RPisaStats: PISA tools for Thesis

source("R/sources.R")

# Remove everything in memory. rm(list = ls(all.names = TRUE))

# Choose memory limit. memory.limit(size = 56000)

# data <- pisa_2018_check(data = "student", path = "data/raw/", file = "CY07_MSU_STU_QQQ.sav")
data <- pisa_2018_students("data/rdata/pisa_2018_students.Rdata")
head(data)
undesired_countries <- c(
  "Vietnam",
  "Moscow City (RUS)",
  "Moscow Region (RUS)",
  "Tatarstan (RUS)"
)

student_info <- dplyr::filter(.data = data, !(filter <- CNTRYID %in% undesired_countries))
student_info <- dplyr::select(.data = student_info, c(
  CNTRYID,
  OECD,
  ST004D01T,
  dplyr::starts_with("PV"),
  dplyr::starts_with("W_FSTU")
))

rm(
  data,
  undesired_countries
)

# Dataframe to generate first 3 columns
oecd <- oecd_info(data = student_info, oecd_string = "Yes")
no_oecd <- oecd_info(data = student_info, oecd_string = "No")

rm(student_info)

# OECD countries Info
oecd_reading_mean <- subject_mean_by_country(oecd, "READ", "Reading_Mean")
oecd_math_mean <- subject_mean_by_country(oecd, "MATH", "Math_Mean")
oecd_science_mean <- subject_mean_by_country(oecd, "SCIE", "Science_Mean")
oecd_countries <- means_generator(
  oecd_reading_mean,
  oecd_math_mean,
  oecd_science_mean
)
global_oecd_reading_mean <- oecd_means_by_country(oecd_reading_mean)
global_oecd_math_mean <- oecd_means_by_country(oecd_math_mean)
global_oecd_science_mean <- oecd_means_by_country(oecd_science_mean)
oecd_mean_df <- means_generator(
  global_oecd_reading_mean,
  global_oecd_math_mean,
  global_oecd_science_mean
)

rm(
  oecd,
  oecd_reading_mean,
  oecd_math_mean,
  oecd_science_mean,
  global_oecd_reading_mean,
  global_oecd_math_mean,
  global_oecd_science_mean
)

# No OECD countries info
no_oecd_reading_mean <- subject_mean_by_country(no_oecd, "READ", "Reading_Mean")
no_oecd_math_mean <- subject_mean_by_country(no_oecd, "MATH", "Math_Mean")
no_oecd_science_mean <- subject_mean_by_country(no_oecd, "SCIE", "Science_Mean")
no_oecd_countries <- means_generator(
  no_oecd_reading_mean,
  no_oecd_math_mean,
  no_oecd_science_mean
)

rm(
  no_oecd,
  no_oecd_reading_mean,
  no_oecd_math_mean,
  no_oecd_science_mean
)

countries <- dplyr::bind_rows(oecd_countries, no_oecd_countries)
countries <- dplyr::arrange(.data = countries, dplyr::desc(countries[[2]]))

first_oecd_countries <- dplyr::arrange(.data = oecd_countries, dplyr::desc(oecd_countries[[2]]))
first_no_oecd_countries <- dplyr::arrange(.data = no_oecd_countries, dplyr::desc(no_oecd_countries[[2]]))

first_countries <- data.frame(dplyr::bind_rows(oecd_mean_df, head(first_oecd_countries), head(first_no_oecd_countries)))

rm(
  oecd_countries,
  no_oecd_countries,
  first_oecd_countries,
  first_no_oecd_countries
)

final_df <- data.frame(dplyr::bind_rows(oecd_mean_df, countries))

rm(
  oecd_mean_df,
  countries
)

final_table <- knitr::kable(final_df, "latex", longtable = T, booktabs = T, caption = "Snapshot Perfomance PISA 2018", label = "FullSnapshotTable")

countries_comp <- knitr::kable(first_countries[1:13, 1:4], "latex", caption = "Comparison of top 6 countries by membership with the OECD average", booktabs = T, label = "MiniSnapshotTable")
# countries_comp <- kableExtra::kable_styling(countries_comp, latex_options = "hold_position")
countries_comp <- kableExtra::pack_rows(countries_comp, "OECD Countries", 2, 7)
countries_comp <- kableExtra::pack_rows(countries_comp, "Not OECD Countries", 8, 13)

save(final_table, countries_comp, file = paste0(here::here(), "/vignettes/chapters/loads/rdata/rdatatest.Rdata"))

rm(
  final_table,
  first_countries
)