More meaningful graph

r/thunder_configure.R

@@ -148,7 +148,7 @@ v8 <- ggplot(data=latency_evol, aes(x=ident,y=lat_ms)) +
   theme_classic()
 
 thunder_drop <- read.csv("thunder_configure_16_drop.csv")
-thunder_drop_2 <- sqldf("select run, packet_range, 1.0*count / 990 as packet_ratio, row_number() OVER (partition by packet_range order by run) sorting from thunder_drop where run LIKE '%-24' ")
+thunder_drop_2 <- sqldf("select run, packet_range, 1.0*count / 990 as packet_ratio, row_number() OVER (partition by packet_range order by run) sorting from thunder_drop where run LIKE '%-26' ")
 #cats <- c("0-989","990-1979","1980-2969","2970-3959","3960-4949","4950-5939","5940-6929","6930-7919","7920-8909","8910-9899")
 thunder_drop_2$packet_range <- as.factor(thunder_drop_2$packet_range)
 thunder_drop_2$sorting <- as.factor(thunder_drop_2$sorting)
@@ -171,28 +171,62 @@ v9 <- ggplot(data = thunder_drop_2, aes(x=packet_range, y=packet_ratio,fill=sort
 
 thunder_drop_burst <- read.csv("thunder_configure_16_drop_burst.csv")
 tdb_ag <- sqldf("select run,count,COUNT(count) as oc from thunder_drop_burst where run LIKE '%-24' group by run,count")
-tdb_ag_2 <- sqldf("select run,count,oc,row_number() OVER (partition by count order by run) as sorting from tdb_ag")
+tdb_ag_2 <- sqldf(
+"
+select 
+  td.run as r,
+  count,
+  oc,
+  total,
+  1.0 * oc / total as oc_ratio,
+  row_number() OVER (partition by count order by td.run) as sorting 
+from 
+  tdb_ag as td,
+  (select run,SUM(oc) as total from tdb_ag group by run) as ag
+where
+  td.run = ag.run
+")
+
 tdb_ag_2$sorting <- as.factor(tdb_ag_2$sorting)
 tdb_ag_2$count <- as.factor(tdb_ag_2$count)
 
-v10 <- ggplot(data = tdb_ag_2, aes(x=count, y=oc)) +
+v10 <- ggplot(data = tdb_ag_2, aes(x=count, y=oc_ratio)) +
   #geom_bar(stat="summary",position = "dodge") +
   #scale_y_log10() +
   geom_violin(scale='width') +
   geom_boxplot(width=0.1, outlier.shape=NA) +
-  scale_y_continuous() +
+  scale_y_continuous(labels = scales::percent) +
-  ylab("Occurence") +
+  ylab("% observed drops") +
-  xlab("Packets dropped in a row") +
+  xlab("Packets lost during the drop") +
   scale_fill_grey() +
   theme_classic()
 
 thunder_red <- read.csv("thunder_configure_16_red.csv")
-tred <- sqldf("select run,delivered_at_once,occur,row_number() OVER (partition by delivered_at_once order by run) as sorting from thunder_red WHERE run LIKE '%-24'")
+tred <- sqldf(
+"
+select 
+  tr.run as r, 
+  delivered_at_once,
+  1.0 * occur / total as occur_ratio,
+  occur,
+  total,
+  row_number() OVER (partition by delivered_at_once order by tr.run) as sorting 
+from 
+  thunder_red tr,
+  (select run,SUM(occur) as total from thunder_red group by run) as ag
+WHERE 
+  tr.run LIKE '%-26'
+  and tr.run = ag.run
+
+")
 tred$sorting <- as.factor(tred$sorting)
 tred$delivered_at_once <- as.factor(tred$delivered_at_once)
-v11 <- ggplot(data = tred, aes(x=delivered_at_once, y=occur)) +
+v11 <- ggplot(data = tred, aes(x=delivered_at_once, y=occur_ratio)) +
   #geom_bar(stat="summary",position = "dodge") +
   geom_violin(scale='width') +
+  xlab('Fresh packets per cell') +
+  ylab('% of received cells') +
+  scale_y_continuous(labels = scales::percent) +
   geom_boxplot(width=0.1, outlier.shape=NA) +
   theme_classic()