import pandas as pdfrom matplotlib import pyplot as plt
birth=pd.read_csv(r"https://raw.githubusercontent.com/jakevdp/data-CDCbirths/master/births.csv")
fig,ax=plt.subplots()birth=birth.iloc[:15067]
birth["day"]=birth["day"].astype(int)birth["date"]=pd.to_datetime({"year":birth["year"],"month":birth["month"],"day":birth["day"]},errors='coerce')
birth=birth[birth["date"].notnull()]

       year  month  day gender  births       date
0      1969      1    1      F    4046 1969-01-01
1      1969      1    1      M    4440 1969-01-01
2      1969      1    2      F    4454 1969-01-02
3      1969      1    2      M    4548 1969-01-02
4      1969      1    3      F    4548 1969-01-03

import numpy as np
import pandas as pd
from matplotlib import pyplot as plt
birth=pd.read_csv(r"https://raw.githubusercontent.com/jakevdp/data-CDCbirths/master/births.csv")
fig,ax=plt.subplots()birth=birth.iloc[:15067]
birth["day"]=birth["day"].astype(int)birth["date"]=pd.to_datetime({"year":birth["year"],"month":birth["month"],"day":birth["day"]},errors='coerce')
birth=birth[birth["date"].notnull()]#提取1986年-1988年男女出生人数数据，并转换成numpy的array格式
birth1986_female=np.array(birth.births[(birth["year"]==1986) & (birth["gender"]=="F")])
birth1986_male=np.array(birth.births[(birth["year"]==1986) & (birth["gender"]=="M")])
birth1987_female=np.array(birth.births[(birth["year"]==1987) & (birth["gender"]=="F")])
birth1987_male=np.array(birth.births[(birth["year"]==1987) & (birth["gender"]=="M")])
birth1988_female=np.array(birth.births[(birth["year"]==1988) & (birth["gender"]=="F")])
birth1988_male=np.array(birth.births[(birth["year"]==1988) & (birth["gender"]=="M")])#由于需要绘制多个箱线图，因此把这些数据放入一个列表
data=[birth1986_female,birth1986_male,birth1987_female,birth1987_male,birth1988_female,birth1988_male]
ax.boxplot(data,positions=[0,0.6,1.5,2.1,3,3.6]) #用positions参数设置各箱线图的位置
ax.set_xticklabels(["1986\nfemale","1986\nmale","1987\nfemale","1987\nmale","1988\nfemale","1988\nmale"]) #设置x轴刻度标签

plt.show()