A05 - Project: Popular Names

Kaplan, Daniel & Matthew Beckman. (2021). Data Computing. 2nd Ed. Home.

https://davefriedman01.github.io/Mathematics/computer/program/rlang/STAT184/intro.html

---

Revised

19 Jun 2023

---

Programming Environment

library(dcData)
library(tidyverse)
library(mosaic)

sessionInfo()

── Attaching core tidyverse packages ───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────── tidyverse 2.0.0 ──
✔ dplyr     1.1.2     ✔ readr     2.1.4
✔ forcats   1.0.0     ✔ stringr   1.5.0
✔ ggplot2   3.4.3     ✔ tibble    3.2.1
✔ lubridate 1.9.2     ✔ tidyr     1.3.0
✔ purrr     1.0.2     

── Conflicts ─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────── tidyverse_conflicts() ──
✖ dplyr::filter() masks stats::filter()
✖ dplyr::lag()    masks stats::lag()
ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors

Registered S3 method overwritten by 'mosaic':
  method                           from   
  fortify.SpatialPolygonsDataFrame ggplot2

The 'mosaic' package masks several functions from core packages in order to add 
additional features.  The original behavior of these functions should not be affected by this.

Attaching package: ‘mosaic’

The following object is masked from ‘package:Matrix’:

    mean

The following objects are masked from ‘package:dplyr’:

    count, do, tally

The following object is masked from ‘package:purrr’:

    cross

The following object is masked from ‘package:ggplot2’:

    stat

The following objects are masked from ‘package:stats’:

    binom.test, cor, cor.test, cov, fivenum, IQR, median, prop.test,
    quantile, sd, t.test, var

The following objects are masked from ‘package:base’:

    max, mean, min, prod, range, sample, sum

R version 4.3.0 (2023-04-21)
Platform: aarch64-apple-darwin20 (64-bit)
Running under: macOS 14.4.1

Matrix products: default
BLAS:   /Library/Frameworks/R.framework/Versions/4.3-arm64/Resources/lib/libRblas.0.dylib 
LAPACK: /Library/Frameworks/R.framework/Versions/4.3-arm64/Resources/lib/libRlapack.dylib;  LAPACK version 3.11.0

locale:
[1] en_US.UTF-8/en_US.UTF-8/en_US.UTF-8/C/en_US.UTF-8/en_US.UTF-8

time zone: America/New_York
tzcode source: internal

attached base packages:
[1] stats     graphics  grDevices utils     datasets  methods   base     

other attached packages:
 [1] mosaic_1.8.4.2    mosaicData_0.20.3 ggformula_0.10.4  Matrix_1.5-4     
 [5] lattice_0.21-8    lubridate_1.9.2   forcats_1.0.0     stringr_1.5.0    
 [9] dplyr_1.1.2       purrr_1.0.2       readr_2.1.4       tidyr_1.3.0      
[13] tibble_3.2.1      ggplot2_3.4.3     tidyverse_2.0.0   dcData_0.1.0     

loaded via a namespace (and not attached):
 [1] utf8_1.2.3         generics_0.1.3     stringi_1.7.12     hms_1.1.3         
 [5] digest_0.6.31      magrittr_2.0.3     evaluate_0.21      grid_4.3.0        
 [9] timechange_0.2.0   pbdZMQ_0.3-9       fastmap_1.1.1      jsonlite_1.8.5    
[13] fansi_1.0.4        scales_1.2.1       tweenr_2.0.2       labelled_2.11.0   
[17] cli_3.6.1          rlang_1.1.1        crayon_1.5.2       polyclip_1.10-4   
[21] munsell_0.5.0      base64enc_0.1-3    withr_2.5.0        repr_1.1.6        
[25] tools_4.3.0        tzdb_0.4.0         uuid_1.1-0         colorspace_2.1-0  
[29] mosaicCore_0.9.2.1 IRdisplay_1.1      vctrs_0.6.3        R6_2.5.1          
[33] ggridges_0.5.4     lifecycle_1.0.3    ggstance_0.3.6     MASS_7.3-58.4     
[37] pkgconfig_2.0.3    pillar_1.9.0       gtable_0.3.3       glue_1.6.2        
[41] Rcpp_1.0.10        ggforce_0.4.1      haven_2.5.2        tidyselect_1.2.0  
[45] IRkernel_1.3.2     farver_2.1.1       htmltools_0.5.5    compiler_4.3.0    

---

?dcData::BabyNames

head(x = dcData::BabyNames)

