Solr Data Ingestion Visualization

library("ggplot2")
library("dplyr")
library("lubridate")
library("grid")

s3_files <- read.csv(file="s3.csv", head=FALSE)
colnames(s3_files) <- c("date", "time", "size", "filename")

s3_files$time <- hms(s3_files$time) 
s3_files$hour <- factor(hour(s3_files$time)) 

break.down.hour.date <- s3_files %>%
  select(-time) %>% # dplyr doesn't like this column for some reason
  group_by(date, hour) %>%
  summarise(size=sum(size))

hour.date.graph <- ggplot(break.down.hour.date, aes(x=break.down.hour.date$hour, y=break.down.hour.date$date, size=size, color=size))
hour.date.graph + geom_point() + 
  ggtitle("Hourly breakdown of files from Jan 05 - Mar 04") +
  xlab("Hour of day") +
  ylab("Date") +
  guides(size=FALSE) + 
  scale_size(range=c(5, 15)) +
  guides(color=FALSE) +
  theme(axis.title=element_text(size=16),
        plot.title=element_text(size=18, face="bold"),
        panel.grid.major = element_line(colour="grey"),
        panel.grid.minor = element_line(colour="grey"),
        plot.background = element_rect(fill="grey90"),
        plot.margin = unit(c(4, 4, 10, 4), "mm"),
        panel.background = element_rect(fill="grey90"))