sciruby 0.1.0 → 0.1.3
Sign up to get free protection for your applications and to get access to all the features.
- data/.autotest +23 -0
- data/.gemtest +0 -0
- data/History.txt +6 -0
- data/Manifest.txt +119 -0
- data/Rakefile +178 -0
- data/bin/sciruby-plotter +12 -0
- data/data/r/man/AirPassengers.Rd +51 -0
- data/data/r/man/BJsales.Rd +34 -0
- data/data/r/man/BOD.Rd +53 -0
- data/data/r/man/ChickWeight.Rd +68 -0
- data/data/r/man/DNase.Rd +63 -0
- data/data/r/man/EuStockMarkets.Rd +28 -0
- data/data/r/man/Formaldehyde.Rd +44 -0
- data/data/r/man/HairEyeColor.Rd +77 -0
- data/data/r/man/Harman23.cor.Rd +25 -0
- data/data/r/man/Harman74.cor.Rd +28 -0
- data/data/r/man/Indometh.Rd +57 -0
- data/data/r/man/InsectSprays.Rd +45 -0
- data/data/r/man/JohnsonJohnson.Rd +37 -0
- data/data/r/man/LakeHuron.Rd +27 -0
- data/data/r/man/LifeCycleSavings.Rd +54 -0
- data/data/r/man/Loblolly.Rd +56 -0
- data/data/r/man/Nile.Rd +78 -0
- data/data/r/man/Orange.Rd +57 -0
- data/data/r/man/OrchardSprays.Rd +62 -0
- data/data/r/man/PlantGrowth.Rd +39 -0
- data/data/r/man/Puromycin.Rd +84 -0
- data/data/r/man/Theoph.Rd +84 -0
- data/data/r/man/Titanic.Rd +73 -0
- data/data/r/man/ToothGrowth.Rd +40 -0
- data/data/r/man/UCBAdmissions.Rd +68 -0
- data/data/r/man/UKDriverDeaths.Rd +72 -0
- data/data/r/man/UKLungDeaths.Rd +40 -0
- data/data/r/man/UKgas.Rd +25 -0
- data/data/r/man/USAccDeaths.Rd +23 -0
- data/data/r/man/USArrests.Rd +45 -0
- data/data/r/man/USJudgeRatings.Rd +38 -0
- data/data/r/man/USPersonalExpenditure.Rd +33 -0
- data/data/r/man/VADeaths.Rd +51 -0
- data/data/r/man/WWWusage.Rd +41 -0
- data/data/r/man/WorldPhones.Rd +40 -0
- data/data/r/man/ability.cov.Rd +50 -0
- data/data/r/man/airmiles.Rd +29 -0
- data/data/r/man/airquality.Rd +56 -0
- data/data/r/man/anscombe.Rd +62 -0
- data/data/r/man/attenu.Rd +66 -0
- data/data/r/man/attitude.Rd +48 -0
- data/data/r/man/austres.Rd +22 -0
- data/data/r/man/beavers.Rd +73 -0
- data/data/r/man/cars.Rd +59 -0
- data/data/r/man/chickwts.Rd +47 -0
- data/data/r/man/co2.Rd +43 -0
- data/data/r/man/crimtab.Rd +129 -0
- data/data/r/man/datasets-package.Rd +24 -0
- data/data/r/man/discoveries.Rd +30 -0
- data/data/r/man/esoph.Rd +66 -0
- data/data/r/man/euro.Rd +56 -0
- data/data/r/man/eurodist.Rd +25 -0
- data/data/r/man/faithful.Rd +63 -0
- data/data/r/man/freeny.Rd +56 -0
- data/data/r/man/infert.Rd +56 -0
- data/data/r/man/iris.Rd +62 -0
- data/data/r/man/islands.Rd +29 -0
- data/data/r/man/lh.Rd +22 -0
- data/data/r/man/longley.Rd +56 -0
- data/data/r/man/lynx.Rd +33 -0
- data/data/r/man/morley.Rd +50 -0
- data/data/r/man/mtcars.Rd +44 -0
- data/data/r/man/nhtemp.Rd +30 -0
