Agus Assignment 1

1 Initialization

1.1 Library Call and Data Generation

library(tidyr)
library(dplyr)
library(ggplot2)
library(plotly)
library(lubridate)
genData <- read.csv("generation.csv")

2 Answers

2.1 (a)

longData <- gather(genData, TP, MWh, starts_with("TP"))
longData$MWh <- longData$MWh/1000
longData$TP <- as.numeric(sub("TP", "", longData$TP))
longData$Date <- parse_date_time(longData$Date, "dmy")
longData$Month <- as.factor(months(longData$Date))
longData$Year <- as.factor(year(longData$Date))
longData$DayOfMonth <- as.factor(day(longData$Date))

2.2 (b)

longData %>% 
  group_by(Fuel)  %>%
  summarise(MWh = sum(MWh, na.rm = TRUE))

## # A tibble: 7 x 2
##   Fuel         MWh
##   <fct>      <dbl>
## 1 Coal    1172104.
## 2 Diesel     6442.
## 3 Gas     5152130.
## 4 Geo     7186039.
## 5 Hydro  25301653.
## 6 Wind    1658297.
## 7 Wood     220021.

2.3 (c)

regionData <- longData %>% 
  group_by(Region, Fuel)  %>%
  summarise(MWh = sum(MWh, na.rm = TRUE))

ggplot(data = regionData, aes(fill=Fuel, y=MWh, x=Region)) +
  geom_bar(position="stack", stat="identity") +
  scale_y_continuous(labels=function(x) format(x, big.mark = ",", scientific = FALSE))

2.4 (d)

tpData <- longData %>% 
  filter(TP <= 48) %>% 
  group_by(TP, Month)  %>%
  summarise(AveragePower = mean(MWh, na.rm = TRUE))

ggplot(data = tpData, aes(color=Month, y=AveragePower, x=TP)) +
  geom_line(stat="identity")

2.5 (e)

totGenData <- longData %>% 
  group_by(DayOfMonth, Month, Fuel) %>% 
  summarise(TotalPower = sum(MWh, na.rm=T))

ggplot(totGenData, aes(x=Fuel, y=TotalPower)) + 
  geom_boxplot() +
  facet_wrap(~Month)