数据科学之matplotlib库

入门实例：画折线图

from matplotlib import pyplot as pltx = range(2, 26, 2)
y = [15, 13, 14.5, 17, 20, 25, 26, 26, 24, 22, 18, 15]plt.plot(x, y)
plt.show()

设置图片大小

from matplotlib import pyplot as pltfig = plt.figure(figsize=(20, 8), dpi=80) # 实例化一个figure对象，并传递参数，在图像模糊时可以传入dpi参数，让图像更加清晰x = range(2, 26, 2)
y = [15, 13, 14.5, 17, 20, 25, 26, 26, 24, 22, 18, 15]plt.plot(x, y)plt.savefig("./sig_size.png") # 保存图片plt.show()

调整x轴/y轴上的刻度

from matplotlib import pyplot as pltfig = plt.figure(figsize=(10, 5))x = range(2, 26, 2)
y = [15, 13, 14.5, 17, 20, 25, 26, 26, 24, 22, 18, 15]plt.plot(x, y)
plt.xticks(x) # 设置x轴的刻度
# plt.xticks(x[::2]) # 当刻度太密集时可以使用列表的步长（间隔取值）来解决plt.show()

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)]

from matplotlib import pyplot as plt
import randomplt.figure(figsize=(20, 8))
x = range(120)random.seed(10) # 设置随机种子
y = [random.uniform(20, 35) for i in range(120)]plt.plot(x, y)# 设置x轴的字符串的刻度
_x_ticks = ["10点{}分".format(i) for i in x if i<60]
_x_ticks += ["11点{}分".format(i-60) for i in x if i>60]# 每隔5个选一个数据进行展示
# 为了让字符串不会覆盖，让字符串旋转90度显示
plt.xticks(x[::5], _x_ticks[::5], rotation=90)plt.show()

C:\software\Anaconda3\envs\tensorflow-gpu\lib\site-packages\matplotlib\backends\backend_agg.py:238: RuntimeWarning: Glyph 28857 missing from current font.font.set_text(s, 0.0, flags=flags)
C:\software\Anaconda3\envs\tensorflow-gpu\lib\site-packages\matplotlib\backends\backend_agg.py:238: RuntimeWarning: Glyph 20998 missing from current font.font.set_text(s, 0.0, flags=flags)
C:\software\Anaconda3\envs\tensorflow-gpu\lib\site-packages\matplotlib\backends\backend_agg.py:201: RuntimeWarning: Glyph 28857 missing from current font.font.set_text(s, 0, flags=flags)
C:\software\Anaconda3\envs\tensorflow-gpu\lib\site-packages\matplotlib\backends\backend_agg.py:201: RuntimeWarning: Glyph 20998 missing from current font.font.set_text(s, 0, flags=flags)

设置中文显示

from matplotlib import pyplot as plt
import randomplt.rcParams['font.sans-serif']=['SimHei'] #用来正常显示中文标签
plt.rcParams['axes.unicode_minus']=False #用来正常显示负号plt.figure(figsize=(20, 8))
x = range(120)random.seed(10) # 设置随机种子
y = [random.uniform(20, 35) for i in range(120)]plt.plot(x, y)# 设置x轴的字符串的刻度
_x_ticks = ["10点{}分".format(i) for i in x if i<60]
_x_ticks += ["11点{}分".format(i-60) for i in x if i>60]# 每隔5个选一个数据进行展示
# 为了让字符串不会覆盖，让字符串旋转90度显示
plt.xticks(x[::5], _x_ticks[::5], rotation=90)plt.show()

给图像添加描述信息

from matplotlib import pyplot as plt
import randomplt.rcParams['font.sans-serif']=['SimHei'] #用来正常显示中文标签
plt.rcParams['axes.unicode_minus']=False #用来正常显示负号plt.figure(figsize=(20, 8))
x = range(120)random.seed(10) # 设置随机种子
y = [random.uniform(20, 35) for i in range(120)]plt.plot(x, y)# 设置x轴的字符串的刻度
_x_ticks = ["10点{}分".format(i) for i in x if i<60]
_x_ticks += ["11点{}分".format(i-60) for i in x if i>60]# 每隔5个选一个数据进行展示
# 为了让字符串不会覆盖，让字符串旋转90度显示
plt.xticks(x[::5], _x_ticks[::5], rotation=90)
plt.xlabel("时间") # 设置x轴的label
plt.ylabel("温度(℃)") # 设置y轴的label
plt.title("10点到12点每分钟的时间变化情况")plt.show()

动手1

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 pltplt.rcParams['font.sans-serif']=['SimHei'] #用来正常显示中文标签
plt.rcParams['axes.unicode_minus']=False #用来正常显示负号y = [1,0,1,1,2,4,3,2,3,4,4,5,6,5,4,3,3,1,1,1]
x = range(11,31)#设置图形大小
plt.figure(figsize=(20,8),dpi=80)plt.plot(x,y)#设置x轴刻度
_xtick_labels = ["{}岁".format(i) for i in x]
plt.xticks(x,_xtick_labels)
plt.yticks(range(0,9))#绘制网格
plt.grid(alpha=0.1)#展示
plt.show()

动手2

from matplotlib import pyplot as pltplt.rcParams['font.sans-serif']=['SimHei'] #用来正常显示中文标签
plt.rcParams['axes.unicode_minus']=False #用来正常显示负号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]x = range(11,31)#设置图形大小
plt.figure(figsize=(20,8),dpi=80)plt.plot(x,y_1,label="自己",color="#F08080")
plt.plot(x,y_2,label="同桌",color="#DB7093",linestyle="--")#设置x轴刻度
_xtick_labels = ["{}岁".format(i) for i in x]
plt.xticks(x,_xtick_labels)
# plt.yticks(range(0,9))#绘制网格
plt.grid(alpha=0.4,linestyle=':')#添加图例
plt.legend(loc="upper right")#展示
plt.show()

