16 - Data Visualization

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)

library(ggplot2)
unitCost <-  c(700, 200, 150, 50, 15, 3, 1)
shipCost <-  c(10.00, 1.50, 1.00, 0.15, 0.15, 0.05, 0.01)
diff <-  shipCost/unitCost*100
item <-  c('TV set', 'DVD player', 'Vacuum cleaner', 'Scotch whisky', 'Coffee', 'Biscuits', 'Beer')
df2 <-  data.frame(unitCost, shipCost,diff, item)
# ggplot
ggplot(df2,aes(item, diff)) +
  geom_col(fill = 'bisque') +
  xlab('Item') +
  ylab('Relative cost of shipping (%)')

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')

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 MONTH(paymentDate) as month, SUM(amount) AS monthTotal FROM Payments WHERE YEAR(paymentDate)= 2004 GROUP BY MONTH(paymentDate);") 
# ggplot
ggplot(d,aes(month, monthTotal)) +
  geom_line(color = 'green') +
  xlab('Month') +
  ylab('Total payments')

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')

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 count(*) as frequency, productLine, city
FROM Products, OrderDetails, Orders, Customers
                WHERE Products.productCode = OrderDetails.productCode
                AND OrderDetails.orderNumber = Orders.orderNumber
                AND Orders.customerNumber = Customers.customerNumber
                AND country = 'Norway'
                GROUP BY productLine, city")
# ggplot
ggplot(d,aes(productLine, city)) + 
  geom_tile(aes(fill=frequency)) + 
  scale_fill_gradient(low=" light blue", high="dark blue") + 
  xlab('Line') + 
  ylab('Scale')

library(ggplot2)
library(DBI)
library(RMySQL)
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')

library(ggplot2)
library(DBI)
library(RMySQL)
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(customerLocation) AS lon, x(customerLocation) AS lat 
FROM Customers WHERE customerNumber NOT IN (SELECT customerNumber FROM Orders);")
map <-  get_googlemap('europe',marker=d,zoom=4)
ggmap(map) + labs(x = 'Longitude', y = 'Latitude') + ggtitle('European customers without orders')

library(ggplot2)
library(readr)
# read with Import Dataset
url <-  'http://www.richardtwatson.com/data/electricityprices.csv'
t <-  read_delim (url, delim = ',')
# ggplot
ggplot(t,aes(factor(0),cost)) + 
  geom_boxplot(outlier.colour='red') +  
  xlab("Hourly measures") + 
  ylab("Cost")

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')

library(readr)
library(dplyr)
wurl <-  'http://www.richardtwatson.com/data/weather.csv'
w <-  read_delim(wurl,delim = ',')
eurl <-  'http://www.richardtwatson.com/data/electricityprices.csv'
e <-  read_delim(eurl,delim = ',')
m <- inner_join(e,w, by = c('timestamp' = 'Timestamp'))
m$airtemp <-  as.numeric(as.character(m$Air.Temp..F.))
head(m)