inst/doc/dobin.R

## ----setup, include = FALSE---------------------------------------------------
knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>",
  fig.width=8, fig.height=6
)

## ----load2, echo=FALSE, eval=TRUE, message=FALSE------------------------------
if (!requireNamespace("dobin", quietly = TRUE)) {
    stop("Package dobin is needed for the vignette. Please install it.",
      call. = FALSE)
}
if (!requireNamespace("OutliersO3", quietly = TRUE)) {
    stop("Package OutliersO3 is needed for the vignette. Please install it.",
      call. = FALSE)
}
if (!requireNamespace("ggplot2", quietly = TRUE)) {
    stop("Package ggplot2 is needed for the vignette. Please install it.",
      call. = FALSE)
}

## ----install_dobin_cran, eval=FALSE-------------------------------------------
#   install.packages("dobin")

## ----install_dobin, eval=FALSE------------------------------------------------
#   install.packages("devtools")
#   devtools::install_github("sevvandi/dobin")

## ----load, echo=TRUE----------------------------------------------------------
library(dobin)
library(ggplot2)
library(OutliersO3)

## ----election2005, echo=FALSE-------------------------------------------------
data <- 
structure(list(Flaeche.km2. = c(2127.9, 2742.5, 2000.7, 2161, 
142.8, 1301.7, 664.2, 1333.4, 1532.7, 1350, 406.2, 4350, 2647.4, 
633.3, 3181.6, 3881.8, 4680.9, 3799.3, 119.7, 78.3, 49.8, 114.9, 
77.2, 315.4, 1399.7, 2596.5, 1367.6, 831.2, 1947.2, 2015.9, 1973.3, 
2351.2, 2230.7, 2487, 2857.7, 2390.1, 3271.4, 1916, 325.3, 1575, 
112.7, 91.3, 1131.7, 2998.8, 1824.1, 1621.9, 954.7, 1205.7, 1235.2, 
192.1, 1151.2, 2299.1, 1264, 153.9, 249.2, 5114.8, 3851.9, 2457.9, 
2828.4, 3383.3, 809.9, 3861.7, 2390.1, 1812.1, 2967.2, 4715.2, 
4021.2, 2001, 200.9, 1987.6, 2166, 1529.3, 135, 1700.1, 1989, 
39.5, 96.6, 89.3, 99.5, 102.5, 57.1, 53.1, 44.9, 26.6, 167.7, 
61.8, 52.3, 160.8, 547, 628, 940.6, 525.1, 1428.4, 128.3, 101.7, 
122.9, 141.2, 660.7, 492.8, 918.5, 437.6, 131.1, 130.8, 201.6, 
183.8, 223.3, 129.6, 87.4, 347.6, 170.4, 302.6, 563.2, 1232.1, 
883.6, 175.2, 123.4, 109.4, 124.7, 115.9, 67.7, 118.1, 165.1, 
388.2, 104.9, 976.5, 307.7, 994.9, 1258.9, 1091, 302.9, 1317.3, 
864.5, 293.1, 514.8, 1087.2, 759.9, 1686.4, 1312.8, 323.3, 245.4, 
103.1, 93.8, 126.1, 154.2, 347.1, 421.8, 1327.4, 1958.8, 1131.6, 
1158.8, 610.9, 2257, 170.9, 126.7, 1645.1, 2012.6, 1281, 1786.2, 
1653.6, 81.5, 453.3, 1509, 1622.3, 220.9, 602, 966.4, 613.6, 
1412, 2166.6, 357.5, 2121.8, 2262.6, 1262.5, 1153.4, 1586.6, 
2437.2, 812.6, 1240.9, 1171.3, 203.9, 840.6, 270.5, 85.6, 162.7, 
453.1, 241.4, 449.3, 1115.1, 719.6, 1908.7, 2126.2, 2550.6, 1778.9, 
445.2, 1083.4, 1412.6, 2616.4, 2250.2, 1268.8, 1337.1, 635, 2297.1, 
1640.4, 3100.7, 1208.1, 1508.3, 524.2, 876.6, 314.8, 866, 1696, 
1388.3, 1186, 1374.7, 1420.2, 1560, 1013.8, 2087.5, 87.5, 79.8, 
52.5, 90.7, 683.3, 1476.7, 2446.2, 2373.9, 2783, 1845.3, 2480.5, 
1599.8, 2159.3, 2244.9, 2650, 1473.8, 2984.6, 2582.6, 1003.1, 
