From cccb10bc6bf733e6cc3e0a46f7ac3e296eebb4c4 Mon Sep 17 00:00:00 2001
From: HeNine <>
Date: Mon, 8 Aug 2022 14:35:43 +0200
Subject: [PATCH] something about data?

---
 data/transcript_freq_study.R | 49 +++++++++++++++++++++++++++++-------
 1 file changed, 40 insertions(+), 9 deletions(-)

diff --git a/data/transcript_freq_study.R b/data/transcript_freq_study.R
index ed7d4f0..c747908 100644
--- a/data/transcript_freq_study.R
+++ b/data/transcript_freq_study.R
@@ -6,8 +6,8 @@ library(dplyr)
 #------
 messages <- read.csv2("transcript/minecraft_data-1659808309634.csv", sep = ",")
 messages <- messages %>% mutate(
-  start_time = as.POSIXct(strptime(start_time, "%Y-%m-%d %T")),
-  end_time = as.POSIXct(strptime(end_time, "%Y-%m-%d %T"))
+  start_time = as.POSIXct(strptime(start_time, "%F %T")),
+  end_time = as.POSIXct(strptime(end_time, "%F %T"))
 )
 
 n_m <- nrow(messages)
@@ -20,16 +20,26 @@ ggplot(messages %>% transmute(tdiff = difftime(start_time, lag(start_time), unit
   stat_ecdf(data=data.frame(tdiff=rlomax(n_m*10, 1/(b_p + len),
                                          (a_p + n_m))), color="red")
 
+ggplot(messages %>% transmute(tdiff = as.numeric(difftime(start_time, lag(start_time)), units = "secs")), aes(x=tdiff)) + theme_minimal() +
+  geom_histogram(binwidth = 10) +
+  geom_vline(xintercept = qdiff)
+
+ggplot(messages, aes(x=start_time)) + theme_minimal() + geom_vline(aes(xintercept=start_time)) + geom_histogram(binwidth = 3600)
+
+ggplot(messages %>% mutate(tdiff = difftime(start_time, lag(start_time), units = "secs")), aes(x=start_time, y=tdiff)) + theme_minimal() +
+  geom_point() +
+  geom_hline(yintercept = qdiff)
+
 #-------
 
 # Print messages
 
-for(i in 1:nrow(fmess)) {
-  line = fmess[i,]
+for(i in 1:nrow(messages)) {
+  line = messages[i,]
   
-  cat(sprintf("[%s] <%s> %s\n", line$pub_time, line$nick, line$message))  
+  cat(sprintf("[%s] <%s> %s\n", line$start_time, line$names, line$transcription_line))  
   
-  if(difftime(fmess[i+1,"pub_time"], line$pub_time, units = "secs") > qdiff)
+  if(difftime(messages[i+1,"start_time"], line$start_time, units = "secs") > qdiff + 20)
     cat("----------------------\n")
 }
 
@@ -72,9 +82,30 @@ ggplot(messages, aes(x=start_time)) + theme_minimal() +
 #---------------
 
 # Diff with 0.01 quantile
-qdiff <- qlomax(0.01,   1/(b_p + len), (a_p + n_m))
+qdiff <- qlomax(0.02,   1/(b_p + len), (a_p + n_m))
 
 fmess <- messages %>% filter(
-  as.numeric(difftime(pub_time, lag(pub_time), units = "secs")) < qdiff |
-    as.numeric(difftime(lead(pub_time), pub_time, units = "secs")) < qdiff
+  as.numeric(difftime(start_time, lag(start_time), units = "secs")) < qdiff |
+    as.numeric(difftime(lead(start_time), start_time, units = "secs")) < qdiff
 )
+
+#----------------
+
+ggplot(messages %>% mutate(len = as.double(difftime(end_time, start_time, unit="secs"))), aes(x=len)) + geom_histogram(binwidth = 0.5)
+
+ggplot(messages[1:50,], aes(xmin=start_time, xmax=end_time, ymin=-1, ymax = 1)) + theme_minimal() + geom_rect()
+
+#---------
+
+last <- 1
+for (i in 2:nrow(messages)) {
+  if (messages[i,]$start_time == messages[last,]$end_time) {
+    messages[last,]$transcription_line <- paste(messages[last,]$transcription_line, messages[i,]$transcription_line)
+    messages[last,]$end_time <- messages[i,]$end_time
+    messages[i,]$transcription_line <- NA
+  } else {
+    last <- i
+  }
+}
+messages <- messages %>% filter(!is.na(transcription_line))
+messages %>% transmute(touch = start_time == lag(end_time))