Project 3

Question 1:
As a researcher, you frequently compare mortality rates from particular causes across different States. You need a visualization that will let you see (for 2010 only) the crude mortality rate, across all States, from one cause (for example, Neoplasms, which are effectively cancers). Create a visualization that allows you to rank States by crude mortality for each cause of death.

library(tidyverse)

cdc <- read.csv("https://raw.githubusercontent.com/charleyferrari/CUNY_DATA_608/master/module3/data/cleaned-cdc-mortality-1999-2010-2.csv")
head(cdc)

##                                 ICD.Chapter State Year Deaths Population
## 1 Certain infectious and parasitic diseases    AL 1999   1092    4430141
## 2 Certain infectious and parasitic diseases    AL 2000   1188    4447100
## 3 Certain infectious and parasitic diseases    AL 2001   1211    4467634
## 4 Certain infectious and parasitic diseases    AL 2002   1215    4480089
## 5 Certain infectious and parasitic diseases    AL 2003   1350    4503491
## 6 Certain infectious and parasitic diseases    AL 2004   1251    4530729
##   Crude.Rate
## 1       24.6
## 2       26.7
## 3       27.1
## 4       27.1
## 5       30.0
## 6       27.6

ui <- fluidPage(
  titlePanel("Crude Mortality Rate Across All States by Causes"), 
      sidebarLayout(
        selectInput("select", label = h3("Causes of Death"), 
                    choices = cdc$ICD.Chapter, 
                    selected = 1,
                    width = '100%'),
        
        mainPanel(
           plotOutput("distPlot")
        )
    )
)

server <- function(input, output) {
    output$distPlot <- renderPlot({
      ggplot(cdc[cdc$ICD.Chapter == input$select,] , aes(x = reorder(State, Crude.Rate), y = Crude.Rate)) +
        labs(x = "State", y = "Crude Mortality Rate") +  
        geom_bar(stat = "identity") +
        coord_flip() +
        theme_minimal()
    }, width = 'auto', height = 'auto')
}

shinyApp(ui = ui, server = server)

Question 2: Often you are asked whether particular States are improving their mortality rates (per cause) faster than, or slower than, the national average. Create a visualization that lets your clients see this for themselves for one cause of death at the time. Keep in mind that the national average should be weighted by the national population.

ui <- fluidPage(
    titlePanel("Crude Mortality Rate Across All States Vs National Average"), 
    sidebarPanel(
        selectInput("select1", label = strong("State"), 
                    choices = levels(as.factor(cdc$State)), 
                    selected = 1),
    
        selectInput("select2", label = strong("Cause of Death"), 
                    choices = levels(as.factor(cdc$ICD.Chapter)), 
                    selected = 1),

        width = "auto"
        ),
        
        mainPanel(
            plotOutput("distPlot")
        )
    )



server <- function(input, output) {
    output$distPlot <- renderPlot({
        cdc %>% 
            group_by(Year, ICD.Chapter) %>%
            mutate(N_Population = sum(Population),
                   N_Count = sum(Deaths), 
                   N_Crude_Rate = 10^5*(N_Count/N_Population)) %>% 
            group_by(Year, ICD.Chapter, State) %>%
            mutate(S_Count=sum(Deaths),
                   S_Crude_Rate=10^5*(S_Count/Population)) %>%
            select(ICD.Chapter, State, Year, N_Crude_Rate, S_Crude_Rate) %>% 
            filter(ICD.Chapter == input$select2, State == input$select1) %>% 
            ggplot() +
            geom_bar(aes(x = Year, weight = S_Crude_Rate)) +
            labs(x = "State", y = "Crude Mortality Rate") + 
            geom_line(aes(x = Year, y = N_Crude_Rate, linetype = "National Average"), col = "red", lwd = 1) +
            scale_linetype(name = NULL) +
            theme_minimal()
        }
    )
    }


shinyApp(ui = ui, server = server)