matplotlib

matplotlib库的使用

matplotlib库由各种可视化类结构构成，内部结构复杂，受到MATLAB的启发。

matplotlib.pyplot是绘制各类可视化图形的命令字库，相当于字库。

matplotlib的基本要点

设置图片大小

示例1

from matplotlib import pyplot as plt

x = range(2,26,2)
y = [15,13,14,5,17,20,25,26,27,22,18,15]

#设置图片的大小
plt.figure(figsize=(20,8),dpi=88)

#绘图
plt.plot(x,y)

#设置x轴的刻度
_xtick_labels = [i/2 for i in range(4,49)]
plt.xticks(range(25,50))
plt.yticks(range(min(y),max(y)+1))
plt.savefig('./t1.png')
#展示图形
plt.show()

设置中文显示

给图片添加描述信息

示例2

from matplotlib import pyplot as plt
import random
from matplotlib import font_manager
#windos和linuxd的字体设置
# font = {'family':'MicroSoft YaHei,',
#         'weight':'bold',
#         'size':'larger'}
# matplotlib.rc("font",family='MicroSoft YaHei',weight='blod')
# matplotlib.rc("font",**font)
#另一种设置字体的方式
my_font = font_manager.FontProperties(fname='C:\WINDOWS\FONTS\SIMFANG.TTF')
x = range(0,120)
y = [random.randint(20,35) for i in range(120)]
plt.figure(figsize=(20,8),dpi=80)
plt.plot(x,y)
#调整x轴的刻度
_xtick_labels = ["10点{}分".format(i) for i in range(120)]
_xtick_labels += ["11点{}分".format(i) for i in range(120)]
#取步长
plt.xticks(list(x)[::3],_xtick_labels[::3],rotation=45,fontproperties=my_font)

#添加描述信息
plt.xlabel("时间",fontproperties=my_font)
plt.ylabel("温度 单位()",fontproperties=my_font)
plt.title("10点到12点的气温变化情况",fontproperties=my_font)
plt.show()

 自定义绘图风格

添加图例

 

示例3

from matplotlib import pyplot as plt
from matplotlib import font_manager

my_font = font_manager.FontProperties(fname='C:\WINDOWS\FONTS\SIMFANG.TTF')
y_1 = [1,0,1,1,2,4,3,2,3,4,4,5,6,5,4,3,1,1,1]
y_2 = [1,0,2,1,3,4,0,1,3,3,4,2,1,2,1,1,1,1,1]
x = range(11,30)
plt.figure(figsize=(20,8),dpi=80)
plt.plot(x,y_1,label="自己")
plt.plot(x,y_2,label="同桌")
# 设置x的刻度
_xtck_labels = ["{}岁".format(i) for i in x]
plt.xticks(x,_xtck_labels,fontproperties=my_font)

# 绘制网
plt.grid(alpha=0.4) #透明度
# 添加图例
plt.legend(prop=my_font,loc='upper left')
plt.show()

总结

思维导图

 

import matplotlib.pyplot as plt

plt.plot([0,2,4,6,8],[3,1,4,5,2])
plt.ylabel("greade")
plt.xlabel("xx")
plt.axes([-1,10,0,6])
plt.savefig('test',dpi=600)
plt.show()

指定绘图区域

import matplotlib.pyplot as plt
import numpy as np
def f(t):
    return np.exp(-t)*np.cos(2*np.pi*t)
a = np.arange(0.0,5.0,0.02)
plt.subplot(211)
plt.plot(a,f(a))
plt.subplot(212)
plt.plot(a,np.cos(2*np.pi*a),'r--')
plt.show()

format_string：控制曲线的格式字符串

import matplotlib.pyplot as plt
import numpy as np
a = np.arange(10)
plt.plot(a,a*1.5,'go-',a,a*2.5,'rx',a,a*3.5,'*',a,a*4.5,'b-.')
plt.show()

中文显示方法

方式一：

import matplotlib
matplotlib.rcParams['font.family'] = 'SimHei'

方式二:在需要显示中文的地方使用

plt.ylabel('纵轴',fontproperties='SimHei',fontsize=20)

import matplotlib.pyplot as plt
import numpy as np
a = np.arange(0.0,5.0,0.02)
plt.plot(a,np.cos(2*np.pi*a),'r--')
plt.xlabel('横轴：时间',fontproperties='SimHei',fontsize=15,color='green')
plt.ylabel('纵轴:振幅',fontproperties='SimHei',fontsize=15)
plt.title('正弦波实例$y=cos(2\pi x)$',fontproperties='SiHei',fontsize=25)
plt.text(2,1,r'$\mu=100$',fontsize=15)
plt.axis([-1,6,-2,2])
plt.grid(True)
plt.show()