绘制散点图

使用plt.scatter()方法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 pltplt.rcParams['font.sans-serif']=['SimHei'] #用来正常显示中文标签
plt.rcParams['axes.unicode_minus']=False #用来正常显示负号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)#设置图形大小
plt.figure(figsize=(20,8),dpi=80)#使用scatter方法绘制散点图,和之前绘制折线图的唯一区别
plt.scatter(x_3,y_3,label="3月份")
plt.scatter(x_10,y_10,label="10月份")#调整x轴的刻度
_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],rotation=45)#添加图例
plt.legend(loc="upper left")#添加描述信息
plt.xlabel("时间")
plt.ylabel("温度")
plt.title("标题")
#展示
plt.show()

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

from matplotlib import pyplot as pltplt.rcParams['font.sans-serif']=['SimHei'] #用来正常显示中文标签
plt.rcParams['axes.unicode_minus']=False #用来正常显示负号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]#设置图形大小
plt.figure(figsize=(20,15),dpi=80)
#绘制条形图
plt.bar(range(len(a)),b,width=0.3)
#设置字符串到x轴
plt.xticks(range(len(a)),a,rotation=90)plt.savefig("./movie.png")plt.show()

from matplotlib import pyplot as pltplt.rcParams['font.sans-serif']=['SimHei'] #用来正常显示中文标签
plt.rcParams['axes.unicode_minus']=False #用来正常显示负号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]#设置图形大小
plt.figure(figsize=(20,8),dpi=80)
#绘制条形图
plt.barh(range(len(a)),b,height=0.3,color="orange")
#设置字符串到x轴
plt.yticks(range(len(a)),a)plt.grid(alpha=0.3)
# plt.savefig("./movie.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]

from matplotlib import pyplot as pltplt.rcParams['font.sans-serif']=['SimHei'] #用来正常显示中文标签
plt.rcParams['axes.unicode_minus']=False #用来正常显示负号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 = 0.2x_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]#设置图形大小
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()#设置x轴的刻度
plt.xticks(x_15,a)plt.show()

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 pltplt.rcParams['font.sans-serif']=['SimHei'] #用来正常显示中文标签
plt.rcParams['axes.unicode_minus']=False #用来正常显示负号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
print(max(a),min(a),max(a)-min(a))
print(num_bins)#设置图形的大小
plt.figure(figsize=(20,8),dpi=80)
plt.hist(a,num_bins)#设置x轴的刻度
plt.xticks(range(min(a),max(a)+d,d))plt.grid()plt.show()

156 78 78
26

绘制子图

可以使用subplot()添加子图。

实例：创建2个子图，水平排列。

# 导入numpy库与matplotlib.pyplot库
import numpy as np
import matplotlib.pyplot as plt# 创建一个新的子图，网格1x2，序号为1，第一个数字是行数，第二个数字是列数，表示子图排列方式，第三个数字是子图的序号
plt.subplot(1, 2, 1)
plt.plot([1,2,3,4], [1,4,9,16], "go") # go 表示green circle，绿色圆点
# 设置子图标题
plt.title("1st subplot")# 创建一个新的子图，网格1x2，序号为2
plt.subplot(1, 2, 2)
plt.plot([1,2,3,4], [1,4,9,16], "r^") # r^ 表示 红色(red)三角
# 设置子图标题
plt.title("2nd subplot")# 设置标题
plt.suptitle("2 subplots")# 显示
plt.show()

第1题：请利用matplotlib编写一个程序，显示y=x*x+18这条抛物线。

import numpy as np
import matplotlib.pyplot as plt
x=[x for x in range(-100,100)]y=[]
for num in x:y.append(num*num+18)plt.plot(x,y)#展示
plt.show()

第2题：请利用matplotlib编写一个程序，除了显示y=x*x+18这条抛物线外，还要给图表和坐标轴加上标题（标题名字可以自己起）。

import numpy as np
import matplotlib.pyplot as pltplt.rcParams['font.sans-serif']=['SimHei'] #用来正常显示中文标签
plt.rcParams['axes.unicode_minus']=False #用来正常显示负号
x=[x for x in np.arange(-100,101,0.1)]y=[]
for num in x:y.append(num*num+18)plt.xlabel("x") # 设置x轴的label
plt.ylabel("y") # 设置y轴的label
plt.plot(x,y)
plt.title("y=x*x+18")#展示
plt.show()

第3题：请利用matplotlib编写一个程序，该程序能在一行中并列显示两个子图，一个子图是y=x*x，另一个子图是y=x。

# 导入numpy库与matplotlib.pyplot库
import numpy as np
import matplotlib.pyplot as plt# 创建一个新的子图，网格1x2，序号为1，第一个数字是行数，第二个数字是列数，表示子图排列方式，第三个数字是子图的序号
plt.subplot(1, 2, 1)
x1=[x for x in np.arange(-10,11,0.01) ]
y1=[]
for num in x1:y1.append(num*num)plt.plot(x1, y1, "g.")
# 设置子图标题
plt.title("subplot1")# 创建一个新的子图，网格1x2，序号为2
plt.subplot(1, 2, 2)
y3=x1plt.plot(x1, y3, "r.")
# 设置子图标题
plt.title("subplot2")# 设置标题
plt.suptitle("2 subplots")# 显示
plt.show()