import pandas as pd
import numpy as np

name1880 = pd.read_csv('/Users/lpd/Downloads/names/yob1880.txt',names=['name','sex','births'])

name1880.groupby('sex').births.sum()

years = range(1880,2012)
frames = []
for year in years:
    frame = pd.read_csv('/Users/lpd/Downloads/names/yob%d.txt'%year,names=['name','sex','births'])
    frame['year'] = year
    frames.append(frame)

names = pd.concat(frames, ignore_index=True)

names.describe()

names.year

total_births = names.pivot_table('births', rows='year',cols='sex',aggfunc=sum)

total_births.tail()

total_births.plot()

names

total_births['diff'] = total_births['F']/total_births['M']

total_births.tail()

total_births['diff'].plot()

total_births['diff']

names_pivot1 = names.pivot_table('births',rows='name',aggfunc=sum)

top_names = names_pivot1.order()[-10:]

top_names

top_names_list = list(top_names.index.values)

top_names_list

names_by_year = names.pivot_table('births',rows='year',cols='name',aggfunc=sum)

names_by_year[top_names_list].plot()

top5_names = top_names_list[5:]

names_by_year[top5_names].plot(subplots=True)

same_names = names.pivot_table('births',rows=['sex','name'],cols=['year'])