Week 11-9 All Year Data Analysis

Main Questions

• Frequency of locations
• Urban/rural divides

Read data

CORE2010 = read.csv("~/OneDrive/Johns Hopkins/Ali Sobhi Afshar - HCUP/Data/SIDC_MD_2010/rds/MD_SID_2010_CORE.csv");
CORE2011 = read.csv("~/OneDrive/Johns Hopkins/Ali Sobhi Afshar - HCUP/Data/SIDC_MD_2011/rds/MD_SID_2011_CORE.csv");
CORE2012 = read.csv("~/OneDrive/Johns Hopkins/Ali Sobhi Afshar - HCUP/Data/SIDC_MD_2012/rds/MD_SID_2012_CORE.csv");
CORE2013 = read.csv("~/OneDrive/Johns Hopkins/Ali Sobhi Afshar - HCUP/Data/SIDC_MD_2013/rds/MD_SID_2013_CORE.csv");
CORE2014 = read.csv("~/OneDrive/Johns Hopkins/Ali Sobhi Afshar - HCUP/Data/SIDC_MD_2014/rds/MD_SID_2014_CORE.csv");
CORE2015q4 = read.csv("~/OneDrive/Johns Hopkins/Ali Sobhi Afshar - HCUP/Data/SIDC_MD_2015/rds/MD_SID_2015q4_CORE.csv");
CORE2015q1q3 = read.csv("~/OneDrive/Johns Hopkins/Ali Sobhi Afshar - HCUP/Data/SIDC_MD_2015/rds/MD_SID_2015q1q3_CORE.csv");
colnames(CORE2015q1q3) = colnames(CORE2015q4);
CORE2015=rbind(CORE2015q1q3, CORE2015q4);
CORE2016 = read.csv("~/OneDrive/Johns Hopkins/Ali Sobhi Afshar - HCUP/Data/SIDC_MD_2016/rds/MD_SID_2016_CORE.csv");
CORE2017 = read.csv("~/OneDrive/Johns Hopkins/Ali Sobhi Afshar - HCUP/Data/SIDC_MD_2017/rds/MD_SID_2017_CORE.csv");

Functions for Q1

zipFrequency <- function (yearData) {
    yearData$ZIP3 <- as.factor(yearData$ZIP3);
    zipFreq <- as.data.frame(table(yearData$ZIP3));
    zipFreq <-zipFreq[order(-zipFreq$Freq), ];
    colnames(zipFreq) = c("zip", "zipFreq");
    zipFreq
}

Functions for Q2

UrbanOrRural <- function (yearData) {
    UorR <- as.data.frame(table(yearData$PL_NCHS));
    description = c('Central of >=1 million', 'Fringe of >=1 million',
                    '250,000-999,999', '50,000-249,999', 'Micropolitan', 'Rural');
    UorR = UorR[1:6, ]
    UorR = cbind(UorR, description);
    colnames(UorR) = c("urban/rual", "Freq", "description");
    UorR <-UorR[order(-UorR$Freq), ];
    UorR;
}

Q1 for 2010-2017 overall

##      zip zipFreq           areaName
## 9    212 1534478     Main Baltimore
## 4    207  627743 Annapolis Junction
## 7    210  618730      Baltimore A-L
## 13   217  388135          Frederick
## 8    211  384414      Baltimore M-Z
## 5    208  376002           Bethesda
## 3    206  238806            Waldorf
## 6    209  225010      Silver Spring
## 14   218  173328          Salisbury
## 10 other  509140        other areas

Pie plot for Q1

## Creating a generic function for 'toJSON' from package 'jsonlite' in package 'googleVis'

library(googleVis);
zipPie = as.data.frame(cbind(zipTop10[,3], zipTop10[,2]));
colnames(zipPie) = c("Area", "Frequency");
zipPie$Frequency = as.numeric(zipPie$Frequency);
Pie <- gvisPieChart(zipPie);
plot(Pie);

