Exploring Data with R

This is a introductory tutorial to get you started with Visualization data and Exploring Data with R. There are some popular books and many online materials i will Provide the links and references at the end of the tutorial.

library(ggplot2)
library(gcookbook)

1. Scatter Plots and line plots

plot(cars$dist~cars$speed, # y~x
     main="Relationship between car distance & speed", #Plot Title
     xlab="Speed (miles per hour)", #X axis title
     ylab="Distance travelled (miles)", #Y axis title
     xlim=c(0,30), #Set x axis limits from 0 to 30 ylim=c(0,140), #Set y axis limits from 0 to  30140  xaxs="i", #Set x axis style as internal 
     yaxs="i", #Set y axis style as internal  
     col="red", #Set the colour of plotting symbol to red 
     pch=19) #Set the plotting symbol to filled dots

plot of chunk unnamed-chunk-2

Let's draw vertical error bars with 5% errors on our cars scatterplot using arrows function


plot(mpg ~ disp, data = mtcars)
arrows(x0 = mtcars$disp, y0 = mtcars$mpg * 0.95, x1 = mtcars$disp, y1 = mtcars$mpg * 
    1.05, angle = 90, code = 3, length = 0.04, lwd = 0.4)

plot of chunk unnamed-chunk-3

How to draw histograms in the top and right margins of a bivariate scatter plot


 layout(matrix(c(2,0,1,3),2,2,byrow=TRUE), widths=c(3,1), heights=c(1,3), TRUE)
 par(mar=c(5.1,4.1,0.1,0))
 plot(cars$dist~cars$speed, # y~x
      xlab="Speed (miles per hour)", #X axis title
      ylab="Distance travelled (miles)", #Y axis title
      xlim=c(0,30), #Set x axis limits from 0 to 30 ylim=c(0,140), #Set y axis limits from 0 to  30140  xaxs="i", #Set x axis style as internal 
      yaxs="i", #Set y axis style as internal  
      col="red", #Set the colour of plotting symbol to red 
      pch=19) #Set the plotting symbol to filled dots

 par(mar=c(0,4.1,3,0))
 hist(cars$speed,ann=FALSE,axes=FALSE,col="black",border="white")

 yhist <- hist(cars$dist,plot=FALSE)
 par(mar=c(5.1,0,0.1,1))
 barplot(yhist$density,
         horiz=TRUE,space=0,axes=FALSE,
         col="black",border="white")

plot of chunk unnamed-chunk-4

Using ggplot library


ggplot(mtcars, aes(x = wt, y = mpg)) + geom_point()

plot of chunk unnamed-chunk-5


## Multiple lines in a plot
plot(pressure$temperature, pressure$pressure, type = "l")
points(pressure$temperature, pressure$pressure)

lines(pressure$temperature, pressure$pressure/2, col = "red")
points(pressure$temperature, pressure$pressure/2, col = "red")

plot of chunk unnamed-chunk-6


ggplot(pressure, aes(x = temperature, y = pressure)) + geom_line()

plot of chunk unnamed-chunk-7


# Lines and points together
ggplot(pressure, aes(x = temperature, y = pressure)) + geom_line() + geom_point()

plot of chunk unnamed-chunk-7


# Showing Lines Along the Axes
ggplot(pressure, aes(x = temperature, y = pressure)) + geom_line() + geom_point() + 
    theme(axis.line = element_line(colour = "black"))

plot of chunk unnamed-chunk-7

# Logarithmic axis
ggplot(pressure, aes(x = temperature, y = pressure)) + geom_line() + geom_point() + 
    theme(axis.line = element_line(colour = "black")) + scale_x_log10() + scale_y_log10()

plot of chunk unnamed-chunk-7

From library(gcookbook) I am using heightweight dataset to group data points by variables, The grouping variable must be categorical—in other words, a factor or character vector.


ggplot(heightweight, aes(x = ageYear, y = heightIn, shape = sex, colour = sex)) + 
    geom_point()

plot of chunk unnamed-chunk-8

# Other shapes and color can be used by scale_shape_manual()
# scale_colour_manual()

# Change shape of points
ggplot(heightweight, aes(x = ageYear, y = heightIn)) + geom_point(shape = 3)

plot of chunk unnamed-chunk-8


# Change point size sex is categorical
ggplot(heightweight, aes(x = ageYear, y = heightIn, shape = sex)) + geom_point(size = 3) + 
    scale_shape_manual(values = c(1, 4))

plot of chunk unnamed-chunk-8


# Represent a third continuous variable using color or size.

ggplot(heightweight, aes(x = weightLb, y = heightIn, fill = ageYear)) + geom_point(shape = 21, 
    size = 2.5) + scale_fill_gradient(low = "black", high = "white", breaks = 12:17, 
    guide = guide_legend())

plot of chunk unnamed-chunk-8

Adding Fitted Regression Model Lines

sp <- ggplot(heightweight, aes(x = ageYear, y = heightIn))
sp + geom_point() + stat_smooth(method = lm)

plot of chunk unnamed-chunk-9


# Adding annotations to regression plot
model <- lm(heightIn ~ ageYear, heightweight)
summary(model)
# First generate prediction data Given a model, predict values of yvar from
# xvar This supports one predictor and one predicted variable xrange: If
# NULL, determine the x range from the model object. If a vector with two
# numbers, use those as the min and max of the prediction range.  samples:
# Number of samples across the x range.  ...: Further arguments to be passed
# to predict()
predictvals <- function(model, xvar, yvar, xrange = NULL, samples = 100, ...) {

