R Programming Programming Assignment 3 (Week 4) John Hopkins Data Science Specialization Coursera for the github repo https://github.com/mGalarnyk/datasciencecoursera

assignment3.md

R Programming Project 3

github repo for rest of specialization: Data Science Coursera

The zip file containing the data can be downloaded here: Assignment 3 Data

Part 1 Plot the 30-day mortality rates for heart attack (outcome.R)

# install.packages("data.table")
library("data.table")

# Reading in data
outcome <- data.table::fread('outcome-of-care-measures.csv')
outcome[, (11) := lapply(.SD, as.numeric), .SDcols = (11)]
outcome[, lapply(.SD
                 , hist
                 , xlab= "Deaths"
                 , main = "Hospital 30-Day Death (Mortality) Rates from Heart Attack"
                 , col="lightblue")
        , .SDcols = (11)]

Part 2 Finding the best hospital in a state (best.R)

best <- function(state, outcome) {
  
  # Read outcome data
  out_dt <- data.table::fread('outcome-of-care-measures.csv')
  
  outcome <- tolower(outcome)
  
  # Column name is same as variable so changing it 
  chosen_state <- state 

  # Check that state and outcome are valid
  if (!chosen_state %in% unique(out_dt[["State"]])) {
    stop('invalid state')
  }
  
  if (!outcome %in% c("heart attack", "heart failure", "pneumonia")) {
    stop('invalid outcome')
  }
  
  # Renaming Columns to be less verbose and lowercase
  setnames(out_dt
           , tolower(sapply(colnames(out_dt), gsub, pattern = "^Hospital 30-Day Death \\(Mortality\\) Rates from ", replacement = "" ))
  )
  
  #Filter by state
  out_dt <- out_dt[state == chosen_state]
  
  # Columns indices to keep
  col_indices <- grep(paste0("hospital name|state|^",outcome), colnames(out_dt))
  
  # Filtering out unnessecary data 
  out_dt <- out_dt[, .SD ,.SDcols = col_indices]
  
  # Find out what class each column is 
  # sapply(out_dt,class)
  out_dt[, outcome] <- out_dt[,  as.numeric(get(outcome))]
  
  
  # Removing Missing Values for numerical datatype (outcome column)
  out_dt <- out_dt[complete.cases(out_dt),]
  
  # Order Column to Top 
  out_dt <- out_dt[order(get(outcome), `hospital name`)]
  
  return(out_dt[, "hospital name"][1])

}

Part 3 Ranking hospitals by outcome in a state (rankhospital.R)

rankhospital <- function(state, outcome, num = "best") {
  
  # Read outcome data
  out_dt <- data.table::fread('outcome-of-care-measures.csv')
  
  outcome <- tolower(outcome)
  
  # Column name is same as variable so changing it 
  chosen_state <- state 
  
  # Check that state and outcome are valid
  if (!chosen_state %in% unique(out_dt[["State"]])) {
    stop('invalid state')
  }
  
  if (!outcome %in% c("heart attack", "heart failure", "pneumonia")) {
    stop('invalid outcome')
  }
  
  # Renaming Columns to be less verbose and lowercase
  setnames(out_dt
           , tolower(sapply(colnames(out_dt), gsub, pattern = "^Hospital 30-Day Death \\(Mortality\\) Rates from ", replacement = "" ))
  )
  
  #Filter by state
  out_dt <- out_dt[state == chosen_state]
  
  # Columns indices to keep
  col_indices <- grep(paste0("hospital name|state|^",outcome), colnames(out_dt))
  
  # Filtering out unnessecary data 
  out_dt <- out_dt[, .SD ,.SDcols = col_indices]
  
  # Find out what class each column is 
  # sapply(out_dt,class)
  out_dt[, outcome] <- out_dt[,  as.numeric(get(outcome))]
  
  
  # Removing Missing Values for numerical datatype (outcome column)
  out_dt <- out_dt[complete.cases(out_dt),]
  
  # Order Column to Top 
  out_dt <- out_dt[order(get(outcome), `hospital name`)]
  
  out_dt <- out_dt[,  .(`hospital name` = `hospital name`, state = state, rate = get(outcome), Rank = .I)]
  
  if (num == "best"){
    return(out_dt[1,`hospital name`])
  }
  
  if (num == "worst"){
    return(out_dt[.N,`hospital name`])
  }
  
  return(out_dt[num,`hospital name`])

}

Part 4 Ranking hospitals in all states (rankall.R)

rankall <- function(outcome, num = "best") {
  
  # Read outcome data
  out_dt <- data.table::fread('outcome-of-care-measures.csv')
  
  outcome <- tolower(outcome)
  
  if (!outcome %in% c("heart attack", "heart failure", "pneumonia")) {
    stop('invalid outcome')
  }
  
  # Renaming Columns to be less verbose and lowercase
  setnames(out_dt
           , tolower(sapply(colnames(out_dt), gsub, pattern = "^Hospital 30-Day Death \\(Mortality\\) Rates from ", replacement = "" ))
  )
  
  # Columns indices to keep
  col_indices <- grep(paste0("hospital name|state|^",outcome), colnames(out_dt))
  
  # Filtering out unnessecary data 
  out_dt <- out_dt[, .SD ,.SDcols = col_indices]
  
  # Find out what class each column is 
  # sapply(out_dt,class)
  
  # Change outcome column class
  out_dt[, outcome] <- out_dt[,  as.numeric(get(outcome))]
  
  if (num == "best"){
    return(out_dt[order(state, get(outcome), `hospital name`)
    , .(hospital = head(`hospital name`, 1))
    , by = state])
  }
  
  if (num == "worst"){
    return(out_dt[order(get(outcome), `hospital name`)
    , .(hospital = tail(`hospital name`, 1))
    , by = state])
  }
  
  return(out_dt[order(state, get(outcome), `hospital name`)
                , head(.SD,num)
                , by = state, .SDcols = c("hospital name") ])
  
}

Thank you for help. I believe that the course already expects us to look for solutions like this one from mGalarnyk, otherwise it would not make sense to pass on an assignment of this complexity for beginners to do, because many like me would get frustrated and give up the course, as I read in some comments made here. Thank you mGalarnyk

Thanks mGalarnyk. I have a feeling that this course is definitely not for beginners, unlikely for intermediates as well. The assignments are too advanced. I have been struggling to understand functions. I am a beginner having taken the Google Data Analutics course previously. This is too advanced. Would likely leave. Just wanted to ask if there are better courses more suitable for someone who is a beginner and going to intermediate level? An other platform?