- data/data/r/man/nottem.Rd +30 -0
- data/data/r/man/occupationalStatus.Rd +44 -0
- data/data/r/man/precip.Rd +31 -0
- data/data/r/man/presidents.Rd +36 -0
- data/data/r/man/pressure.Rd +41 -0
- data/data/r/man/quakes.Rd +40 -0
- data/data/r/man/randu.Rd +46 -0
- data/data/r/man/rivers.Rd +21 -0
- data/data/r/man/rock.Rd +34 -0
- data/data/r/man/sleep.Rd +51 -0
- data/data/r/man/stackloss.Rd +77 -0
- data/data/r/man/state.Rd +80 -0
- data/data/r/man/sunspot.month.Rd +49 -0
- data/data/r/man/sunspot.year.Rd +26 -0
- data/data/r/man/sunspots.Rd +33 -0
- data/data/r/man/swiss.Rd +79 -0
- data/data/r/man/treering.Rd +38 -0
- data/data/r/man/trees.Rd +48 -0
- data/data/r/man/uspop.Rd +27 -0
- data/data/r/man/volcano.Rd +31 -0
- data/data/r/man/warpbreaks.Rd +56 -0
- data/data/r/man/women.Rd +40 -0
- data/data/r/man/zCO2.Rd +81 -0
- data/lib/ext/csv.rb +22 -0
- data/lib/ext/shoes.rb +131 -0
- data/lib/ext/string.rb +39 -0
- data/lib/sciruby.rb +50 -4
- data/lib/sciruby/analysis.rb +98 -0
- data/lib/sciruby/analysis/suite.rb +87 -0
- data/lib/sciruby/analysis/suite_report_builder.rb +44 -0
- data/lib/sciruby/config.rb +93 -0
- data/lib/sciruby/data.rb +168 -0
- data/lib/sciruby/data/guardian.rb +96 -0
- data/lib/sciruby/data/r.rb +155 -0
- data/lib/sciruby/data/r/base.rb +110 -0
- data/lib/sciruby/data/r/data_frame.rb +24 -0
- data/lib/sciruby/data/r/grouped_data.rb +7 -0
- data/lib/sciruby/data/r/list.rb +20 -0
- data/lib/sciruby/data/r/multi_time_series.rb +24 -0
- data/lib/sciruby/data/r/r_matrix.rb +7 -0
- data/lib/sciruby/data/r/time_series.rb +19 -0
- data/lib/sciruby/data/r/time_series_base.rb +40 -0
- data/lib/sciruby/data/r/vector.rb +125 -0
- data/lib/sciruby/editor.rb +82 -0
- data/lib/sciruby/plotter.rb +128 -0
- data/lib/sciruby/recommend.rb +4 -0
- data/lib/sciruby/validation.rb +368 -0
- data/readme.md +75 -0
- data/static/sciruby-icon.png +0 -0
- data/test/helpers_tests.rb +58 -0
- data/test/test_recommend.rb +16 -0
- metadata +396 -20
@@ -0,0 +1,30 @@
|
|
1
|
+
% File src/library/datasets/man/discoveries.Rd
|
2
|
+
% Part of the R package, http://www.R-project.org
|
3
|
+
% Copyright 1995-2007 R Core Development Team
|
4
|
+
% Distributed under GPL 2 or later
|
5
|
+
|
6
|
+
\name{discoveries}
|
7
|
+
\docType{data}
|
8
|
+
\alias{discoveries}
|
9
|
+
\title{Yearly Numbers of Important Discoveries}
|
10
|
+
\description{
|
11
|
+
The numbers of \dQuote{great} inventions and scientific
|
12
|
+
discoveries in each year from 1860 to 1959.
|
13
|
+
}
|
14
|
+
\usage{discoveries}
|
15
|
+
\format{A time series of 100 values.}
|
16
|
+
\source{
|
17
|
+
The World Almanac and Book of Facts, 1975 Edition, pages 315--318.
