mtf_merge.R

library(haven)

# Set the path to the directory containing your .dta files
path <- "E:/mtf/new/all"

# List all .dta files in the directory
files <- list.files(path, pattern = "\\.dta$", full.names = TRUE)

# Function to create a valid R variable name from the filename
make_var_name <- function(filepath) {
  base_name <- basename(filepath)
  no_extension <- tools::file_path_sans_ext(base_name)
  return(no_extension)
}

# Import each file and assign it to a variable in the global environment
lapply(files, function(file) {
  data_name <- make_var_name(file)
  assign(data_name, import(file), envir = .GlobalEnv)
})

mtf <- import("E://data/mtf_full1.dta")


mtf <- mtf %>% 
  mutate(year = 1900 + V5) %>% 
  mutate(attend = V33) %>% 
  mutate(relimp = V34) %>% 
  mutate(drink  = V74) %>% 
  mutate(smoke  = V72) %>% 
  mutate(gender = V13) %>% 
  mutate(race   = V14) %>% 
  mutate(sibs   = V17) %>% 
  mutate(paed   = V27) %>% 
  mutate(maed   = V28) %>% 
  mutate(pid7   = V30) %>% 
  mutate(id5    = V31) %>% 
  mutate(grade  = V43) %>% 
  mutate(weight = V8)



one <- mtf %>% 
  select(year, attend, relimp, drink, smoke, gender, race, sibs, paed, maed, pid7, id5, grade, weight)



for (i in c(95:99, 0:11)) {
  year_suffix <- ifelse(i <= 11, sprintf("%02d", i), i) 
  dataset_name <- paste0('mtf', year_suffix) 
  
  assign(dataset_name, 
         get(dataset_name) %>%
           mutate(attend = V169,
                  relimp = V170,
                  drink = V103,
                  smoke = V101,
                  gender = V150,
                  race = V151,
                  sibs = V49, 
                  paed = V163, 
                  maed = V164, 
                  pid7 = V166, 
                  id5  = V167, 
                  grade = V179, 
                  weight = V5),
         envir = .GlobalEnv) 
}






########################################


for (i in 12:22) {
  dataset_name <- paste0('mtf', i) 
  assign(dataset_name, get(dataset_name) %>%
           mutate(attend = V2169), envir = .GlobalEnv) 
}


for (i in 12:22) {
  dataset_name <- paste0('mtf', i) 
  assign(dataset_name, get(dataset_name) %>%
           mutate(relimp = V2170), envir = .GlobalEnv) 
}


for (i in 12:21) {
  dataset_name <- paste0('mtf', i) 
  assign(dataset_name, get(dataset_name) %>%
           mutate(drink = V2103), envir = .GlobalEnv) 
}


for (i in 12:22) {
  dataset_name <- paste0('mtf', i) 
  assign(dataset_name, get(dataset_name) %>%
           mutate(smoke = V2101), envir = .GlobalEnv) 
}


for (i in 12:22) {
  dataset_name <- paste0('mtf', i) 
  assign(dataset_name, get(dataset_name) %>%
           mutate(gender = V2150), envir = .GlobalEnv) 
}


for (i in 12:22) {
  dataset_name <- paste0('mtf', i) 
  assign(dataset_name, get(dataset_name) %>%
           mutate(race = V2151), envir = .GlobalEnv) 
}


for (i in 12:22) {
  dataset_name <- paste0('mtf', i) 
  assign(dataset_name, get(dataset_name) %>%
           mutate(sibs = V49), envir = .GlobalEnv) 
}


for (i in 12:22) {
  dataset_name <- paste0('mtf', i) 
  assign(dataset_name, get(dataset_name) %>%
           mutate(paed = V2163), envir = .GlobalEnv) 
}


for (i in 12:22) {
  dataset_name <- paste0('mtf', i) 
  assign(dataset_name, get(dataset_name) %>%
           mutate(maed = V2164), envir = .GlobalEnv) 
}


for (i in 12:22) {
  dataset_name <- paste0('mtf', i) 
  assign(dataset_name, get(dataset_name) %>%
           mutate(pid7 = V2166), envir = .GlobalEnv) 
}


for (i in 12:22) {
  dataset_name <- paste0('mtf', i) 
  assign(dataset_name, get(dataset_name) %>%
           mutate(pid7 = V2167), envir = .GlobalEnv) 
}


for (i in 12:22) {
  dataset_name <- paste0('mtf', i) 
  assign(dataset_name, get(dataset_name) %>%
           mutate(grade = V2179), envir = .GlobalEnv) 
}


for (i in 12:22) {
  dataset_name <- paste0('mtf', i) 
  assign(dataset_name, get(dataset_name) %>%
           mutate(id5 = V2167), envir = .GlobalEnv) 
}


for (i in 12:22) {
  dataset_name <- paste0('mtf', i) 
  assign(dataset_name, get(dataset_name) %>%
           mutate(weight = ARCHIVE_WT), envir = .GlobalEnv) 
}


