save_CAMs_as_pictures = TRUE
# consider_Protocol = FALSE # not needed at current stageData Preperation - Teacher Study
Background Information
This is an R Markdown document. Instructions for writing these documents and background information can be found in the book written by Xie, Allaire, and Grolemund (2018) When you execute code within the document, the results appear beneath the code. This is an R Markdown document. Instructions for writing these documents and background information can be found in the book written by Xie, Allaire, and Grolemund (2018) When you execute code within the document, the results appear beneath the code. This file contains summary statistics, respectively the analysis step (confirmatory and exploratory analyses). Files are split into multiple subfiles like data processing and data analyses steps, which follows the classical data-analysis pipeline (see Peng and Matsui 2016; Wickham and Grolemund 2017).
Setup
Global variables
Load packages
require(pacman)Lade nötiges Paket: pacmanp_load('tidyverse', 'jsonlite', 'magrittr',
'stargazer', 'psych', 'jtools', 'DT', 'igraph',
'writexl', 'Cairo')Check your raw data:
### list data files
setwd("data")
folders <- list.files(pattern = "^study_result.*")
for(i in 1:length(folders)){
setwd(folders[i])
if(length(dir()) == 3){
cat("\n ################## \n")
print(i)
# pre CAM data
setwd(dir()[1])
tmp <- jsonlite::fromJSON(txt = "data.txt")
tmp_id <- tmp$ID[!is.na(tmp$ID)]
cat("01:\n")
cat("tmp_id:", tmp_id, "\n")
cat("sender:", tmp$sender[!is.na(tmp$sender)], "\n")
setwd("..")
# tmp_backup <- tmp
# CAM data t1
setwd(dir()[2])
tmp2 <- jsonlite::fromJSON(txt = "data.txt")
# tmp_backup2 <- tmp2
cat("02:\n")
cat("tmp2$creator:", tmp2$creator, "\n")
# print(tmp2$projectCAM)
# print(tmp2$creator)
# print(length(tmp2$nodes))
setwd("..")
# post CAM data
setwd(dir()[3])
tmp <- jsonlite::fromJSON(txt = "data.txt")
tmp_id <- tmp$ID[!is.na(tmp$ID)]
cat("03:\n")
cat("tmp_id:", tmp_id, "\n")
cat("sender:", tmp$sender[!is.na(tmp$sender)], "\n")
setwd("..")
cat("\n")
}
setwd("..")
}
##################
[1] 6
01:
tmp_id: 578843
sender: Greetings InformedConsent InformedConsentNO socioDemographic Videopage CAMsDetailedInst
02:
tmp2$creator: 578843
03:
tmp_id:
sender: CAMfeedbackGeneral additional scale SCALES Sequence DonationScreen FeedbackScreen EndingScreen
##################
[1] 11
01:
tmp_id: 238101
sender: Greetings InformedConsent InformedConsentNO socioDemographic Videopage CAMsDetailedInst
02:
tmp2$creator: 238101
03:
tmp_id:
sender: CAMfeedbackGeneral additional scale SCALES Sequence DonationScreen FeedbackScreen EndingScreen
##################
[1] 12
01:
tmp_id: 858644
sender: Greetings InformedConsent InformedConsentNO socioDemographic Videopage CAMsDetailedInst
02:
tmp2$creator: 858644
03:
tmp_id:
sender: CAMfeedbackGeneral additional scale SCALES Sequence DonationScreen FeedbackScreen EndingScreen
##################
[1] 19
01:
tmp_id: 376106
sender: Greetings InformedConsent InformedConsentNO socioDemographic Videopage CAMsDetailedInst
02:
tmp2$creator: 376106
03:
tmp_id:
sender: CAMfeedbackGeneral additional scale SCALES Sequence DonationScreen FeedbackScreen EndingScreen
##################
[1] 22
01:
tmp_id: 35549
sender: Greetings InformedConsent InformedConsentNO socioDemographic Videopage CAMsDetailedInst
02:
tmp2$creator: 35549
03:
tmp_id:
sender: CAMfeedbackGeneral additional scale SCALES Sequence DonationScreen FeedbackScreen EndingScreen
