#filter for women in fertility years

library(plyr)
## ------------------------------------------------------------------------------
## You have loaded plyr after dplyr - this is likely to cause problems.
## If you need functions from both plyr and dplyr, please load plyr first, then dplyr:
## library(plyr); library(dplyr)
## ------------------------------------------------------------------------------
## 
## Attaching package: 'plyr'
## The following objects are masked from 'package:dplyr':
## 
##     arrange, count, desc, failwith, id, mutate, rename, summarise,
##     summarize
## The following object is masked from 'package:purrr':
## 
##     compact
library(dplyr)
datawomen<-mutate(pr, cbrwomen = (SEX== 2))
cbrpri <- filter(datawomen, AGE >= 15, AGE<= 44)
cbrpr<-filter(cbrpri, HISPAN==2)

#apply weights to get total number of women

cbrpr<-cbrpr%>%
  filter(SEX==2)

cbrpr$cbrprwomen <-  cbrpr$PERWT

cbrpr$ages <- as.numeric(cbrpr$AGE)

#apply weights to get total number of births

cbrpr$Fertility<-as.numeric(cbrpr$FERTYR)
cbrpr$Fertility2<-recode(cbrpr$Fertility,'1'=0, '2'=1, '0'=5, '8'=5)
cbrpr<-cbrpr%>%
  filter(Fertility2<5)


cbrpr$births<-cbrpr$Fertility2*cbrpr$PERWT


library(dplyr)

agegroups<-cbrpr %>%
  mutate(ages = case_when(
      ages >= 15 & ages <= 19 ~ "15-19",
      ages >= 20 & ages <= 25 ~ "20-25",
    ages >= 26 & ages <= 30 ~ "26-30",
    ages >= 31 & ages <= 35 ~ "31-35",
     ages >= 36 & ages <= 40 ~ "36-40",
     ages >= 41 & ages <= 44 ~ "41-44"))
    
  

#total number of puerto rican women and births to puerto rican women by year and age group

totalwomen<-aggregate(x=agegroups$cbrprwomen, by=list(agegroups$YEAR,agegroups$ages), FUN=sum)
totalbirths<-aggregate(x=agegroups$births, by=list(agegroups$YEAR,agegroups$ages), FUN=sum)


#divide number of children per women to get age specific fertility rate

#number births/number of women in given year


#unit is per 1,000

15-19
## [1] -4
20-25
## [1] -5
26-30
## [1] -4
31-35
## [1] -4
36-40
## [1] -4
41-44
## [1] -3
#sum fertility age specific fertility rates and divide by total groups to get TFR per year

#sum of ASFRs x5
#mimic this for

#filter for only Puerto Rican samples
#PR women living in PR

PRwomen<-filter(agegroups, SAMPLE==201502 |  201602 |   201702 | 201802 |  201902)
PRwomen2<-filter(PRwomen, SEX==2)

totalwomenPR<-aggregate(x=PRwomen2$cbrprwomen, by=list(PRwomen2$YEAR,PRwomen2$ages), FUN=sum)
totalbirthsPR<-aggregate(x=PRwomen2$births, by=list(PRwomen2$YEAR,PRwomen2$ages), FUN=sum)

#what % of  women living in PR were born in the mainland US and what % was born on the island

