library(tidyverse)
## Warning: package 'tidyverse' was built under R version 4.3.2
## Warning: package 'ggplot2' was built under R version 4.3.2
## Warning: package 'tidyr' was built under R version 4.3.2
## Warning: package 'readr' was built under R version 4.3.2
## Warning: package 'dplyr' was built under R version 4.3.2
## Warning: package 'stringr' was built under R version 4.3.2
## Warning: package 'forcats' was built under R version 4.3.2
## Warning: package 'lubridate' was built under R version 4.3.2
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.4     ✔ readr     2.1.5
## ✔ forcats   1.0.0     ✔ stringr   1.5.1
## ✔ ggplot2   3.4.4     ✔ tibble    3.2.1
## ✔ lubridate 1.9.3     ✔ tidyr     1.3.1
## ✔ 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

Data acquisition

# Read data
dataReductions_df <- "cc-est2022-all.csv"
if (file.exists("cc-est2022-all.csv")) {
  print("File exists.")
} else {
  print("File not found.")
}
## [1] "File exists."
dataReductions_df <- read.csv("cc-est2022-all.csv")


# Data dictionary
Data_dictionary <- "https://www2.census.gov/programs-surveys/popest/technical-documentation/file-layouts/2020-2022/cc-est2022-alldata.pdf"

download.file(Data_dictionary, destfile = "cc-est2022-alldata.pdf", mode = "wb")


# Remove missing values from data frame
dataReductions_df <- dataReductions_df[complete.cases(dataReductions_df), ]


# Select needed attributes
selected_attributes <- dataReductions_df[, c("STNAME", "CTYNAME", "YEAR", "AGEGRP", 
                             "TOT_POP", "TOT_MALE", "TOT_FEMALE")]

# Save new data set
save(selected_attributes, file = "Selected_Attributes.RData")


# Check if new file exists
if (file.exists("Selected_Attributes.RData")) {
  load("Selected_Attributes.RData")
} else {
  print("No file found.")
}

Data split

Data_set1 <- selected_attributes %>%
  filter(AGEGRP == 0)

Data_set2 <- selected_attributes %>%
  filter(AGEGRP != 0)


# Data split verification
if (nrow(Data_set1) + nrow(Data_set2) == nrow(selected_attributes)) {
  print("Good!")
} else {
  print("Bad!")
}
## [1] "Good!"

Aggregate across age groups

# Aggregate across Age groups
Aggregated_set <- Data_set2 %>%
  group_by(STNAME, CTYNAME, YEAR) %>%
  summarise(TOT_POP = sum(TOT_POP), TOT_MALE = sum(TOT_MALE), 
            TOT_FEMALE = sum(TOT_FEMALE))
## `summarise()` has grouped output by 'STNAME', 'CTYNAME'. You can override using
## the `.groups` argument.

Does this reduced data set have the same dimensions as set1?

Aggregate across years

Aggregated_set <- Aggregated_set %>%
  group_by(STNAME, CTYNAME) %>%
  summarise(TOT_POP = mean(TOT_POP), TOT_MALE = mean(TOT_MALE), 
            TOT_FEMALE = mean(TOT_FEMALE))
## `summarise()` has grouped output by 'STNAME'. You can override using the
## `.groups` argument.

Aggregate across counties

State_populations <- Aggregated_set %>%
  group_by(STNAME) %>%
  summarise(Total_Population = sum(TOT_POP))

Aggregate across states

Total_pop <- sum(State_populations$Total_Population)

print(Total_pop)
## [1] 332070036

Is this true? (provide a reference) and does this make sense?