##################
[1] 27
01:
tmp_id: 128115
sender: Greetings InformedConsent InformedConsentNO socioDemographic Videopage CAMsDetailedInst
02:
tmp2$creator: 128115
03:
tmp_id:
sender: CAMfeedbackGeneral additional scale SCALES Sequence DonationScreen FeedbackScreen EndingScreen
##################
[1] 28
01:
tmp_id: 702927
sender: Greetings InformedConsent InformedConsentNO socioDemographic Videopage CAMsDetailedInst
02:
tmp2$creator: 702927
03:
tmp_id:
sender: CAMfeedbackGeneral additional scale SCALES Sequence DonationScreen FeedbackScreen EndingScreen
##################
[1] 33
01:
tmp_id: 432155
sender: Greetings InformedConsent InformedConsentNO socioDemographic Videopage CAMsDetailedInst
02:
tmp2$creator: 432155
03:
tmp_id:
sender: CAMfeedbackGeneral additional scale SCALES Sequence DonationScreen FeedbackScreen EndingScreen
##################
[1] 35
01:
tmp_id: 29087
sender: Greetings InformedConsent InformedConsentNO socioDemographic Videopage CAMsDetailedInst
02:
tmp2$creator: 29087
03:
tmp_id:
sender: CAMfeedbackGeneral additional scale SCALES Sequence DonationScreen FeedbackScreen
##################
[1] 38
01:
tmp_id: 293295
sender: Greetings InformedConsent InformedConsentNO socioDemographic Videopage CAMsDetailedInst
02:
tmp2$creator: 293295
03:
tmp_id:
sender: CAMfeedbackGeneral additional scale SCALES Sequence DonationScreen FeedbackScreen EndingScreen
##################
[1] 39
01:
tmp_id: 330258
sender: Greetings InformedConsent InformedConsentNO socioDemographic Videopage CAMsDetailedInst
02:
tmp2$creator: 330258
03:
tmp_id:
sender: CAMfeedbackGeneral additional scale SCALES Sequence DonationScreen FeedbackScreen EndingScreen
##################
[1] 41
01:
tmp_id: 555046
sender: Greetings InformedConsent InformedConsentNO socioDemographic Videopage CAMsDetailedInst
02:
tmp2$creator: 555046
03:
tmp_id:
sender: CAMfeedbackGeneral additional scale SCALES Sequence DonationScreen FeedbackScreen EndingScreen rm(tmp); rm(tmp2)create raw data files
### list data files
setwd("data")
folders <- list.files(pattern = "^study_result.*")
### create data files - GERMANY
# get CAM data
writeLines("", "CAM_t1.txt") # create file
text_connection <-
file("CAM_t1.txt", "a") # open connection to append
# get pre CAM data
writeLines("", "preCAM.txt") # create file
text_connection_pre <-
file("preCAM.txt", "a") # open connection to append
# get post CAM data
writeLines("", "postCAM.txt") # create file
text_connection_post <-
file("postCAM.txt", "a") # open connection to append
for (i in 1:length(folders)) {
setwd(folders[i])
if (length(dir()) == 3) {
# print(i)
# pre CAM data
setwd(dir()[1])
tmp1 <- jsonlite::fromJSON(txt = "data.txt")
tmp_id <- tmp1$ID[!is.na(tmp1$ID)]
setwd("..")
# CAM data
setwd(dir()[2])
tmp2 <- jsonlite::fromJSON(txt = "data.txt")
if (!("creator" %in% names(tmp2)) || tmp2$creator != tmp_id) {
warning("IDs (primary keys) not matching or order of datasets is distorted - 1")
tmp2 <- NULL
}
setwd("..")
# post CAM data
setwd(dir()[3])
tmp3 <- jsonlite::fromJSON(txt = "data.txt")
tmp3$ID <- NA
tmp3$ID[2] <- tmp_id
setwd("..")
cat("checks for i:", i, !is.null(tmp1) &&
!is.null(tmp2) &&
!is.null(tmp3), "\n")
if (!is.null(tmp1) &&
!is.null(tmp2) &&
!is.null(tmp3)) {
writeLines(jsonlite::toJSON(x = tmp1), text_connection_pre)
writeLines(jsonlite::toJSON(x = tmp2), text_connection)
writeLines(jsonlite::toJSON(x = tmp3), text_connection_post)
}
}
setwd("..")
