R Notebook

library(tidyverse)

## Registered S3 methods overwritten by 'ggplot2':
##   method         from 
##   [.quosures     rlang
##   c.quosures     rlang
##   print.quosures rlang

## Registered S3 method overwritten by 'rvest':
##   method            from
##   read_xml.response xml2

## ── Attaching packages ─────────────────────────────────────────────────────────────────────────── tidyverse 1.2.1 ──

## ✔ ggplot2 3.1.0       ✔ purrr   0.3.2  
## ✔ tibble  2.1.1       ✔ dplyr   0.8.0.1
## ✔ tidyr   0.8.3       ✔ stringr 1.4.0  
## ✔ readr   1.3.1       ✔ forcats 0.4.0

## ── Conflicts ────────────────────────────────────────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()

RESEARCH_HOME = "/home/and/Documents/PhD/Research"
lines = readLines(paste0(RESEARCH_HOME, "/Scripts/R/Benchmarks/MultiAndSingleNode/R12/aws/monitor.txt"))
lines = lines[grepl("\\|SCALE\\|", lines)]
monitor = as_tibble(lines) %>%
  separate(value, into=c("Timestamp", "Scale", "Time", "ID", "Nodes", "Stage", "RDDs", "Task", "Dura", "Load"), sep="\\|") %>%
  separate(ID, into=c(NA, NA, "ID"), sep="_") %>%
  mutate(ID = as.numeric(ID)) %>%
  select(ID, Time, Nodes, Stage, RDDs, Task, Load) %>%
  mutate(Time=as.numeric(Time), RDDs=as.numeric(RDDs), Tasks=as.numeric(Task), Load=as.numeric(Load)) %>%
  group_by(ID, Time, Nodes, Stage) %>% summarise(RDDs=mean(RDDs), Tasks=mean(Tasks), Load=mean(Load)) %>%
  filter(Stage != "")

## Warning: Calling `as_tibble()` on a vector is discouraged, because the behavior is likely to change in the future. Use `tibble::enframe(name = NULL)` instead.
## This warning is displayed once per session.

head(monitor)

monitor[monitor$ID == 13, "Nodes"] = 3
monitor[monitor$ID == 14, "Nodes"] = 2
monitor[monitor$ID == 15, "Nodes"] = 1
monitor[monitor$ID == 16, "Nodes"] = 1
monitor[monitor$ID == 17, "Nodes"] = 2
monitor[monitor$ID == 18, "Nodes"] = 3
monitor[monitor$ID == 19, "Nodes"] = 1
monitor[monitor$ID == 20, "Nodes"] = 2
monitor[monitor$ID == 21, "Nodes"] = 3
monitor[monitor$ID == 22, "Nodes"] = 1
monitor[monitor$ID == 23, "Nodes"] = 2
monitor[monitor$ID == 24, "Nodes"] = 3
monitor[monitor$ID == 25, "Nodes"] = 1
monitor[monitor$ID == 26, "Nodes"] = 2
monitor[monitor$ID == 27, "Nodes"] = 3
monitor[monitor$ID == 28, "Nodes"] = 1
monitor[monitor$ID == 29, "Nodes"] = 2
monitor[monitor$ID == 30, "Nodes"] = 3

nodes = monitor %>% ungroup %>% 
  select(Nodes, Stage, Time) %>%
  mutate(Nodes = factor(Nodes)) %>%
  group_by(Nodes, Stage) %>%
  summarise(Time = mean(Time)) %>%
  arrange(Time)

stageLevels = nodes[nodes$Nodes==1,"Stage"]
nodes$Stage = factor(nodes$Stage, levels = as.character(stageLevels$Stage))

p = ggplot(data = nodes, aes(x = Stage, y = Time, fill = Nodes)) +
  geom_bar(stat="identity", position=position_dodge(width = 0.75), width = 0.7) + 
  theme(axis.text.x = element_text(angle = 90, hjust = 1))
plot(p)