totalwomenPR
##    Group.1 Group.2      x
## 1     2015   15-19 340310
## 2     2016   15-19 344347
## 3     2017   15-19 334439
## 4     2018   15-19 320392
## 5     2019   15-19 323276
## 6     2021   15-19 308077
## 7     2015   20-25 397136
## 8     2016   20-25 392508
## 9     2017   20-25 393567
## 10    2018   20-25 387311
## 11    2019   20-25 382884
## 12    2021   20-25 385484
## 13    2015   26-30 311074
## 14    2016   26-30 313410
## 15    2017   26-30 320047
## 16    2018   26-30 320761
## 17    2019   26-30 310966
## 18    2021   26-30 320323
## 19    2015   31-35 314478
## 20    2016   31-35 293880
## 21    2017   31-35 301952
## 22    2018   31-35 290507
## 23    2019   31-35 302002
## 24    2021   31-35 297205
## 25    2015   36-40 302084
## 26    2016   36-40 309330
## 27    2017   36-40 305923
## 28    2018   36-40 300766
## 29    2019   36-40 313575
## 30    2021   36-40 298722
## 31    2015   41-44 231238
## 32    2016   41-44 234096
## 33    2017   41-44 218247
## 34    2018   41-44 230746
## 35    2019   41-44 227956
## 36    2021   41-44 242010
totalbirthsPR
##    Group.1 Group.2     x
## 1     2015   15-19  9593
## 2     2016   15-19  9139
## 3     2017   15-19  4726
## 4     2018   15-19  6857
## 5     2019   15-19  4793
## 6     2021   15-19  2462
## 7     2015   20-25 33909
## 8     2016   20-25 33137
## 9     2017   20-25 28269
## 10    2018   20-25 26071
## 11    2019   20-25 27401
## 12    2021   20-25 24902
## 13    2015   26-30 28784
## 14    2016   26-30 29089
## 15    2017   26-30 24007
## 16    2018   26-30 26814
## 17    2019   26-30 27543
## 18    2021   26-30 26990
## 19    2015   31-35 20032
## 20    2016   31-35 20113
## 21    2017   31-35 22788
## 22    2018   31-35 19507
## 23    2019   31-35 21391
## 24    2021   31-35 19005
## 25    2015   36-40  8427
## 26    2016   36-40 10361
## 27    2017   36-40 11216
## 28    2018   36-40 11048
## 29    2019   36-40 14118
## 30    2021   36-40 10975
## 31    2015   41-44  2753
## 32    2016   41-44  2937
## 33    2017   41-44  2700
## 34    2018   41-44  3483
## 35    2019   41-44  2314
## 36    2021   41-44  3043
#filter for US Samples only and nativity as PR 
#PR women born in PR living in US
PRwomenbornUS<-filter(agegroups, SAMPLE==201501 |  201601 |   201701 |  201802 |  201901)
PRwomenbornus2<-filter(PRwomenbornUS, SEX==2)
PRwomeninUSbornPR<-filter(PRwomenbornus2, BPL==110)

totalwomenUSbornPR<-aggregate(x=PRwomeninUSbornPR$cbrprwomen, by=list(PRwomeninUSbornPR$YEAR,PRwomeninUSbornPR$ages), FUN=sum)
totalbirthsUSbornPR<-aggregate(x=PRwomeninUSbornPR$births, by=list(PRwomeninUSbornPR$YEAR,PRwomeninUSbornPR$ages), FUN=sum)

totalwomenUSbornPR
##    Group.1 Group.2      x
## 1     2015   15-19 144659
## 2     2016   15-19 145668
## 3     2017   15-19 140992
## 4     2018   15-19 131214
## 5     2019   15-19 128227
## 6     2021   15-19 120919
## 7     2015   20-25 182562
## 8     2016   20-25 179779
## 9     2017   20-25 179499
## 10    2018   20-25 178246
## 11    2019   20-25 178242
## 12    2021   20-25 174772
## 13    2015   26-30 145911
## 14    2016   26-30 149244
## 15    2017   26-30 149690
## 16    2018   26-30 144748
## 17    2019   26-30 146062
## 18    2021   26-30 154694
## 19    2015   31-35 164043
## 20    2016   31-35 153347
## 21    2017   31-35 152774
## 22    2018   31-35 141147
## 23    2019   31-35 147799
## 24    2021   31-35 137503
## 25    2015   36-40 163509
## 26    2016   36-40 179464
## 27    2017   36-40 175903
## 28    2018   36-40 158441
## 29    2019   36-40 160211
## 30    2021   36-40 160302
## 31    2015   41-44 136278
## 32    2016   41-44 135121
## 33    2017   41-44 132845
## 34    2018   41-44 133557
## 35    2019   41-44 132726
## 36    2021   41-44 140716
totalbirthsUSbornPR
##    Group.1 Group.2     x
## 1     2015   15-19  5434
## 2     2016   15-19  4585
## 3     2017   15-19  2941
## 4     2018   15-19  3502
## 5     2019   15-19  1170
## 6     2021   15-19  1111
## 7     2015   20-25 14458
## 8     2016   20-25 15273
## 9     2017   20-25  9405
## 10    2018   20-25 12084
## 11    2019   20-25 10854
## 12    2021   20-25  8546
## 13    2015   26-30 10800
## 14    2016   26-30 11840
## 15    2017   26-30  8654
## 16    2018   26-30 10200
## 17    2019   26-30 12641
## 18    2021   26-30  9044
## 19    2015   31-35  8369
## 20    2016   31-35 10053
## 21    2017   31-35  9609
## 22    2018   31-35  8413
## 23    2019   31-35  8377
## 24    2021   31-35  7873
## 25    2015   36-40  3840
## 26    2016   36-40  4976
## 27    2017   36-40  4970
## 28    2018   36-40  3941
## 29    2019   36-40  7405
## 30    2021   36-40  3454
## 31    2015   41-44  1379
## 32    2016   41-44  1691
## 33    2017   41-44  1863
## 34    2018   41-44  2363
## 35    2019   41-44  1351
## 36    2021   41-44  1595
#filter for US Samples only nativity as US
#PR women born in US but ethnically PR

