The document is a tutorial on learning R programming, emphasizing the importance of mastering basic R before using tools like RStudio. It provides various code snippets and data manipulations demonstrating how to work with vectors, matrices, and data frames in R. Additionally, it lists essential tools and reference sites for learning R effectively.

1. Chapter-02-R-Tutorial file:///C:/Users/rk215/Documents/R-Tutorial.html#Learning_R_to_do_D...
1 of 31 10/18/2020, 4:30 AM

2. https://www.r-project.org/
Essential tools:
RGUI Basic R processing,
RScript to run batch scripts,
RCMD (to install in Unix/Linux) variants
RStudio is a compelling tool – though defer RStudio until you know R very we
ll – tools are limiting you – bad idea to start with RStudio to learn the la
nguage, IMHO.
Reference Sites: (that I often use, don’t leave home without it)
https://www.r-bloggers.com
https://nabble.com/
http://rfunction.com
https://stackoverflow.com/
https://stats.stackexchange.com/
https://www.datasciencemadesimple.com/
http://www.r-tutor.com/
There are thousands if not more, useful R sites you can learn from
Again to do what you want to get done…otherwise you will be sucked into
vortex..
…
Chapter-02-R-Tutorial file:///C:/Users/rk215/Documents/R-Tutorial.html#Learning_R_to_do_D...
2 of 31 10/18/2020, 4:30 AM

3. ls()
## character(0)
X<-5
7->Y
ifelse(X<Y,'X is Less than Y', 'X is atleast equal to Y')
## [1] "X is Less than Y"
vec<-1:13
is.vector(vec)
## [1] TRUE
vec[4]
## [1] 4
by2<-seq(1,13,2)
(xy2<-seq(1,13,2))
## [1] 1 3 5 7 9 11 13
xy2[4]
## [1] 7
Chapter-02-R-Tutorial file:///C:/Users/rk215/Documents/R-Tutorial.html#Learning_R_to_do_D...
3 of 31 10/18/2020, 4:30 AM

4. is.vector(xy2[4])
## [1] TRUE
length(xy2[4])
## [1] 1
vec[vec %in% by2]
## [1] 1 3 5 7 9 11 13
(xyeven<-seq(0,13,2))
## [1] 0 2 4 6 8 10 12
length(vec)
## [1] 13
mean(vec)
## [1] 7
sd(vec)
## [1] 3.89444
sum(vec)
## [1] 91
cumprod(vec)
## [1] 1 2 6 24 120 720
## [7] 5040 40320 362880 3628800 39916800 479001600
## [13] 6227020800
Chapter-02-R-Tutorial file:///C:/Users/rk215/Documents/R-Tutorial.html#Learning_R_to_do_D...
4 of 31 10/18/2020, 4:30 AM

5. L<-list(X=5,reason="I like 5")
L
## $X
## [1] 5
##
## $reason
## [1] "I like 5"
mx<-matrix(c(rep(0,5),seq(1:5)),nrow=2,ncol=5) # fixed the error now the mx
should have correct values not ALL zeros
mx
## [,1] [,2] [,3] [,4] [,5]
## [1,] 0 0 0 2 4
## [2,] 0 0 1 3 5
mxbyr<-matrix(c(rep(0,5),seq(1:5)),nrow=2,ncol=5,byrow=TRUE)
mxbyr
## [,1] [,2] [,3] [,4] [,5]
## [1,] 0 0 0 0 0
## [2,] 1 2 3 4 5
dd <- structure(list(
population = c(4.560667108, 1.275920972)
,continents = c('Asia', 'Africa'))
,.Names = c("Pop", "Continent")
,row.names = c(NA, -2L)
,class = "data.frame")
dd
## Pop Continent
## 1 4.560667 Asia
## 2 1.275921 Africa
Chapter-02-R-Tutorial file:///C:/Users/rk215/Documents/R-Tutorial.html#Learning_R_to_do_D...
5 of 31 10/18/2020, 4:30 AM

