R version 4.2.1 (2022-06-23 ucrt) -- "Funny-Looking Kid"
Copyright (C) 2022 The R Foundation for Statistical Computing
Platform: x86_64-w64-mingw32/x64 (64-bit)
R is free software and comes with ABSOLUTELY NO WARRANTY.
You are welcome to redistribute it under certain conditions.
Type 'license()' or 'licence()' for distribution details.
R is a collaborative project with many contributors.
Type 'contributors()' for more information and
'citation()' on how to cite R or R packages in publications.
Type 'demo()' for some demos, 'help()' for on-line help, or
'help.start()' for an HTML browser interface to help.
Type 'q()' to quit R.
> library(classInt)
> set.seed(1)
> data_censored<-c(rep(0,10), rnorm(100, mean=20,sd=1),rep(26,10))
> cl2<-classIntervals(data_censored, n=4, style="fixed",dataPrecision=2,fixedBreaks=c(-1,1,19,25,30))
>
> print(cl2, unique=FALSE)
style: fixed
one of 166,650 possible partitions of this variable into 4 classes
[-1,1) [1,19) [19,25) [25,30]
10 11 89 10
> print(cl2, unique=TRUE)
style: fixed
one of 166,650 possible partitions of this variable into 4 classes
Class found with one single (possibly repeated) value: changed label
0 [1,19) [19,25) 26
10 11 89 10
>
> ### example from man page
> classIntervals(data_censored, n=5, style="fixed", fixedBreaks=c(15.57, 25, 50, 75, 100, 155.30))
style: fixed
one of 4,082,925 possible partitions of this variable into 5 classes
[15.57,25) [25,50) [50,75) [75,100) [100,155.3]
110 10 0 0 0
Warning message:
In classIntervals(data_censored, n = 5, style = "fixed", fixedBreaks = c(15.57, :
variable range greater than fixedBreaks
>
> print(classIntervals(data_censored, n=5, style="sd"), unique=FALSE)
style: sd
one of 79,208,745 possible partitions of this variable into 6 classes
[-5.126688,0.8860022) [0.8860022,6.898692) [6.898692,12.91138)
10 0 0
[12.91138,18.92407) [18.92407,24.93676) [24.93676,30.94945]
10 90 10
> print(classIntervals(data_censored, n=5, style="sd"), unique=TRUE)
style: sd
one of 79,208,745 possible partitions of this variable into 6 classes
Class found with one single (possibly repeated) value: changed label
0 [0.8860022,6.898692) [6.898692,12.91138)
10 0 0
[12.91138,18.92407) [18.92407,24.93676) 26
10 90 10
> print(classIntervals(data_censored, n=5, style="equal"), unique=TRUE)
style: equal
one of 4,082,925 possible partitions of this variable into 5 classes
Class found with one single (possibly repeated) value: changed label
0 [5.2,10.4) [10.4,15.6) [15.6,20.8) [20.8,26]
10 0 0 81 29
> print(classIntervals(data_censored, n=5, style="quantile"), unique=TRUE)
style: quantile
one of 4,082,925 possible partitions of this variable into 5 classes
[0,19.24129) [19.24129,19.87857) [19.87857,20.39315) [20.39315,21.07048)
24 24 24 24
[21.07048,26]
24
> set.seed(1)
> print(classIntervals(data_censored, n=5, style="kmeans"), unique=TRUE)
style: kmeans
one of 4,082,925 possible partitions of this variable into 5 classes
Class found with one single (possibly repeated) value: changed label
0 [8.89265,19.11514) [19.11514,20.31048) [20.31048,24.20081)
10 12 43 45
26
10
> print(classIntervals(data_censored, n=5, style="hclust", method="complete"), unique=TRUE)
style: hclust
one of 4,082,925 possible partitions of this variable into 5 classes
Class found with one single (possibly repeated) value: changed label
0 [8.89265,19.01088) [19.01088,21.00347) [21.00347,24.20081)
10 11 74 15
26
10
> print(classIntervals(data_censored, n=5, style="hclust", method="single"), unique=TRUE)
style: hclust
one of 4,082,925 possible partitions of this variable into 5 classes
Class found with one single (possibly repeated) value: changed label
0 [8.89265,18.33574) [18.33574,21.78784) [21.78784,24.20081)
10 3 94 3
26
10