}checks for i: 6 TRUE
checks for i: 11 TRUE
checks for i: 12 TRUE
checks for i: 19 TRUE
checks for i: 22 TRUE
checks for i: 27 TRUE
checks for i: 28 TRUE
checks for i: 33 TRUE
checks for i: 35 TRUE
checks for i: 38 TRUE
checks for i: 39 TRUE
checks for i: 41 TRUE close(text_connection) # close connection CAM
close(text_connection_pre) # close connection
close(text_connection_post) # close connection
### move files to output folder
# copy files (not overwritten)
tmp_file_from <- getwd()
setwd("../outputs/data_raw")
file.copy(
from = paste0(tmp_file_from, "/CAM_t1.txt"),
to = paste0(getwd(), "/CAM_t1.txt")
)[1] FALSEfile.copy(
from = paste0(tmp_file_from, "/preCAM.txt"),
to = paste0(getwd(), "/preCAM.txt")
)[1] FALSEfile.copy(
from = paste0(tmp_file_from, "/postCAM.txt"),
to = paste0(getwd(), "/postCAM.txt")
)[1] FALSE# remove files
file.remove(paste0(tmp_file_from, "/CAM_t1.txt"))[1] TRUEfile.remove(paste0(tmp_file_from, "/preCAM.txt"))[1] TRUEfile.remove(paste0(tmp_file_from, "/postCAM.txt"))[1] TRUE### load functions
# print(getwd())
setwd("../../../../functions")
for (i in 1:length(dir())) {
# print(dir()[i])
source(dir()[i], encoding = "utf-8")
}
setwd("../functions_CAMapp")
for (i in 1:length(dir())) {
# print(dir()[i])
source(dir()[i], encoding = "utf-8")
}
rm(i)
rm(tmp1)
rm(tmp2)
rm(tmp3)
rm(tmp_id)
rm(folders)
rm(tmp_file_from)
rm(text_connection)
rm(text_connection_pre)
rm(text_connection_post)set up data.frame questionnaires
load data:
setwd("outputs/data_raw")
# > pre study
suppressMessages(read_file('preCAM.txt') %>%
# ... split it into lines ...
str_split('\n') %>% first() %>%
# ... filter empty rows ...
discard(function(x) x == '') %>%
discard(function(x) x == '\r') %>%
# ... parse JSON into a data.frame
map_dfr(fromJSON, flatten=TRUE)) -> dat_preCAM
# > post first CAM
suppressMessages(read_file('postCAM.txt') %>%
# ... split it into lines ...
str_split('\n') %>% first() %>%
# ... filter empty rows ...
discard(function(x) x == '') %>%
discard(function(x) x == '\r') %>%
# ... parse JSON into a data.frame
map_dfr(fromJSON, flatten=TRUE)) -> dat_postCAMcolnames(dat_preCAM)[colnames(dat_preCAM) == "ID"] <- "uniqueID"
colnames(dat_postCAM)[colnames(dat_postCAM) == "ID"] <- "uniqueID"
sum(!is.na(dat_preCAM$uniqueID))[1] 12sum(!is.na(dat_postCAM$uniqueID))[1] 12add unique ID variable to match rows to participants, only keep complete data sets:
### create counter variable for both data sets
# pre study
dat_preCAM$ID <- NA
tmp_IDcounter <- 0
for(i in 1:nrow(dat_preCAM)){
if(!is.na(dat_preCAM$sender[i]) && dat_preCAM$sender[i] == "Greetings"){
tmp_IDcounter = tmp_IDcounter + 1
}
dat_preCAM$ID[i] <- tmp_IDcounter
}
# post study
dat_postCAM$ID <- NA
tmp_IDcounter <- 0
for(i in 1:nrow(dat_postCAM)){
if(!is.na(dat_postCAM$sender[i]) && dat_postCAM$sender[i] == "CAMfeedbackGeneral"){
tmp_IDcounter = tmp_IDcounter + 1
}
dat_postCAM$ID[i] <- tmp_IDcounter
}
### keep only complete data sets
# pre-study
# sort(table(dat_preCAM$ID))
sum(table(dat_preCAM$ID) != max(table(dat_preCAM$ID)))[1] 0sum(table(dat_preCAM$ID) == max(table(dat_preCAM$ID)))[1] 12dat_preCAM <- dat_preCAM[dat_preCAM$ID %in% names(table(dat_preCAM$ID))[table(dat_preCAM$ID) == max(table(dat_preCAM$ID))],]
# post-study
# sort(table(dat_postCAM$ID))
sum(table(dat_postCAM$ID) != max(table(dat_postCAM$ID)))[1] 1sum(table(dat_postCAM$ID) == max(table(dat_postCAM$ID)))[1] 11dat_postCAM <- dat_postCAM[dat_postCAM$ID %in% names(table(dat_postCAM$ID))[table(dat_postCAM$ID) == max(table(dat_postCAM$ID))],]
all(unique(dat_preCAM$ID) %in% unique(dat_postCAM$ID))[1] FALSErename ID variable for data sets:
questionnaire pre-study (component 1)
colnames(dat_preCAM) [1] "sender" "sender_type"