A data.frame: 6 × 4

	name	sex	count	year
	<chr>	<chr>	<int>	<int>
1	Mary	F	7065	1880
2	Anna	F	2604	1880
3	Emma	F	2003	1880
4	Elizabeth	F	1939	1880
5	Minnie	F	1746	1880
6	Margaret	F	1578	1880

count(x = dcData::BabyNames, sex)

A data.frame: 2 × 2

sex	n
<chr>	<int>
F	1062432
M	729659

count(x = dcData::BabyNames, year) %>%
  arrange(desc(n)) %>%
    head(n = 10)

A data.frame: 10 × 2

	year	n
	<int>	<int>
1	2008	35038
2	2007	34925
3	2009	34668
4	2006	34066
5	2010	34027
6	2011	33858
7	2012	33658
8	2013	33072
9	2005	32527
10	2004	32033

select(.data = dcData::BabyNames, name, count) %>%
  arrange(desc(count)) %>%
    head(n = 10)

A data.frame: 10 × 2

	name	count
	<chr>	<int>
1	Linda	99674
2	Linda	96210
3	James	94758
4	Michael	92711
5	Robert	91652
6	Linda	90994
7	Michael	90629
8	Michael	90512
9	James	88610
10	Michael	88481

select(.data = dcData::BabyNames, name, count) %>%
  arrange(desc(count)) %>%
    filter(count == 5)

A data.frame: 249909 × 2

name	count
<chr>	<int>
Adelle	5
Adina	5
Adrienne	5
Albertine	5
Alys	5
Ana	5
Araminta	5
Arthur	5
Birtha	5
Bulah	5
Caddie	5
Celie	5
Charlotta	5
Clair	5
Concepcion	5
Cordella	5
Corrine	5
Delila	5
Delphine	5
Dosha	5
Edgar	5
Elaine	5
Elisa	5
Ellar	5
Elmire	5
Elvina	5
Ena	5
Estie	5
Etter	5
Fronnie	5
⋮	⋮
Zayceon	5
Zayid	5
Zaylynn	5
Zecheriah	5
Zedric	5
Zefram	5
Zekhi	5
Zenith	5
Zennon	5
Zepplin	5
Zevon	5
Zhaiden	5
Zhen	5
Zhian	5
Zien	5
Zierre	5
Zimri	5
Ziquan	5
Ziyaad	5
Ziyang	5
Zmari	5
Zolan	5
Zurich	5
Zyeer	5
Zyere	5
Zyhier	5
Zylar	5
Zymari	5
Zymeer	5
Zyree	5

nonGlyphReadyForm <- dcData::BabyNames %>%
  filter(name %in% c('Abraham', 'Franklin', 'Woodrow'))
head(x = nonGlyphReadyForm)

nonGlyphReadyForm %>%
  ggplot() +
    geom_line(
      alpha     = 0.5,
      linewidth = 1,
      mapping   = aes(x        = year,
                      y        = count,
                      color    = name,
                      linetype = name),
      position  = 'identity',
      stat      = 'identity',
      show.legend=TRUE
    ) +
    xlab('Year') +
    ylab('Popularity') +
    ggtitle('Popularity of Names Over Time')

A data.frame: 6 × 4

	name	sex	count	year
	<chr>	<chr>	<int>	<int>
1	Franklin	M	120	1880
2	Abraham	M	81	1880
3	Franklin	M	117	1881
4	Abraham	M	86	1881
5	Franklin	M	112	1882
6	Abraham	M	91	1882

GlyphReadyForm <- dcData::BabyNames %>%
  filter(name %in% c('Abraham', 'Franklin', 'Woodrow')) %>%
    group_by(year, name) %>%
      summarize(total = sum(count))
head(x = GlyphReadyForm)

GlyphReadyForm %>%
  ggplot() +
    geom_line(
      alpha     = 0.5,
      linewidth = 1,
      mapping   = aes(x        = year,
                      y        = total,
                      color    = name,
                      linetype = name),
      position  = 'identity',
      stat      = 'identity',
      show.legend=TRUE
    ) +
    xlab('Year') +
    ylab('Popularity') +
    ggtitle('Popularity of Names Over Time')

`summarise()` has grouped output by 'year'. You can override using the `.groups` argument.