|
18
|
+
}
|
19
|
+
\references{
|
20
|
+
McNeil, D. R. (1977)
|
21
|
+
\emph{Interactive Data Analysis}.
|
22
|
+
Wiley.
|
23
|
+
}
|
24
|
+
\examples{
|
25
|
+
require(graphics)
|
26
|
+
plot(discoveries, ylab = "Number of important discoveries",
|
27
|
+
las = 1)
|
28
|
+
title(main = "discoveries data set")
|
29
|
+
}
|
30
|
+
\keyword{datasets}
|
data/data/r/man/esoph.Rd
ADDED
@@ -0,0 +1,66 @@
|
|
1
|
+
% File src/library/datasets/man/esoph.Rd
|
2
|
+
% Part of the R package, http://www.R-project.org
|
3
|
+
% Copyright 1995-2007 R Core Development Team
|
4
|
+
% Distributed under GPL 2 or later
|
5
|
+
|
6
|
+
\name{esoph}
|
7
|
+
\docType{data}
|
8
|
+
\alias{esoph}
|
9
|
+
\title{Smoking, Alcohol and (O)esophageal Cancer}
|
10
|
+
\description{
|
11
|
+
Data from a case-control study of (o)esophageal cancer in
|
12
|
+
Ile-et-Vilaine, France.
|
13
|
+
}
|
14
|
+
\usage{esoph}
|
15
|
+
\format{
|
16
|
+
A data frame with records for 88 age/alcohol/tobacco combinations.
|
17
|
+
|
18
|
+
\tabular{rlll}{
|
19
|
+
[,1] \tab "agegp" \tab Age group \tab 1 25--34 years\cr
|
20
|
+
\tab \tab \tab 2 35--44\cr
|
21
|
+
\tab \tab \tab 3 45--54\cr
|
22
|
+
\tab \tab \tab 4 55--64\cr
|
23
|
+
\tab \tab \tab 5 65--74\cr
|
24
|
+
\tab \tab \tab 6 75+\cr
|
25
|
+
[,2] \tab "alcgp" \tab Alcohol consumption \tab 1 0--39 gm/day\cr
|
26
|
+
\tab \tab \tab 2 40--79\cr
|
27
|
+
\tab \tab \tab 3 80--119\cr
|
28
|
+
\tab \tab \tab 4 120+\cr
|
29
|
+
[,3] \tab "tobgp" \tab Tobacco consumption \tab 1 0-- 9 gm/day\cr
|
30
|
+
\tab \tab \tab 2 10--19\cr
|
31
|
+
\tab \tab \tab 3 20--29\cr
|
32
|
+
\tab \tab \tab 4 30+\cr
|
33
|
+
[,4] \tab "ncases" \tab Number of cases \tab \cr
|
34
|
+
[,5] \tab "ncontrols" \tab Number of controls \tab
|
35
|
+
}
|
36
|
+
}
|
37
|
+
\source{
|
38
|
+
Breslow, N. E. and Day, N. E. (1980)
|
39
|
+
\emph{Statistical Methods in Cancer Research. 1: The Analysis of
|
40
|
+
Case-Control Studies.} IARC Lyon / Oxford University Press.
