Soc712 HW #2

Examining Cancer Deaths in New York State by Race, 2007-2013

---

Reading in Dataset and Loading Packages

library(readr)
library(dplyr)
library(ggplot2)
library(tidyverse)
library(magrittr)
CancDataset <- read_csv("C:/Users/Raven/Desktop/CanDataset.csv")

Viewing Data

print(CancDataset)

Selecting Variables

CancDataset2 <- select(CancDataset, 
               SE_T011_002,SE_T011_003,SE_T011_004,SE_T011_005,SE_T011_006, SE_T011_007)  

Renaming Variables

• “white”
• “whitenonhisp” = White non-Hispanic
• “black”
• “blacknonhisp” = Black non-Hispanic
• “asianpacific” = Asian/Pacific Islander
• “nativeamerican” = Native American or Alaska Native

CancDataset2 <- rename (CancDataset2, 
               "white" = SE_T011_002, 
               "whitenonhisp" = SE_T011_003, 
               "black" = SE_T011_004, 
               "blacknonhisp" = SE_T011_005, 
               "asianpacific" = SE_T011_006, 
               "nativeamerican" = SE_T011_007)

Using one Script to Select and Rename Variables with Magrittr

CancDataset3 <- CancDataset%>%
  select (SE_T011_002,SE_T011_003,SE_T011_004,SE_T011_005,SE_T011_006, SE_T011_007)%>%
  rename("white" = SE_T011_002, 
         "whitenonhisp" = SE_T011_003, 
         "black" = SE_T011_004, 
         "blacknonhisp" = SE_T011_005, 
         "asianpacific" = SE_T011_006, 
         "nativeamerican" = SE_T011_007)%>%
  
print(CancDataset3)

Creating a GGplot

• Arranging data

CancDataset5= data.frame(race)
race <- c("White", "White(non-Hispanic)","Black","Black(non-Hispanic)", "Asian/Pacific Islander", "Native American")
deaths <- c(167.6, 169.2, 163.2, 179.1, 97.2, 45.4)

• Creating Graph (Number of Cancer Deaths in New York State by Race, 2007-2013)

ggplot(data = CancDataset5)+
   geom_col (aes(x=race, y=deaths))+ 
   xlab("Race") + ylab("Number of Cancer Deaths")+ 
   coord_flip()