《利用Python进行数据分析》第二章-学习笔记

注：使用软件版本为anaconda3-4-3.1

#python常用基础包
import matplotlib.pyplot as plt
import pylab as py
import math as m
import scipy.stats as stats
import numpy as np
import pandas as pd

#加载1880年的数据，并以name、sex、births为列
names1880=pd.read_csv('names/yob1880.txt',names=['name','sex','births'])
names1880.head()

	name	sex	births
0	Mary	F	7065
1	Anna	F	2604
2	Emma	F	2003
3	Elizabeth	F	1939
4	Minnie	F	1746

#计算1880年男女出生人数（以sex为行，对births求和）
names1880.groupby(['sex']).births.sum()
# names1880.groupby(['sex']).sum()

sex
F     90993
M    110493
Name: births, dtype: int64

#将历年数据整合并添加‘year’列
years=range(1880,2011)
pieces=[]
columns=['name','sex','births']
for year in years:
    path='names/yob%d.txt' %year
    frame=pd.read_csv(path,names=columns)
    frame['year']=year
    pieces.append(frame)
names=pd.concat(pieces,ignore_index=True) 
names.head()

	name	sex	births	year
0	Mary	F	7065	1880
1	Anna	F	2604	1880
2	Emma	F	2003	1880
3	Elizabeth	F	1939	1880
4	Minnie	F	1746	1880

#按年份统计男女的总出生人数
total_births=names.pivot_table('births',index='year',columns='sex',aggfunc=sum)
#total_births.head()
total_births.plot()
plt.show()

#添加每年每个名字在对应性别中的比例
def add_prop(group):
    births=gr