6. dd<-rbind(dd,c(4.1570842,'Oceania'))
dd
## Pop Continent
## 1 4.560667108 Asia
## 2 1.275920972 Africa
## 3 4.1570842 Oceania
dd<-cbind(dd,density=c(100,36,4))
dd<-rbind(dd,c(0,'pangea'))
dd
## Pop Continent density
## 1 4.560667108 Asia 100
## 2 1.275920972 Africa 36
## 3 4.1570842 Oceania 4
## 4 0 pangea 0
which(dd$Pop==0)
## [1] 4
dd<-dd[-which(dd$Pop==0),]
dd
## Pop Continent density
## 1 4.560667108 Asia 100
## 2 1.275920972 Africa 36
## 3 4.1570842 Oceania 4
birds<-data.frame(nlegs=rep(2,5),can_fly=c(0,1,1,0,1),height=c(25,40,20,150,
10),
color=c('black','black','blue','black','brown'))
birds2<-cbind(birds,c('chicken','vulture','parrot','ostrich','sparrow'))
names(birds2)<-c('nlegs','can_fly','height','color','species')
birds2
Chapter-02-R-Tutorial file:///C:/Users/rk215/Documents/R-Tutorial.html#Learning_R_to_do_D...
6 of 31 10/18/2020, 4:30 AM

7. ## nlegs can_fly height color species
## 1 2 0 25 black chicken
## 2 2 1 40 black vulture
## 3 2 1 20 blue parrot
## 4 2 0 150 black ostrich
## 5 2 1 10 brown sparrow
…
chickencolors<-c('black','white','red','mixed')
vulturecolors<-c('grey','black','white')
parrotcolors<-c('teal','green','blue','mixed','pink')
ostrichcolors<-c('grey','black')
sparrowcolors<-c('dark cement','brown')
hchicken<-sample(rnorm(10,25,6),5)
hvulture<-sample(rnorm(10,40,4),5)
hparrot<-sample(rnorm(10,20,2),5)
hostrich<-sample(rnorm(10,150,20),5)
hsparrow<-sample(rnorm(10,10,1),5)
cdset<-rbind(birds2,data.frame(nlegs=rep(2,5),can_fly=rep(0,5), height=hchic
ken,
color=sample(chickencolors,5,replace=T),species=rep('chicken',5)),
data.frame(nlegs=rep(2,5),can_fly=rep(1,5), height=hvulture,
color=sample(vulturecolors,5,replace=T),species=rep('vulture',5)),
data.frame(nlegs=rep(2,5),can_fly=rep(1,5), height=hparrot,
color=sample(parrotcolors,5,replace=T),species=rep('parrot',5)),
data.frame(nlegs=rep(2,5),can_fly=rep(0,5), height=hostrich,
color=sample(ostrichcolors,5,replace=T),species=rep('ostrich',5)),
data.frame(nlegs=rep(2,5),can_fly=rep(1,5), height=hsparrow,
color=sample(sparrowcolors,5,replace=T),species=rep('sparrow',5)))
cdset # just print out the contents
Chapter-02-R-Tutorial file:///C:/Users/rk215/Documents/R-Tutorial.html#Learning_R_to_do_D...
7 of 31 10/18/2020, 4:30 AM

8. ## nlegs can_fly height color species
## 1 2 0 25.000000 black chicken
## 2 2 1 40.000000 black vulture
## 3 2 1 20.000000 blue parrot
## 4 2 0 150.000000 black ostrich
## 5 2 1 10.000000 brown sparrow
## 6 2 0 21.795787 red chicken
## 7 2 0 39.459162 mixed chicken
## 8 2 0 22.981968 black chicken
## 9 2 0 17.744720 black chicken
## 10 2 0 25.911222 mixed chicken
## 11 2 1 39.016163 white vulture
## 12 2 1 40.037789 white vulture
## 13 2 1 42.251693 grey vulture
## 14 2 1 39.014589 grey vulture
## 15 2 1 38.475420 white vulture
## 16 2 1 20.316044 mixed parrot
## 17 2 1 22.712721 teal parrot
## 18 2 1 22.840455 mixed parrot
## 19 2 1 14.934359 blue parrot
## 20 2 1 21.195914 blue parrot
## 21 2 0 160.085412 black ostrich
## 22 2 0 140.594205 black ostrich
## 23 2 0 174.088029 grey ostrich
## 24 2 0 157.684178 grey ostrich
## 25 2 0 135.249085 grey ostrich
## 26 2 1 9.295639 dark cement sparrow
## 27 2 1 11.266186 dark cement sparrow
## 28 2 1 9.336063 brown sparrow
## 29 2 1 10.169087 brown sparrow
## 30 2 1 11.060101 brown sparrow
dim(cdset) # what are the dimensions
## [1] 30 5
nrow(cdset) # number of rows
## [1] 30
ncol(cdset) # number of columns
## [1] 5
names(cdset) # data.frames have names matrices dont
Chapter-02-R-Tutorial file:///C:/Users/rk215/Documents/R-Tutorial.html#Learning_R_to_do_D...
8 of 31 10/18/2020, 4:30 AM