A grouped_df: 6 × 3

year	name	total
<int>	<chr>	<int>
1880	Abraham	81
1880	Franklin	120
1881	Abraham	86
1881	Franklin	117
1882	Abraham	91
1882	Franklin	112

---

GlyphReadyForm <- dcData::BabyNames %>%
  filter(name %in% c('Dave', 'Davey', 'David')) %>%
    group_by(year, name) %>%
      summarize(total = sum(count))
head(x = GlyphReadyForm)

GlyphReadyForm %>%
  ggplot() +
    geom_line(
      alpha     = 0.5,
      linewidth = 1,
      mapping   = aes(x        = year,
                      y        = total,
                      color    = name,
                      linetype = name),
      position  = 'identity',
      stat      = 'identity',
      show.legend=TRUE
    ) +
    xlab('Year') +
    ylab('Popularity') +
    ggtitle('Popularity of Names Over Time')

`summarise()` has grouped output by 'year'. You can override using the `.groups` argument.

A grouped_df: 6 × 3

year	name	total
<int>	<chr>	<int>
1880	Dave	131
1880	David	869
1881	Dave	135
1881	David	750
1882	Dave	144
1882	David	838

dcData::BabyNames %>%
  filter(name %in% c('Davey'))

A data.frame: 94 × 4

name	sex	count	year
<chr>	<chr>	<int>	<int>
Davey	M	5	1925
Davey	M	9	1928
Davey	M	89	1929
Davey	F	5	1930
Davey	M	54	1930
Davey	M	45	1931
Davey	M	26	1932
Davey	M	15	1933
Davey	M	22	1934
Davey	M	17	1935
Davey	M	9	1936
Davey	M	15	1937
Davey	M	14	1938
Davey	M	16	1939
Davey	M	8	1940
Davey	M	17	1941
Davey	M	18	1942
Davey	F	5	1943
Davey	M	19	1943
Davey	M	10	1944
Davey	M	15	1945
Davey	M	25	1946
Davey	M	37	1947
Davey	M	42	1948
Davey	M	50	1949
Davey	M	41	1950
Davey	M	39	1951
Davey	M	44	1952
Davey	M	74	1953
Davey	M	55	1954
⋮	⋮	⋮	⋮
Davey	M	29	1988
Davey	M	33	1989
Davey	M	20	1990
Davey	M	26	1991
Davey	M	26	1992
Davey	M	72	1993
Davey	F	5	1994
Davey	M	75	1994
Davey	M	34	1995
Davey	M	31	1996
Davey	M	34	1997
Davey	M	25	1998
Davey	M	28	1999
Davey	F	6	2000
Davey	M	14	2000
Davey	M	20	2001
Davey	M	29	2002
Davey	M	14	2003
Davey	M	14	2004
Davey	M	22	2005
Davey	F	5	2006
Davey	M	18	2006
Davey	M	25	2007
Davey	M	14	2008
Davey	M	14	2009
Davey	M	26	2010
Davey	M	19	2011
Davey	M	17	2012
Davey	F	7	2013
Davey	M	18	2013

GlyphReadyForm <- dcData::BabyNames %>%
  filter(name %in% c('Davey')) %>%
    group_by(year, name) %>%
      summarize(total = sum(count))
head(x = GlyphReadyForm)

GlyphReadyForm %>%
  ggplot() +
    geom_line(
      alpha     = 0.5,
      linewidth = 1,
      mapping   = aes(x        = year,
                      y        = total,
                      color    = name,
                      linetype = name),
      position  = 'identity',
      stat      = 'identity',
      show.legend=TRUE
    ) +
    xlab('Year') +
    ylab('Popularity') +
    ggtitle('Popularity of Names Over Time')

`summarise()` has grouped output by 'year'. You can override using the `.groups` argument.

A grouped_df: 6 × 3

year	name	total
<int>	<chr>	<int>
1925	Davey	5
1928	Davey	9
1929	Davey	89
1930	Davey	59
1931	Davey	45
1932	Davey	26

GlyphReadyForm <- dcData::BabyNames %>%
  filter(name %in% c('Carol', 'Carole', 'Caroline', 'Carolyn', 'Carrie')) %>%
    group_by(year, name) %>%
      summarize(total = sum(count))
head(x = GlyphReadyForm)

GlyphReadyForm %>%
  ggplot() +
    geom_line(
      alpha     = 0.5,
      linewidth = 1,
      mapping   = aes(x        = year,
                      y        = total,
                      color    = name,
                      linetype = name),
      position  = 'identity',
      stat      = 'identity',
      show.legend=TRUE
    ) +
    xlab('Year') +
    ylab('Popularity') +
    ggtitle('Popularity of Names Over Time')

`summarise()` has grouped output by 'year'. You can override using the `.groups` argument.

