This is an R Markdown document. Markdown is a simple formatting syntax for authoring HTML, PDF, and MS Word documents. For more details on using R Markdown see http://rmarkdown.rstudio.com.

When you click the Knit button a document will be generated that includes both content as well as the output of any embedded R code chunks within the document. You can embed an R code chunk like this:

library(ISLR); library(ggplot2); library(caret);library(Hmisc); library(gridExtra);
## Loading required package: lattice
## Loading required package: grid
## Loading required package: survival
## 
## Attaching package: 'survival'
## 
## The following object is masked from 'package:caret':
## 
##     cluster
## 
## Loading required package: Formula
## 
## Attaching package: 'Hmisc'
## 
## The following objects are masked from 'package:base':
## 
##     format.pval, round.POSIXt, trunc.POSIXt, units
data(Wage)
summary(Wage)
##       year           age               sex                    maritl    
##  Min.   :2003   Min.   :18.00   1. Male  :3000   1. Never Married: 648  
##  1st Qu.:2004   1st Qu.:33.75   2. Female:   0   2. Married      :2074  
##  Median :2006   Median :42.00                    3. Widowed      :  19  
##  Mean   :2006   Mean   :42.41                    4. Divorced     : 204  
##  3rd Qu.:2008   3rd Qu.:51.00                    5. Separated    :  55  
##  Max.   :2009   Max.   :80.00                                           
##                                                                         
##        race                   education                     region    
##  1. White:2480   1. < HS Grad      :268   2. Middle Atlantic   :3000  
##  2. Black: 293   2. HS Grad        :971   1. New England       :   0  
##  3. Asian: 190   3. Some College   :650   3. East North Central:   0  
##  4. Other:  37   4. College Grad   :685   4. West North Central:   0  
##                  5. Advanced Degree:426   5. South Atlantic    :   0  
##                                           6. East South Central:   0  
##                                           (Other)              :   0  
##            jobclass               health      health_ins      logwage     
##  1. Industrial :1544   1. <=Good     : 858   1. Yes:2083   Min.   :3.000  
##  2. Information:1456   2. >=Very Good:2142   2. No : 917   1st Qu.:4.447  
##                                                            Median :4.653  
##                                                            Mean   :4.654  
##                                                            3rd Qu.:4.857  
##                                                            Max.   :5.763  
##                                                                           
##       wage       
##  Min.   : 20.09  
##  1st Qu.: 85.38  
##  Median :104.92  
##  Mean   :111.70  
##  3rd Qu.:128.68  
##  Max.   :318.34  
##

You can also embed plots, for example:

Note that the echo = FALSE parameter was added to the code chunk to prevent printing of the R code that generated the plot. Get training/test sets

inTrain <- createDataPartition(y=Wage$wage,
                              p=0.7, list=FALSE)
training <- Wage[inTrain,]
testing <- Wage[-inTrain,]
dim(training); dim(testing)
## [1] 2102   12
## [1] 898  12

Feature plot (caret package)

featurePlot(x=training[,c("age","education","jobclass")],
            y = training$wage,
            plot="pairs")

Qplot (ggplot2 package)

qplot(age,wage,data=training)

Qplot with color (ggplot2 package)

qplot(age,wage,colour=jobclass,data=training)

Add regression smoothers (ggplot2 package)

qq <- qplot(age,wage,colour=education,data=training)
qq +  geom_smooth(method='lm',formula=y~x)

cut2, making factors (Hmisc package)

cutWage <- cut2(training$wage,g=3)
table(cutWage)
## cutWage
## [ 20.1, 93) [ 93.0,119) [118.9,318] 
##         714         715         673

Boxplots with cut2

p1 <- qplot(cutWage,age, data=training,fill=cutWage,
      geom=c("boxplot"))
p1

Boxplots with points overlayed

p2 <- qplot(cutWage,age, data=training,fill=cutWage, geom=c("boxplot","jitter"))
grid.arrange(p1,p2,ncol=2)

Tables

t1 <- table(cutWage,training$jobclass)
t1
##              
## cutWage       1. Industrial 2. Information
##   [ 20.1, 93)           446            268
##   [ 93.0,119)           361            354
##   [118.9,318]           260            413
prop.table(t1,1)
##              
## cutWage       1. Industrial 2. Information
##   [ 20.1, 93)     0.6246499      0.3753501
##   [ 93.0,119)     0.5048951      0.4951049
##   [118.9,318]     0.3863299      0.6136701

Density plots

qplot(wage,colour=education,data=training,geom="density")