一、matplotlib基础
from matplotlib import pyplot as plt
"""设置图片大小"""
plt.figure(figsize=(16,6),dpi=80)
"""准备数据"""
x = range(2,26,2) #x轴，数据是一个可迭代对象
y = [15,13,14.5,17,20,25,26,26,27,22,18,15] #y轴数据也是一个可迭代对象
"""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(_xtick_labels[::2]) #当列表太密集可以设置列表步长调整间距
plt.yticks(range(min(y),max(y)+1))
"""图形保存"""
# plt.savefig('t1.png')
"""图形显示"""
plt.show()
二、折线图基础
import random
"""
如果列表a表示10点到12点的每一分钟的气温,如何绘制折线图观察每分钟气温的变化情况?
a= [random.randint(20,35) for i in range(120)]
用matplotlib用图形画出变化的折线图
"""
from matplotlib import pyplot as plt
import matplotlib
from matplotlib import font_manager
#方式一
#windows和linux设置字体
# font = {'family' : 'SimHei'}
# matplotlib.rc('font', **font)
#方式二
my_font = font_manager.FontProperties(fname='font/simsun.ttc')
x = range(120)
y = [random.randint(20,35) for i in range(120)]
plt.figure(figsize=(13,8),dpi=80)
plt.plot(x,y)
#设置x的轴的刻度
_x = list(x) #只有列表才可以取步长，range不可以取步长
_xtick_labels = ['10点{}分'.format(i) for i in range(60)]
_xtick_labels += ['11点{}分'.format(i) for i in range(60)]
#取步长，数字和字符串一一对应，数据的长度一样
plt.xticks(_x[::3],_xtick_labels[::3], rotation=45,fontproperties=my_font) #rotation旋转的度数
#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点每分钟的气温变化情况',fontproperties=my_font)
plt.show()
三、交女朋友数量走势图
# -*- coding: utf-8 -*-
"""
@Datetime: 2018/11/17
@Author: Zhang Yafei
"""
"""
假设大家在30岁的时候,根据自己的实际情况,统计出来了从11岁到30岁每年交的女(男)朋友的数量如列表a,请绘制出该数据的折线图,以便分析自己每年交女(男)朋友的数量走势
a = [1,0,1,1,2,4,3,2,3,4,4,5,6,5,4,3,3,1,1,1]
要求:
y轴表示个数
x轴表示岁数,比如11岁,12岁等
"""
from matplotlib import pyplot as plt
from matplotlib import font_manager
#解决中文字体正常显示
my_font = font_manager.FontProperties(fname='font/simsun.ttc')
#准备数据
x = range(11,31)
y = [1,0,1,1,2,4,3,2,3,4,4,5,6,5,4,3,3,1,1,1]
#设置图形大小
plt.figure(figsize=(11,6),dpi=80)
#设置x,y轴的刻度
_x = list(x)
_xtick_labels = ['{}岁'.format(i) for i in _x]
plt.xticks(_x,_xtick_labels,rotation=45,fontproperties=my_font)
plt.yticks(range(0,9))
#绘制网格
plt.grid(alpha=0.4) #alpha透明度
#设置描述信息
plt.xlabel('年龄',fontproperties=my_font)
plt.ylabel('个数',fontproperties=my_font)
plt.title('11-30岁交女朋友数量走势图',fontproperties=my_font)
plt.plot(x,y)
plt.show()
四、交女朋友数量走势图2
# -*- coding: utf-8 -*-
"""
@Datetime: 2018/11/17
@Author: Zhang Yafei
"""
"""
假设大家在30岁的时候,根据自己的实际情况,统计出来了你和你同桌各自从11岁到30岁每年交的女(男)朋友的数量如列表a和b,请在一个图中绘制出该数据的折线图,以便比较自己和同桌20年间的差异,同时分析每年交女(男)朋友的数量走势
a = [1,0,1,1,2,4,3,2,3,4,4,5,6,5,4,3,3,1,1,1]
b = [1,0,3,1,2,2,3,3,2,1 ,2,1,1,1,1,1,1,1,1,1]
要求:
y轴表示个数
x轴表示岁数,比如11岁,12岁等
"""
from matplotlib import pyplot as plt
from matplotlib import font_manager
#解决中文字体正常显示
my_font = font_manager.FontProperties(fname='font/simsun.ttc')
#准备数据
x = range(11,31)
y_1 = [1,0,1,1,2,4,3,2,3,4,4,5,6,5,4,3,3,1,1,1]
y_2 = [1,0,3,1,2,2,3,3,2,1 ,2,1,1,1,1,1,1,1,1,1]
#设置图形大小
plt.figure(figsize=(11,6),dpi=80)
#设置x,y轴的刻度
_x = list(x)
_xtick_labels = ['{}岁'.format(i) for i in _x]
plt.xticks(_x,_xtick_labels,rotation=45,fontproperties=my_font)
# plt.yticks(range(0,9))
#绘制网格
plt.grid(alpha=0.4) #alpha透明度
#设置描述信息
plt.xlabel('年龄',fontproperties=my_font)
plt.ylabel('个数',fontproperties=my_font)
plt.title('11-30岁交女朋友数量走势图',fontproperties=my_font)
plt.plot(x,y_1,label='自己',color='orange',linestyle=':')
plt.plot(x,y_2,label='同桌',color='cyan',linestyle='--')
plt.legend(prop=my_font,loc='upper left')
plt.show()
五、散点图
# -*- coding: utf-8 -*-
"""
@Datetime: 2018/11/17
@Author: Zhang Yafei
"""
"""
假设通过爬虫你获取到了北京2016年3,10月份每天白天的最高气温(分别位于列表a,b),那么此时如何寻找出气温和随时间(天)变化的某种规律?
