LagSelectionBias:

library(readr)
library(dplyr)
library(magrittr)
library(tidyr)

lsb_data2 <- read_csv(("~/LagSelectionBias/inst/extdata/Mortality 1967 and Prior - 1910-1939.csv"))

#colored minus black/african american ='s "other"

lsb_data2 %>%
  gather("Age_Group", "Deaths", 4:30) %>% 
  mutate(Race_2 = NA) %>%
  mutate(Race_2 = ifelse(Race == "Other Race" & is.na(Race_2), "Other Race", Race_2)) %>%
  mutate(Race_2 = ifelse(Race == "Colored" & is.na(Race_2), "Colored", Race_2)) %>%
  mutate(Race_2 = ifelse(Race == "White" & is.na(Race_2), "White", Race_2)) %>%
  mutate(Race_2 = ifelse (Race == "Black or African American" & is.na(Race_2), "Black or African American", Race_2)) %>% 
  mutate(Race_2 = ifelse(Race == "Chinese" & is.na(Race_2), "Other Race", Race_2)) %>%
  mutate(Race_2 = ifelse(Race == "Japanese" & is.na(Race_2), "Other Race", Race_2)) %>%
  mutate(Race_2 = ifelse(Race == "Indian" & is.na(Race_2), "Other Race", Race_2)) %>%
  mutate(Race_2 = ifelse(Race == "Other Colored" & is.na(Race_2), "Other Race", Race_2)) %>%
  mutate(Age_Group = ifelse(Age_Group == "1 year", "1 to 4 years", Age_Group)) %>% 
  mutate(Age_Group = ifelse(Age_Group == "2 years", "1 to 4 years", Age_Group)) %>% 
  mutate(Age_Group = ifelse(Age_Group == "3 years", "1 to 4 years", Age_Group)) %>% 
  mutate(Age_Group = ifelse(Age_Group == "4 years", "1 to 4 years", Age_Group)) %>% 
  group_by(Year, Race_2, Sex, Age_Group) %>% 
  summarise(Deaths = sum(Deaths)) %>%
  rename(Race = Race_2) %>% 
  spread(Race, Deaths) %>% 
  mutate(Other = ifelse(`Colored` > `Black or African American`, `Colored` - `Black or African American`, `Black or African American`)) %>% 
  mutate(`Other Race` =ifelse(!is.na(Other), Other, `Other Race` )) %>% 
  mutate(Age_Group = ifelse(Age_Group == "80 to 84 years", "85+ years", Age_Group)) %>% 
  mutate(Age_Group =ifelse(Age_Group == "85 to 89 years", "85+ years", Age_Group)) %>% 
  mutate(Age_Group = ifelse(Age_Group == "90 to 94 years", "85+ years", Age_Group)) %>% 
  mutate(Age_Group = ifelse(Age_Group == "90 to 95 years", "85+ years", Age_Group)) %>% 
  mutate(Age_Group = ifelse(Age_Group == "95 to 99 years", "85+ years", Age_Group)) %>% 
  mutate(Age_Group = ifelse(Age_Group == "100 years and over", "85+ years", Age_Group)) %>%
  group_by(Year, Sex, Age_Group) %>% 
  summarise_all(sum) %>% 
  select(-Other, -Colored) %>% 
  View()
  
  # spread into (race and deaths then create a new column which is the mutate of the difference)
  
  
  # mutate(`1 to 4 years` = `1 year` + `2 years` + `3 years `+ `4 years`) %>% 
   # put a  mutate for ages 1 - 4 here instead of 1 year, 2 year, etc then check + join it with the other data from 1940 onward
  

  summarise(Under.1.year = sum(Under.1.year))%>%
  View()
  summarise(X1.year = sum(X1.year)) %>%
  summarise(X2.year = sum(X2.year)) %>%
  summarise(X3.year = sum(X3.year)) %>%
  summarise(X4.year = sum(X4.year)) %>%
  summarise(Under.5.years = sum(Under.5.years)) %>%
  summarise(X5.to.9.years = sum(X5.to.9.years)) %>%
  summarise(X10.to.14.years = sum(X10.to.14.years)) %>%
  summarise(X15.to.19.years = sum(X15.to.19.years)) %>%
  summarise(X20.to.24.years = sum(X20.to.24.years)) %>%
  summarise(X25.to.29.years = sum(X25.to.29.years)) %>%
  summarise(X30.to.34.years = sum(X30.to.34.years)) %>%
  summarise(X35.to.39.years = sum(X35.to.39.years)) %>%
  summarise(X40.to.44.years = sum(X40.to.44.years)) %>%
  summarise(X45.to.49.years = sum(X45.to.49.years)) %>%
  summarise(X50.to.54.years = sum(X50.to.54.years)) %>%
  summarise(X55.to.59.years = sum(X55.to.59.years)) %>%
  summarise(X60.to.64.years = sum(X60.to.64.years)) %>%
  summarise(X65.to.69.years = sum(X65.to.69.years)) %>%
  summarise(X70.to.74.years = sum(X70.to.74.years)) %>%
  summarise(X75.to.79.years = sum(X75.to.79.years)) %>%
  summarise(X80.to.84.years = sum(X80.to.84.years)) %>%
  summarise(X85.to.89.years = sum(X85.to.89.years)) %>%
  summarise(X90.to.94.years = sum(X90.to.94.years)) %>%
  summarise(X95.to.99.years = sum(X95.to.99.years)) %>%
  summarise(X100.years.and.over = sum(X100.years.and.over)) %>%
  summarise(Not.stated = sum(Not.stated))

  
 #  # summarise(lsb_data2, `Under 1 year` = sum(Under.1.year, na.rm = FALSE))
 #  
 #  dataFrame$Race == "Colored"
 #  otherCalc <- function(dataFrame, rowsLarge, rowsSmall) {
 #    data.frame(var = dataFrame[rowsLarge] - dataFrame[rowsSmall])
 #  }
 #  # agegrps <- names(dat1910)[4:length(dat1910)]
 #  lapply(dat1910[ , agegrps], function(x) {otherCalc(x, dat1910$Race == "Colored", dat1910$Race == "Black or African American")})
 #  
 #  
 # # do this: dat.col cbind()