9. ## [1] "nlegs" "can_fly" "height" "color" "species"
head(cdset)
## nlegs can_fly height color species
## 1 2 0 25.00000 black chicken
## 2 2 1 40.00000 black vulture
## 3 2 1 20.00000 blue parrot
## 4 2 0 150.00000 black ostrich
## 5 2 1 10.00000 brown sparrow
## 6 2 0 21.79579 red chicken
tail(cdset)
## nlegs can_fly height color species
## 25 2 0 135.249085 grey ostrich
## 26 2 1 9.295639 dark cement sparrow
## 27 2 1 11.266186 dark cement sparrow
## 28 2 1 9.336063 brown sparrow
## 29 2 1 10.169087 brown sparrow
## 30 2 1 11.060101 brown sparrow
row.names(cdset)
## [1] "1" "2" "3" "4" "5" "6" "7" "8" "9" "10" "11" "12" "13" "1
4" "15"
## [16] "16" "17" "18" "19" "20" "21" "22" "23" "24" "25" "26" "27" "28" "2
9" "30"
cdset[1,3]# just one cell
## [1] 25
cdset[1,] # entire observation
## nlegs can_fly height color species
## 1 2 0 25 black chicken
cdset[,3]# entire column or the feature
Chapter-02-R-Tutorial file:///C:/Users/rk215/Documents/R-Tutorial.html#Learning_R_to_do_D...
9 of 31 10/18/2020, 4:30 AM

10. ## [1] 25.000000 40.000000 20.000000 150.000000 10.000000 21.795787
## [7] 39.459162 22.981968 17.744720 25.911222 39.016163 40.037789
## [13] 42.251693 39.014589 38.475420 20.316044 22.712721 22.840455
## [19] 14.934359 21.195914 160.085412 140.594205 174.088029 157.684178
## [25] 135.249085 9.295639 11.266186 9.336063 10.169087 11.060101
cdset[cdset$species=='sparrow',]# review just the sparrow data.entire observ
ations
## nlegs can_fly height color species
## 5 2 1 10.000000 brown sparrow
## 26 2 1 9.295639 dark cement sparrow
## 27 2 1 11.266186 dark cement sparrow
## 28 2 1 9.336063 brown sparrow
## 29 2 1 10.169087 brown sparrow
## 30 2 1 11.060101 brown sparrow
cdset[cdset$species=='sparrow',c(1,3,5)]# just some of the columns
## nlegs height species
## 5 2 10.000000 sparrow
## 26 2 9.295639 sparrow
## 27 2 11.266186 sparrow
## 28 2 9.336063 sparrow
## 29 2 10.169087 sparrow
## 30 2 11.060101 sparrow
cdset[cdset$species=='sparrow',c('nlegs','species')]# or by column names
## nlegs species
## 5 2 sparrow
## 26 2 sparrow
## 27 2 sparrow
## 28 2 sparrow
## 29 2 sparrow
## 30 2 sparrow
cdset[cdset$species=='sparrow',-which(names(cdset)=='species')]# filter OUT
some columns
Chapter-02-R-Tutorial file:///C:/Users/rk215/Documents/R-Tutorial.html#Learning_R_to_do_D...
10 of 31 10/18/2020, 4:30 AM

11. ## nlegs can_fly height color
## 5 2 1 10.000000 brown
## 26 2 1 9.295639 dark cement
## 27 2 1 11.266186 dark cement
## 28 2 1 9.336063 brown
## 29 2 1 10.169087 brown
## 30 2 1 11.060101 brown
cdset[cdset$species=='sparrow',-which(names(cdset)%in%c('nlegs','species'))]
## can_fly height color
## 5 1 10.000000 brown
## 26 1 9.295639 dark cement
## 27 1 11.266186 dark cement
## 28 1 9.336063 brown
## 29 1 10.169087 brown
## 30 1 11.060101 brown
…
…
…
lapply(1:3,FUN=function(x)x*x) -> exl
exl
## [[1]]
## [1] 1
##
## [[2]]
## [1] 4
##
## [[3]]
## [1] 9
Chapter-02-R-Tutorial file:///C:/Users/rk215/Documents/R-Tutorial.html#Learning_R_to_do_D...
11 of 31 10/18/2020, 4:30 AM

