16 - Data Visualization

Answers to exercises

Given the following data on the world’s cargo carrying capacity in millions of dead weight tons (dwt) for the given years, graph the relationship as a point plot. Add a linear prediction model to the graph. What is the approximate increase in the world capacity each year?

dwt <-  c(2566, 3704, 4008, 5984, 7700, 8034, 8229, 7858, 8408, 8939)
year <-  c(1970, 1980, 1990, 2000, 2006, 2007, 2008, 2009, 2010, 2011)

    library(ggplot2)
    dwt <-  c(2566, 3704, 4008, 5984, 7700, 8034, 8229, 7858, 8408, 8939)
    year <-  c(1970, 1980, 1990, 2000, 2006, 2007, 2008, 2009, 2010, 2011)
    df1 <-  data.frame(year, dwt)
    # ggplot
    ggplot(df1,aes(year, dwt)) +
      geom_point(color = 'red') +
      xlab('Year') +
      ylab('Millions of dead weight tons') +
      ylim(0,10000)

Visualize in blue the number of items for each product scale.

    library(ggplot2)
    library(DBI)
    library(RMySQL)
    # connect to the database
    conn <- dbConnect(RMySQL::MySQL(),"www.richardtwatson.com", dbname = "ClassicModels", user = "student", password = "student")
    # Query the database and create file for use with R
    d <- dbGetQuery(conn,"SELECT productScale from Products;") 
    # Plot the number of product lines by specifying the appropriate column name
    # Internal fill color is blue
    # ggplot
    ggplot(d,aes(productScale)) +
      geom_bar(fill = 'blue') +
      xlab('Product scale') +
      ylab('Frequency')

Create a histogram with appropriate labels for the value of orders received from the Nordic countries (Denmark, Finland, Norway, Sweden).

    library(ggplot2)
    library(DBI)
    library(RMySQL)
    # connect to the database
    conn <- dbConnect(RMySQL::MySQL(),"www.richardtwatson.com", dbname = "ClassicModels", user = "student", password = "student")
    # Query the database and create file for use with R
    d <- dbGetQuery(conn,"SELECT country, sum(quantityOrdered*priceEach) AS orders FROM Orders, OrderDetails, Customers WHERE Orders.orderNumber = OrderDetails.orderNumber and Customers.customerNumber = Orders.customerNumber AND country IN ('Denmark','Finland', 'Norway','Sweden') GROUP BY countr
    # ggplot
    ggplot(d,aes(country, orders)) +
      geom_col(fill = 'yellow') +
      xlab('Country') +
      ylab('Orders')

Show the customers in Japan on a Google map.

    library(ggplot2)
    library(DBI)
    library(ggmap)
    # connect to the database
    conn <- dbConnect(RMySQL::MySQL(),"www.richardtwatson.com", dbname = "ClassicModels", user = "student", password = "student")
    # Query the database and create file for use with R
    d <- dbGetQuery(conn,"SELECT y(officeLocation) AS lon, x(officeLocation) AS lat FROM Offices;")
    map <-  get_googlemap('tokyo, japan',marker=d,zoom=5)
    ggmap(map) + labs(x = 'Longitude', y = 'Latitude') + ggtitle('Japanese offices')

http://www.richardtwatson.com/data/manheim.txt, which contains details of the sales of three car models: X, Y, and Z.

9a.

Create a bar chart for sales of each model (X, Y, or Z)

    library(ggplot2)
    library(readr)
    url <-  'http://www.richardtwatson.com/data/manheim.txt'
    t <-  read_delim(url, delim=',')
    # ggplot
    ggplot(t,aes(model)) +
      geom_bar(fill = 'lightgreen')

11.

Read the table http://www.richardtwatson.com/data/wealth.csv containing details of the wealth of various countries. Create histograms for each of the wealth measures. Use the list of valid colors to give a bit of color to your graphics.

    library(ggplot2)
    library(readr)
    url <-  'http://www.richardtwatson.com/data/wealth.csv'
    t <-  read_delim(url, delim=',')
    # ggplot
    ggplot(t, aes(`GDP per capita`)) +
         geom_histogram(fill='firebrick')
    ggplot(t, aes(`GDP per capita`)) +
         geom_histogram(fill='darkorange')
    ggplot(t, aes(`GDP per capita`)) +
         geom_histogram(fill='darkolivegreen')