Created on Aug 23 2013
Revised on Mon Aug 26 13:14:49 2013
original post is here ,here, here and here and here
counts <- table(mtcars$gear)
barplot(counts, main = "Car Distribution", xlab = "Number of Gears")
barplot(counts, main = "Car Distribution", horiz = TRUE, names.arg = c("3 Gears",
"4 Gears", "5 Gears"))
counts <- table(mtcars$vs, mtcars$gear)
barplot(counts, main = "Car Distribution by Gears and VS", xlab = "Number of Gears",
col = c("darkblue", "red"), legend = rownames(counts))
barplot(counts, main = "Car Distribution by Gears and VS", xlab = "Number of Gears",
col = c("darkblue", "red"), legend = rownames(counts), beside = TRUE)
slices <- c(10, 12, 4, 16, 8)
lbls <- c("US", "UK", "Australia", "Germany", "France")
pie(slices, labels = lbls, main = "Pie Chart of Countries")
pct <- round(slices/sum(slices) * 100)
lbls <- paste(lbls, pct) # add percents to labels
lbls <- paste(lbls, "%", sep = "") # ad % to labels
pie(slices, labels = lbls, col = rainbow(length(lbls)), main = "Pie Chart of Countries")
library(plotrix)
slices <- c(10, 12, 4, 16, 8)
lbls <- c("US", "UK", "Australia", "Germany", "France")
pie3D(slices, labels = lbls, explode = 0.1, main = "Pie Chart of Countries ")
attach(mtcars)
plot(wt, mpg, main = "Scatterplot Example", xlab = "Car Weight ", ylab = "Miles Per Gallon ",
pch = 19)
attach(mtcars)
## 下列对象被屏蔽了from mtcars (position 3):
##
## am, carb, cyl, disp, drat, gear, hp, mpg, qsec, vs, wt
plot(wt, mpg, main = "Scatterplot Example", xlab = "Car Weight ", ylab = "Miles Per Gallon ",
pch = 19)
abline(lm(mpg ~ wt), col = "red") # regression line (y~x)
lines(lowess(wt, mpg), col = "blue") # lowess line (x,y)
pairs(~mpg + disp + drat + wt, data = mtcars, main = "Simple Scatterplot Matrix")
The lattice package provides options to condition the scatterplot matrix on a factor.
library(lattice)
super.sym <- trellis.par.get("superpose.symbol")
splom(mtcars[c(1, 3, 5, 6)], groups = cyl, data = mtcars, panel = panel.superpose,
key = list(title = "Three Cylinder Options", columns = 3, points = list(pch = super.sym$pch[1:3],
col = super.sym$col[1:3]), text = list(c("4 Cylinder", "6 Cylinder",
"8 Cylinder"))))
## Warning: explicit 'data' specification ignored
The car package can condition the scatterplot matrix on a factor, and optionally include lowess and linear best fit lines, and boxplot, densities, or histograms in the principal diagonal, as well as rug plots in the margins of the cells.
library(car)
## Loading required package: MASS Loading required package: nnet
scatterplot.matrix(~mpg + disp + drat + wt | cyl, data = mtcars, main = "Three Cylinder Options")
## Warning: 'scatterplot.matrix' is deprecated. Use 'scatterplotMatrix'
## instead. See help("Deprecated") and help("car-deprecated").
The gclus package provides options to rearrange the variables so that those with higher correlations are closer to the principal diagonal. It can also color code the cells to reflect the size of the correlations.
library(gclus)
## Loading required package: cluster
dta <- mtcars[c(1, 3, 5, 6)] # get data
dta.r <- abs(cor(dta)) # get correlations
dta.col <- dmat.color(dta.r) # get colors
# reorder variables so those with highest correlation are closest to the
# diagonal
dta.o <- order.single(dta.r)
cpairs(dta, dta.o, panel.colors = dta.col, gap = 0.5, main = "Variables Ordered and Colored by Correlation")
hist(mtcars$mpg)
hist(mtcars$mpg, breaks = 12, col = "red")
x <- mtcars$mpg
h <- hist(x, breaks = 10, col = "red", xlab = "Miles Per Gallon", main = "Histogram with Normal Curve")
xfit <- seq(min(x), max(x), length = 40)
yfit <- dnorm(xfit, mean = mean(x), sd = sd(x))
yfit <- yfit * diff(h$mids[1:2]) * length(x)
lines(xfit, yfit, col = "blue", lwd = 2)
Kernal density plots are usually a much more effective way to view the distribution of a variable. Create the plot using plot(density(x)) where x is a numeric vector.
plot(density(mtcars$mpg))
d <- density(mtcars$mpg)
plot(d, main = "Kernel Density of Miles Per Gallon")
polygon(d, col = "red", border = "blue")
The sm.density.compare() function in the sm package allows you to superimpose the kernal density plots of two or more groups. The format is sm.density.compare(x, factor) where x is a numeric vector and factor is the grouping variable.