    # If xrange isn't passed in, determine xrange from the models.  Different
    # ways of extracting the x range, depending on model type
    if (is.null(xrange)) {
        if (any(class(model) %in% c("lm", "glm"))) 
            xrange <- range(model$model[[xvar]]) else if (any(class(model) %in% "loess")) 
            xrange <- range(model$x)
    }

    newdata <- data.frame(x = seq(xrange[1], xrange[2], length.out = samples))
    names(newdata) <- xvar
    newdata[[yvar]] <- predict(model, newdata = newdata, ...)
    newdata
}


pred <- predictvals(model, "ageYear", "heightIn")
sp <- ggplot(heightweight, aes(x = ageYear, y = heightIn)) + geom_point() + 
    geom_line(data = pred)
sp + annotate("text", label = "r^2 == 0.42", x = 16.5, y = 52, parse = TRUE)

plot of chunk unnamed-chunk-9

Scatter plot matrix and correlation matrix using mtcars dataset and first five variables


library(corrplot)
pairs(mtcars[, 1:5])

plot of chunk unnamed-chunk-10


# Scatter plot with correlations in the upper triangle, smoothing lines in
# the lower triangle, and histograms on the diagonal
panel.cor <- function(x, y, digits = 2, prefix = "", cex.cor, ...) {
    usr <- par("usr")
    on.exit(par(usr))
    par(usr = c(0, 1, 0, 1))
    r <- abs(cor(x, y, use = "complete.obs"))
    txt <- format(c(r, 0.123456789), digits = digits)[1]
    txt <- paste(prefix, txt, sep = "")
    if (missing(cex.cor)) 
        cex.cor <- 0.8/strwidth(txt)
    text(0.5, 0.5, txt, cex = cex.cor * (1 + r)/2)
}
panel.hist <- function(x, ...) {
    usr <- par("usr")
    on.exit(par(usr))
    par(usr = c(usr[1:2], 0, 1.5))
    h <- hist(x, plot = FALSE)
    breaks <- h$breaks
    nB <- length(breaks)
    y <- h$counts
    y <- y/max(y)
    rect(breaks[-nB], 0, breaks[-1], y, col = "white", ...)
}

pairs(mtcars[, 1:5], upper.panel = panel.cor, diag.panel = panel.hist, lower.panel = panel.smooth)

plot of chunk unnamed-chunk-10


mcor <- cor(mtcars)
corrplot(mcor)

plot of chunk unnamed-chunk-10


# Correlation matrix with colored squares and black, rotated labels
corrplot(mcor, method = "shade", shade.col = NA, tl.col = "black", tl.srt = 45)

plot of chunk unnamed-chunk-10


# create a three-dimensional (3D) scatter plot.
library(rgl)
plot3d(mtcars$wt, mtcars$disp, mtcars$mpg, type = "s", size = 0.75, lit = FALSE)

# add vertical segments to help give a sense of the spatial positions of the
# points

interleave <- function(v1, v2) as.vector(rbind(v1, v2))
# Plot the points
plot3d(mtcars$wt, mtcars$disp, mtcars$mpg, xlab = "Weight", ylab = "Displacement", 
    zlab = "MPG", size = 0.75, type = "s", lit = FALSE)
# Add the segments
segments3d(interleave(mtcars$wt, mtcars$wt), interleave(mtcars$disp, mtcars$disp), 
    interleave(mtcars$mpg, min(mtcars$mpg)), alpha = 0.4, col = "blue")

Scattter plot with jitter rugs,spikes and density


x <- rnorm(1000, 50, 30)
y <- 3 * x + rnorm(1000, 0, 20)
require(Hmisc)
plot(x, y)
# scat1d adds tick marks (bar codes. rug plot) on any of the four sides of
# an existing plot, corresponding with non-missing values of a vector x.
scat1d(x, col = "red")  # density bars on top of graph
scat1d(y, 4, col = "blue")  # density bars at right

plot of chunk unnamed-chunk-11


plot(x, y, pch = 19)
histSpike(x, add = TRUE, col = "green4", lwd = 2)
histSpike(y, 4, add = TRUE, col = "blue", lwd = 2)
histSpike(x, type = "density", col = "red", add = TRUE)  # smooth density at bottom
histSpike(y, 4, type = "density", col = "red", add = TRUE)

plot of chunk unnamed-chunk-11