12. mx
## [,1] [,2] [,3] [,4] [,5]
## [1,] 0 0 0 2 4
## [2,] 0 0 1 3 5
apply(mx,2,sd)
## [1] 0.0000000 0.0000000 0.7071068 0.7071068 0.7071068
(mx1<-sapply(mx,FUN=function(x)x+1))
## [1] 1 1 1 1 1 2 3 4 5 6
…
…
prodidlist<-c(paste("P0",1:9,sep=''),paste("P",10:99,sep=''))
cidlist<-c(paste("C0",1:9,sep=''),paste("C",10:22,sep=''))
(df<-data.frame(DID=1,CID="C01",
PID=sample(prodidlist,sample(1:20,1),replace=F),
stringsAsFactors=F))
## DID CID PID
## 1 1 C01 P88
## 2 1 C01 P53
## 3 1 C01 P86
## 4 1 C01 P90
## 5 1 C01 P21
## 6 1 C01 P34
(sample(prodidlist,sample(1:20,1),replace=F))
## [1] "P75" "P34" "P40" "P27" "P71" "P06" "P72"
Chapter-02-R-Tutorial file:///C:/Users/rk215/Documents/R-Tutorial.html#Learning_R_to_do_D...
12 of 31 10/18/2020, 4:30 AM

13. mdf<-do.call('rbind',lapply(1:50,FUN=function(x)
{
cidlist<-sample(cidlist,sample(1:length(cidlist),1),replace=F)
dfi<-do.call('rbind',lapply(cidlist,FUN=
function(cid)data.frame(DID=x,CID=cid,
PID=sample(prodidlist,sample(1:20,1),replace=F))))
}
))
write.table(mdf,
file='purchases.csv',
sep=',',row.names=F,
col.names=T,
quote=F)
head(mdf)
## DID CID PID
## 1 1 C19 P19
## 2 1 C19 P33
## 3 1 C19 P91
## 4 1 C19 P78
## 5 1 C19 P66
## 6 1 C19 P64
nrow(mdf)
## [1] 6436
…
read.csv('purchases.csv',head=T,sep=',')->rmdf
titanic<-read.csv("http://christianherta.de/lehre/dataScience/machineLearnin
g/data/titanic-train.csv",header=T)
head(titanic)
Chapter-02-R-Tutorial file:///C:/Users/rk215/Documents/R-Tutorial.html#Learning_R_to_do_D...
13 of 31 10/18/2020, 4:30 AM

14. ## PassengerId Survived Pclass
## 1 1 0 3
## 2 2 1 1
## 3 3 1 3
## 4 4 1 1
## 5 5 0 3
## 6 6 0 3
## Name Sex Age SibSp Pa
rch
## 1 Braund, Mr. Owen Harris male 22 1
0
## 2 Cumings, Mrs. John Bradley (Florence Briggs Thayer) female 38 1
0
## 3 Heikkinen, Miss. Laina female 26 0
0
## 4 Futrelle, Mrs. Jacques Heath (Lily May Peel) female 35 1
0
## 5 Allen, Mr. William Henry male 35 0
0
## 6 Moran, Mr. James male NA 0
0
## Ticket Fare Cabin Embarked
## 1 A/5 21171 7.2500 S
## 2 PC 17599 71.2833 C85 C
## 3 STON/O2. 3101282 7.9250 S
## 4 113803 53.1000 C123 S
## 5 373450 8.0500 S
## 6 330877 8.4583 Q
dim(titanic)
## [1] 891 12
table(mdf==rmdf)
##
## TRUE
## 19308
cumprod(dim(mdf)) #rows ^ columns the number of elements all of them match a
s they should
Chapter-02-R-Tutorial file:///C:/Users/rk215/Documents/R-Tutorial.html#Learning_R_to_do_D...
14 of 31 10/18/2020, 4:30 AM

15. ## [1] 6436 19308
nrow(rmdf)* ncol(rmdf)
## [1] 19308
quantmod::getSymbols(c("IBM","SPY"),from='2020-01-01')
## Registered S3 method overwritten by 'quantmod':
## method from
## as.zoo.data.frame zoo
## 'getSymbols' currently uses auto.assign=TRUE by default, but will
## use auto.assign=FALSE in 0.5-0. You will still be able to use
## 'loadSymbols' to automatically load data. getOption("getSymbols.env")
## and getOption("getSymbols.auto.assign") will still be checked for
## alternate defaults.
##
## This message is shown once per session and may be disabled by setting
## options("getSymbols.warning4.0"=FALSE). See ?getSymbols for details.
## [1] "IBM" "SPY"
dim(IBM)
## [1] 201 6
#dim(JNJ)
#quantmod::getSymbols(c("SPY"),from='2020-01-01')
head(IBM)
Chapter-02-R-Tutorial file:///C:/Users/rk215/Documents/R-Tutorial.html#Learning_R_to_do_D...
15 of 31 10/18/2020, 4:30 AM

