import pandas as pd
import numpy as np
import matplotlib.font_manager as fm
font_path = 'C:/Windows/Fonts/NGULIM.TTF'
fontprop = fm.FontProperties(fname=font_path, size=15)
font_family = fm.FontProperties(fname=font_path).get_name()

plt.rcParams["font.family"] = font_family

years = range(2008,2021)
pieces = [] #전체 연도의 리스트를 합칠 것
columns = ['name','gender','births']

for year in years:
    path = 'korea/y{}.txt'.format(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='gender',aggfunc=sum)
total_births

total_births = names.pivot_table('births', index='year',columns='gender',aggfunc=sum)
total_births.plot(title='total births(gender/year)')

def add_prop(group):
    group['prop'] = group.births / group.births.sum()
    return group

names = names.groupby(['year','gender']).apply(add_prop)
names

names.groupby(['year','gender']).prop.sum()

names

def get_top100(group):
    return group.sort_values(by='births',ascending=False)[:100]

grouped = names.groupby(['year','gender'])
top100 = grouped.apply(get_top100)
top100

top100.reset_index(inplace = True , drop = True)
top100

boys = top100[top100.gender == 'M']
girls = top100[top100.gender == 'F']

total_births = top100.pivot_table('births',index ='year',columns='name',aggfunc=sum)
total_births.info()

total_births

total_births[['민준','하준','서연','지우']]

subset = total_births[['민준','하준','서연','지우']]
subset.plot(subplots=True,figsize=(12,10),grid=False,title='Number of birth per year')

table = top100.pivot_table('prop', index = 'year',columns='gender',aggfunc=sum)
table

import matplotlib.pyplot as plt
plt.figure()
table = top100.pivot_table('prop', index = 'year',columns='gender',aggfunc=sum)

table.plot(title='Sum of table100.prop by year and sex',
           yticks=np.linspace(0.5, 0.7, 5), xticks=range(2008, 2021, 1))

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

prop_cumsum = df.sort_values(by='prop',ascending=False).prop.cumsum()
prop_cumsum.values.searchsorted(0.5)+1

prop_cumsum[:10]

prop_cumsum.values

df = boys[boys.year == 2020]
y2020 = df.sort_values(by='prop',ascending=False).prop.cumsum()
y2020.values.searchsorted(0.5)+1

def get_quantile_count(group, q=0.5):
    group = group.sort_values(by='prop', ascending=False)
    return group.prop.cumsum().values.searchsorted(q) + 1

diversity = top100.groupby(['year', 'gender']).apply(get_quantile_count)
diversity = diversity.unstack('gender')
fig = plt.figure()
diversity.plot(title="Number of popular names in top 50%")

get_last_letter= lambda x: x[-1]
last_letters= names.name.map(get_last_letter)
last_letters.name= 'last_letter'

table = names.pivot_table('births', index=last_letters, columns=['gender', 'year'], aggfunc=sum)

subtable= table.reindex(columns=[2008,2010,2020], level='year')
subtable.head()

subtable.sum()
letter_prop= subtable / subtable.sum()
letter_prop

import matplotlib.pyplot as plt

fig, axes = plt.subplots(2, 1, figsize=(30, 11))
letter_prop['M'].plot(kind='bar', rot=0, ax=axes[0], title='Male')
letter_prop['F'].plot(kind='bar', rot=0, ax=axes[1], title='Female',
                      legend=False)