#########################################



m95 <- mtf95 %>% select( attend, relimp, drink, smoke, gender, race, sibs, paed, maed, pid7, id5, grade, weight) %>% mutate(year = 1995)
m96 <- mtf96 %>% select( attend, relimp, drink, smoke, gender, race, sibs, paed, maed, pid7, id5, grade, weight) %>% mutate(year = 1996)
m97 <- mtf97 %>% select( attend, relimp, drink, smoke, gender, race, sibs, paed, maed, pid7, id5, grade, weight) %>% mutate(year = 1997)
m98 <- mtf98 %>% select( attend, relimp, drink, smoke, gender, race, sibs, paed, maed, pid7, id5, grade, weight) %>% mutate(year = 1998)
m99 <- mtf99 %>% select( attend, relimp, drink, smoke, gender, race, sibs, paed, maed, pid7, id5, grade, weight) %>% mutate(year = 1999)
m00 <- mtf00 %>% select( attend, relimp, drink, smoke, gender, race, sibs, paed, maed, pid7, id5, grade, weight) %>% mutate(year = 2000)
m01 <- mtf01 %>% select( attend, relimp, drink, smoke, gender, race, sibs, paed, maed, pid7, id5, grade, weight) %>% mutate(year = 2001)
m02 <- mtf02 %>% select( attend, relimp, drink, smoke, gender, race, sibs, paed, maed, pid7, id5, grade, weight) %>% mutate(year = 2002)
m03 <- mtf03 %>% select( attend, relimp, drink, smoke, gender, race, sibs, paed, maed, pid7, id5, grade, weight) %>% mutate(year = 2003)
m04 <- mtf04 %>% select( attend, relimp, drink, smoke, gender, race, sibs, paed, maed, pid7, id5, grade, weight) %>% mutate(year = 2004)
m05 <- mtf05 %>% select( attend, relimp, drink, smoke, gender, race, sibs, paed, maed, pid7, id5, grade, weight) %>% mutate(year = 2005)
m06 <- mtf06 %>% select( attend, relimp, drink, smoke, gender, race, sibs, paed, maed, pid7, id5, grade, weight) %>% mutate(year = 2006)
m07 <- mtf07 %>% select( attend, relimp, drink, smoke, gender, race, sibs, paed, maed, pid7, id5, grade, weight) %>% mutate(year = 2007)
m08 <- mtf08 %>% select( attend, relimp, drink, smoke, gender, race, sibs, paed, maed, pid7, id5, grade, weight) %>% mutate(year = 2008)
m09 <- mtf09 %>% select( attend, relimp, drink, smoke, gender, race, sibs, paed, maed, pid7, id5, grade, weight) %>% mutate(year = 2009)
m10 <- mtf10 %>% select( attend, relimp, drink, smoke, gender, race, sibs, paed, maed, pid7, id5, grade, weight) %>% mutate(year = 2010)
m11 <- mtf11 %>% select( attend, relimp, drink, smoke, gender, race, sibs, paed, maed, pid7, id5, grade, weight) %>% mutate(year = 2011)
m12 <- mtf12 %>% select( attend, relimp, drink, smoke, gender, race, sibs, paed, maed, pid7, id5, grade, weight) %>% mutate(year = 2012)
m13 <- mtf13 %>% select( attend, relimp, drink, smoke, gender, race, sibs, paed, maed, pid7, id5, grade, weight) %>% mutate(year = 2013)
m14 <- mtf14 %>% select( attend, relimp, drink, smoke, gender, race, sibs, paed, maed, pid7, id5, grade, weight) %>% mutate(year = 2014)
m15 <- mtf15 %>% select( attend, relimp, drink, smoke, gender, race, sibs, paed, maed, pid7, id5, grade, weight) %>% mutate(year = 2015)
m16 <- mtf16 %>% select( attend, relimp, drink, smoke, gender, race, sibs, paed, maed, pid7, id5, grade, weight) %>% mutate(year = 2016)
m17 <- mtf17 %>% select( attend, relimp, drink, smoke, gender, race, sibs, paed, maed, pid7, id5, grade, weight) %>% mutate(year = 2017)
m18 <- mtf18 %>% select( attend, relimp, drink, smoke, gender, race, sibs, paed, maed, pid7, id5, grade, weight) %>% mutate(year = 2018)
m19 <- mtf19 %>% select( attend, relimp, drink, smoke, gender, race, sibs, paed, maed, pid7, id5, grade, weight) %>% mutate(year = 2019)
m20 <- mtf20 %>% select( attend, relimp, drink, smoke, gender, race, sibs, paed, maed, pid7, id5, grade, weight) %>% mutate(year = 2020)
m21 <- mtf21 %>% select( attend, relimp, drink, smoke, gender, race, sibs, paed, maed, pid7, id5, grade, weight) %>% mutate(year = 2021)
m22 <- mtf22 %>% select( attend, relimp, smoke, gender, race, sibs, paed, maed, pid7, id5, grade, weight) %>% mutate(year = 2022)



# Generate a list of dataset names from m95 to m22
years <- c(paste0("m", 95:99), paste0("m", sprintf("%02d", 0:9)), paste0("m", 10:22))
dataset_names <- lapply(years, function(year) paste0(year))

# Use map to retrieve each dataset and then combine them with bind_rows
combined_df <- map_dfr(dataset_names, function(name) {
  if(exists(name)) {
    get(name)
  } else {
    # If a dataset doesn't exist, create an empty placeholder to prevent errors
    tibble()
  }
})

write_csv(combined_df, "E://data/all_mtf.csv")


two <- import("E://data/all_mtf.csv")

complete <- bind_rows(one, two)

write_csv(complete, "E://data/final_mtf.csv")