# 01_preprocessing.R
#
# Cleaning up data for toy data set Methods Seminar SS2024
#
# Input: RDM_MS_SS2024_download_2024-06-07.csv
# Output: results/data_rdm-ms-ss2024_cleaned.csv
#         results/data_rdm-ms-ss2024_cleaned.RData
#
# created: 2024-06-03

# setwd("C:/Users/nwickelmaier/Nextcloud/Documents/teaching/iwm/data_management/03_data_organisation/example/")

dat <- read.table("data/rawdata/RDM_MS_SS2024_download_2024-06-07.csv",
                  sep = ",", skip = 3, stringsAsFactors = TRUE, na.string = "")

names(dat) <-
  readLines("data/rawdata/RDM_MS_SS2024_download_2024-06-07.csv", 1) |>
  strsplit(split = ",") |>
  unlist()

# Clean up variables
dat$ResponseId <- factor(dat$ResponseId)

dat$sex <- factor(dat$sex,
                  levels = c("m", "f", "d", "not indicated"))

dat$data_sharing_1 <- factor(dat$data_sharing_1,
                             levels = c("No", "Yes"))

dat$career_level_1 <- factor(dat$career_level_1,
                             levels = c("Student", "PhD student", "Postdoc",
                                        "Senior researcher", "Professor",
                                        "Other"))

dat$rdm_stmnt_1 <- factor(dat$rdm_stmnt_1,
                          levels = c("Strongly disagree", "Disagree",
                                     "Neither agree nor disagree", "Agree",
                                     "Strongly agree"))

dat$rdm_stmnt_2 <- factor(dat$rdm_stmnt_2,
                          levels = c("Strongly disagree", "Disagree",
                                     "Neither agree nor disagree", "Agree",
                                     "Strongly agree"))

dat$rdm_stmnt_3 <- factor(dat$rdm_stmnt_3,
                          levels = c("Strongly disagree", "Disagree",
                                     "Neither agree nor disagree", "Agree",
                                     "Strongly agree"))

dat$rdm_stmnt_4 <- factor(dat$rdm_stmnt_4,
                          levels = c("Strongly disagree", "Disagree",
                                     "Neither agree nor disagree", "Agree",
                                     "Strongly agree"))

dat$rdm_stmnt_5 <- factor(dat$rdm_stmnt_5,
                          levels = c("Strongly disagree", "Disagree",
                                     "Neither agree nor disagree", "Agree",
                                     "Strongly agree"))

## Fix data_sharing_2
dat$data_sharing_2[dat$data_sharing_2 == "1 out of 4"] <- 1
dat$data_sharing_2 <- as.numeric(dat$data_sharing_2)

# Create numeric statement variables

dat$rdm_stmnt_1 <- as.numeric(dat$rdm_stmnt_1)
dat$rdm_stmnt_2 <- as.numeric(dat$rdm_stmnt_2)
dat$rdm_stmnt_3 <- as.numeric(dat$rdm_stmnt_3)
dat$rdm_stmnt_4 <- as.numeric(dat$rdm_stmnt_5)
dat$rdm_stmnt_4 <- as.numeric(dat$rdm_stmnt_4)
dat$rdm_stmnt_5 <- as.numeric(dat$rdm_stmnt_5)

# Save cleaned data set
write.table(dat, file = "data/results/data_rdm-ms-ss2024_cleaned.csv", sep = ";",
            row.names = FALSE, quote = FALSE)

save(dat, file = "data/results/data_rdm-ms-ss2024_cleaned.RData")