16. ## IBM.Open IBM.High IBM.Low IBM.Close IBM.Volume IBM.Adjusted
## 2020-01-02 135.00 135.92 134.77 135.42 3148600 130.5377
## 2020-01-03 133.57 134.86 133.56 134.34 2373700 129.4967
## 2020-01-06 133.42 134.24 133.20 134.10 2425500 129.2654
## 2020-01-07 133.69 134.96 133.40 134.19 3090800 129.3521
## 2020-01-08 134.51 135.86 133.92 135.31 4346000 130.4317
## 2020-01-09 135.74 136.79 135.31 136.74 3730600 131.8102
head(IBM$IBM.Adjusted)
## IBM.Adjusted
## 2020-01-02 130.5377
## 2020-01-03 129.4967
## 2020-01-06 129.2654
## 2020-01-07 129.3521
## 2020-01-08 130.4317
## 2020-01-09 131.8102
DIBM<-c(head(IBM$IBM.Adjusted,1),head(IBM$IBM.Adjusted,200)) ## fixed the er
ror
head((dailyIBMReturns<-(((as.numeric(IBM$IBM.Adjusted)/DIBM) -1)*100))) ## f
ixed the error now results are full precision
## IBM.Adjusted
## 2020-01-02 0.00000000
## 2020-01-02 -0.79751719
## 2020-01-03 -0.17863237
## 2020-01-06 0.06709531
## 2020-01-07 0.83464824
## 2020-01-08 1.05682335
dailyReturnIBM<-dailyIBMReturns#(IBM[[6]]/DIBM)-1
head(dailyReturnIBM)
## IBM.Adjusted
## 2020-01-02 0.00000000
## 2020-01-02 -0.79751719
## 2020-01-03 -0.17863237
## 2020-01-06 0.06709531
## 2020-01-07 0.83464824
## 2020-01-08 1.05682335
DSPY<-c(head(SPY$SPY.Adjusted,1),head(SPY$SPY.Adjusted,200)) ## fixed the er
ror
head((dailySPYReturns<-(((as.numeric(SPY$SPY.Adjusted)/DSPY) -1)*100))) ## f
ixed the error now results are full precision
Chapter-02-R-Tutorial file:///C:/Users/rk215/Documents/R-Tutorial.html#Learning_R_to_do_D...
16 of 31 10/18/2020, 4:30 AM

17. ## SPY.Adjusted
## 2020-01-02 0.0000000
## 2020-01-02 -0.7572182
## 2020-01-03 0.3815075
## 2020-01-06 -0.2811862
## 2020-01-07 0.5329669
## 2020-01-08 0.6780544
dailyReturnSPY<-dailySPYReturns#(SPY[[6]]/DSPY)-1
lmModel<-lm(dailyReturnIBM~dailyReturnSPY)
summary(lmModel)
##
## Call:
## lm(formula = dailyReturnIBM ~ dailyReturnSPY)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.7497 -0.7827 -0.1046 0.6906 7.0070
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.04934 0.09647 -0.511 0.61
## dailyReturnSPY 1.02923 0.04193 24.547 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.367 on 199 degrees of freedom
## Multiple R-squared: 0.7517, Adjusted R-squared: 0.7505
## F-statistic: 602.6 on 1 and 199 DF, p-value: < 2.2e-16
oldPar<-par(mfrow=c(2,1))
plot(dailyReturnIBM,color='black')
plot(dailyReturnSPY,color='blue')
Chapter-02-R-Tutorial file:///C:/Users/rk215/Documents/R-Tutorial.html#Learning_R_to_do_D...
17 of 31 10/18/2020, 4:30 AM

18. #abline(dailyReturnIBM,dailyReturnSPY)
cor(dailyReturnIBM,dailyReturnSPY)
## SPY.Adjusted
## IBM.Adjusted 0.8670258
#plot(dailyReturnIBM,pch=3,color='black')
#points(dailyReturnSPY,pch=3,color='blue')
library(sqldf)
Chapter-02-R-Tutorial file:///C:/Users/rk215/Documents/R-Tutorial.html#Learning_R_to_do_D...
18 of 31 10/18/2020, 4:30 AM