[3] "sender_id" "6"
[5] "ended_on" "duration"
[7] "time_run" "time_render"
[9] "time_show" "time_end"
[11] "time_commit" "timestamp"
[13] "time_switch" "para_defocuscount"
[15] "currentLocation" "IDtype"
[17] "uniqueID" "dummy_informedconsent"
[19] "sociodemo_age" "sociodemo_gender"
[21] "sociodemo_language" "sociodemo_subjects_taught"
[23] "sociodemo_school_types" "sociodemo_teaching_experience"
[25] "meta.labjs_version" "meta.location"
[27] "meta.userAgent" "meta.platform"
[29] "meta.language" "meta.locale"
[31] "meta.timeZone" "meta.timezoneOffset"
[33] "meta.screen_width" "meta.screen_height"
[35] "meta.scroll_width" "meta.scroll_height"
[37] "meta.window_innerWidth" "meta.window_innerHeight"
[39] "meta.devicePixelRatio" "meta.labjs_build.flavor"
[41] "meta.labjs_build.commit" "7"
[43] "ID" tmp_notNumeric <- str_subset(string = colnames(dat_preCAM), pattern = "^meta|^R")
tmp_notNumeric <- str_subset(string = tmp_notNumeric, pattern = "labjs|location", negate = TRUE)
tmp_notNumeric <- c(tmp_notNumeric, "sociodemo_gender", "sociodemo_language", "sociodemo_subjects_taught", "sociodemo_school_types")
vec_ques <- c("uniqueID",
"currentLocation", "IDtype",
"dummy_informedconsent",
"commCheck",
"sociodemo_age", "sociodemo_gender", "sociodemo_language", "sociodemo_subjects_taught", "sociodemo_school_types", "sociodemo_teaching_experience",
tmp_notNumeric)
vec_notNumeric = c("uniqueID", "currentLocation", "IDtype", tmp_notNumeric)
questionnaire_c1 <- questionnairetype(dataset = dat_preCAM,
listvars = vec_ques,
notNumeric = vec_notNumeric, verbose = FALSE)
dim(questionnaire_c1)[1] 12 24colnames(questionnaire_c1) [1] "ID" "uniqueID"
[3] "currentLocation" "IDtype"
[5] "dummy_informedconsent" "sociodemo_age"
[7] "sociodemo_gender" "sociodemo_language"
[9] "sociodemo_subjects_taught" "sociodemo_school_types"
[11] "sociodemo_teaching_experience" "meta.userAgent"
[13] "meta.platform" "meta.language"
[15] "meta.locale" "meta.timeZone"
[17] "meta.timezoneOffset" "meta.screen_width"
[19] "meta.screen_height" "meta.scroll_width"
[21] "meta.scroll_height" "meta.window_innerWidth"
[23] "meta.window_innerHeight" "meta.devicePixelRatio" questionnaire post-CAM (component 3)
colnames(dat_postCAM) [1] "sender" "sender_type"
[3] "sender_id" "feedCAM_repres"
[5] "ease_mindmap" "feedCAM_technicalprobs"
[7] "feedCAM_technicalprobsText" "feedCAM_already"
[9] "feedCAM_alreadyText" "10"
[11] "ended_on" "duration"
[13] "time_run" "time_render"
[15] "time_show" "time_end"
[17] "time_commit" "timestamp"
[19] "time_switch" "guttman-item"
[21] "not_needed" "guttman-response"
[23] "uniqueID" "para_countclicks"
[25] "education-4" "education-1"
[27] "education-3" "education-2"
[29] "donation_choice" "feedback_critic"
[31] "para_defocuscount" "11"
[33] "ID" vec_ques <- c("uniqueID",
"feedCAM_repres",
"ease_mindmap",
"feedCAM_technicalprobs", "feedCAM_technicalprobsText",
"feedCAM_already", "feedCAM_alreadyText",
sort(str_subset(string = colnames(dat_postCAM), pattern = "^education")),
"donation_choice",
"feedback_critic")
vec_notNumeric = c("uniqueID",
"feedCAM_technicalprobsText", "feedCAM_alreadyText", "donation_choice", "feedback_critic")
questionnaire_c3 <- questionnairetype(dataset = dat_postCAM,
listvars = vec_ques,
notNumeric = vec_notNumeric, verbose = TRUE)[1] 1
[1] "uniqueID"
[1] 2
[1] "feedCAM_repres"
[1] 3
[1] "ease_mindmap"
[1] 4
[1] "feedCAM_technicalprobs"
[1] 5
[1] "feedCAM_technicalprobsText"
[1] 6
[1] "feedCAM_already"
[1] 7
[1] "feedCAM_alreadyText"
[1] 8
[1] "education-1"
[1] 9
[1] "education-2"
[1] 10
[1] "education-3"
[1] 11
[1] "education-4"
[1] 12
[1] "donation_choice"
[1] 13
[1] "feedback_critic"dim(questionnaire_c3)[1] 11 14colnames(questionnaire_c3) [1] "ID" "uniqueID"
