mtt_haum/code/04_modeling_haum.R

#' ---
#' title: "Modelling log files with Process Mining"
#' author: "Nora Wickelmaier"
#' date: "`r Sys.Date()`"
#' output:
#'   html_document:
#'     toc: true
#'     toc_float: true
#'   pdf_document:
#'     toc: true
#'     number_sections: true
#' geometry: margin = 2.5cm
#' ---

# setwd("C:/Users/nwickelmaier/Nextcloud/Documents/MDS/2023ss/60100_master_thesis/code")

#' # Read data

dat <- read.table("../data/haum/event_logfiles_small.csv", sep = ";", header = TRUE)
dat$date.start <- as.POSIXct(dat$date.start)
dat$date.stop <- as.POSIXct(dat$date.stop)

#' # Creating event logs

library(bupaverse)

names(dat)[names(dat) %in% c("date.start", "date.stop")] <- c("start",
                                                              "complete")

table(table(dat$start))
# --> hmm...

summary(aggregate(duration ~ trace, dat, mean))


alog <- activitylog(dat,
                    case_id = "trace",
                    activity_id = "event",
                    #resource_id = "case",
                    resource_id = "artwork",
                    timestamps = c("start", "complete"))

# --> have not understood, yet, which ist what...

process_map(alog)

process_map(alog, frequency("relative"))
process_map(alog, frequency("relative_consequent"))

library(processanimateR)

animate_process(to_eventlog(alog))

col_vector <- c("#7FC97F", "#BEAED4", "#FDC086", "#FFFF99", "#386CB0",
                "#F0027F", "#BF5B17", "#666666", "#1B9E77", "#D95F02",
                "#7570B3", "#E7298A", "#66A61E", "#E6AB02", "#A6761D",
                "#666666", "#A6CEE3", "#1F78B4", "#B2DF8A", "#33A02C",
                "#FB9A99", "#E31A1C", "#FDBF6F", "#FF7F00", "#CAB2D6",
                "#6A3D9A", "#FFFF99", "#B15928", "#FBB4AE", "#B3CDE3",
                "#CCEBC5", "#DECBE4", "#FED9A6", "#FFFFCC", "#E5D8BD",
                "#FDDAEC", "#F2F2F2", "#B3E2CD", "#FDCDAC", "#CBD5E8",
                "#F4CAE4", "#E6F5C9", "#FFF2AE", "#F1E2CC", "#CCCCCC",
                "#E41A1C", "#377EB8", "#4DAF4A", "#984EA3", "#FF7F00",
                "#FFFF33", "#A65628", "#F781BF", "#999999", "#66C2A5",
                "#FC8D62", "#8DA0CB", "#E78AC3", "#A6D854", "#FFD92F",
                "#E5C494", "#B3B3B3", "#8DD3C7", "#FFFFB3", "#BEBADA",
                "#FB8072", "#80B1D3", "#FDB462", "#B3DE69", "#FCCDE5",
                "#D9D9D9")

animate_process(to_eventlog(alog), mode = "relative", jitter = 10, legend = "color",
  mapping = token_aes(color = token_scale("artwork", 
    scale = "ordinal", 
    range = col_vector)))

elog <- to_eventlog(alog)
animate_process(elog[elog$artwork == "054", ])
animate_process(elog[elog$artwork == "080", ])
animate_process(elog[elog$artwork == "501", ])

process_map(alog[alog$artwork == "054", ])

animate_process(elog[elog$artwork %in% c("080", "054"), ],
                mode = "relative", jitter = 10, legend = "color",
                mapping = token_aes(color = token_scale("artwork",
                                                scale = "ordinal",
                                                range = c("black", "gray"))))
# --> not sure, yet, how to interpret this...




alog080 <- activitylog(dat[dat$artwork %in% "080", ],
                    #case_id = "case",
                    case_id = "trace",
                    activity_id = "event",
                    #resource_id = "trace",
                    resource_id = "case",
                    timestamps = c("start", "complete"))

process_map(alog080, frequency("relative"))



alog054 <- activitylog(dat[dat$artwork %in% "054", ],
                    #case_id = "case",
                    case_id = "trace",
                    activity_id = "event",
                    #resource_id = "trace",
                    resource_id = "case",
                    timestamps = c("start", "complete"))

process_map(alog054, frequency("relative"))