19. ## Loading required package: gsubfn
## Loading required package: proto
## Loading required package: RSQLite
purchases<-mdf
rpt01<-sqldf('select DID,count(distinct(CID)) from mdf group by DID')
head(rpt01)
## DID count(distinct(CID))
## 1 1 14
## 2 2 19
## 3 3 6
## 4 4 16
## 5 5 16
## 6 6 9
tail(rpt01)
## DID count(distinct(CID))
## 45 45 22
## 46 46 15
## 47 47 15
## 48 48 19
## 49 49 10
## 50 50 10
sqldf('select distinct CID from mdf where DID=50')
## CID
## 1 C06
## 2 C21
## 3 C03
## 4 C11
## 5 C04
## 6 C17
## 7 C08
## 8 C14
## 9 C18
## 10 C15
Chapter-02-R-Tutorial file:///C:/Users/rk215/Documents/R-Tutorial.html#Learning_R_to_do_D...
19 of 31 10/18/2020, 4:30 AM

20. Chapter-02-R-Tutorial file:///C:/Users/rk215/Documents/R-Tutorial.html#Learning_R_to_do_D...
20 of 31 10/18/2020, 4:30 AM

21. SELECT A.p1,
A.p2,
A.p1p2c / B.p1c AS condProb
FROM (SELECT apid P1,
bpid P2,
Count(*) P1P2C
FROM (SELECT A.did AS ADID,
A.cid AS ACID,
A.pid AS APID,
B.did AS BDID,
B.cid AS BCID,
B.pid AS BPID
FROM purchases A
JOIN purchases B
ON A.cid = B.cid
AND A.did = B.did
AND A.pid < B.pid) X
GROUP BY apid,
bpid) A
JOIN (SELECT pid AS P1,
Count(*) P1C
FROM purchases
GROUP BY pid) B
ON A.p1 = B.p1
ORDER BY condprob DESC;
sqlstr<-"select A.P1,A.P2, (A.P1P2C*100)/B.P1C as condProb from ( Select API
D P1,BPID P2,count(*) P1P2C from ( select A.DID as
ADID, A.CID as ACID , A.PID as APID , B.DID as BDID, B.CID as BCID , B.PID a
s BPID from purchases A join purchases B on
A.CID=B.CID AND A.DID=B.DID AND A.PID < B.PID ) X group by APID,BPID ) A jo
in (select PID as P1, count(*) P1C from purchases group by PID) B on A.P1=B.
P1 order by condProb desc"
sqlstr
## [1] "select A.P1,A.P2, (A.P1P2C*100)/B.P1C as condProb from ( Select APID
P1,BPID P2,count(*) P1P2C from ( select A.DID asnADID, A.CID as ACID , A.P
ID as APID , B.DID as BDID, B.CID as BCID , B.PID as BPID from purchases A j
oin purchases B onnA.CID=B.CID AND A.DID=B.DID AND A.PID < B.PID ) X group
by APID,BPID ) A join (select PID as P1, count(*) P1C from purchases group b
y PID) B on A.P1=B.P1 order by condProb desc"
Chapter-02-R-Tutorial file:///C:/Users/rk215/Documents/R-Tutorial.html#Learning_R_to_do_D...
21 of 31 10/18/2020, 4:30 AM

22. condprob<-sqldf(sqlstr)
#condprob
head(condprob)
## P1 P2 condProb
## 1 P27 P61 31
## 2 P66 P97 31
## 3 P04 P92 29
## 4 P27 P53 29
## 5 P27 P95 29
## 6 P52 P79 29
require(rpart)
## Loading required package: rpart
require(rpart.plot)
## Loading required package: rpart.plot
require(klaR)
## Loading required package: klaR
## Loading required package: MASS
Chapter-02-R-Tutorial file:///C:/Users/rk215/Documents/R-Tutorial.html#Learning_R_to_do_D...
22 of 31 10/18/2020, 4:30 AM

23. set.seed(43)
tridx<-sample(1:30,20,replace=F)
trdata<-cdset[tridx,]
tstdata<-cdset[-tridx,]
trmodel.rpart<-rpart(species~.,data=trdata,minsplit=2)
rpart.plot(trmodel.rpart)
#compare this to
table(trdata$species)/nrow(trdata)
##
## chicken ostrich parrot sparrow vulture
## 0.20 0.25 0.15 0.20 0.20
predicted.trmodel.rpart<-predict(trmodel.rpart,trdata[,-5],type='class')
table(trdata[,5],predicted.trmodel.rpart)
Chapter-02-R-Tutorial file:///C:/Users/rk215/Documents/R-Tutorial.html#Learning_R_to_do_D...
23 of 31 10/18/2020, 4:30 AM

