mtt_haum/code/02_preprocessing.R

61 lines
1.9 KiB
R

# setwd("C:/Users/nwickelmaier/Nextcloud/Documents/MDS/2023ss/60100_master_thesis/code")
source("functions.R")
# Read data
dat0 <- read.table("../data/rawdata_logfiles_small.csv", sep = ";",
header = TRUE)
dat0$date <- as.POSIXct(dat0$date)
dat0$glossar <- ifelse(dat0$artwork == "glossar", 1, 0)
# Remove irrelevant events
dat <- subset(dat0, !(dat0$event %in% c("Start Application",
"Show Application")))
# Add trace variable
dat1 <- add_trace(dat)
# Close events
dat2 <- rbind(close_events(dat1, "move"),
close_events(dat1, "flipCard"),
close_events(dat1, "openTopic"),
close_events(dat1, "openPopup"))
dat2 <- dat2[order(dat2$date.start, dat2$fileId.start), ]
# Remove durations when event spans more than one log file, since they are
# not interpretable
dat2[which(dat2$fileId.start != dat2$fileId.stop), "duration"] <- NA
# Remove all events that do not have a `date.start`
dat2 <- dat2[!is.na(dat2$date.start), ]
rownames(dat2) <- NULL
#summary(dat2)
# Add case variable
dat3 <- add_case(dat2)
# Add event ID
dat3$eventId <- seq_len(nrow(dat3))
dat3 <- dat3[, c("fileId.start", "fileId.stop", "eventId", "case",
"trace", "glossar", "event", "artwork",
"date.start", "date.stop", "timeMs.start",
"timeMs.stop", "duration", "topicNumber", "popup",
"x.start", "y.start", "x.stop", "y.stop",
"distance", "scale.start", "scale.stop",
"scaleSize", "rotation.start", "rotation.stop",
"rotationDegree")]
# Add trace for move events
dat4 <- add_trace_moves(dat3)
# Fill in topics
# topics <- read.table("../data/topics.csv", sep = ";", header = TRUE)
# TODO: Add topics to data frame
# Export data
write.table(dat4, "../data/event_logfiles.csv", sep = ";",
row.names = FALSE)