matplotlib描绘直方图

注意：没有处理过的原始数据才能进行直方图的绘制

假设你获取了250部电影的时长(列表a中),希望统计出这些电影时长的分布状态(比如时长为100分钟到120分钟电影的数量,出现的频率)等信息,你应该如何呈现这些数据?

a=[131, 98, 125, 131, 124, 139, 131, 117, 128, 108, 135, 138, 131, 102, 107, 114, 119, 128, 121, 142, 127, 130, 124, 101, 110, 116, 117, 110, 128, 128, 115, 99, 136, 126, 134, 95, 138, 117, 111,78, 132, 124, 113, 150, 110, 117, 86, 95, 144, 105, 126, 130,126, 130, 126, 116, 123, 106, 112, 138, 123, 86, 101, 99, 136,123, 117, 119, 105, 137, 123, 128, 125, 104, 109, 134, 125, 127,105, 120, 107, 129, 116, 108, 132, 103, 136, 118, 102, 120, 114,105, 115, 132, 145, 119, 121, 112, 139, 125, 138, 109, 132, 134,156, 106, 117, 127, 144, 139, 139, 119, 140, 83, 110, 102,123,107, 143, 115, 136, 118, 139, 123, 112, 118, 125, 109, 119, 133,112, 114, 122, 109, 106, 123, 116, 131, 127, 115, 118, 112, 135,115, 146, 137, 116, 103, 144, 83, 123, 111, 110, 111, 100, 154,136, 100, 118, 119, 133, 134, 106, 129, 126, 110, 111, 109, 141,120, 117, 106, 149, 122, 122, 110, 118, 127, 121, 114, 125, 126,114, 140, 103, 130, 141, 117, 106, 114, 121, 114, 133, 137, 92,121, 112, 146, 97, 137, 105, 98, 117, 112, 81, 97, 139, 113,134, 106, 144, 110, 137, 137, 111, 104, 117, 100, 111, 101, 110,105, 129, 137, 112, 120, 113, 133, 112, 83, 94, 146, 133, 101,131, 116, 111, 84, 137, 115, 122, 106, 144, 109, 123, 116, 111,111, 133, 150]

'''
Created on 2018年9月17日

@author: TuringEmmy
'''
# encoding=utf-8

from matplotlib import pyplot as plt
from matplotlib import font_manager

my_font = font_manager.FontProperties(fname="SIMFANG.TTF")

a = [131, 98, 125, 131, 124, 139, 131, 117, 128, 108, 135, 138, 131, 102, 107, 114, 119, 128, 121, 142, 127, 130, 124, 101, 110, 116, 117, 110, 128, 128, 115, 99, 136, 126, 134, 95, 138, 117, 111, 78, 132, 124, 113, 150, 110, 117, 86, 95, 144, 105, 126, 130, 126, 130, 126, 116, 123, 106, 112, 138, 123, 86, 101, 99, 136, 123, 117, 119, 105, 137, 123, 128, 125, 104, 109, 134, 125, 127, 105, 120, 107, 129, 116, 108, 132, 103, 136, 118, 102, 120, 114, 105, 115, 132, 145, 119, 121, 112, 139, 125, 138, 109, 132, 134, 156, 106, 117, 127, 144, 139, 139, 119, 140, 83, 110, 102, 123, 107, 143, 115, 136, 118, 139, 123, 112, 118, 125, 109, 119, 133, 112, 114, 122, 109, 106, 123, 116, 131, 127, 115, 118, 112, 135, 115, 146, 137, 116, 103, 144, 83, 123, 111, 110, 111, 100, 154, 136, 100, 118, 119, 133, 134, 106, 129, 126, 110, 111, 109, 141, 120, 117, 106, 149, 122, 122, 110, 118, 127, 121, 114, 125, 126, 114, 140, 103, 130, 141, 117, 106, 114, 121, 114, 133, 137, 92, 121, 112, 146, 97, 137, 105, 98, 117, 112, 81, 97, 139, 113, 134, 106, 144, 110, 137, 137, 111, 104, 117, 100, 111, 101, 110, 105, 129, 137, 112, 120, 113, 133, 112, 83, 94, 146, 133, 101, 131, 116, 111, 84, 137, 115, 122, 106, 144, 109, 123, 116, 111, 111, 133, 150]

# 计算组数
d = 3  # 组距
num_bins = (max(a) - min(a)) // d + 1
print(num_bins)

plt.figure(figsize=(20, 8), dpi=80)
plt.hist(a, 20, normed=1)  # normed将图形编程频率分布图

# 设置x轴的刻度
plt.xticks(range(min(a), max(a) + d, d))
# 这里需要注意(左闭右开)，如果不加d,最后有值娶不到
plt.grid(alpha=0.5)
plt.show()

plt.hist(a, 20, normed=1) # normed将图形编程频率分布图
hist的第二个参数表示划分成多少组
normed将图形编程频率分布图

运行效果：

二：用条形图绘制直方图

案例
在美国2004年人口普查发现有124 million的人在离家相对较远的地方工作.根据他们从家到上班地点所需要的时间，通过抽样统计（最后一列）出了下表的数据，这些数据怎么绘制成直方图：

这些数据是无法直接使用hist来绘制直方图的，但是可以通过条形图改造绘制成直方图

from matplotlib import pyplot as plt
from matplotlib import font_manager

my_font = font_manager.FontProperties(fname=’/usr/share/fonts/cjkuni-uming/uming.ttc’)

interval = [0,5,10,15,20,25,30,35,40,45,60,90]
width = [5,5,5,5,5,5,5,5,5,15,30,60]
quantity = [836,2737,3723,3926,3596,1438,3273,642,824,613,215,57]

plt.figure(figsize=(20, 8), dpi=80)

plt.bar(range(len(quantity)), quantity, width=1) # width=1 表示之间没有空隙，默认为0.8

_x = [i-0.5 for i in range(13)] # 设置起点在方格的左侧
_xtick_labels = interval+[150] # 最后一个间距是60，到150，将150添加到列表中

plt.xticks(_x, _xtick_labels)

plt.grid()

plt.show()

效果：
下面三行代码的效果
_x = [i for i in range(13)]
_xtick_labels = interval+[150] # 最后一个间距是60，到150，将150添加到列表中

plt.xticks(_x, _xtick_labels)

修改后的效果：

_x = [i-0.5 for i in range(13)] # 设置起点在方格的左侧
_xtick_labels = interval+[150] # 最后一个间距是60，到150，将150添加到列表中

plt.xticks(_x, _xtick_labels)