> print(classIntervals(data_censored, n=5, style="fisher"), unique=TRUE)
style: fisher
one of 4,082,925 possible partitions of this variable into 5 classes
Class found with one single (possibly repeated) value: changed label
0 [8.89265,19.72123) [19.72123,20.85116) [20.85116,24.20081)
10 33 49 18
26
10
> print(classIntervals(data_censored, n=5, style="jenks"), unique=TRUE)
style: jenks
one of 4,082,925 possible partitions of this variable into 5 classes
Class found with one single (possibly repeated) value: changed label
0 (0,19.69582] (19.69582,20.82122] (20.82122,22.40162]
10 33 49 18
26
10
>
> print(classIntervals(data_censored, n=5, style="fixed", fixedBreaks=c(15.57, 25, 50, 75, 100, 155.30)), unique=TRUE)
style: fixed
one of 4,082,925 possible partitions of this variable into 5 classes
Class found with one single (possibly repeated) value: changed label
[15.57,25) 26 [50,75) [75,100) [100,155.3]
110 10 0 0 0
Warning message:
In classIntervals(data_censored, n = 5, style = "fixed", fixedBreaks = c(15.57, :
variable range greater than fixedBreaks
> print(classIntervals(data_censored, n=5, style="sd"), unique=TRUE)
style: sd
one of 79,208,745 possible partitions of this variable into 6 classes
Class found with one single (possibly repeated) value: changed label
0 [0.8860022,6.898692) [6.898692,12.91138)
10 0 0
[12.91138,18.92407) [18.92407,24.93676) 26
10 90 10
> print(classIntervals(data_censored, n=5, style="equal"), unique=TRUE)
style: equal
one of 4,082,925 possible partitions of this variable into 5 classes
Class found with one single (possibly repeated) value: changed label
0 [5.2,10.4) [10.4,15.6) [15.6,20.8) [20.8,26]
10 0 0 81 29
> print(classIntervals(data_censored, n=5, style="quantile"), unique=TRUE)
style: quantile
one of 4,082,925 possible partitions of this variable into 5 classes
[0,19.24129) [19.24129,19.87857) [19.87857,20.39315) [20.39315,21.07048)
24 24 24 24
[21.07048,26]
24
> set.seed(1)
> print(classIntervals(data_censored, n=5, style="kmeans"), unique=TRUE)
style: kmeans
one of 4,082,925 possible partitions of this variable into 5 classes
Class found with one single (possibly repeated) value: changed label
0 [8.89265,19.11514) [19.11514,20.31048) [20.31048,24.20081)
10 12 43 45
26
10
> set.seed(1)
> print(classIntervals(data_censored, n=5, style="kmeans", intervalClosure="right"), unique=TRUE)
style: kmeans
one of 4,082,925 possible partitions of this variable into 5 classes
Class found with one single (possibly repeated) value: changed label
0 (8.89265,19.11514] (19.11514,20.31048] (20.31048,24.20081]
10 12 43 45
26
10
> set.seed(1)
> print(classIntervals(data_censored, n=5, style="kmeans", dataPrecision=0), unique=TRUE)
style: kmeans
one of 4,082,925 possible partitions of this variable into 5 classes
Class found with one single (possibly repeated) value: changed label
0 [9,20) [20,21) [21,25) 26
10 12 43 45 10
> set.seed(1)
> print(classIntervals(data_censored, n=5, style="kmeans"), cutlabels=FALSE, unique=TRUE)
style: kmeans
one of 4,082,925 possible partitions of this variable into 5 classes
Class found with one single (possibly repeated) value: changed label
0 8.89265 - 19.11514 19.11514 - 20.31048 20.31048 - 24.20081
10 12 43 45
26
10
> print(classIntervals(data_censored, n=5, style="hclust", method="complete"), unique=TRUE)
style: hclust
one of 4,082,925 possible partitions of this variable into 5 classes
Class found with one single (possibly repeated) value: changed label
0 [8.89265,19.01088) [19.01088,21.00347) [21.00347,24.20081)
10 11 74 15
26
10
> print(classIntervals(data_censored, n=5, style="hclust", method="single"), unique=TRUE)
style: hclust
one of 4,082,925 possible partitions of this variable into 5 classes
