Popular US Baby Names Since 1880

import math
import collections

import numpy as np
import pandas as pd
import matplotlib.pyplot as pp

%matplotlib inline

pd.options.display.max_rows = 8

open('names/yob2011.txt','r').readlines()[:10]

['Sophia,F,21842\n',
 'Isabella,F,19910\n',
 'Emma,F,18803\n',
 'Olivia,F,17322\n',
 'Ava,F,15503\n',
 'Emily,F,14258\n',
 'Abigail,F,13248\n',
 'Madison,F,12389\n',
 'Mia,F,11530\n',
 'Chloe,F,10991\n']

pd.read_csv('names/yob2011.txt')

	Sophia	F	21842
0	Isabella	F	19910
1	Emma	F	18803
2	Olivia	F	17322
3	Ava	F	15503
...	...	...	...
33903	Zylas	M	5
33904	Zyran	M	5
33905	Zyshawn	M	5
33906	Zytavion	M	5

33907 rows × 3 columns

pd.read_csv('names/yob2011.txt',names=['name','sex','number'])

	name	sex	number
0	Sophia	F	21842
1	Isabella	F	19910
2	Emma	F	18803
...	...	...	...
33905	Zyran	M	5
33906	Zyshawn	M	5
33907	Zytavion	M	5

33908 rows × 3 columns

pd.read_csv('names/yob2011.txt',names=['name','sex','number']).assign(year=2011)

	name	sex	number	year
0	Sophia	F	21842	2011
1	Isabella	F	19910	2011
2	Emma	F	18803	2011
...	...	...	...	...
33905	Zyran	M	5	2011
33906	Zyshawn	M	5	2011
33907	Zytavion	M	5	2011

33908 rows × 4 columns

allyears = pd.concat(pd.read_csv(f'names/yob{year}.txt',names=['name','sex','number']).assign(year=year)
                     for year in range(1880, 2019))

allyears.info()

<class 'pandas.core.frame.DataFrame'>
Int64Index: 1957046 entries, 0 to 32032
Data columns (total 4 columns):
 #   Column  Dtype 
---  ------  ----- 
 0   name    object
 1   sex     object
 2   number  int64 
 3   year    int64 
dtypes: int64(2), object(2)
memory usage: 59.7+ MB

allyears.year.min(), allyears.year.max()

(1880, 2018)

allyears.to_csv('allyears.csv.zip',index=False)

pd.options.display.max_rows = 6

allyears = pd.read_csv('allyears.csv.zip')

allyears

	name	sex	number	year
0	Mary	F	7065	1880
1	Anna	F	2604	1880
2	Emma	F	2003	1880
...	...	...	...	...
1957043	Zyrie	M	5	2018
1957044	Zyron	M	5	2018
1957045	Zzyzx	M	5	2018

1957046 rows × 4 columns

allyears_indexed = allyears.set_index(['sex','name','year']).sort_index()

pp.plot(allyears_indexed.loc[('F','Mary')])

[<matplotlib.lines.Line2D at 0xb61fe30>]

pp.plot(allyears_indexed.loc[('F','Mary')] / allyears.groupby('year').sum())

[<matplotlib.lines.Line2D at 0xa843150>]

def plotname(sex, name):
    data = allyears_indexed.loc[(sex,name)]
    
    pp.plot(data.index, data.values, label=name)
    pp.axis(xmin=1880, xmax=2018)

def comparenames(sex, names):
    pp.figure(figsize=(12,2.5))
    
    for name in names:
        plotname(sex, name)
        
        pp.legend()

comparenames('M' ,['Michael','John','David','Martin'])

comparenames('F' ,['Emily','Anna','Claire','Elizabeth'])

claires = ['Claire','Clare','Clara','Chiara','Ciara']

comparenames('F', claires)

allyears_indexed.loc[('F',claires),:]

			number
sex	name	year
F	Claire	1880	21
		1881	23
		1882	30
	...	...	...
	Ciara	2016	321
		2017	243
		2018	256

522 rows × 1 columns

pp.figure(figsize=(12,2.5))
pp.stackplot(range(1880,2019), allyears_indexed.loc[('F',claires),:].unstack(level=2));

pp.figure(figsize=(12,2.5))
pp.stackplot(range(1880,2019), allyears_indexed.loc[('F',claires),:].unstack(level=2).fillna(0),labels=claires);

pp.legend(loc='upper left')
pp.axis(xmin=1880, xmax=2018);

pd.options.display.max_rows = 10

allyears = pd.read_csv('allyears.csv.zip')

allyears_byyear = allyears.set_index(['sex','year']).sort_index()

allyears_byyear.loc['M',2018].sort_values('number', ascending=False) 

		name	number
sex	year
M	2018	Liam	19837
	2018	Noah	18267
	2018	William	14516
	2018	James	13525
	2018	Oliver	13389
	...	...	...
	2018	Gaylon	5
	2018	Gavynn	5
	2018	Gavon	5
	2018	Gaurav	5
	2018	Zzyzx	5