A grouped_df: 6 × 3

year	name	total
<int>	<chr>	<int>
1880	Carol	7
1880	Caroline	306
1880	Carolyn	80
1880	Carrie	957
1881	Carol	11
1881	Caroline	316

GlyphReadyForm <- dcData::BabyNames %>%
  filter(name %in% c('Jeff', 'Jeffrey', 'Geof', 'Geoff', 'Geoffrey')) %>%
    group_by(year, name) %>%
      summarize(total = sum(count))
head(x = GlyphReadyForm)

GlyphReadyForm %>%
  ggplot() +
    geom_line(
      alpha     = 0.5,
      linewidth = 1,
      mapping   = aes(x        = year,
                      y        = total,
                      color    = name,
                      linetype = name),
      position  = 'identity',
      stat      = 'identity',
      show.legend=TRUE
    ) +
    xlab('Year') +
    ylab('Popularity') +
    ggtitle('Popularity of Names Over Time')

`summarise()` has grouped output by 'year'. You can override using the `.groups` argument.

A grouped_df: 6 × 3

year	name	total
<int>	<chr>	<int>
1880	Jeff	66
1881	Jeff	61
1882	Jeff	81
1883	Jeff	44
1884	Jeff	74
1885	Jeff	63

GlyphReadyForm <- dcData::BabyNames %>%
  filter(name %in% c('Geof', 'Geoff')) %>%
    group_by(year, name) %>%
      summarize(total = sum(count))
head(x = GlyphReadyForm)

GlyphReadyForm %>%
  ggplot() +
    geom_line(
      alpha     = 0.5,
      linewidth = 1,
      mapping   = aes(x        = year,
                      y        = total,
                      color    = name,
                      linetype = name),
      position  = 'identity',
      stat      = 'identity',
      show.legend=TRUE
    ) +
    xlab('Year') +
    ylab('Popularity') +
    ggtitle('Popularity of Names Over Time')

`summarise()` has grouped output by 'year'. You can override using the `.groups` argument.

A grouped_df: 6 × 3

year	name	total
<int>	<chr>	<int>
1940	Geoff	5
1942	Geoff	7
1943	Geoff	5
1944	Geoff	8
1945	Geoff	8
1946	Geoff	7

GlyphReadyForm <- dcData::BabyNames %>%
  filter(name %in% c(
    'Elizabeth',
    'Elisa',
    'Elise',
    'Eliza',
    'Ellie',
    'Elsa',
    'Isabelle',
    'Lisa',
    'Liz',
    'Liza',
    'Lizzie'
    )) %>%
    group_by(year, name) %>%
      summarize(total = sum(count))
head(x = GlyphReadyForm)

GlyphReadyForm %>%
  ggplot() +
    geom_line(
      alpha     = 0.5,
      linewidth = 1,
      mapping   = aes(x        = year,
                      y        = total,
                      color    = name,
                      linetype = name),
      position  = 'identity',
      stat      = 'identity',
      show.legend=TRUE
    ) +
    xlab('Year') +
    ylab('Popularity') +
    ggtitle('Popularity of Names Over Time')

`summarise()` has grouped output by 'year'. You can override using the `.groups` argument.

A grouped_df: 6 × 3

year	name	total
<int>	<chr>	<int>
1880	Elisa	5
1880	Elise	24
1880	Eliza	258
1880	Elizabeth	1948
1880	Ellie	17
1880	Elsa	20

GlyphReadyForm <- dcData::BabyNames %>%
  filter(name %in% c(
    'Bethany',
    'Bessie',
    'Betsey',
    'Betta',
    'Betty'
    )) %>%
    group_by(year, name) %>%
      summarize(total = sum(count))
head(x = GlyphReadyForm)

GlyphReadyForm %>%
  ggplot() +
    geom_line(
      alpha     = 0.5,
      linewidth = 1,
      mapping   = aes(x        = year,
                      y        = total,
                      color    = name,
                      linetype = name),
      position  = 'identity',
      stat      = 'identity',
      show.legend=TRUE
    ) +
    xlab('Year') +
    ylab('Popularity') +
    ggtitle('Popularity of Names Over Time')

`summarise()` has grouped output by 'year'. You can override using the `.groups` argument.

A grouped_df: 6 × 3

year	name	total
<int>	<chr>	<int>
1880	Bessie	796
1880	Betty	117
1881	Bessie	911
1881	Betty	112
1882	Bessie	1153
1882	Betty	123

---