IS-607 Final Project
Mohamed Elmoudni
Sunday, May 24, 2015
Loading necessary packages
#install.packages("Rserve")
library(Rserve)## Warning: package 'Rserve' was built under R version 3.1.3Rserve()## Starting Rserve...
## "C:\Users\user\DOCUME~1\R\WIN-LI~1\3.1\Rserve\libs\x64\Rserve.exe"library(XML)## Warning: package 'XML' was built under R version 3.1.3library(maps)
data(county.fips)
require(mapproj)## Loading required package: mapprojrequire(ggplot2)## Loading required package: ggplot2## Warning: package 'ggplot2' was built under R version 3.1.3data(state.fips)
data(city.fips)## Warning in data(city.fips): data set 'city.fips' not foundlibrary(dplyr)## Warning: package 'dplyr' was built under R version 3.1.3##
## Attaching package: 'dplyr'
##
## The following object is masked from 'package:stats':
##
## filter
##
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, unionlibrary(knitr)Data Formatting
## NYC data format
nyc_df<- data.frame("Cause"= nyc_dt$MCD...ICD.10.113.Cause.List,
"County"= nyc_dt$County,
"County_Code"= nyc_dt$County.Code,
"Gender"= nyc_dt$Gender.Code,
"Race"= nyc_dt$Race,
"Age"= nyc_dt$Ten.Year.Age.Groups,
"Deaths"= nyc_dt$Deaths
)
# NYC sample data
kable(head(nyc_df))| Cause | County | County_Code | Gender | Race | Age | Deaths |
|---|---|---|---|---|---|---|
| Septicemia (A40-A41) | Bronx County, NY | 36005 | F | White | 45-54 years | 15 |
| Septicemia (A40-A41) | Bronx County, NY | 36005 | M | White | 45-54 years | 16 |
| Septicemia (A40-A41) | Bronx County, NY | 36005 | F | White | 55-64 years | 13 |
| Septicemia (A40-A41) | Bronx County, NY | 36005 | M | White | 55-64 years | 26 |
| Septicemia (A40-A41) | Bronx County, NY | 36005 | F | White | 65-74 years | 29 |
| Septicemia (A40-A41) | Bronx County, NY | 36005 | M | White | 65-74 years | 31 |
## NY state data format
nys_df<- data.frame("Cause"= nys_dt$MCD...ICD.10.113.Cause.List,
"County"= nys_dt$County,
"County_Code"= nys_dt$County.Code,
"Gender"= nys_dt$Gender.Code,
"Race"= nys_dt$Race,
"Age"= nys_dt$Ten.Year.Age.Groups,
"Deaths"= nys_dt$Deaths
)
# NYS data sample outpt
kable(head(nys_df))| Cause | County | County_Code | Gender | Race | Age | Deaths |
|---|---|---|---|---|---|---|
| Septicemia (A40-A41) | Bronx County, NY | 36005 | F | White | 45-54 years | 15 |
| Septicemia (A40-A41) | Bronx County, NY | 36005 | M | White | 45-54 years | 16 |
| Septicemia (A40-A41) | Bronx County, NY | 36005 | F | White | 55-64 years | 13 |
| Septicemia (A40-A41) | Bronx County, NY | 36005 | M | White | 55-64 years | 26 |
| Septicemia (A40-A41) | Bronx County, NY | 36005 | F | White | 65-74 years | 29 |
| Septicemia (A40-A41) | Bronx County, NY | 36005 | M | White | 65-74 years | 31 |
## US Female data format
usf_df<- data.frame("Cause"= usf_dt$MCD...ICD.10.113.Cause.List,
"State"= usf_dt$State,
"State_Code"= usf_dt$State.Code,
"Gender"= usf_dt$Gender.Code,
"Race"= usf_dt$Race,
"Age"= usf_dt$Ten.Year.Age.Groups,
"Deaths"= usf_dt$Deaths
)
# US Female sample data
kable(head(usf_df))| Cause | State | State_Code | Gender | Race | Age | Deaths |
|---|---|---|---|---|---|---|
| Certain other intestinal infections (A04,A07-A09) | California | 6 | FALSE | White | 45-54 years | 10 |
| Certain other intestinal infections (A04,A07-A09) | California | 6 | FALSE | White | 75-84 years | 17 |
| Certain other intestinal infections (A04,A07-A09) | California | 6 | FALSE | White | 85+ years | 24 |
| Certain other intestinal infections (A04,A07-A09) | Florida | 12 | FALSE | White | 85+ years | 12 |
| Septicemia (A40-A41) | Arizona | 4 | FALSE | White | 45-54 years | 11 |
| Septicemia (A40-A41) | Arizona | 4 | FALSE | White | 55-64 years | 12 |
