《利用Python进行数据分析》笔记---第2章--1880-2010年间全美婴儿姓名

写在前面的话：

实例中的所有数据都是在GitHub上下载的，打包下载即可。

地址是：http://github.com/pydata/pydata-book

还有一定要说明的：

我使用的是Python2.7，书中的代码有一些有错误，我使用自己的2.7版本调通。

# coding: utf-8
import pandas as pd
import numpy as np
names1880 = pd.read_csv('D:\Source Code\pydata-book-master\ch02\\names\yob1880.txt', names=['name','sex','births'])
names1880

names1880.groupby('sex').births.sum()

years = range(1880, 2011)
pieces = []
columns = ['name','sex','births']
for year in years:
    path = 'D:\Source Code\pydata-book-master\ch02\\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

total_births = names.pivot_table('births', index='year', columns='sex', aggfunc=sum)
total_births.tail()

total_births.plot(title='Total births by sex and year')
def add_group(group):
    births = group.births.astype(float)
    group['prop'] = births / births.sum()
    return group
names = names.groupby(['year','sex']).apply(add_group)
names
np.allclose(names.groupby(['year','sex']).prop.sum(),1)
def get_top1000(group):
    return group.sort_index(by='births',ascending=False)[:1000]
grouped = names.groupby(['year','sex'])
top1000 = grouped.apply(get_top1000)
top1000

boys = top1000[top1000.sex == 'M']
girls = top1000[top1000.sex == 'F']

total_births = top1000.pivot_table('births', index='year', columns='name', aggfunc=sum)
total_births
subset = total_births[['John','Harry','Mary','Marilyn']]
subset.plot(subplots=True,figsize=(12,10),grid=False,title="Number of births per year")

table = top1000.pivot_table('prop',index='year',columns='sex',aggfunc=sum)
table.plot(title='sum of table1000.prop by year and sex',yticks=np.linspace(0,1.2,13),xticks=range(1880,2020,10))

df = boys[boys.year == 2010]
df

prop_cumsum = df.sort_index(by='prop', ascending=False).prop.cumsum()
prop_cumsum[:10]
prop_cumsum.searchsorted(0.5)

df = boys[boys.year == 1900]
in1900 = df.sort_index(by='prop', ascending=False).prop.cumsum()
in1900.searchsorted(0.5)+1

def get_quantile_count(group, q=0.5):
    group = group.sort_index(by='prop',ascending=False)
    return group.prop.cumsum().searchsorted(q)+1
diversity = top1000.groupby(['year','sex']).apply(get_quantile_count)
diversity = diversity.unstack('sex')
diversity.head()

get_last_letter = lambda x:x[-1]
last_letter = names.name.map(get_last_letter)
last_letter.name = 'last_letter'
table = names.pivot_table('births', index=last_letter, columns=['sex','year'], aggfunc=sum)

subtable = table.reindex(columns=[1910,1960,2010], level='year')
subtable.head()
subtable.sum()
letter_prop = subtable / subtable.sum().astype(float)

import matplotlib.pyplot as plt
fig,axex = plt.subplots(2,1,figsize=(10,8))
letter_prop['M'].plot(kind='bar',rot=0,ax=axex[0],title='Male')
letter_prop['F'].plot(kind='bar',rot=0,ax=axex[1],title='Female',legend=False)

letter_prop = table / table.sum().astype(float)
dny_ts = letter_prop.ix[['d','n','y'],'M'].T
dny_ts.head()
dny_ts.plot()

all_names = top1000.name.unique()
mask = np.array(['lesl' in x.lower() for x in all_names])
lesley_like = all_names[mask]
lesley_like

filtered = top1000[top1000.name.isin(lesley_like)]
filtered.groupby('name').births.sum()

table = filtered.pivot_table('births', index='year', columns='sex', aggfunc = 'sum')
table = table.div(table.sum(1), axis = 0)
table.tail()
table.plot(style={'M':'k-','F':'k--'})