Column Chart for Q1

suppressPackageStartupMessages(library(googleVis));
zip2017$year = 2017;
zip2016$year = 2016;
zip2015$year = 2015;
zip2014$year = 2014;
zip2013$year = 2013;
zip2012$year = 2012;
zip2011$year = 2011;
zip2010$year = 2010;
zipAllyears = rbind(zip2017, zip2016, zip2015, zip2014, zip2013, zip2012, zip2011, zip2010);
df = as.data.frame(tapply(zipAllyears$zipFreq,list(zipAllyears$zip,zipAllyears$year),sum,na.rm=T));
df <-as.data.frame(df[order(-df$'2017'), ]);
df$zip = rownames(df);
df = as.data.frame(merge(df, area, by="zip"));
df <-as.data.frame(df[order(-df$'2017'), ]);
df = cbind(df[,10], df[, c(2:9)]);
df = df[c(1:10), ];
Column <- gvisColumnChart(df);
plot(Column);

Q2 for 2010-2017 Overall

UorR2017 = UrbanOrRural(CORE2017);
UorR2016 = UrbanOrRural(CORE2016);
UorR2015 = UrbanOrRural(CORE2015);
UorR2014 = UrbanOrRural(CORE2014);
UorR2013 = UrbanOrRural(CORE2013);
UorR2012 = UrbanOrRural(CORE2012);
UorR2011 = UrbanOrRural(CORE2011);
UorR2010 = UrbanOrRural(CORE2010);
UorRAll = rbind(UorR2017, UorR2016, UorR2015, UorR2014, UorR2013, UorR2012, UorR2011, UorR2010);
UorRAll = as.data.frame(tapply(UorRAll$Freq, UorRAll$'urban/rual', FUN=sum));
UorRAll = as.data.frame(UorRAll[1:6, ]);
colnames(UorRAll) = "Frequency";
UorRAll$description = c('Central of >=1 million', 'Fringe of >=1 million',
                    '250,000-999,999', '50,000-249,999', 'Micropolitan', 'Rural');
UorRAll;

##   Frequency            description
## 1    871432 Central of >=1 million
## 2   3240855  Fringe of >=1 million
## 3    187554        250,000-999,999
## 4    289097         50,000-249,999
## 5    173899           Micropolitan
## 6     92007                  Rural

Pie plot for Q2

suppressPackageStartupMessages(library(googleVis));
UorRAll = as.data.frame(cbind(UorRAll$description, UorRAll$Frequency));
colnames(UorRAll) = c("description", "Frequency");
UorRAll$Frequency = as.numeric(UorRAll$Frequency);
UorRAllpie = gvisPieChart(UorRAll);
plot(UorRAllpie);

Column Chart for Q2

suppressPackageStartupMessages(library(googleVis));
UorR2017$year = 2017;
UorR2016$year = 2016;
UorR2015$year = 2015;
UorR2014$year = 2014;
UorR2013$year = 2013;
UorR2012$year = 2012;
UorR2011$year = 2011;
UorR2010$year = 2010;
UorRAll = rbind(UorR2017, UorR2016, UorR2015, UorR2014, UorR2013, UorR2012, UorR2011, UorR2010);
UorRAll = as.data.frame(tapply(UorRAll$Freq,list(UorRAll$'urban/rual',UorRAll$year),sum,na.rm=T));
UorRAll = UorRAll[1:6, ]
description = c('Central of >=1 million', 'Fringe of >=1 million',
                    '250,000-999,999', '50,000-249,999', 'Micropolitan', 'Rural');
UorRAll = cbind(description, UorRAll);
UorRAll <-as.data.frame(UorRAll[order(-UorRAll$'2017'), ]);
Column <- gvisColumnChart(UorRAll, options = list(width = "automatic", height = "automatic"));
plot(Column)

Stepped Area Chart for Q2

suppressPackageStartupMessages(library(googleVis));
SteppedArea <- gvisSteppedAreaChart(UorRAll, xvar="description", 
                                    yvar=c("2010", "2011", "2012", "2013", "2014", "2015", "2016", "2017"),
                                    options=list(isStacked=TRUE))
plot(SteppedArea)