assignment1

#Part 1

#function to calculate pollutant mean
pollutantmean <- function(directory, pollutant, id = 1:332){
  #create list of files with correct path
  files_full <- list.files("specdata", full.names = TRUE)
  #create empty data frame
  dat <- data.frame()
  #run loop that reads files specifed in id and bind them into new file
  for (i in id) {
    dat <- rbind(dat, read.csv(files_full[i]))
  }
  #calculate mean from subset above for specificed pollutant
  mean(dat[, pollutant], na.rm = TRUE)

}


#Part 2
complete <- function(directory, id = 1:332) {
  #create list of files with correct path
  files_full <- list.files("specdata", full.names = TRUE)
  
  #run loop that sums up complete cases
  nobs <- numeric()
  idx <- 1
  for (i in id) {
    nobs[idx] <- sum(complete.cases(read.csv(files_full[i])))
    
    idx <- idx +1
  }

  part2 <- data.frame(id, nobs)
  part2
}


#Part3
#create functiont that will find the cor of sulfate and nitrate only in stations with enough observations
corr <- function(directory, threshold = 0) {
  crt <- vector(mode = "numeric", length = 332)
  dat <- data.frame()
  nobs <- numeric()
  idx <- 1
  
  
  for (i in 1:332) {
    dat <- rbind(dat, read.csv(files_full[i]))
  }
  #clean data for only complete cases
    dat <- dat[complete.cases(dat),]
    
#run loop with if/else statment that only includes data above indicated threshold; produce correlation for pollutants that are above threshold
    for (i in 1:332) {
      nobs[i] <- nrow(dat[dat$ID == i,])
    
    if(nobs[i] > threshold) 
      crt[i] <- cor(dat$sulfate[dat$ID == i], dat$nitrate[dat$ID == i])
      else 
      crt[i] <- NA
    }
    crt
}

#pratice code
cr <- corr("specdata", 2000)
cr <- sort(cr)
n <- length(cr)
print(n)
print(cr)


for (i in 1:332) {
    crt[i] <- cor(dat2$sulfate[dat2$ID == i], dat2$nitrate[dat2$ID == i])
}

crt <- cor(dat2$sulfate[dat2$ID == "2"], dat2$nitrate[dat2$ID == "2"])
cor(top10$Age[top10$Gender == "F"], top10$Count[top10$Gender == "F"])


sum(dat2$nitrate[dat2$ID == "2",])
cor(dat2$sulfate, dat2$nitrate)



#question 7
set.seed(42)
cc <- complete("specdata", 332:1)
use <- sample(332, 10)
print(cc[use, "nobs"])

#question 8
cr <- corr("specdata")                
cr <- sort(cr)              
set.seed(868)
out <- round(cr[sample(length(cr), 5)], 4)
print(out)

#question 9
cr <- corr("specdata", 129)                
cr <- sort(cr)              
n <- length(cr)    
set.seed(197)
out <- c(n, round(cr[sample(n, 5)], 4))
print(out)

#question 10
cr <- corr("specdata", 2000)                
n <- length(cr)               
cr <- corr("specdata", 1000)                
cr <- sort(cr)
print(c(n, round(cr, 4)))