24. ## predicted.trmodel.rpart
## chicken ostrich parrot sparrow vulture
## chicken 4 0 0 0 0
## ostrich 0 5 0 0 0
## parrot 0 0 3 0 0
## sparrow 0 0 0 4 0
## vulture 0 0 0 0 4
# removing colors that are present in test but not in train -- in small data
set
# tree cannot process that
tstdatnw<-tstdata[tstdata$color %in% trdata$color,]
tstdatnw
## nlegs can_fly height color species
## 10 2 0 25.91122 mixed chicken
## 11 2 1 39.01616 white vulture
## 15 2 1 38.47542 white vulture
## 18 2 1 22.84045 mixed parrot
## 20 2 1 21.19591 blue parrot
## 25 2 0 135.24908 grey ostrich
## 29 2 1 10.16909 brown sparrow
## 30 2 1 11.06010 brown sparrow
predicted.tstdatnw.rpart<-predict(trmodel.rpart,tstdatnw[,-5],type='class')
table(tstdatnw[,5],predicted.tstdatnw.rpart)
## predicted.tstdatnw.rpart
## chicken ostrich parrot sparrow vulture
## chicken 1 0 0 0 0
## ostrich 0 1 0 0 0
## parrot 0 0 2 0 0
## sparrow 0 0 0 2 0
## vulture 0 0 0 0 2
caret::confusionMatrix( table(tstdatnw[,5],predicted.tstdatnw.rpart))
Chapter-02-R-Tutorial file:///C:/Users/rk215/Documents/R-Tutorial.html#Learning_R_to_do_D...
24 of 31 10/18/2020, 4:30 AM

25. ## Confusion Matrix and Statistics
##
## predicted.tstdatnw.rpart
## chicken ostrich parrot sparrow vulture
## chicken 1 0 0 0 0
## ostrich 0 1 0 0 0
## parrot 0 0 2 0 0
## sparrow 0 0 0 2 0
## vulture 0 0 0 0 2
##
## Overall Statistics
##
## Accuracy : 1
## 95% CI : (0.6306, 1)
## No Information Rate : 0.25
## P-Value [Acc > NIR] : 1.526e-05
##
## Kappa : 1
##
## Mcnemar's Test P-Value : NA
##
## Statistics by Class:
##
## Class: chicken Class: ostrich Class: parrot Class: s
parrow
## Sensitivity 1.000 1.000 1.00
1.00
## Specificity 1.000 1.000 1.00
1.00
## Pos Pred Value 1.000 1.000 1.00
1.00
## Neg Pred Value 1.000 1.000 1.00
1.00
## Prevalence 0.125 0.125 0.25
0.25
## Detection Rate 0.125 0.125 0.25
0.25
## Detection Prevalence 0.125 0.125 0.25
0.25
## Balanced Accuracy 1.000 1.000 1.00
1.00
## Class: vulture
## Sensitivity 1.00
## Specificity 1.00
## Pos Pred Value 1.00
## Neg Pred Value 1.00
## Prevalence 0.25
## Detection Rate 0.25
## Detection Prevalence 0.25
## Balanced Accuracy 1.00
Chapter-02-R-Tutorial file:///C:/Users/rk215/Documents/R-Tutorial.html#Learning_R_to_do_D...
25 of 31 10/18/2020, 4:30 AM

26. tstdatnw[,5]
## [1] "chicken" "vulture" "vulture" "parrot" "parrot" "ostrich" "sparrow"
## [8] "sparrow"
predicted.tstdatnw.rpart
## 10 11 15 18 20 25 29 30
## chicken vulture vulture parrot parrot ostrich sparrow sparrow
## Levels: chicken ostrich parrot sparrow vulture
table(as.character(tstdatnw[,5]),as.character(predicted.tstdatnw.rpart))
##
## chicken ostrich parrot sparrow vulture
## chicken 1 0 0 0 0
## ostrich 0 1 0 0 0
## parrot 0 0 2 0 0
## sparrow 0 0 0 2 0
## vulture 0 0 0 0 2
caret::confusionMatrix( table(tstdatnw[,5],predicted.tstdatnw.rpart))
Chapter-02-R-Tutorial file:///C:/Users/rk215/Documents/R-Tutorial.html#Learning_R_to_do_D...
26 of 31 10/18/2020, 4:30 AM