[3] "feedCAM_repres" "ease_mindmap"
[5] "feedCAM_technicalprobs" "feedCAM_technicalprobsText"
[7] "feedCAM_already" "feedCAM_alreadyText"
[9] "education-1" "education-2"
[11] "education-3" "education-4"
[13] "donation_choice" "feedback_critic" get ratings of law and guttman
# Pre-define the column names with rat_ pattern
guttman_cols <- sort(str_subset(string = colnames(dat_postCAM), pattern = "^guttman"))
# to merge data sets
# for(i in 1:length(guttman_cols)){
# dat_postCAM[[guttman_cols[i]]] <- NA
# }
# Create an empty list to store processed data
result_list <- list()
dat_merged <- dat_postCAM[, c("ID", "uniqueID", "sender", guttman_cols)]
dat_merged$`guttman-response`[!is.na(dat_merged$`guttman-item`) & dat_merged$`guttman-response` == "NA"] <- "LNA"
# Loop over each unique ID
for (i in unique(dat_merged$ID)) {
tmp <- dat_merged[dat_merged$ID == i, c("uniqueID", "sender", guttman_cols)]
# Fill down uniqueID if missing
tmp <- tmp %>%
fill(uniqueID, .direction = "downup")
# Filter rows where all rat_ columns are not NA
tmp <- tmp %>%
filter(
if_any(all_of(guttman_cols), ~ !is.na(.)) # at least one guttman_* value present
)
tmp$sender[is.na(tmp$sender)] <- paste0("GI_", tmp$`guttman-item`[!is.na(tmp$`guttman-item`)])
# Append to result list
result_list[[as.character(i)]] <- tmp
}
# Combine all into one dataframe
questionnaire_rating_long <- bind_rows(result_list)
questionnaire_rating_long$sender <- factor(questionnaire_rating_long$sender)
# wide data set for guttman ratings
colnames(questionnaire_rating_long)[colnames(questionnaire_rating_long) == "guttman-item"] <- "item"
colnames(questionnaire_rating_long)[colnames(questionnaire_rating_long) == "guttman-response"] <- "response"
questionnaire_rating_wide_guttman <- questionnaire_rating_long %>%
pivot_wider(
id_cols = uniqueID,
names_from = item,
values_from = response,
names_glue = "response_{item}"
)merge all data sets
# Start with the first dataset
merged_data <- questionnaire_c1
# Left join the others one by one
merged_data <- merged_data %>%
left_join(questionnaire_c3, by = "uniqueID") %>%
left_join(questionnaire_rating_wide_guttman, by = "uniqueID")
merged_data$ID.x <- NULL
merged_data$ID.y <- NULL
dim(merged_data)[1] 12 39colnames(merged_data) [1] "uniqueID" "currentLocation"
[3] "IDtype" "dummy_informedconsent"
[5] "sociodemo_age" "sociodemo_gender"
[7] "sociodemo_language" "sociodemo_subjects_taught"
[9] "sociodemo_school_types" "sociodemo_teaching_experience"
[11] "meta.userAgent" "meta.platform"
[13] "meta.language" "meta.locale"
[15] "meta.timeZone" "meta.timezoneOffset"
[17] "meta.screen_width" "meta.screen_height"
[19] "meta.scroll_width" "meta.scroll_height"
[21] "meta.window_innerWidth" "meta.window_innerHeight"
[23] "meta.devicePixelRatio" "feedCAM_repres"
[25] "ease_mindmap" "feedCAM_technicalprobs"
[27] "feedCAM_technicalprobsText" "feedCAM_already"
[29] "feedCAM_alreadyText" "education-1"
[31] "education-2" "education-3"
[33] "education-4" "donation_choice"
[35] "feedback_critic" "response_1"
[37] "response_4" "response_3"
[39] "response_2" save all data sets
setwd("outputs/questionnaire")
# Save as .RData objects
save(questionnaire_c1, file = "questionnaire_c1.RData")
save(questionnaire_c3, file = "questionnaire_c3.RData")
save(merged_data, file = "merged_data.RData")
save(questionnaire_rating_long, file = "questionnaire_rating_long.RData")
# Save as Excel files
write_xlsx(questionnaire_c1, "questionnaire_c1.xlsx")
write_xlsx(questionnaire_c3, "questionnaire_c3.xlsx")
write_xlsx(merged_data, "merged_data.xlsx")
write_xlsx(questionnaire_rating_long, "questionnaire_rating_long.xlsx")set up CAM data
pre CAM (component 2)
Load CAM data
setwd("outputs/data_raw")
