R programming Assignment 3 - Part II

rankhospital.R

## R Programming Assignment 3 - Part II

## Introduction

# The data for this assignment come from the Hospital Compare web site (http://hospitalcompare.hhs.gov)
# run by the U.S. Department of Health and Human Services. The purpose of the web site is to provide data and
# information about the quality of care at over 4,000 Medicare-certified hospitals in the U.S. This dataset essentially
# covers all major U.S. hospitals. This dataset is used for a variety of purposes, including determining
# whether hospitals should be fined for not providing high quality care to patients (see http://goo.gl/jAXFX
# for some background on this particular topic).

# The Hospital Compare web site contains a lot of data and we will only look at a small subset for this
# assignment. The zip file for this assignment contains three files
# - outcome-of-care-measures.csv: Contains information about 30-day mortality and readmission rates for heart attacks, 
#   heart failure, and pneumonia for over 4,000 hospitals.
# - hospital-data.csv: Contains information about each hospital.
# - Hospital_Revised_Flatfiles.pdf: Descriptions of the variables in each file (i.e the code book).

## TASKS: 
## (1)  Plot the 30-day mortality rates for heart attack
## (2)  Finding the best hospital in a state
## -> (3)  Ranking hospitals by outcome in a state
## (4)  Ranking hospitals in all states


## (3) Ranking hospitals by outcome in a state

rankhospital <- function (state, outcome_name, num = "best") {
        
        setwd("/Users/lucky1eva/Downloads/rprog-data-ProgAssignment3-data/")
        outcome <- read.csv("outcome-of-care-measures.csv") 
        
        # Check validity
        if (!state %in% State) {
                
                stop("invalid state")
                
        } else if (!outcome_name %in% c("heart attack", "heart failure", "pneumonia")) {
                
                stop("invalid outcome")
                
        } else if (! (num == "worst" | class(num) == "numeric" )) stop("invalid input")
         
        # sort table
        State_outcome <- subset(outcome, State == state, select = c("Hospital.Name","State", "Hospital.30.Day.Death..Mortality..Rates.from.Heart.Attack", 
                                                                    "Hospital.30.Day.Death..Mortality..Rates.from.Heart.Failure",
                                                                    "Hospital.30.Day.Death..Mortality..Rates.from.Pneumonia"))
        
        colnames(State_outcome) <- c("Name","State", "heart attack", "heart failure", "pneumonia")
        State_outcome[, 3:5] <- apply(State_outcome[, 3:5], 2, function(x) as.numeric(x))
        State_outcome[, 1:2] <- apply(State_outcome[, 1:2], 2, function(x) as.character(x))
        
        outcome_sorted <- State_outcome[order(State_outcome[, outcome_name], State_outcome$Name), ]
        
        if (num %in% 1:nrow(outcome_sorted)) {
                
                list(outcome_sorted[num, 1])
                
        } else if (num == "best") {list(outcome_sorted[1, 1])
                
                } else if (num == "worst") {
                
                        list(outcome_sorted[sum(!is.na(outcome_sorted[, outcome_name])) , 1])
                
        } else {return(NA)}
        
}