绘制箭头

plt.annotate(r'$\mu=100$',xy=(2,1),xytext=(2,1.5),
arrowprops=dict(facecolor='black',shrink=0.1,width=2))

plt.subplot2grid()

设定网格选中网格，确定选中行列中的区域数量，编号从零开始。

GridSpace类

绘制饼图

import matplotlib.pyplot as plt
labels = 'F','H','D','L'

size=[15,30,20,10]

explode = (0,0.1,0,0)

plt.pie(size,explode=explode,labels=labels,autopct='%1.1f%%',shadow=True,startangle=90)

 绘制散点图

from matplotlib import pyplot as plt
from matplotlib import font_manager

my_font = font_manager.FontProperties(fname='C:\WINDOWS\FONTS\SIMFANG.TTF')
y_3 = [11,17,16,11,12,11,12,6,6,7,8,9,12,15,14,17,18,21,16,17,20,14,15,15,15,19,21,22,22,22,23]
y_10 = [26,26,28,19,21,17,16,19,18,20,20,19,22,23,17,20,21,20,22,15,11,15,5,13,17,10,11,13,12,13,6]
x_3 = range(1,32)
x_10 = range(51,82)
#设置图形大的大小
plt.figure(figsize=(20,8),dpi=80)
plt.scatter(x_3,y_3,label="3月份")
plt.scatter(x_10,y_10,label="10月份")
# 设置x的刻度
_x = list(x_3)+list(x_10)
_xtick_labels = ["3月{}日".format(i) for i in x_3]
_xtick_labels += ["10月{}日".format(i-50) for i in x_10]
plt.xticks(_x[::3],_xtick_labels[::3],fontproperties=my_font,rotation=45)

# 绘制网
plt.grid(alpha=0.4) #透明度
# 添加图例
plt.legend(prop=my_font,loc='upper left')
#添加描述信息
plt.xlabel('时间',fontproperties=my_font)
plt.xlabel('温度',fontproperties=my_font)
plt.title('温度散点',fontproperties=my_font)
plt.show()

散点图应用的更多场景

不同条件（维度之间）内在的关联关系

观察数据的离散聚合程度

绘制条形图

假设你获取到了2017年内地电影票房前20的电影(列表a)和电影票房数据(列表b),那么如何更加直观的展示该数据?

a = ["战狼2","速度与激情8","功夫瑜伽","西游伏妖篇","变形金刚5：最后的骑士","摔跤吧！爸爸","加勒比海盗5：死无对证","金刚：骷髅岛","极限特工：终极回归","生化危机6：终章","乘风破浪","神偷奶爸3","智取威虎山","大闹天竺","金刚狼3：殊死一战","蜘蛛侠：英雄归来","悟空传","银河护卫队2","情圣","新木乃伊",]

b=[56.01,26.94,17.53,16.49,15.45,12.96,11.8,11.61,11.28,11.12,10.49,10.3,8.75,7.55,7.32,6.99,6.88,6.86,6.58,6.23] 单位:亿


数据来源: http://58921.com/alltime/2017

from matplotlib import pyplot as plt
from matplotlib import font_manager

my_font = font_manager.FontProperties(fname='C:\WINDOWS\FONTS\SIMFANG.TTF')
a = ["战狼2","速度与激情8","功夫瑜伽","西游伏妖篇","变形金刚5：最后的骑士","摔跤吧！爸爸","加勒比海盗5：死无对证","金刚：骷髅岛","极限特工：终极回归","生化危机6：终章","乘风破浪","神偷奶爸3","智取威虎山","大闹天竺","金刚狼3：殊死一战","蜘蛛侠：英雄归来","悟空传","银河护卫队2","情圣","新木乃伊",]

b=[56.01,26.94,17.53,16.49,15.45,12.96,11.8,11.61,11.28,11.12,10.49,10.3,8.75,7.55,7.32,6.99,6.88,6.86,6.58,6.23]