suppressMessages(read_file("CAM_t1.txt") %>%
# ... split it into lines ...
str_split('\n') %>% first() %>%
discard(function(x) x == '') %>%
discard(function(x) x == '\r') %>%
# ... filter empty rows ...
discard(function(x) x == '')) -> dat_CAM_pre
raw_CAM_pre <- list()
for(i in 1:length(dat_CAM_pre)){
raw_CAM_pre[[i]] <- jsonlite::fromJSON(txt = dat_CAM_pre[[i]])
}Create CAM files, draw CAMs and compute network indicators
### create CAM single files (nodes, connectors, merged)
CAMfiles_pre <- create_CAMfiles(datCAM = raw_CAM_pre, reDeleted = TRUE)Nodes and connectors, which were deleted by participants were removed.
# deleted nodes: 57
# deleted connectors: 21# remove testing data sets
nrow(CAMfiles_pre[[1]])[1] 201# CAMfiles_pre[[1]] <- CAMfiles_pre[[1]][nchar(CAMfiles_pre[[1]]$participantCAM) == 24,]
# CAMfiles_pre[[2]] <- CAMfiles_pre[[2]][nchar(CAMfiles_pre[[2]]$participantCAM) == 24,]
# CAMfiles_pre[[3]] <- CAMfiles_pre[[3]][nchar(CAMfiles_pre[[3]]$participantCAM.x) == 24,]
# number of CAMs collected
nrow(CAMfiles_pre[[1]])[1] 201# remove person who draw many empty concepts
# tmp_pid <- unique(CAMfiles_pre[[1]]$participantCAM[CAMfiles_pre[[1]]$CAM %in% c("a0c6edeb-267a-4f27-8199-79f896e033ce", "8d74f576-e617-4eb1-8ccf-93589ce6c65b")])
# print(tmp_pid)
## remove person from questionnaire data
# questionnaire <- questionnaire[!questionnaire$PROLIFIC_PID %in% tmp_pid,]
## remove person from CAM data
# table(CAMfiles_pre[[1]][CAMfiles_pre[[1]]$participantCAM %in% tmp_pid,]$text)
# CAMfiles_pre[[1]] <- CAMfiles_pre[[1]][!CAMfiles_pre[[1]]$participantCAM %in% tmp_pid,]
# CAMfiles_pre[[2]] <- CAMfiles_pre[[2]][!CAMfiles_pre[[2]]$participantCAM %in% tmp_pid,]
# CAMfiles_pre[[3]] <- CAMfiles_pre[[3]][!CAMfiles_pre[[3]]$participantCAM.x %in% tmp_pid,]
# remove 7 empty concepts:
# CAMfiles_pre[[1]]$text[nchar(CAMfiles_pre[[1]]$text) < 2]
# tmp_ids <- CAMfiles_pre[[1]]$id[nchar(CAMfiles_pre[[1]]$text) < 2]
# table(CAMfiles_pre[[1]]$isActive[CAMfiles_pre[[1]]$id %in% tmp_ids])
# table(CAMfiles_pre[[1]]$participantCAM[CAMfiles_pre[[1]]$id %in% tmp_ids])
#
# CAMfiles_pre[[1]] <- CAMfiles_pre[[1]][!CAMfiles_pre[[1]]$id %in% tmp_ids,]
CAMfiles_pre[[1]]$text[CAMfiles_pre[[1]]$text == "Wissenschaft- Interesse"] <- "Wissenschaft-Interesse"
CAMfiles_pre[[1]]$text[CAMfiles_pre[[1]]$text == "BNE fächerbezogen"] <- "BNE-fächerbezogen"
### draw CAMs
CAMdrawn_pre <- draw_CAM(dat_merged = CAMfiles_pre[[3]],
dat_nodes = CAMfiles_pre[[1]],ids_CAMs = "all",
plot_CAM = FALSE,
useCoordinates = TRUE,
relvertexsize = 3,
reledgesize = 1)processing 12 CAMs... Warning: `graph.data.frame()` was deprecated in igraph 2.0.0.
ℹ Please use `graph_from_data_frame()` instead.Warning: `as.undirected()` was deprecated in igraph 2.1.0.
