C = [i for i, x in enumerate(data) if x == 2]
    return A,B,C

def to_xy(*events):
    x, y = [], []
    for i,event in enumerate(events):
        y.extend([i]*len(event))
        x.extend(event)
    x, y = np.array(x), np.array(y)
    return x,y

def event_string(x,y):
    labels = np.array(list(string.uppercase))        
    seq = labels[y[np.argsort(x)]]
    return seq.tostring()

def plot_events(x,y):
    labels = np.array(list(string.uppercase))    
    plt.hlines(y, x, x+1, lw = 2, color = 'red')
    plt.ylim(max(y)+0.5, min(y)-0.5)
    plt.yticks(range(y.max()+1), labels)
    plt.show()

A,B,C = generate_data(20)
x,y = to_xy(A,B,C)
print(event_string(x,y))
plot_events(x,y)

产量

BBACBCACCABACCBCABCC

Answer 2

作为对前面答案的扩展，您可以使用plt.hbar：

import matplotlib.pyplot as plt
import numpy as np
import string

x = np.array([0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13])
y = np.array([0, 0, 1, 0, 0, 0, 1, 1, 2, 2, 0, 2, 0, 2])

labels = np.array(list(string.uppercase))    
plt.barh(y, [1]*len(x), left=x, color = 'red', edgecolor = 'red', align='center', height=1)
plt.ylim(max(y)+0.5, min(y)-0.5)
plt.yticks(np.arange(y.max()+1), labels)
plt.show()

或者，你可以尝试这样的事情：

import matplotlib.pyplot as plt
import numpy as np

data = [[1, 1, 0, 1, 1, 1, 0, 0, 0, 0, 1, 0, 1, 0],
        [0, 0, 2, 0, 0, 0, 2, 2, 0, 0, 0, 0, 0, 0], 
        [0, 0, 0, 0, 0, 0, 0, 0, 3, 3, 0, 3, 0, 3]]

fig = plt.figure()
ax = fig.add_subplot(111)
ax.axes.get_yaxis().set_visible(False)
ax.set_aspect(1)

def avg(a, b):
    return (a + b) / 2.0

for y, row in enumerate(data):
    for x, col in enumerate(row):
        x1 = [x, x+1]
        y1 = np.array([y, y])
        y2 = y1+1
        if col == 1:
            plt.fill_between(x1, y1, y2=y2, color='red')
            plt.text(avg(x1[0], x1[1]), avg(y1[0], y2[0]), "A", 
                                        horizontalalignment='center',
                                        verticalalignment='center')
        if col == 2:
            plt.fill_between(x1, y1, y2=y2, color='orange')
            plt.text(avg(x1[0], x1[0]+1), avg(y1[0], y2[0]), "B", 
                                        horizontalalignment='center',
                                        verticalalignment='center')
        if col == 3:
            plt.fill_between(x1, y1, y2=y2, color='yellow')
            plt.text(avg(x1[0], x1[0]+1), avg(y1[0], y2[0]), "C", 
                                        horizontalalignment='center',
                                        verticalalignment='center')

plt.ylim(3, 0)
plt.show()

如果您希望所有插槽位于同一行，只需进行一些更改，如下所示：

import matplotlib.pyplot as plt
import numpy as np

data = [[1, 1, 0, 1, 1, 1, 0, 0, 0, 0, 1, 0, 1, 0],
        [0, 0, 2, 0, 0, 0, 2, 2, 0, 0, 0, 0, 0, 0], 
        [0, 0, 0, 0, 0, 0, 0, 0, 3, 3, 0, 3, 0, 3]]

fig = plt.figure()
ax = fig.add_subplot(111)
ax.axes.get_yaxis().set_visible(False)
ax.set_aspect(1)

def avg(a, b):
    return (a + b) / 2.0

for y, row in enumerate(data):
    for x, col in enumerate(row):
        x1 = [x, x+1]
        y1 = [0, 0]
        y2 = [1, 1]
        if col == 1:
            plt.fill_between(x1, y1, y2=y2, color='red')
            plt.text(avg(x1[0], x1[1]), avg(y1[0], y2[0]), "A", 
                                        horizontalalignment='center',
                                        verticalalignment='center')
        if col == 2:
            plt.fill_between(x1, y1, y2=y2, color='orange')
            plt.text(avg(x1[0], x1[0]+1), avg(y1[0], y2[0]), "B", 
                                        horizontalalignment='center',
                                        verticalalignment='center')
        if col == 3:
            plt.fill_between(x1, y1, y2=y2, color='yellow')
            plt.text(avg(x1[0], x1[0]+1), avg(y1[0], y2[0]), "C", 
                                        horizontalalignment='center',
                                        verticalalignment='center')

plt.ylim(1, 0)
plt.show()

第二个和第三个选项代码更多，但它们产生的结果要好得多。

Answer 3

以@amillerrhodes 的最后一张图为基础并对其进行简化（同时删除文本部分）：

import matplotlib.pyplot as plt
import numpy as np

# run-length encoding, instead of a list of lists with a bunch of zeros
data = [(2, 1), (1, 2), (3, 1), (2, 2), (2, 3), (1, 1), (1, 3), (1, 1), (1, 3)]

fig = plt.figure()
ax = fig.add_subplot(111)
ax.axes.get_yaxis().set_visible(False)
ax.set_aspect(1)

for i, (num, cat) in enumerate(data):

    if i > 0:
        x_start += data[i-1][0] # get previous end position
    else:
        x_start = i             # start from 0

    x1 = [x_start, x_start+num]

    y1 = [0, 0]
    y2 = [1, 1]

    if cat == 1:
        plt.fill_between(x1, y1, y2=y2, color='red')
    if cat == 2:
        plt.fill_between(x1, y1, y2=y2, color='orange')
    if cat == 3:
        plt.fill_between(x1, y1, y2=y2, color='yellow')

plt.ylim(1, 0)
plt.show()

Answer 4

这是您可以开始的一种方法：

from matplotlib import pyplot as plt

A = [23,45,56,78,32,11]
B = [44,56,78,98]
C = [23,46,67,79]

x = []
y = []
for idx, lst in enumerate((A, B, C)):
    for time in lst:
        x.append(time)
        y.append(idx) 

plt.ylim((-3,5))
plt.yticks([0, 1, 2], ['A', 'B', 'C'])
plt.scatter(x,y, color='r', s=70)
plt.show()

Answer 5

您可能需要考虑在 Edward Tufte 的The Visual Display of Quantitative Information 的封面上使用的火车时刻表显示。这对于显示不同时间的事件变化率很有用（参见第 31 页，第 2 版的解释），但这仅适用于您的事件发生在不规则时间。

无论哪种方式，其他答案都为您的第二个请求提供了很好的选择。您可能只想绘制线条，使用 pyplot（或轴）plot(x) 命令。您可以更改其他答案中显示的标签，以便它们是代表您的事件的文本。最后为了模拟火车时刻表图中显示的效果，您可以使用 pyplot grid 方法（或 axes.xaxis.grid）设置网格。