# Compare MPG distributions for cars with 4,6, or 8 cylinders
library(sm)
## Package `sm', version 2.2-5: type help(sm) for summary information
##
## Attaching package: 'sm'
##
## 下列对象被屏蔽了from 'package:MASS':
##
## muscle
attach(mtcars)
## 下列对象被屏蔽了from mtcars (position 10):
##
## am, carb, cyl, disp, drat, gear, hp, mpg, qsec, vs, wt
## 下列对象被屏蔽了from mtcars (position 11):
##
## am, carb, cyl, disp, drat, gear, hp, mpg, qsec, vs, wt
# create value labels
cyl.f <- factor(cyl, levels = c(4, 6, 8), labels = c("4 cylinder", "6 cylinder",
"8 cylinder"))
# plot densities
sm.density.compare(mpg, cyl, xlab = "Miles Per Gallon")
title(main = "MPG Distribution by Car Cylinders")
# add legend via mouse click
colfill <- c(2:(2 + length(levels(cyl.f))))
legend(locator(1), levels(cyl.f), fill = colfill)
## Error: invalid coordinate lengths
xaxt=“n” will suppresses plotting of the axis
# par() # view current settings
opar <- par() # make a copy of current settings
par(col.lab = "red") # red x and y labels
hist(mtcars$mpg) # create a plot with these new settings
par(opar) # restore original settings
## Warning: graphical parameter "cin" cannot be set Warning: graphical
## parameter "cra" cannot be set Warning: graphical parameter "csi" cannot be
## set Warning: graphical parameter "cxy" cannot be set Warning: graphical
## parameter "din" cannot be set
text() places text within the graph while mtext() places text in one of the four margins.
attach(mtcars)
## 下列对象被屏蔽了from mtcars (position 3):
##
## am, carb, cyl, disp, drat, gear, hp, mpg, qsec, vs, wt
## 下列对象被屏蔽了from mtcars (position 11):
##
## am, carb, cyl, disp, drat, gear, hp, mpg, qsec, vs, wt
## 下列对象被屏蔽了from mtcars (position 12):
##
## am, carb, cyl, disp, drat, gear, hp, mpg, qsec, vs, wt
plot(wt, mpg, main = "Milage vs. Car Weight", xlab = "Weight", ylab = "Mileage",
pch = 18, col = "blue")
text(wt, mpg, row.names(mtcars), cex = 0.6, pos = 4, col = "red")
par(mfrow = c(2, 2))
plot(wt, mpg, main = "Scatterplot of wt vs. mpg")
plot(wt, disp, main = "Scatterplot of wt vs disp")
hist(wt, main = "Histogram of wt")
boxplot(wt, main = "Boxplot of wt")
# One figure in row 1 and two figures in row 2 row 1 is 1/3 the height of
# row 2 column 2 is 1/4 the width of the column 1
layout(matrix(c(1, 1, 2, 3), 2, 2, byrow = TRUE), widths = c(3, 1), heights = c(1,
2))
hist(wt)
hist(mpg)
hist(disp)
# Add boxplots to a scatterplot
par(fig = c(0, 0.8, 0, 0.8), new = TRUE)
## Warning: calling par(new=TRUE) with no plot
plot(mtcars$wt, mtcars$mpg, xlab = "Miles Per Gallon", ylab = "Car Weight")
par(fig = c(0, 0.8, 0.55, 1), new = TRUE)
boxplot(mtcars$wt, horizontal = TRUE, axes = FALSE)
par(fig = c(0.65, 1, 0, 0.8), new = TRUE)
boxplot(mtcars$mpg, axes = FALSE)
mtext("Enhanced Scatterplot", side = 3, outer = TRUE, line = -3)
To understand this graph, think of the full graph area as going from (0,0) in the lower left corner to (1,1) in the upper right corner. The format of the fig= parameter is a numerical vector of the form c(x1, x2, y1, y2). The first fig= sets up the scatterplot going from 0 to 0.8 on the x axis and 0 to 0.8 on the y axis. The top boxplot goes from 0 to 0.8 on the x axis and 0.55 to 1 on the y axis. I chose 0.55 rather than 0.8 so that the top figure will be pulled closer to the scatter plot. The right hand boxplot goes from 0.65 to 1 on the x axis and 0 to 0.8 on the y axis. Again, I chose a value to pull the right hand boxplot closer to the scatterplot. You have to experiment to get it just right.
attach(mtcars)
## 下列对象被屏蔽了from mtcars (position 3):
##
## am, carb, cyl, disp, drat, gear, hp, mpg, qsec, vs, wt
## 下列对象被屏蔽了from mtcars (position 4):
##
## am, carb, cyl, disp, drat, gear, hp, mpg, qsec, vs, wt
## 下列对象被屏蔽了from mtcars (position 12):
##
## am, carb, cyl, disp, drat, gear, hp, mpg, qsec, vs, wt
## 下列对象被屏蔽了from mtcars (position 13):
##
## am, carb, cyl, disp, drat, gear, hp, mpg, qsec, vs, wt
boxplot(mpg ~ cyl, main = "Milage by Car Weight", yaxt = "n", xlab = "Milage",
horizontal = TRUE, col = terrain.colors(3))
legend("topright", inset = 0.05, title = "Number of Cylinders", c("4", "6",
"8"), fill = terrain.colors(3), horiz = TRUE)