ℹ Please use `as_undirected()` instead.[1] "== participantCAM in drawnCAM"for(i in 1:length(CAMdrawn_pre)){
if(any(nchar(V(CAMdrawn_pre[[i]])$label) < 3)){
print(V(CAMdrawn_pre[[i]])$label)
}
}
### network indicators
tmp_microIndicator <- c("BNE", "BNE-fächerbezogen", "BNE Relevanz", "Empirische Fachdidaktik", "Wissenschaft-Interesse", "Verantwortung")
networkIndicators_pre <- compute_indicatorsCAM(drawn_CAM = CAMdrawn_pre,
micro_degree = tmp_microIndicator,
micro_valence = tmp_microIndicator,
micro_centr_clo = tmp_microIndicator,
micro_transitivity = tmp_microIndicator,
largestClique = FALSE)Warning: `graph.density()` was deprecated in igraph 2.0.0.
ℹ Please use `edge_density()` instead.Warning: The `types1` argument of `assortativity()` is deprecated as of igraph 1.6.0.
ℹ Please use the `values` argument instead.Warning: `assortativity.degree()` was deprecated in igraph 2.0.0.
ℹ Please use `assortativity_degree()` instead.### wordlist
CAMwordlist_pre <- create_wordlist(
dat_nodes = CAMfiles_pre[[1]],
dat_merged = CAMfiles_pre[[3]],
useSummarized = TRUE,
order = "frequency",
splitByValence = FALSE,
comments = TRUE,
raterSubsetWords = NULL,
rater = FALSE
)[1] "create_wordlist - use raw words"
[1] 0
[1] 201
[1] "temporarily suffixes are added, because not all words have been summarized"
processing 12 CAMs...
[1] "== participantCAM in drawnCAM"if(all(nchar(CAMwordlist_pre$Words) > 2)){
print("sucessfully removed empty words")
}[1] "sucessfully removed empty words"DT::datatable(CAMwordlist_pre, options = list(pageLength = 5)) save CAMs as .json files, and as .png (igraph)
if(save_CAMs_as_pictures){
setwd("outputs")
setwd("savedCAMs")
setwd("png")
### remove all files if there are any
if(length(list.files()) >= 1){
file.remove(list.files())
cat('\n!
all former .png files have been deleted')
}
### if no participant ID was provided replace by randomly generated CAM ID
# if(all(CAMfiles_pre[[3]]$participantCAM.x == "noID")){
# CAMfiles_pre[[3]]$participantCAM.x <- CAMfiles_pre[[3]]$CAM.x
# }
### save as .json files, and as .png (igraph)
ids_CAMs <- unique(CAMfiles_pre[[3]]$participantCAM.x); length(ids_CAMs)
for(i in 1:length(ids_CAMs)){
save_graphic(filename = paste0("CAM", "_t1_", ids_CAMs[i])) # paste0(ids_CAMs[i]))
CAM_igraph <- CAMdrawn_pre[[c(1:length(CAMdrawn_pre))[
names(CAMdrawn_pre) == paste0(unique(CAMfiles_pre[[3]]$participantCAM.x)[i])]]]
plot(CAM_igraph, edge.arrow.size = .7,
layout=layout_nicely, vertex.frame.color="black", asp = .5, margin = -0.1,
vertex.size = 10, vertex.label.cex = .9)
dev.off()
}
setwd("../json")
### remove all files if there are any
if(length(list.files()) >= 1){
file.remove(list.files())
cat('\n!
all former .json files have been deleted')
}
for(i in 1:length(raw_CAM_pre)){
if(!is_empty(raw_CAM_pre[[i]]$nodes)){
if(nrow(raw_CAM_pre[[i]]$nodes) > 5){
write(toJSON(raw_CAM_pre[[i]], encoding = "UTF-8"),
paste0(raw_CAM_pre[[i]]$creator, ".json"))
}
}
}
}
!
all former .png files have been deleted
!