|
41
|
+
}
|
42
|
+
\author{Thomas Lumley}
|
43
|
+
\examples{
|
44
|
+
require(stats)
|
45
|
+
require(graphics) # for mosaicplot
|
46
|
+
summary(esoph)
|
47
|
+
## effects of alcohol, tobacco and interaction, age-adjusted
|
48
|
+
model1 <- glm(cbind(ncases, ncontrols) ~ agegp + tobgp * alcgp,
|
49
|
+
data = esoph, family = binomial())
|
50
|
+
anova(model1)
|
51
|
+
## Try a linear effect of alcohol and tobacco
|
52
|
+
model2 <- glm(cbind(ncases, ncontrols) ~ agegp + unclass(tobgp)
|
53
|
+
+ unclass(alcgp),
|
54
|
+
data = esoph, family = binomial())
|
55
|
+
summary(model2)
|
56
|
+
## Re-arrange data for a mosaic plot
|
57
|
+
ttt <- table(esoph$agegp, esoph$alcgp, esoph$tobgp)
|
58
|
+
o <- with(esoph, order(tobgp, alcgp, agegp))
|
59
|
+
ttt[ttt == 1] <- esoph$ncases[o]
|
60
|
+
tt1 <- table(esoph$agegp, esoph$alcgp, esoph$tobgp)
|
61
|
+
tt1[tt1 == 1] <- esoph$ncontrols[o]
|
62
|
+
tt <- array(c(ttt, tt1), c(dim(ttt),2),
|
63
|
+
c(dimnames(ttt), list(c("Cancer", "control"))))
|
64
|
+
mosaicplot(tt, main = "esoph data set", color = TRUE)
|
65
|
+
}
|
66
|
+
\keyword{datasets}
|
data/data/r/man/euro.Rd
ADDED
@@ -0,0 +1,56 @@
|
|
1
|
+
% File src/library/datasets/man/euro.Rd
|
2
|
+
% Part of the R package, http://www.R-project.org
|
3
|
+
% Copyright 1995-2007 R Core Development Team
|
4
|
+
% Distributed under GPL 2 or later
|
5
|
+
|
6
|
+
\name{euro}
|
7
|
+
\docType{data}
|
8
|
+
\alias{euro}
|
9
|
+
\alias{euro.cross}
|
10
|
+
\title{Conversion Rates of Euro Currencies}
|
11
|
+
\description{Conversion rates between the various Euro currencies.}
|
12
|
+
\usage{
|
13
|
+
euro
|
14
|
+
euro.cross
|
15
|
+
}
|
16
|
+
\format{
|
17
|
+
\code{euro} is a named vector of length 11, \code{euro.cross} a
|
18
|
+
matrix of size 11 by 11, with dimnames.
|
19
|
+
}
|
20
|
+
\details{
|
21
|
+
The data set \code{euro} contains the value of 1 Euro in all
|
22
|
+
currencies participating in the European monetary union (Austrian
|
23
|
+
Schilling ATS, Belgian Franc BEF, German Mark DEM, Spanish Peseta ESP,
|
24
|
+
Finnish Markka FIM, French Franc FRF, Irish Punt IEP, Italian Lira
|
25
|
+
ITL, Luxembourg Franc LUF, Dutch Guilder NLG and Portuguese Escudo
|
26
|
+
PTE). These conversion rates were fixed by the European Union on
|
27
|
+
December 31, 1998. To convert old prices to Euro prices, divide by
|
28
|
+
the respective rate and round to 2 digits.
|
29
|
+
|
30
|
+
The data set \code{euro.cross} contains conversion rates between the
|
31
|
+
various Euro currencies, i.e., the result of
|
32
|
+
\code{outer(1 / euro, euro)}.
|
33
|
+
}
|
34
|
+
\examples{
|
35
|
+
cbind(euro)
|
36
|
+
|
37
|
+
## These relations hold:
|
38
|
+
euro == signif(euro,6) # [6 digit precision in Euro's definition]
|
39
|
+
all(euro.cross == outer(1/euro, euro))
|
40
|
+
|
41
|
+
## Convert 20 Euro to Belgian Franc
|
42
|
+
20 * euro["BEF"]
|
43
|
+
## Convert 20 Austrian Schilling to Euro
|
44
|
+
20 / euro["ATS"]
|
45
|
+
## Convert 20 Spanish Pesetas to Italian Lira
|
46
|
+
20 * euro.cross["ESP", "ITL"]
|
47
|
+
|
48
|
+
require(graphics)
|
49
|
+
dotchart(euro,
|
50
|
+
main = "euro data: 1 Euro in currency unit")
|
51
|
+
dotchart(1/euro,
|
52
|
+
main = "euro data: 1 currency unit in Euros")
|
53
|
+
dotchart(log(euro, 10),
|
54
|
+
main = "euro data: log10(1 Euro in currency unit)")
|
55
|
+
}
|
56
|
+
\keyword{datasets}
|
@@ -0,0 +1,25 @@
|
|
1
|
+
% File src/library/datasets/man/eurodist.Rd
|
2
|
+
% Part of the R package, http://www.R-project.org
|
3
|
+
% Copyright 1995-2007 R Core Development Team
|
4
|
+
% Distributed under GPL 2 or later
|
5
|
+
|
6
|
+
\name{eurodist}
|
7
|
+
\docType{data}
|
8
|
+
\alias{eurodist}
|
9
|
+
\title{Distances Between European Cities}
|
10
|
+
\description{
|
11
|
+
The data give the road distances (in km) between 21 cities in Europe.
