2020-10-25 数据科学包学习第二天笔记Matplotlib

绘制散点图(plt.scatter)

1.北京三月份和十月份气温对比散点图

from matplotlib import pyplot as plt
from matplotlib import font_manager

my_font = font_manager.FontProperties(fname="C:\Windows\Fonts\msyh.ttc")
x1 = range(1,32)
x2 = range(50,81)
y1 = [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]
y2 = [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]

plt.figure(figsize=(20,8))
plt.scatter(x1,y1,label="3月份")
plt.scatter(x2,y2,label="10月份")

x = list(x1)+list(x2)
x1_lable = ["3月{0}日".format(i) for i in x1]
x2_lable = ["10月{0}日".format(i) for i in x1]
x_lable = x1_lable+x2_lable
plt.xticks(x[::5],x_lable[::5],fontproperties = my_font)

plt.legend(prop = my_font)
plt.xlabel("日期",fontproperties = my_font)
plt.ylabel("温度（℃）",fontproperties = my_font)

plt.show()

绘制条形图

1.电影票房条形图(plt.barh)

from matplotlib import pyplot as plt
from matplotlib import font_manager
my_font = font_manager.FontProperties(fname="C:\Windows\Fonts\msyh.ttc")

x = ["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"]
y = [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]
_x =range(len(x))

plt.figure(figsize=(20,8))
plt.barh(_x,y,height=0.2,color="orange")
plt.yticks(_x,x,fontproperties=my_font)

plt.xlabel("票房数（亿）",fontproperties = my_font)
plt.ylabel("电影名",fontproperties = my_font)

plt.show()

注意: barh——>height,yticks, bar——>width,xticks legend里面是prop=my_font,其余里面是fontproperties=my_font

2.三日电影票房统计图(plt.bar)

from matplotlib import pyplot as plt
from matplotlib import font_manager
my_font = font_manager.FontProperties(fname="C:\Windows\Fonts\msyh.ttc")

a = ["猩球崛起3：终极之战","敦刻尔克","蜘蛛侠：英雄归来","战狼2"]
x_14 = range(len(a))
x_15 = [i+0.2 for i in x_14]
x_16 = [i+0.2*2 for i in x_14]
b_16 = [15746,312,4497,319]
b_15 = [12357,156,2045,168]
b_14 = [2358,399,2358,362]

plt.bar(x_14,b_14,width=0.2,color="cyan",label="9月14日")
plt.bar(x_15,b_15,width=0.2,color = "blue",label="9月15日")
plt.bar(x_16,b_16,width=0.2,color="orange",label="9月16日")

plt.xticks(x_15,a,fontproperties=my_font)

plt.legend(prop=my_font)
plt.show()

绘制直方图

1.250部电影的片长直方图（plt.hist）

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]
bin_width = 3 #组距，每个小组两个端点的距离
num_bins = int(max(a)-min(a)/bin_width)  #组数要合适，太少有较大统计误差，太多数据规律不明显

plt.figure(figsize=(20,8))
plt.hist(a,num_bins)
#plt.hist(a,[min(a)+i*bin_width for in range(num_bins)])
              #可以传入一个列表，长度为组数，值为分组依据，当组距不均匀的时候使用
#plt.hist(a,num_bins,normed=1)
             #normed=1,是否绘制频率分布直方图，默认为频数直方图
plt.xticks(list(range(min(a),max(a)))[::bin_width])

plt.show()

2.根据从家到上班地所需时间，抽样统计数据，绘制成直方图（用plt.bar方法）

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]

num = len(quantity)
a = list(range(num))
x = [i-0.5 for i in range(num+1)]
plt.bar(a,quantity,width=1)

plt.xticks(x,interval+[150])

plt.grid(alpha=0.4)
plt.show()

常用画图工具：百度echart,plotly,seaborn