14004 rows × 2 columns

allyears_byyear.loc['M',2018].sort_values('number', ascending=False).head(10) 

		name	number
sex	year
M	2018	Liam	19837
	2018	Noah	18267
	2018	William	14516
	2018	James	13525
	2018	Oliver	13389
	2018	Benjamin	13381
	2018	Elijah	12886
	2018	Lucas	12585
	2018	Mason	12435
	2018	Logan	12352

allyears_byyear.loc['F',2018].sort_values('number', ascending=False) 

		name	number
sex	year
F	2018	Emma	18688
	2018	Olivia	17921
	2018	Ava	14924
	2018	Isabella	14464
	2018	Sophia	13928
	...	...	...
	2018	Ghala	5
	2018	Ghalia	5
	2018	Ghislaine	5
	2018	Giahna	5
	2018	Zyona	5

18029 rows × 2 columns

allyears_byyear.loc['F',2018].sort_values('number', ascending=False).head(10).reset_index().name 

0         Emma
1       Olivia
2          Ava
3     Isabella
4       Sophia
5    Charlotte
6          Mia
7       Amelia
8       Harper
9       Evelyn
Name: name, dtype: object

def getyear(sex, year):
    return (allyears_byyear.loc[sex, year]
                                .sort_values('number', ascending=False)
                                .head(10)
                                .reset_index()
                                .name)

pd.DataFrame({year: getyear('M',year) for year in range(2010,2019)})

	2010	2011	2012	2013	2014	2015	2016	2017	2018
0	Jacob	Jacob	Jacob	Noah	Noah	Noah	Noah	Liam	Liam
1	Ethan	Mason	Mason	Jacob	Liam	Liam	Liam	Noah	Noah
2	Michael	William	Ethan	Liam	Mason	Mason	William	William	William
3	Jayden	Jayden	Noah	Mason	Jacob	Jacob	Mason	James	James
4	William	Noah	William	William	William	William	James	Logan	Oliver
5	Alexander	Michael	Liam	Ethan	Ethan	Ethan	Benjamin	Benjamin	Benjamin
6	Noah	Ethan	Michael	Michael	Michael	James	Jacob	Mason	Elijah
7	Daniel	Alexander	Jayden	Alexander	Alexander	Alexander	Michael	Elijah	Lucas
8	Aiden	Aiden	Alexander	Jayden	James	Michael	Elijah	Oliver	Mason
9	Anthony	Daniel	Aiden	Daniel	Daniel	Benjamin	Ethan	Jacob	Logan

pd.DataFrame({year: getyear('F',year) for year in range(2010,2019)})

	2010	2011	2012	2013	2014	2015	2016	2017	2018
0	Isabella	Sophia	Sophia	Sophia	Emma	Emma	Emma	Emma	Emma
1	Sophia	Isabella	Emma	Emma	Olivia	Olivia	Olivia	Olivia	Olivia
2	Emma	Emma	Isabella	Olivia	Sophia	Sophia	Ava	Ava	Ava
3	Olivia	Olivia	Olivia	Isabella	Isabella	Ava	Sophia	Isabella	Isabella
4	Ava	Ava	Ava	Ava	Ava	Isabella	Isabella	Sophia	Sophia
5	Emily	Emily	Emily	Mia	Mia	Mia	Mia	Mia	Charlotte
6	Abigail	Abigail	Abigail	Emily	Emily	Abigail	Charlotte	Charlotte	Mia
7	Madison	Madison	Mia	Abigail	Abigail	Emily	Abigail	Amelia	Amelia
8	Chloe	Mia	Madison	Madison	Madison	Charlotte	Emily	Evelyn	Harper
9	Mia	Chloe	Elizabeth	Elizabeth	Charlotte	Harper	Harper	Abigail	Evelyn

def plotname(sex, name):
    data = allyears.query('sex ==@sex and name == @name')
    
    pp.plot(data.year, data.number, label=name)
    pp.axis(xmin=1880, xmax=2018)

pp.figure(figsize=(12,2.5))

for name in getyear('F',2018):
    plotname('F', name)
    
    pp.legend()