1648.2, 1289.9, 1557, 1732.6, 3043, 641.4, 1638.6, 85.8, 141.4, 
1694.7, 761.6, 3114.8, 2037.3, 1561.3, 1056, 165.2, 1567.4, 2332.6, 
1683.6, 1914.7, 2328.5, 113.7, 93.6, 585.4, 208.7, 465.2, 642.4, 
513.4, 339.3, 642.4, 904.9, 2260.8, 838.7, 1644.8, 173.5, 718.4, 
879, 305.6, 145, 2430.7, 724.9, 506.6, 671.8, 1668.2, 452.9, 
1155.1, 1194.5, 1104.6, 1503.8, 1266.8, 818, 1861.4, 1094.2, 
788.9, 1476, 2423.4, 1152.5, 1982.8, 325.3, 891.4, 801.6, 550.4
), BDichte.je.km2. = c(134L, 86L, 115L, 116L, 1785L, 174L, 449L, 
223L, 146L, 219L, 566L, 62L, 86L, 369L, 77L, 65L, 56L, 61L, 3064L, 
3133L, 4970L, 2315L, 3762L, 1010L, 173L, 117L, 178L, 329L, 152L, 
134L, 124L, 129L, 128L, 99L, 105L, 135L, 87L, 137L, 801L, 165L, 
2239L, 2885L, 269L, 93L, 156L, 159L, 323L, 242L, 231L, 1280L, 
213L, 122L, 236L, 2216L, 1293L, 41L, 55L, 119L, 105L, 72L, 385L, 
66L, 108L, 136L, 81L, 49L, 71L, 122L, 1128L, 124L, 125L, 160L, 
1767L, 154L, 124L, 8131L, 2970L, 2749L, 2580L, 2814L, 4972L, 
6298L, 6803L, 12109L, 1399L, 4066L, 4921L, 1603L, 567L, 409L, 
290L, 632L, 227L, 2072L, 2746L, 2311L, 2209L, 475L, 573L, 316L, 
638L, 2305L, 2420L, 1614L, 1502L, 1030L, 2300L, 3142L, 842L, 
1537L, 918L, 540L, 249L, 305L, 1432L, 2111L, 2229L, 2324L, 2220L, 
3640L, 2158L, 1398L, 673L, 2576L, 279L, 901L, 262L, 196L, 231L, 
892L, 215L, 364L, 1158L, 591L, 251L, 303L, 170L, 247L, 940L, 
977L, 2842L, 2847L, 2269L, 1961L, 799L, 792L, 233L, 142L, 259L, 
258L, 482L, 122L, 1441L, 1990L, 171L, 128L, 192L, 117L, 160L, 
3276L, 676L, 157L, 167L, 1125L, 376L, 225L, 373L, 186L, 115L, 
832L, 112L, 112L, 201L, 246L, 190L, 129L, 306L, 266L, 253L, 1344L, 
397L, 990L, 3746L, 2004L, 557L, 1425L, 720L, 289L, 370L, 134L, 
116L, 98L, 148L, 615L, 276L, 160L, 109L, 113L, 255L, 188L, 401L, 
100L, 151L, 70L, 198L, 185L, 628L, 303L, 989L, 332L, 182L, 172L, 
234L, 160L, 173L, 176L, 328L, 160L, 3581L, 4065L, 5546L, 3535L, 
459L, 207L, 137L, 115L, 118L, 108L, 129L, 150L, 98L, 100L, 106L, 
211L, 93L, 86L, 227L, 129L, 161L, 153L, 127L, 105L, 364L, 199L, 
3173L, 1851L, 174L, 321L, 91L, 129L, 167L, 278L, 1743L, 203L, 
107L, 190L, 152L, 137L, 2497L, 3276L, 610L, 1154L, 617L, 402L, 
612L, 888L, 484L, 387L, 132L, 294L, 188L, 1638L, 387L, 321L, 
980L, 2121L, 119L, 369L, 512L, 469L, 170L, 657L, 266L, 234L, 
245L, 184L, 184L, 335L, 132L, 258L, 338L, 210L, 133L, 289L, 145L, 
861L, 313L, 292L, 479L), LebGeb.je.1000. = c(8.4, 9.2, 9.1, 8.9, 
8.6, 7.9, 8.5, 9.1, 7.6, 8.5, 8.6, 7.4, 7.8, 8, 6.7, 7.4, 7.4, 
7.1, 9.2, 9.2, 9.2, 9.2, 9.2, 9.2, 9.1, 9.7, 8.4, 9.2, 8.9, 8.3, 
9.6, 10, 11.4, 8.1, 9.5, 9, 8.8, 9.8, 8.6, 8.6, 8.6, 8.6, 8.6, 
8.6, 9.1, 8.2, 8.6, 8.5, 8, 8.2, 7.3, 7.4, 8.4, 8.4, 8.6, 6.6, 
6.7, 7.6, 6.7, 6.8, 9.6, 7.1, 6.8, 6.3, 6.4, 7, 6.6, 6.7, 7, 
6.5, 6.2, 6.2, 8.1, 6.5, 6.3, 8.5, 8.5, 8.5, 8.5, 8.5, 8.5, 8.5, 
8.5, 8.5, 8.5, 8.5, 8.5, 9, 9.1, 8.8, 8.6, 8.4, 8.7, 9.8, 9.8, 
9.8, 10.1, 8.8, 8.8, 9.3, 8.7, 9, 8.4, 8.5, 8.2, 8.2, 9.1, 9.1, 
8.8, 8.7, 8.3, 8.2, 8.7, 8, 8, 8.6, 8.6, 7.7, 7.6, 8.1, 8.1, 