a = [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]
b = [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]
"""
from matplotlib import pyplot as plt
from matplotlib import font_manager
#设置中文字体
my_font = font_manager.FontProperties(fname='font/simsun.ttc')
#设置图形大小
plt.figure(figsize=(13,6),dpi=80)
#数据准备
x_3 = range(1,32)
x_10 = range(51,82)
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]
#使用scatter绘制散点图和折线图的唯一区别
plt.scatter(x_3,y_3,label='3月份')
plt.scatter(x_10,y_10,label='10月份')
plt.legend(loc='upper left',prop=my_font)
#调整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)
#添加描述信息
plt.xlabel('时间',fontproperties=my_font)
plt.ylabel('温度',fontproperties=my_font)
plt.title('3月份和10月份温度对比图',fontproperties=my_font)
#显示
plt.show()
六、条形图
# -*- coding: utf-8 -*-
"""
@Datetime: 2018/11/17
@Author: Zhang Yafei
"""
"""
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
"""
from matplotlib import pyplot as plt
from matplotlib import font_manager
my_font = font_manager.FontProperties(fname='font/simsun.ttc')
plt.figure(figsize=(15,8),dpi=80)
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]
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()
七、横条形图
"""
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
"""
from matplotlib import pyplot as plt
from matplotlib import font_manager
my_font = font_manager.FontProperties(fname='font/simsun.ttc')
plt.figure(figsize=(15,8),dpi=80)
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]
plt.barh(range(len(a)),b,height=0.3,color='orange')
plt.yticks(range(len(a)),a,fontproperties=my_font)
plt.grid(alpha=0.4)
# plt.savefig('movie.png')
plt.show()
八、绘制多次条形图
# -*- coding: utf-8 -*-
"""
@Datetime: 2018/11/17
@Author: Zhang Yafei
"""
"""
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]
"""
from matplotlib import pyplot as plt
from matplotlib import font_manager
my_font = font_manager.FontProperties(fname='font/simsun.ttc')
plt.figure(figsize=(15,8),dpi=80)
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.bar(range(len(a)),b_14,width=bar_width,label='14日')
plt.bar(x_15,b_15,width=bar_width,label='15日')
plt.bar(x_16,b_16,width=bar_width,label='16日')
plt.legend(prop=my_font)
plt.xticks(x_14,a,fontproperties=my_font)
plt.grid(alpha=0.4)
# plt.savefig('movie.png')
plt.show()
九、直方图
# -*- coding: utf-8 -*- """ @Datetime: 2018/11/17 @Author: Zhang Yafei """ """ 直方图：分布状态 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 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 num_bins = (max(a)-min(a))//d #设置图形大小 plt.figure(figsize=(15,8),dpi=80) plt.hist(a,num_bins) #频数分布直方图 # plt.hist(a,num_bins,density=True) #频率分布直方图 #设置x轴的刻度 plt.xticks(range(min(a),max(a)+d,d)) plt.grid(alpha=0.3) plt.show()
十、案例
# -*- coding: utf-8 -*- """ @Datetime: 2018/11/17 @Author: Zhang Yafei """ """ 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] """ from matplotlib import pyplot as plt from matplotlib import font_manager 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] plt.figure(figsize=(13,6),dpi=80) plt.bar(range(len(quantity)),quantity,width=1) #设置x轴的刻度 _x = [i-0.5 for i in range(13)] _xtick_labels = interval + [150] plt.xticks(_x,_xtick_labels) plt.show()
