library(tidyverse)
## -- Attaching packages --------------------------------------- tidyverse 1.3.1 --
## v ggplot2 3.3.5     v purrr   0.3.4
## v tibble  3.1.6     v dplyr   1.0.7
## v tidyr   1.1.4     v stringr 1.4.0
## v readr   2.1.1     v forcats 0.5.1
## -- Conflicts ------------------------------------------ tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag()    masks stats::lag()
library(plotly)
## 
## Attaching package: 'plotly'
## The following object is masked from 'package:ggplot2':
## 
##     last_plot
## The following object is masked from 'package:stats':
## 
##     filter
## The following object is masked from 'package:graphics':
## 
##     layout
eth_region_0306 <- read_delim("~/R/Natality, 2003-2006 F1.txt", 
     delim = "\t", escape_double = FALSE, 
     trim_ws = TRUE)
## Warning: One or more parsing issues, see `problems()` for details
## Rows: 427 Columns: 12
## -- Column specification --------------------------------------------------------
## Delimiter: "\t"
## chr (9): Notes, Mother's Hispanic Origin, Mother's Hispanic Origin Code, Age...
## dbl (3): Year, Year Code, Births
## 
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.
eth_region_0720 <- read_delim("~/R/Natality, 2007-2020 F1.txt", 
     delim = "\t", escape_double = FALSE, 
     trim_ws = TRUE)
## Warning: One or more parsing issues, see `problems()` for details
## Rows: 1455 Columns: 12
## -- Column specification --------------------------------------------------------
## Delimiter: "\t"
## chr (9): Notes, Mother's Hispanic Origin, Mother's Hispanic Origin Code, Age...
## dbl (3): Year, Year Code, Births
## 
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.
eth_region_0320 <- rbind(eth_region_0306,eth_region_0720)
glimpse(eth_region_0320)
## Rows: 1,882
## Columns: 12
## $ Notes                           <chr> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA~
## $ `Mother's Hispanic Origin`      <chr> "Hispanic or Latino", "Hispanic or Lat~
## $ `Mother's Hispanic Origin Code` <chr> "2135-2", "2135-2", "2135-2", "2135-2"~
## $ `Age of Mother 9`               <chr> "Under 15 years", "Under 15 years", "U~
## $ `Age of Mother 9 Code`          <chr> "15", "15", "15", "15", "15", "15", "1~
## $ Year                            <dbl> 2003, 2003, 2003, 2003, 2004, 2004, 20~
## $ `Year Code`                     <dbl> 2003, 2003, 2003, 2003, 2004, 2004, 20~
## $ `Census Region`                 <chr> "Census Region 1: Northeast", "Census ~
## $ `Census Region Code`            <chr> "CENS-R1", "CENS-R2", "CENS-R3", "CENS~
## $ Births                          <dbl> 257, 190, 936, 973, 257, 192, 956, 951~
## $ `Female Population`             <chr> "Not Available", "Not Available", "Not~
## $ `Fertility Rate`                <chr> "Not Available", "Not Available", "Not~

#rename and select

eth_region_0320 = eth_region_0320 %>%
  rename(Region = `Census Region Code`,
         Ethnicity = `Mother's Hispanic Origin`,
         Age = `Age of Mother 9 Code`,
         Fpop = `Female Population`,
         Rate = `Fertility Rate` ) %>% 
  select(Ethnicity, Year, Region, Age, Fpop, Births, Rate)
glimpse(eth_region_0320)
## Rows: 1,882
## Columns: 7
## $ Ethnicity <chr> "Hispanic or Latino", "Hispanic or Latino", "Hispanic or Lat~
## $ Year      <dbl> 2003, 2003, 2003, 2003, 2004, 2004, 2004, 2004, 2005, 2005, ~
## $ Region    <chr> "CENS-R1", "CENS-R2", "CENS-R3", "CENS-R4", "CENS-R1", "CENS~
## $ Age       <chr> "15", "15", "15", "15", "15", "15", "15", "15", "15", "15", ~
## $ Fpop      <chr> "Not Available", "Not Available", "Not Available", "Not Avai~
## $ Births    <dbl> 257, 190, 936, 973, 257, 192, 956, 951, 263, 216, 989, 998, ~
## $ Rate      <chr> "Not Available", "Not Available", "Not Available", "Not Avai~