8.1, 8.1, 8.5, 9.6, 8.1, 10, 9.1, 9.6, 9.7, 9.7, 10.1, 9.6, 8.9, 
9.4, 9.5, 8.8, 10.4, 9.1, 7.8, 7.7, 7.9, 8.5, 8.5, 8.3, 9.2, 
9.1, 9.2, 8.7, 9.2, 8.7, 7.3, 7.9, 7.9, 6.7, 7.1, 7, 7.2, 7.4, 
9.3, 7.7, 7.3, 6.8, 7.1, 6.9, 7.1, 7, 6.7, 7.9, 8.4, 7.7, 7.9, 
8.4, 8.6, 8.4, 9.5, 9.1, 8.9, 8.8, 10, 8.7, 9.6, 10, 10, 9.5, 
9.6, 9.1, 8.5, 8.2, 7.4, 7.7, 7.2, 7, 8.4, 7.1, 6.3, 6.5, 6.4, 
8.7, 8, 9.2, 8.2, 8.1, 8.3, 8.6, 8.6, 9.2, 9, 8.2, 8.3, 8.3, 
7.6, 8, 8.8, 9.5, 10.2, 9.2, 10, 10.2, 10.2, 10.2, 10.2, 9.2, 
9.1, 9, 7.9, 8.8, 8.6, 9.4, 8.4, 8.9, 8.7, 8.7, 8.8, 8.7, 8.4, 
8.8, 8.2, 7.7, 7.5, 7.8, 8.9, 8.9, 8.7, 8.7, 7.6, 8.2, 8.7, 8.7, 
8.4, 8.6, 8.1, 9.6, 9.1, 9.3, 9.8, 8.7, 9.2, 9, 9, 10.1, 9.4, 
9.4, 8.6, 9.6, 9.9, 9.9, 9.4, 9.5, 9.3, 9.3, 9, 8.4, 8.2, 8.4, 
8.8, 8.9, 8.8, 8.4, 8.7, 9.3, 9.2, 8.6, 9.2, 8.9, 9.6, 8.8, 8.4, 
8.6, 9.3, 9.9, 10, 9.6, 9.1, 8.8, 7.4, 7.4, 6.8, 6.7), KFZ.je.1000. = c(664, 
727.9, 544.8, 706.5, 526.2, 641.7, 648.4, 739.2, 673.2, 698.5, 
529, 646.5, 606.2, 468.9, 602.7, 612.3, 649.3, 635.9, 546.4, 
546.4, 546.4, 546.4, 546.4, 546.4, 627.7, 653.6, 656.2, 647.1, 
674.6, 711.6, 702.2, 675.8, 673.6, 744.9, 753.4, 726.8, 663.2, 
695.6, 554.6, 779.8, 481, 481, 666.7, 676.9, 692.4, 680.4, 666.7, 
637.5, 639.3, 600.7, 756.8, 692.9, 601, 516, 494, 675.5, 640.3, 
634, 663.7, 665.5, 463.7, 678.2, 629.7, 637.2, 662.4, 649.6, 
678.3, 602, 510.6, 613.3, 602.3, 656.5, 443.1, 627.6, 634.5, 
424.5, 424.5, 424.5, 424.5, 424.5, 424.5, 424.5, 424.5, 424.5, 
424.5, 424.5, 424.5, 570.6, 570.6, 647.7, 859.4, 640, 705.3, 
572.8, 572.8, 572.8, 587.1, 640.4, 640.4, 683.8, 694.5, 600.5, 
560.1, 617.4, 647.4, 647.4, 600, 600, 666.1, 597.1, 562.5, 673.7, 
653.7, 653, 653, 540.7, 540.7, 569.4, 629, 565.9, 565.9, 597.4, 
597.4, 518.2, 651.5, 626.9, 633.8, 660.3, 651.5, 593.1, 654.3, 
690.2, 569.8, 697.6, 707.8, 665.2, 675.7, 639.1, 578.9, 650.3, 
568.4, 517.4, 547.2, 547.2, 606.9, 563.4, 657.6, 672.6, 680.5, 
667.9, 642.1, 660.9, 441, 441, 655.3, 655.8, 604.5, 669.3, 660, 
495, 625.4, 668.1, 683.6, 592.4, 655.3, 645.3, 632.6, 678.4, 
728.7, 526, 738.8, 757, 641.9, 704.6, 699.4, 722.3, 733, 692.9, 
719.4, 746.9, 686.9, 740.9, 592.2, 592.2, 736.3, 657.9, 674.6, 
716.3, 725.5, 637.9, 639.4, 660.6, 626.2, 524.4, 568.5, 667.5, 
678.8, 688.1, 702.2, 705.7, 645.4, 769, 699.8, 803.6, 675.1, 
733.1, 754.2, 700.5, 631.1, 707, 684.5, 706, 738.3, 728.9, 731.8, 
750.8, 668.6, 772.2, 630.3, 630.3, 630.3, 630.3, 764.9, 720.3, 
749.1, 732.9, 739, 774.4, 753.2, 749.5, 836.4, 758, 737.5, 728.5, 
812, 767.1, 741.9, 721.3, 721.2, 718.9, 766.9, 785.3, 679.2, 
707.6, 588.8, 753.4, 750.3, 703.8, 768.1, 726.7, 725.5, 657.4, 
570.4, 736.3, 773.4, 733.4, 736, 754.6, 597.2, 597.2, 725, 704.4, 
704.4, 698.3, 695.7, 683.7, 683.7, 737.6, 781.2, 703.9, 703.9, 
595, 691.6, 723.5, 492.1, 580.9, 732.4, 684, 691.6, 650.8, 697.5, 
493.8, 691.5, 700.7, 715.1, 721.3, 700.7, 642.8, 727.6, 703.7, 
621.5, 685.3, 728.3, 724.5, 742.9, 670, 717.9, 717.3, 724.6)), class = "data.frame", row.names = c(NA, 
-299L))

