bigdata.Rmd

---
title: "bigdataslides"
output: html_document
---

```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = TRUE)
```

```{r}
library(tidyverse)
```

```{r}

# Just some charts for my big data slides.

base_size = 8
iwidth = 3
iheight = 1.75

theme_set(theme_gray(base_size = base_size))

df = data.frame(Tool=c("MapReduce", "Spark"), RunningTime= c(110.0, 0.9))
ggplot(df, aes(Tool, RunningTime)) + geom_bar(stat="identity", aes(fill=Tool)) + 
  ylab("Running Time (seconds)") +
  theme(legend.position = "none")
ggsave(file="spark_time.pdf", width=iwidth, height=iheight)


df = data.frame(Tool=c("Spark", "MapReduce", "Storm", "Tez"), Contribs= c(120, 101, 31, 20))
ggplot(df, aes(x=reorder(Tool, -Contribs), y=Contribs)) + geom_bar(stat="identity", aes(fill=Tool)) + 
  ylab("New Contributors") +
  xlab("Tool") +
  theme(legend.position = "none")
ggsave(file="spark_contrib.pdf", width=4.5, height=2)

df = data.frame(Tool=c("Spark", "MapReduce", "Tez", "Storm"), Patches= c(198, 22, 46, 25))
ggplot(df, aes(x=reorder(Tool, -Patches), y=Patches)) + geom_bar(stat="identity", aes(fill=Tool)) + 
  ylab("Patches") +
  xlab("Tool") +
  theme(legend.position = "none")
ggsave(file="spark_patches.pdf", width=4.5, height=2)

```