Shiny Demo: Kaggle Heart Data UCI EDA K-means Clustering

https://rjcc.shinyapps.io/UCI_Heart_EDA_KM/

It is a Shiny Demo of K-means clustering EDA of Kaggle Heart Data UCI.

https://www.kaggle.com/ronitf/heart-disease-uci

We use a subset of the dataset that only includes scale variables:

1. age;

2. trestbps (resting blood pressure);

3. chol (serum cholesterol in mg/dl);

4. thalach (maximum heart rate);

5. oldpeak (exercise-inducec ST depression).

https://github.com/rjcc/Coursera_DevDataProduct_W4_Shiny_Pitch

heartdata<-read.csv("heart_lab.csv")
fluidPage(
  headerPanel('Kaggle UCI Heart Data Exploratory Data Analysis'),
  sidebarPanel(
    h4('Select variables X, Y, and the cluster count k'),  
    selectInput('xcol', 'Variable X', names(heartdata)),
    selectInput('ycol', 'Variable Y', names(heartdata),
                selected=names(heartdata)[[2]]),
    numericInput('clusters', 'Cluster count k', 3,
                 min = 1, max = 9),
      h4('Data source:'),
      tags$a(href='https://www.kaggle.com/ronitf/heart-disease-uci','https://www.kaggle.com/ronitf/heart-disease-uci'),
      h4('Subset variables:'),
      h5('1. age'),
      h5('2. trestbps (resting blood pressure)'),
      h5('3. chol (serum cholesterol in mg/dl)'),
      h5('4. thalach (maximum heart rate)'),
      h5('5. oldpeak (exercise-inducec ST depression)'),

  ),
  mainPanel(
    h2('K-means Clustering'),
    plotOutput('plot1'),
    h4('11/29/2019'),
    h4('By Dr. Robert J Chen (rjchen@post.harvard.edu)'),
    h4('More EDA:'),
    tags$a(href='http://rpubs.com/rjcc/plotly_rjcc2','http://rpubs.com/rjcc/plotly_rjcc2'),
  )
)

https://github.com/rjcc/Coursera_DevDataProduct_W4_Shiny_Pitch

library(shiny)
library(datasets)
heartdata<-read.csv("heart_lab.csv")

function(input, output, session) {
  # Combine the selected variables into a new data frame
  selectedData <- reactive({
    heartdata[, c(input$xcol, input$ycol)]
  })

  clusters <- reactive({
    kmeans(selectedData(), input$clusters)
  })

  output$plot1 <- renderPlot({
    palette(c("#E41A1C", "#377EB8", "#4DAF4A", "#984EA3",
      "#FF7F00", "#FFFF33", "#A65628", "#F781BF", "#999999"))

    par(mar = c(5.1, 4.1, 0, 1))
    plot(selectedData(),
         col = clusters()$cluster,
         pch = 20, cex = 3)
    points(clusters()$centers, pch = 4, cex = 4, lwd = 4)
  })

}