## ----ex1_dobin----------------------------------------------------------------
names(data) <- c("Area", "Population_density", "Birthrate", "Car_ownership")
out <- dobin(data, frac=0.9, norm=3)

labs <- rep("norm", dim(out$coords)[1])
inds <- which(out$coords[, 1] > 5)
labs[inds] <- "out"
df <- as.data.frame(out$coords[, 1:2])
colnames(df) <- c("DC1", "DC2")
df2 <- df[inds, ]
ggplot(df, aes(x=DC1,y=DC2)) + geom_point(aes(shape=labs, color=labs), size=2 ) + geom_text(data=df2, aes(DC1, DC2, label = inds), nudge_x = 0.5) + theme_bw()

## ----ex2_dobin----------------------------------------------------------------
out$vec[ ,1]

## ----ex1_o3-------------------------------------------------------------------
O3y <- OutliersO3::O3prep(data, method=c("HDo", "PCS", "BAC", "adjOut", "DDC", "MCD"))
O3y1 <- OutliersO3::O3plotM(O3y)
O3y1$gO3

## ----diamonds-----------------------------------------------------------------
data(diamonds, package="ggplot2")
data <- diamonds[1:5000, c(1, 5, 6, 8:10)]

out <- dobin(data, frac=0.9, norm=3)
autoplot(out)

kk <- min(ceiling(dim(data)[1]/10),25)
knn_dist <- FNN::knn.dist(out$coords[, 1:3], k = kk)
knn_dist <- knn_dist[ ,kk]
ord <- order(knn_dist, decreasing=TRUE)
ord[1:4]

## ----diamonds2----------------------------------------------------------------
labs <- rep("norm", length(ord))
labs[ord[1:4]] <- "out"
df <- as.data.frame(out$coords[, 1:2])
colnames(df) <- c("DB1", "DB2")
df2 <- df[ord[1:4], ]
ggplot(df, aes(x=DB1,y=DB2)) + geom_point(aes(shape=labs, color=labs), size=2 ) + geom_text(data=df2, aes(DB1, DB2, label = ord[1:4]), nudge_x = 0.5) + theme_bw()

pPa <- O3prep(data, k1=5, method=c("HDo", "PCS", "adjOut"), tolHDo = 0.001, tolPCS=0.001, toladj=0.001, boxplotLimits=10)
pPx <- O3plotM(pPa)
pPx$gO3x + theme(plot.margin = unit(c(0, 2, 0, 0), "cm"))

Try the dobin package in your browser

Any scripts or data that you put into this service are public.

dobin documentation built on Aug. 26, 2022, 1:06 a.m.