A demo of R + ggplot2, using Guardian/ICM polling data.

seance1.r

# A demo of R + ggplot2, using Guardian/ICM polling data.
# 2014-10-02

# Load packages.
pkgs = c("httr", "ggplot2", "lubridate", "RColorBrewer", "reshape2")
pkgs = lapply(pkgs, FUN = function(x) {

  if(!require(x, character.only = TRUE)) {

    install.packages(x, quiet = TRUE)
    library(x, character.only = TRUE)

  }

})

# Target data file.
file = "icm.polls.8414.csv"

# Download dataset.
if (!file.exists(file)) {
  
  message("Dowloading the data...")
  
  # Read CSV spreadsheet.
  data = GET("http://goo.gl/1tB4eB")
  
  # Write CSV spreadsheet.
  write(content(data), file)
  
}

# Open file.
icm = read.csv(file, stringsAsFactors = FALSE)
# Check result.
str(icm)

# Clean percentages.
icm[, 2:6] = as.numeric(gsub("%", "", as.matrix(icm[, 2:6])))
# Check result.
str(icm)

# Mark general elections.
icm$GE = grepl("RESULT", icm$Sample)
# Check result.
icm[ icm$GE, 2:6 ]

# Convert dates.
icm$Date = dmy(icm$End.of.fieldwork..election.date)
# Check result.
str(icm)

# List polling years.
table(year(icm$Date))
# List general election years.
table(year(icm$Date[ icm$GE ]))

# Subset data.
icm = icm[, c("Date", "GE", "CON", "LAB", "LIB.DEM", "OTHER")]
# Drop missing data.
icm = na.omit(icm)
# Reshape dataset.
icm = melt(icm, id = c("Date", "GE"), variable.name = "Party")
# Check result.
head(icm)

# Check party name order.
levels(icm$Party)

# View Set1 from ColorBrewer.
display.brewer.pal(7, "Set1")
# View selected color codes.
brewer.pal(7,"Set1")[c(2, 1, 5, 4)]

# ggplot2 manual color palette.
colors = scale_colour_manual(values = brewer.pal(7,"Set1")[c(2, 1, 5, 4)])
# ggplot2 manual fill color palette.
fcolors = scale_fill_manual(values = brewer.pal(7,"Set1")[c(2, 1, 5, 4)])
# ggplot2 option to set titles.
titles = labs(title= "Guardian/ICM voting intentions\n", y = NULL, x = NULL)

# Time series.
qplot(data = icm, y = value, x = Date, color = Party, geom = "line") + 
  colors + titles

# Smoothed lines.
qplot(data = icm, y = value, x = Date, 
      color = Party, size = I(.75), geom = "point") +
  geom_smooth(se = FALSE) + 
  colors + titles

# Plotting only general elections.
qplot(data = icm[icm$GE, ], y = value, x = Date, 
      color = Party, size = I(.75), geom = "line") +
  geom_point(size = 12, color = "white") +
  geom_text(aes(label = year(Date)), size = 4) +
  colors + titles +
  theme_minimal(12)

# kthxbye