## US Male data format
usm_df<- data.frame("Cause"= usm_dt$MCD...ICD.10.113.Cause.List,
"State"= usm_dt$State,
"State_Code"= usm_dt$State.Code,
"Gender"= usm_dt$Gender.Code,
"Race"= usm_dt$Race,
"Age"= usm_dt$Ten.Year.Age.Groups,
"Deaths"= usm_dt$Deaths
)
# US Male sample data
kable(head(usm_df))| Cause | State | State_Code | Gender | Race | Age | Deaths |
|---|---|---|---|---|---|---|
| Certain other intestinal infections (A04,A07-A09) | California | 6 | M | White | 65-74 years | 10 |
| Certain other intestinal infections (A04,A07-A09) | California | 6 | M | White | 75-84 years | 14 |
| Septicemia (A40-A41) | Arizona | 4 | M | White | 55-64 years | 23 |
| Septicemia (A40-A41) | Arizona | 4 | M | White | 65-74 years | 15 |
| Septicemia (A40-A41) | Arizona | 4 | M | White | 75-84 years | 20 |
| Septicemia (A40-A41) | California | 6 | M | White | < 1 year | 10 |
## Chicago data format
chicago_df<- data.frame("Cause"= chicago_dt$ICD.10.113.Cause.List,
"State"= chicago_dt$State,
"State_Code"= chicago_dt$State.Code,
"Gender"= chicago_dt$Gender.Code,
"Race"= chicago_dt$Race,
"Age"= chicago_dt$Ten.Year.Age.Groups,
"Deaths"= chicago_dt$Deaths
)
# Chicago sample data
kable(head(chicago_df))| Cause | State | State_Code | Gender | Race | Age | Deaths |
|---|---|---|---|---|---|---|
| Certain other intestinal infections (A04,A07-A09) | Illinois | 17 | F | White | 75-84 years | 28 |
| Certain other intestinal infections (A04,A07-A09) | Illinois | 17 | M | White | 75-84 years | 20 |
| Certain other intestinal infections (A04,A07-A09) | Illinois | 17 | F | White | 85+ years | 46 |
| #Septicemia (A40-A41) | Illinois | 17 | M | Black or African American | 35-44 years | 15 |
| #Septicemia (A40-A41) | Illinois | 17 | F | Black or African American | 45-54 years | 17 |
| #Septicemia (A40-A41) | Illinois | 17 | F | White | 45-54 years | 16 |
## Illinois data format
illinois_df<- data.frame("Cause"= illinois_dt$ICD.10.113.Cause.List,
"County"= illinois_dt$County,
"County_Code"= illinois_dt$County.Code,
"Gender"= illinois_dt$Gender.Code,
"Race"= illinois_dt$Race,
"Age"= illinois_dt$Ten.Year.Age.Groups,
"Deaths"= illinois_dt$Deaths
)
# Illinois sample data
kable(head(illinois_df))| Cause | County | County_Code | Gender | Race | Age | Deaths |
|---|---|---|---|---|---|---|
| Certain other intestinal infections (A04,A07-A09) | Cook County, IL | 17031 | F | White | 75-84 years | 28 |
| Certain other intestinal infections (A04,A07-A09) | Cook County, IL | 17031 | M | White | 75-84 years | 20 |
| Certain other intestinal infections (A04,A07-A09) | Cook County, IL | 17031 | F | White | 85+ years | 46 |
| #Septicemia (A40-A41) | Cook County, IL | 17031 | M | Black or African American | 35-44 years | 15 |
| #Septicemia (A40-A41) | Cook County, IL | 17031 | F | Black or African American | 45-54 years | 17 |
| #Septicemia (A40-A41) | Cook County, IL | 17031 | F | White | 45-54 years | 16 |
All_male_il_df <- data.frame(All_male_il)
kable(All_male_il_df)| V1 | V2 |
|---|---|
| Leading Causes of Death, 2007 – All Ages | NA |
| All causes | 100,254 |
| Diseases of heart | 25,766 |
| Malignant neoplasms | 24,084 |
| Cerebrovascular diseases | 5,851 |
| Chronic lower respiratory diseases | 4,731 |
| Accidents | 4,319 |
|       Motor vehicle accidents | 1,352 |
|       All other accidents | 2,967 |
| Diabetes mellitus | 2,850 |
| Alzheimer’s disease | 2,729 |
| Influenza and pneumonia | 2,549 |
| Nephritis, nephrotic syndrome and nephrosis | 2,532 |
| Septicemia | 2,099 |
| Intentional self-harm (suicide) | 1,102 |
| Chronic liver disease and cirrhosis | 1,029 |
| Essential hypertension and hypertensive renal disease | 855 |