#Recode

eth_region_0320 = eth_region_0320 %>% 
  mutate(Region = ifelse(Region == "CENS-R1","NE",Region),
         Region = ifelse(Region == "CENS-R2","MW",Region),
         Region = ifelse(Region == "CENS-R3","SO",Region),
         Region = ifelse(Region == "CENS-R4","WE",Region),
         Fpop = as.numeric(Fpop),
         Rate = as.numeric(Rate)/1000) %>% 
filter(Ethnicity != "Not Reported") %>% 
drop_na()
## Warning in mask$eval_all_mutate(quo): NAs introduced by coercion

## Warning in mask$eval_all_mutate(quo): NAs introduced by coercion
head(eth_region_0320)
## # A tibble: 6 x 7
##   Ethnicity           Year Region Age     Fpop Births   Rate
##   <chr>              <dbl> <chr>  <chr>  <dbl>  <dbl>  <dbl>
## 1 Hispanic or Latino  2003 NE     15-19 233887  14691 0.0628
## 2 Hispanic or Latino  2003 MW     15-19 148518  12041 0.0811
## 3 Hispanic or Latino  2003 SO     15-19 533647  47220 0.0885
## 4 Hispanic or Latino  2003 WE     15-19 723943  54572 0.0754
## 5 Hispanic or Latino  2004 NE     15-19 242902  15072 0.0620
## 6 Hispanic or Latino  2004 MW     15-19 153522  12406 0.0808

#First Plot

eth_region_0320 %>% 
  filter(Age == "25-29") %>% 
  ggplot(aes(x= Year, y = Rate)) +
  geom_point() +
  facet_grid(Ethnicity~Region) +
  ggtitle("TS Plot of Rate for 25-29 by Ethnicity and Region")

#Flip the Grid

eth_region_0320 %>% 
  filter(Age == "25-29") %>% 
  ggplot(aes(x= Year, y = Rate)) +
  geom_point() +
  facet_grid(Region~Ethnicity) +
  ggtitle("TS Plot of Rate for 25-29 by Ethnicity and Region")

#National TFR by Ethnicity

g1 = eth_region_0320 %>% 
  group_by(Year,Ethnicity,Age) %>% 
  summarize(Births = sum(Births),
            Fpop = sum(Fpop)) %>% 
  mutate(Rate = Births/Fpop)%>% 
  summarize(TFR = sum(Rate) * 5) %>% 
  ungroup() %>% 
  ggplot(aes(x = Year,y = TFR, color = Ethnicity)) +
  geom_point()
## `summarise()` has grouped output by 'Year', 'Ethnicity'. You can override using the `.groups` argument.
## `summarise()` has grouped output by 'Year'. You can override using the `.groups` argument.
ggtitle("National TFR by Year and Ethnicity")
## $title
## [1] "National TFR by Year and Ethnicity"
## 
## attr(,"class")
## [1] "labels"
ggplotly(g1)

#Ethnicity & Region

g2 = eth_region_0320 %>% 
  group_by(Year,Region,Ethnicity,Age) %>% 
  summarize(Births = sum(Births),
            Fpop = sum(Fpop)) %>% 
  mutate(Rate = Births/Fpop)%>% 
  summarize(TFR = sum(Rate) * 5) %>% 
  ungroup() %>% 
  ggplot(aes(x = Year,y = TFR, color = Ethnicity)) +
  geom_point(size=0.5) +
  facet_grid(Ethnicity~Region)
## `summarise()` has grouped output by 'Year', 'Region', 'Ethnicity'. You can override using the `.groups` argument.
## `summarise()` has grouped output by 'Year', 'Region'. You can override using the `.groups` argument.
 ggtitle("Regional TFR by Year and Ethnicity")
## $title
## [1] "Regional TFR by Year and Ethnicity"
## 
## attr(,"class")
## [1] "labels"
 ggplotly(g2)