27. ## Confusion Matrix and Statistics
##
## predicted.tstdatnw.rpart
## chicken ostrich parrot sparrow vulture
## chicken 1 0 0 0 0
## ostrich 0 1 0 0 0
## parrot 0 0 2 0 0
## sparrow 0 0 0 2 0
## vulture 0 0 0 0 2
##
## Overall Statistics
##
## Accuracy : 1
## 95% CI : (0.6306, 1)
## No Information Rate : 0.25
## P-Value [Acc > NIR] : 1.526e-05
##
## Kappa : 1
##
## Mcnemar's Test P-Value : NA
##
## Statistics by Class:
##
## Class: chicken Class: ostrich Class: parrot Class: s
parrow
## Sensitivity 1.000 1.000 1.00
1.00
## Specificity 1.000 1.000 1.00
1.00
## Pos Pred Value 1.000 1.000 1.00
1.00
## Neg Pred Value 1.000 1.000 1.00
1.00
## Prevalence 0.125 0.125 0.25
0.25
## Detection Rate 0.125 0.125 0.25
0.25
## Detection Prevalence 0.125 0.125 0.25
0.25
## Balanced Accuracy 1.000 1.000 1.00
1.00
## Class: vulture
## Sensitivity 1.00
## Specificity 1.00
## Pos Pred Value 1.00
## Neg Pred Value 1.00
## Prevalence 0.25
## Detection Rate 0.25
## Detection Prevalence 0.25
## Balanced Accuracy 1.00
Chapter-02-R-Tutorial file:///C:/Users/rk215/Documents/R-Tutorial.html#Learning_R_to_do_D...
27 of 31 10/18/2020, 4:30 AM

28. …
cdset
## nlegs can_fly height color species
## 1 2 0 25.000000 black chicken
## 2 2 1 40.000000 black vulture
## 3 2 1 20.000000 blue parrot
## 4 2 0 150.000000 black ostrich
## 5 2 1 10.000000 brown sparrow
## 6 2 0 21.795787 red chicken
## 7 2 0 39.459162 mixed chicken
## 8 2 0 22.981968 black chicken
## 9 2 0 17.744720 black chicken
## 10 2 0 25.911222 mixed chicken
## 11 2 1 39.016163 white vulture
## 12 2 1 40.037789 white vulture
## 13 2 1 42.251693 grey vulture
## 14 2 1 39.014589 grey vulture
## 15 2 1 38.475420 white vulture
## 16 2 1 20.316044 mixed parrot
## 17 2 1 22.712721 teal parrot
## 18 2 1 22.840455 mixed parrot
## 19 2 1 14.934359 blue parrot
## 20 2 1 21.195914 blue parrot
## 21 2 0 160.085412 black ostrich
## 22 2 0 140.594205 black ostrich
## 23 2 0 174.088029 grey ostrich
## 24 2 0 157.684178 grey ostrich
## 25 2 0 135.249085 grey ostrich
## 26 2 1 9.295639 dark cement sparrow
## 27 2 1 11.266186 dark cement sparrow
## 28 2 1 9.336063 brown sparrow
## 29 2 1 10.169087 brown sparrow
## 30 2 1 11.060101 brown sparrow
klaR::partimat(Species~.,data=iris,method="lda")
Chapter-02-R-Tutorial file:///C:/Users/rk215/Documents/R-Tutorial.html#Learning_R_to_do_D...
28 of 31 10/18/2020, 4:30 AM

29. cat ("the sample proportions are")
## the sample proportions are
table(cdset$species)
##
## chicken ostrich parrot sparrow vulture
## 6 6 6 6 6
table(cdset$species)/sum(table(cdset$species))
Chapter-02-R-Tutorial file:///C:/Users/rk215/Documents/R-Tutorial.html#Learning_R_to_do_D...
29 of 31 10/18/2020, 4:30 AM

30. ##
## chicken ostrich parrot sparrow vulture
## 0.2 0.2 0.2 0.2 0.2
cat ("the training set proportions are")
## the training set proportions are
table(trdata$species)
##
## chicken ostrich parrot sparrow vulture
## 4 5 3 4 4
table(trdata$species)/sum(table(trdata$species))
##
## chicken ostrich parrot sparrow vulture
## 0.20 0.25 0.15 0.20 0.20
cat ("the test set proportions are")
## the test set proportions are
table(tstdata$species)
##
## chicken ostrich parrot sparrow vulture
## 2 1 3 2 2
table(tstdata$species)/sum(table(tstdata$species))
##
## chicken ostrich parrot sparrow vulture
## 0.2 0.1 0.3 0.2 0.2
Chapter-02-R-Tutorial file:///C:/Users/rk215/Documents/R-Tutorial.html#Learning_R_to_do_D...
30 of 31 10/18/2020, 4:30 AM

31. …
Chapter-02-R-Tutorial file:///C:/Users/rk215/Documents/R-Tutorial.html#Learning_R_to_do_D...
31 of 31 10/18/2020, 4:30 AM