#importing the needed libraries

library(readr)
library(ggplot2)
library(lubridate)
#library(data.table)
library(openair)
library(dplyr)
#library(zoo)
#library(rio)
library(tidyverse)

#========================IMPORTING THE DATA =============================

#======DATA PATH =================================================
data_gh <- 'C:/Users/USER/OneDrive/Documents/WORKSHOPS_SCHOOLS/SUMMER_SCHOOL_2025/PRACTICAL/R_CODES/cleaned_met_aq_data2.csv'
data_uk <- 'C:/Users/USER/OneDrive/Documents/WORKSHOPS_SCHOOLS/SUMMER_SCHOOL_2025/PRACTICAL/R_CODES/ukaqdata2.csv'

#mary <- importAURN(site = "my1", year = 1990:2010)

df <- import(data_gh,header=TRUE,sep = ',', date = 'Time',
             date.format = '%Y-%m-%d %H:%M',
             na.strings = c("-99.0", "-999","-9999",""))

df2 <- import(data_uk,header=TRUE,sep = ',', date = 'Time',
             date.format = '%Y-%m-%d %H:%M%:%S',
             na.strings = c("-99.0", "-999","-9999",""))


df2$date <- ymd_hms(df2$date)

df$date_time <- lubridate::mdy_hm(df$date_time)


#renaming some columns 
df<- rename(df,date = date_time,pm25 = 'PM2.5_ug/m3',pm10='PM10_ug/m3',
             temp=obs_temp,rh=obs_RH,temp2=sensor_temp,rh2=sensor_RH,
             ws=obs_wind_speed,wd2=wd,wd=wind_direc,ws2=windspeed)


#viewing some stats and details of the data
summaryPlot(df,avg.time = 'day')

summaryPlot(df2,avg.time = 'day')


#time variation plot
timeVariation(df, pollutant = c("pm25", "pm10"), normalise = FALSE)

timeVariation(df2, pollutant = c("pm2.5", "pm10"), normalise = FALSE)


#timeplot
timePlot(head(df, 48), pollutant = c("pm25", "pm10"),
         windflow = list(scale = 0.1, lwd = 2, col = "black"),
         lwd = 3, group = FALSE,
         ylab = "concentration (ug/m3)")

timePlot(df2, pollutant =  c("nox", "o3","air_temp","pm2.5"),y.relation = "free", avg.time = "day")


#calender plot
calendarPlot(df, pollutant = "pm25", year =2020)

calendarPlot(df2, pollutant = "pm2.5", year = 2019, annotate = "wd")


calendarPlot(df2, pollutant = "pm2.5", year = 2020,
             breaks = c(0, 14, 50, 100, 150, 300),
             labels = c("Low", "Moderate", "High", "Very High","Severe"),
             cols = c("forestgreen", "yellow","orange", "red", "purple"),
             statistic = "max")

#windrose plots and pollution rose
windRose(df,ws='ws',wd='wd', type = "month", layout = c(6, 2))


windRose(df2, type = "pm2.5")

pollutionRose(df, pollutant = "pm25")


pollutionRose(df2, pollutant = "pm2.5",type='month')


polarPlot(df,pollutant = "pm25",x = "ws",wd = "wd")

polarPlot(df2,pollutant = "pm2.5",x = "ws",wd = "wd")


polarFreq(df, type = "month")

polarFreq(df2, pollutant = "pm2.5", type='month',ws.int = 30, statistic = "weighted.mean",
          offset = 80, trans = FALSE, col = "heat")


trendLevel(df, x = "season", y = "daylight", pollutant = "pm25")


trendLevel(df2, x = "season", y = "daylight", pollutant = "pm2.5")

trendLevel(df2, x = "season", y = "hour", pollutant = "pm2.5",
           cols = "increment")

polarAnnulus(df2, poll = "o3",period = "weekday", main = "weekday")

polarAnnulus(df, poll = "pm25",period = "season", main = "season")