#设置图形大的大小
plt.figure(figsize=(20,15),dpi=80)
plt.bar(range(len(a)),b,width=0.3)
plt.xticks(range(len(a)),a,fontproperties=my_font,rotation=90)
plt.savefig('./movie.png')
plt.show()

from matplotlib import pyplot as plt
from matplotlib import font_manager

my_font = font_manager.FontProperties(fname='C:\WINDOWS\FONTS\SIMFANG.TTF')
a = ["战狼2","速度与激情8","功夫瑜伽","西游伏妖篇","变形金刚5：最后的骑士","摔跤吧！爸爸","加勒比海盗5：死无对证","金刚：骷髅岛","极限特工：终极回归","生化危机6：终章","乘风破浪","神偷奶爸3","智取威虎山","大闹天竺","金刚狼3：殊死一战","蜘蛛侠：英雄归来","悟空传","银河护卫队2","情圣","新木乃伊",]

b=[56.01,26.94,17.53,16.49,15.45,12.96,11.8,11.61,11.28,11.12,10.49,10.3,8.75,7.55,7.32,6.99,6.88,6.86,6.58,6.23]

#设置图形大的大小
plt.figure(figsize=(20,15),dpi=80)
plt.barh(range(len(a)),b,height=0.3)
plt.yticks(range(len(a)),a,fontproperties=my_font)
plt.savefig('./movie1.png')
plt.show()

假设你知道了列表a中电影分别在2017-09-14(b_14), 2017-09-15(b_15), 2017-09-16(b_16)三天的票房,为了展示列表中电影本身的票房以及同其他电影的数据对比情况,应该如何更加直观的呈现该数据?

a = ["猩球崛起3：终极之战","敦刻尔克","蜘蛛侠：英雄归来","战狼2"]
b_16 = [15746,312,4497,319]
b_15 = [12357,156,2045,168]
b_14 = [2358,399,2358,362]


数据来源: http://www.cbooo.cn/movieday

from matplotlib import pyplot as plt
from matplotlib import font_manager

my_font = font_manager.FontProperties(fname='C:\WINDOWS\FONTS\SIMFANG.TTF')
a = ["猩球崛起3：终极之战","敦刻尔克","蜘蛛侠：英雄归来","战狼2"]
b_16 = [15746,312,4497,319]
b_15 = [12357,156,2045,168]
b_14 = [2358,399,2358,362]
bar_width = 0.2
x_14 = list(range(len(a)))
x_15 = [i+bar_width for i in x_14]
x_16 = [i+bar_width*2 for i in x_14]
plt.figure(figsize=(20,8),dpi=80)

plt.bar(range(len(a)),b_14,width=bar_width,label='9月14日')
plt.bar(x_15,b_15,width=bar_width,label='9月15日')
plt.bar(x_16,b_16,width=bar_width,label='9月16日')

#设置图例
plt.legend(prop=my_font)
plt.xticks(x_15,a,fontproperties=my_font)
plt.show()

条形图的更多应用场景

数量统计

频率统计（市场饱和度）

绘制直方图

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]

from matplotlib import pyplot as plt
from matplotlib import font_manager

my_font = font_manager.FontProperties(fname='C:\WINDOWS\FONTS\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]

d = 3 #组距
num_bins = (max(a)-min(a))//d

#设置图形大的大小
plt.figure(figsize=(20,8),dpi=80)
# plt.hist(a,num_bins,)
plt.hist(a,num_bins,normed=True) #频数分布直方图
#设置x轴的长度
plt.xticks(range(min(a),max(a)+d,d))
plt.grid()
plt.show()

那么问题来了

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,这些数据能够绘制成直方图么?
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 = [836,2737,3723,3926,3596,1438,3273,642,824,613,215,47]

数据来源:https://en.wikipedia.org/wiki/Histogram
普查报告地址:https://www.census.gov/prod/2004pubs/c2kbr-33.pdf

from matplotlib import pyplot as plt
from matplotlib import font_manager

my_font = font_manager.FontProperties(fname='C:\WINDOWS\FONTS\SIMFANG.TTF')
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 = [836,2737,3723,3926,3596,1438,3273,642,824,613,215,47]

#设置图形的大小
plt.figure(figsize=(20,8),dpi=80)

plt.bar(range(12),quantity,width=1)

#设置x的刻度值
_x = [i-0.5 for i in range(13)]
_xtick_labels = interval+[150]
plt.xticks(_x,_xtick_labels)
plt.grid()
plt.show()

直方图更多的应用场景

用户的年龄分布状态
一段时间内用户点击次数的分布状态
用户活跃时间的分布状态

总节

matplotlib支持的图形是非常多的，如果有其他的需求，我们
可以查看一下url地址：
        http://matplotlib.org/gallery/index.html

在很多的时候我们可以选择很多的前端的框架来进行绘图例如：https://echarts.baidu.com/examples/#chart-type-scatter;

https://plot.ly/products/cloud/;http://seaborn.pydata.org/examples/scatterplot_matrix.html