PRwomen<-filter(agegroups, SAMPLE==201501   |  201601 |   201701 |  201802 |  20190)
PRwomen2<-filter(PRwomen, SEX==2)
PRwomenbornUS<-filter(PRwomen2, BPL>=001 |  BPL>2 |   BPL<= 056)

totalwomenPRbornUS<-aggregate(x=PRwomenbornUS$cbrprwomen, by=list(PRwomenbornUS$YEAR,PRwomenbornUS$ages), FUN=sum)
totalbirthsPRbornUS<-aggregate(x=PRwomenbornUS$births, by=list(PRwomenbornUS$YEAR,PRwomenbornUS$ages), FUN=sum)

totalwomenPRbornUS
##    Group.1 Group.2      x
## 1     2015   15-19 340310
## 2     2016   15-19 344347
## 3     2017   15-19 334439
## 4     2018   15-19 320392
## 5     2019   15-19 323276
## 6     2021   15-19 308077
## 7     2015   20-25 397136
## 8     2016   20-25 392508
## 9     2017   20-25 393567
## 10    2018   20-25 387311
## 11    2019   20-25 382884
## 12    2021   20-25 385484
## 13    2015   26-30 311074
## 14    2016   26-30 313410
## 15    2017   26-30 320047
## 16    2018   26-30 320761
## 17    2019   26-30 310966
## 18    2021   26-30 320323
## 19    2015   31-35 314478
## 20    2016   31-35 293880
## 21    2017   31-35 301952
## 22    2018   31-35 290507
## 23    2019   31-35 302002
## 24    2021   31-35 297205
## 25    2015   36-40 302084
## 26    2016   36-40 309330
## 27    2017   36-40 305923
## 28    2018   36-40 300766
## 29    2019   36-40 313575
## 30    2021   36-40 298722
## 31    2015   41-44 231238
## 32    2016   41-44 234096
## 33    2017   41-44 218247
## 34    2018   41-44 230746
## 35    2019   41-44 227956
## 36    2021   41-44 242010
totalbirthsPRbornUS
##    Group.1 Group.2     x
## 1     2015   15-19  9593
## 2     2016   15-19  9139
## 3     2017   15-19  4726
## 4     2018   15-19  6857
## 5     2019   15-19  4793
## 6     2021   15-19  2462
## 7     2015   20-25 33909
## 8     2016   20-25 33137
## 9     2017   20-25 28269
## 10    2018   20-25 26071
## 11    2019   20-25 27401
## 12    2021   20-25 24902
## 13    2015   26-30 28784
## 14    2016   26-30 29089
## 15    2017   26-30 24007
## 16    2018   26-30 26814
## 17    2019   26-30 27543
## 18    2021   26-30 26990
## 19    2015   31-35 20032
## 20    2016   31-35 20113
## 21    2017   31-35 22788
## 22    2018   31-35 19507
## 23    2019   31-35 21391
## 24    2021   31-35 19005
## 25    2015   36-40  8427
## 26    2016   36-40 10361
## 27    2017   36-40 11216
## 28    2018   36-40 11048
## 29    2019   36-40 14118
## 30    2021   36-40 10975
## 31    2015   41-44  2753
## 32    2016   41-44  2937
## 33    2017   41-44  2700
## 34    2018   41-44  3483
## 35    2019   41-44  2314
## 36    2021   41-44  3043