all former .json files have been deletedmerge and save all data
setwd("outputs/CAMs")
if(all(unique(CAMfiles_pre[[1]]$participantCAM) == networkIndicators_pre$participantCAM)){
print("pre CAM ID can be set")
networkIndicators_pre$CAM_ID <- unique(CAMfiles_pre[[1]]$CAM)
}[1] "pre CAM ID can be set"### remove all previously removed participants
nrow(networkIndicators_pre)[1] 12nrow(merged_data)[1] 12### match data
if (all(merged_data$PROLIFIC_PID == networkIndicators_pre$participantCAM)) {
print("all data can be matched row by row")
# fix IDs
# networkIndicators_pre$participantCAM <- paste0(networkIndicators_pre$participantCAM, "_pre")
# save questionnaire
merged_data$participantCAM <- networkIndicators_pre$participantCAM
## save as .xlsx file
xlsx::write.xlsx2(x = merged_data, file = "merged_data_final.xlsx")
## save as R object
saveRDS(merged_data, file = "merged_data_final.rds")
# save network indicators pre
## save as .xlsx file
xlsx::write.xlsx2(x = networkIndicators_pre, file = "networkIndicators_pre_final.xlsx")
## save as R object
saveRDS(networkIndicators_pre, file = "networkIndicators_pre_final.rds")
# save CAMfiles pre
saveRDS(CAMfiles_pre, file = "CAMfiles_pre_final.rds")
# save CAMfiles combined and clean
# saveRDS(CAMfiles_combined_translated, file = "CAMfiles_combined_final_translated.rds")
# save questionnaire combined with CAMs
# colnames(networkIndicators_pre) <- paste0(colnames(networkIndicators_pre), "_pre")
merged_dataCAMs <- cbind(merged_data, networkIndicators_pre)
dim(merged_dataCAMs)
## save as .xlsx file
xlsx::write.xlsx2(x = merged_dataCAMs, file = "merged_dataCAMs_final.xlsx")
## save as R object
saveRDS(merged_dataCAMs, file = "merged_dataCAMs_final.rds")
}[1] "all data can be matched row by row"describe sample
pupils who participated:
psych::describe(x = merged_dataCAMs[,c("sociodemo_age", "sociodemo_teaching_experience")]) vars n mean sd median trimmed mad min max
sociodemo_age 1 12 41.33 12.86 43.5 41.8 12.60 18 60
sociodemo_teaching_experience 2 12 15.50 10.25 12.5 15.9 15.57 0 27
range skew kurtosis se
sociodemo_age 42 -0.38 -1.14 3.71
sociodemo_teaching_experience 27 -0.05 -1.72 2.96table(merged_dataCAMs$sociodemo_gender)
female male none
9 2 1 table(merged_dataCAMs$sociodemo_language)
yes
12 table(merged_dataCAMs$sociodemo_subjects_taught)
Biologie, Musik, Kath. Religion, Sport
1
Deutsch, Biologie, Kath. Religion, Informatik
1
Deutsch, Biologie, Technik
1
Deutsch, Geschichte, Sport
1
Deutsch, Mathe, Sachunterricht, BSS, Kunst, Musik
1
Deutsch, naturw.-technischer Sachunterricht
1
Geographie, Biologie, Chemie, NwT, Medienbildung
1
Mathematik, Deutsch, Biologie, DaZ/DaF, Ethik
1
Mathematik, Sport, Biologie
1
Religion, Mathematik, Deutsch, Sachunterricht, Kunst
1
Sachunterricht, Pädagogik
1
Test, Test
1 table(merged_dataCAMs$sociodemo_school_types)
GMS
1
Grundschule
3
Gymnasium
1
Realschule
3
Realschule und Werkrealschule
1
Test, Test
1
Werkreal-/Realschule
1
Zur Zeit gar nicht, da ich voll am Semianr beschäftigt bin
1 table(merged_dataCAMs$sociodemo_teaching_experience)
0 2 8 10 15 23 27
1 1 1 3 1 1 4 CAMs:
psych::describe(x = networkIndicators_pre[,c("mean_valence_macro", "num_nodes_macro", "num_edges_macro")]) vars n mean sd median trimmed mad min max range
mean_valence_macro 1 12 0.99 0.90 0.81 0.94 0.85 -0.17 2.67 2.83
num_nodes_macro 2 12 16.75 6.28 14.00 15.60 2.97 12.00 33.00 21.00
num_edges_macro 3 12 23.25 8.56 23.00 22.60 7.41 12.00 41.00 29.00
skew kurtosis se
mean_valence_macro 0.52 -1.14 0.26
num_nodes_macro 1.42 0.99 1.81
num_edges_macro 0.51 -0.75 2.47References
Peng, Roger D., and Elizabeth Matsui. 2016. The Art of Data Science: A Guide for Anyone Who Works with Data. Lulu.com. https://bookdown.org/rdpeng/artofdatascience/.
Wickham, Hadley, and Garrett Grolemund. 2017. R for Data Science: Import, Tidy, Transform, Visualize, and Model Data. "O’Reilly Media, Inc.". https://r4ds.had.co.nz/.
Xie, Yihui, J. J. Allaire, and Garrett Grolemund. 2018. R Markdown: The Definitive Guide. New York: Chapman; Hall/CRC. https://doi.org/10.1201/9781138359444.