library(tidyverse)

energy <- read_csv("Downloads/archive-2/energy_dataset.csv")

library(PerformanceAnalytics)
chart.Correlation(energy)

library(lubridate)
Year <- year(energy$time)
Year
View(Year)

?mutate

energy <- energy %>% 
  mutate(Year)

Month <- month(energy$time)
energy <- energy %>% 
  mutate(Month)

energy <- energy %>% 
  mutate(DoM = mday(energy$time))

energy <- energy %>% 
  mutate(HoD = hour(energy$time))

plot(energy$time, energy$`generation solar`, cex=0.01)

ggplot(energy)+
  geom_path(aes(energy$time, energy$`generation solar`), size=0.2)

ggplot(energy)+
  geom_path(aes(energy$time, energy$`generation hydro water reservoir`), colour='green')

energynew <- energy %>% 
  select(-time, -`generation fossil coal-derived gas`, -(`generation fossil oil shale`:`generation hydro pumped storage aggregated`), -`generation marine`, -`generation wind offshore`, -`forecast wind offshore eday ahead` )

summary(energynew)

#chart.Correlation(energynew)

require(ggstatsplot)
ggcorrmat(energynew)

ggplot(energy)+
  geom_path(aes(time, `generation solar`))+
  facet_wrap(~Month)

energy %>% 
  filter(Year == 2016, Month == 7, DoM==15) %>% 
  ggplot()+geom_line(aes(time, `generation solar`), size=2, colour='orange')+labs(title = 'July 15, 2016', x = NULL, y='Hourly Solar Generation (MW)')+ylim(0,6000)

str(energy)

plot(energy$`total load forecast`, energy$`total load actual`)