Class found with one single (possibly repeated) value: changed label
0 [8.89265,18.33574) [18.33574,21.78784) [21.78784,24.20081)
10 3 94 3
26
10
> print(classIntervals(data_censored, n=5, style="fisher"), unique=TRUE)
style: fisher
one of 4,082,925 possible partitions of this variable into 5 classes
Class found with one single (possibly repeated) value: changed label
0 [8.89265,19.72123) [19.72123,20.85116) [20.85116,24.20081)
10 33 49 18
26
10
> print(classIntervals(data_censored, n=5, style="jenks"), unique=TRUE)
style: jenks
one of 4,082,925 possible partitions of this variable into 5 classes
Class found with one single (possibly repeated) value: changed label
0 (0,19.69582] (19.69582,20.82122] (20.82122,22.40162]
10 33 49 18
26
10
> print(classIntervals(data_censored, style="headtails"), unique=TRUE)
style: headtails
one of 101 possible partitions of this variable into 2 classes
[0,18.92407) [18.92407,26]
20 100
> print(classIntervals(data_censored, style="headtails", thr = 1))
style: headtails
one of 166,650 possible partitions of this variable into 4 classes
[0,18.92407) [18.92407,20.86153) [20.86153,23.03872) [23.03872,26]
20 72 18 10
> print(classIntervals(data_censored, style="headtails", thr = 0))
style: headtails
one of 101 possible partitions of this variable into 2 classes
[0,18.92407) [18.92407,26]
20 100
> print(classIntervals(data_censored, style="box", iqr_mult = 0))
style: box
one of 79,208,745 possible partitions of this variable into 6 classes
[0,19.38567) [19.38567,19.38567) [19.38567,20.11391) [20.11391,20.77193)
30 0 30 30
[20.77193,20.77193) [20.77193,26]
0 30
> print(classIntervals(data_censored, style="box"))
style: box
one of 79,208,745 possible partitions of this variable into 6 classes
[0,17.30627) [17.30627,19.38567) [19.38567,20.11391) [20.11391,20.77193)
10 20 30 30
[20.77193,22.85133) [22.85133,26]
20 10
> x <- c(0, 0, 0, 1, 2, 50)
> print(classIntervals(x, n=3, style="fisher"), unique=TRUE)
style: fisher
one of 3 possible partitions of this variable into 3 classes
Class found with one single (possibly repeated) value: changed label
0 [0.5,26) 50
3 2 1
> print(classIntervals(x, n=3, style="jenks"), unique=TRUE)
style: jenks
one of 3 possible partitions of this variable into 3 classes
Class found with one single (possibly repeated) value: changed label
0 (0,2] 50
3 2 1
> if (getRversion() > "3.5.3") {
+ suppressWarnings(set.seed(1, sample.kind=c("Rounding")))
+ } else {
+ set.seed(1)
+ }
> print(classIntervals(data_censored, n=5, style="bclust", verbose=FALSE), unique=TRUE)
style: bclust
one of 4,082,925 possible partitions of this variable into 5 classes
Class found with one single (possibly repeated) value: changed label
0 [8.89265,19.01088) [19.01088,21.00347) [21.00347,24.20081)
10 11 74 15
26
10
> print(classIntervals(data_censored, n=5, style="bclust", hclust.method="complete", verbose=FALSE), unique=TRUE)
style: bclust
one of 4,082,925 possible partitions of this variable into 5 classes
Class found with one single (possibly repeated) value: changed label
0 [8.89265,19.79106) [19.79106,21.28327) [21.28327,24.20081)
10 34 57 9
26
10
>
> # the log-likelihood returns a valid logLik object.
> stopifnot(
+ identical(
+ round(logLik(classIntervals(rep(1:3, each=10), n=2, style="jenks")), 5),
+ structure(-14.52876, df = 2, nobs = 30L, class = "logLik")
+ )
+ )
> # logLik for exact intervals (a single value is the unique member of an
> # interval) yields a likelihood of zero.
> stopifnot(
+ identical(
+ suppressWarnings(logLik(classIntervals(rep(1:3, each=10), n=3, style="jenks"))),
+ structure(0, df = 3, nobs = 30L, class = "logLik")
+ )
+ )
>
> proc.time()
user system elapsed
0.37 0.06 0.68
Generated by dwww version 1.15 on Sat May 18 11:57:30 CEST 2024.