| Assault (homicide) | 854 |
| Pneumonitis due to solids and liquids | 821 |
| Parkinsons’s disease | 817 |
| In situ neoplasms, benign neoplasms and neoplasms of uncertain or unknown behavior | 679 |
| Certain conditions originating in the perinatal period | 670 |
| Aortic aneurysm and dissection | 576 |
| Congenital malformations, deformations and chromosomal abnormalities | 402 |
| Atherosclerosis | 306 |
| Human immunodeficiency virus (HIV) disease | 298 |
| Anemias | 249 |
Statistical Analysis
# NYC summary level descriptive statistics: the mean, median, 25th and 75th
# quartiles, min, and max for each of the applicable variables in your data set
summary(nyc_df)## Cause
## Major cardiovascular diseases (I00-I78) : 67
## Diseases of heart (I00-I09,I11,I13,I20-I51) : 66
## Other heart diseases (I26-I51) : 61
## All other forms of heart disease (I26-I28,I34-I38,I42-I49,I51): 60
## All other diseases (Residual) : 49
## Ischemic heart diseases (I20-I25) : 49
## (Other) :662
## County County_Code Gender
## Bronx County, NY :323 Min. :36005 F:462
## Kings County, NY :263 1st Qu.:36005 M:552
## New York County, NY:238 Median :36047
## Queens County, NY :161 Mean :36043
## Richmond County, NY: 29 3rd Qu.:36061
## Max. :36085
##
## Race Age Deaths
## Black or African American: 55 75-84 years:229 Min. : 10.00
## White :959 65-74 years:202 1st Qu.: 14.00
## 85+ years :184 Median : 21.00
## 55-64 years:167 Mean : 40.16
## 45-54 years:132 3rd Qu.: 48.00
## 35-44 years: 63 Max. :280.00
## (Other) : 37# NYS summary level descriptive statistics: the mean, median, 25th and 75th
# quartiles, min, and max for each of the applicable variables in your data set
summary(nys_df)## Cause
## Major cardiovascular diseases (I00-I78) :102
## Diseases of heart (I00-I09,I11,I13,I20-I51) : 99
## Other heart diseases (I26-I51) : 92
## All other forms of heart disease (I26-I28,I34-I38,I42-I49,I51): 89
## Ischemic heart diseases (I20-I25) : 59
## All other diseases (Residual) : 57
## (Other) :694
## County County_Code Gender
## Bronx County, NY :323 Min. :36005 F:549
## Kings County, NY :263 1st Qu.:36005 M:643
## New York County, NY :238 Median :36059
## Queens County, NY :161 Mean :36051
## Suffolk County, NY : 60 3rd Qu.:36081
## Westchester County, NY: 52 Max. :36119
## (Other) : 95
## Race Age Deaths
## Black or African American: 55 75-84 years:276 Min. : 10.00
## White :1137 65-74 years:233 1st Qu.: 13.00
## 85+ years :232 Median : 20.00
## 55-64 years:195 Mean : 36.86
## 45-54 years:144 3rd Qu.: 41.00
## 35-44 years: 71 Max. :280.00
## (Other) : 41# Chicago summary level descriptive statistics: the mean, median, 25th and 75th
# quartiles, min, and max for each of the applicable variables in your data set
summary(chicago_df)## Cause
## #Malignant neoplasms (C00-C97) : 39
## Major cardiovascular diseases (I00-I78) : 37
## #Diseases of heart (I00-I09,I11,I13,I20-I51) : 36
## #Accidents (unintentional injuries) (V01-X59,Y85-Y86): 30
## Ischemic heart diseases (I20-I25) : 30
## All other diseases (Residual) : 29
## (Other) :870
## State State_Code Gender Race
## Illinois:1071 Min. :17 F:492 Asian or Pacific Islander: 48
## 1st Qu.:17 M:579 Black or African American:430
## Median :17 White :593
## Mean :17
## 3rd Qu.:17
## Max. :17
##
## Age Deaths
## 75-84 years:220 Min. : 10.00
## 85+ years :185 1st Qu.: 17.00
## 65-74 years:184 Median : 33.00
## 55-64 years:176 Mean : 85.88
## 45-54 years:145 3rd Qu.: 75.00
## 35-44 years: 77 Max. :2754.00
## (Other) : 84# Illinois summary level descriptive statistics: the mean, median, 25th and 75th
# quartiles, min, and max for each of the applicable variables in your data set
summary(illinois_df)## Cause
## Major cardiovascular diseases (I00-I78) : 479
## #Malignant neoplasms (C00-C97) : 407
## #Diseases of heart (I00-I09,I11,I13,I20-I51) : 394
## Ischemic heart diseases (I20-I25) : 256
## All other diseases (Residual) : 168
## Other forms of chronic ischemic heart disease (I20,I25): 161
## (Other) :2072
## County County_Code Gender
## Cook County, IL :1071 Min. :17001 F:1942
## DuPage County, IL : 240 1st Qu.:17031 M:1995
## Will County, IL : 188 Median :17091
## Lake County, IL : 182 Mean :17093
## Madison County, IL : 134 3rd Qu.:17143
## St. Clair County, IL: 134 Max. :17203
## (Other) :1988
## Race Age Deaths
## Asian or Pacific Islander: 50 85+ years :1236 Min. : 10.00
## Black or African American: 490 75-84 years:1111 1st Qu.: 13.00
## White :3397 65-74 years: 645 Median : 19.00
## 55-64 years: 443 Mean : 42.56
## 45-54 years: 280 3rd Qu.: 36.00
## 35-44 years: 101 Max. :2754.00
## (Other) : 121# USA Female summary level descriptive statistics: the mean, median, 25th and 75th
# quartiles, min, and max for each of the applicable variables in your data set
summary(usf_df)## Cause
## Major cardiovascular diseases (I00-I78) : 90
## Diseases of heart (I00-I09,I11,I13,I20-I51) : 79
## All other diseases (Residual) : 74
## Other heart diseases (I26-I51) : 69
## Malignant neoplasms (C00-C97) : 65
## All other forms of heart disease (I26-I28,I34-I38,I42-I49,I51): 62
## (Other) :1339
## State State_Code Gender
## California:448 Min. : 4.00 Mode :logical
## Texas :303 1st Qu.: 6.00 FALSE:1778
## New York :275 Median :12.00 NA's :0
## Florida :265 Mean :22.52
## Arizona :123 3rd Qu.:36.00
## Illinois :111 Max. :55.00
## (Other) :253
## Race Age
## American Indian or Alaska Native: 1 75-84 years:380
## Black or African American : 56 85+ years :338
## White :1721 65-74 years:319
## 55-64 years:257
## 45-54 years:194
## 35-44 years:104
## (Other) :186
## Deaths
## Min. : 10.00
## 1st Qu.: 15.00
## Median : 26.00
## Mean : 82.19
## 3rd Qu.: 60.00
## Max. :2157.00
## # USA Male summary level descriptive statistics: the mean, median, 25th and 75th
# quartiles, min, and max for each of the applicable variables in your data set
summary(usm_df)## Cause
## Major cardiovascular diseases (I00-I78) : 111
## Diseases of heart (I00-I09,I11,I13,I20-I51) : 98
## All other non causes of death : 96
## All other diseases (Residual) : 91
## Other heart diseases (I26-I51) : 76
## All other forms of heart disease (I26-I28,I34-I38,I42-I49,I51): 70
## (Other) :1758
## State State_Code Gender
## California:529 Min. : 4.00 M:2300
## Texas :366 1st Qu.: 6.00
## Florida :345 Median :17.00
## New York :316 Mean :22.46
## Arizona :185 3rd Qu.:36.00
## Illinois :161 Max. :55.00
## (Other) :398
## Race Age Deaths
## Black or African American: 49 75-84 years:389 Min. : 10.00
## White :2251 65-74 years:383 1st Qu.: 15.00
## 55-64 years:353 Median : 27.00
## 45-54 years:308 Mean : 75.22
## 85+ years :275 3rd Qu.: 65.25
## 35-44 years:214 Max. :1732.00
## (Other) :378Graphical Analysis
## geom_smooth: Only one unique x value each group.Maybe you want aes(group = 1)?
## geom_smooth: Only one unique x value each group.Maybe you want aes(group = 1)?
## geom_smooth: Only one unique x value each group.Maybe you want aes(group = 1)?
Geographic Analysis
The Leading Cause of Deaths in New York State by County
The Leading Cause of Deaths in Illinois State by County
The Leading Cause of Male Deaths in the US by County
The Leading Cause of Female Deaths in the US by State
Final Graphics
## Warning: package 'scatterplot3d' was built under R version 3.1.3