|
12
|
+
The data are taken from a table in \emph{The Cambridge Encyclopaedia}.
|
13
|
+
}
|
14
|
+
\usage{eurodist}
|
15
|
+
\format{
|
16
|
+
A \code{dist} object based on 21 objects.
|
17
|
+
(You must have the \pkg{stats} package loaded to have the methods for this
|
18
|
+
kind of object available).
|
19
|
+
}
|
20
|
+
\source{
|
21
|
+
Crystal, D. Ed. (1990)
|
22
|
+
\emph{The Cambridge Encyclopaedia}.
|
23
|
+
Cambridge: Cambridge University Press,
|
24
|
+
}
|
25
|
+
\keyword{datasets}
|
@@ -0,0 +1,63 @@
|
|
1
|
+
% File src/library/datasets/man/faithful.Rd
|
2
|
+
% Part of the R package, http://www.R-project.org
|
3
|
+
% Copyright 1995-2007 R Core Development Team
|
4
|
+
% Distributed under GPL 2 or later
|
5
|
+
|
6
|
+
\name{faithful}
|
7
|
+
\docType{data}
|
8
|
+
\alias{faithful}
|
9
|
+
\encoding{UTF-8}
|
10
|
+
\title{Old Faithful Geyser Data}
|
11
|
+
\description{
|
12
|
+
Waiting time between eruptions and the duration of the eruption for
|
13
|
+
the Old Faithful geyser in Yellowstone National Park, Wyoming, USA.
|
14
|
+
}
|
15
|
+
\usage{faithful}
|
16
|
+
\format{A data frame with 272 observations on 2 variables.
|
17
|
+
\tabular{rlll}{
|
18
|
+
[,1] \tab eruptions \tab numeric \tab Eruption time in mins \cr
|
19
|
+
[,2] \tab waiting \tab numeric \tab Waiting time to next
|
20
|
+
eruption (in mins)\cr
|
21
|
+
}
|
22
|
+
}
|
23
|
+
\source{W. Härdle.}
|
24
|
+
\references{
|
25
|
+
\enc{Härdle}{Haerdle}, W. (1991)
|
26
|
+
\emph{Smoothing Techniques with Implementation in S}.
|
27
|
+
New York: Springer.
|
28
|
+
|
29
|
+
Azzalini, A. and Bowman, A. W. (1990).
|
30
|
+
A look at some data on the Old Faithful geyser.
|
31
|
+
\emph{Applied Statistics} \bold{39}, 357--365.
|
32
|
+
}
|
33
|
+
\details{
|
34
|
+
A closer look at \code{faithful$eruptions} reveals that these are
|
35
|
+
heavily rounded times originally in seconds, where multiples of 5 are
|
36
|
+
more frequent than expected under non-human measurement. For a
|
37
|
+
better version of the eruption times, see the example below.
|
38
|
+
|
39
|
+
There are many versions of this dataset around: Azzalini and Bowman
|
40
|
+
(1990) use a more complete version.
|
41
|
+
}
|
42
|
+
\seealso{
|
43
|
+
\code{geyser} in package \pkg{MASS} for the Azzalini--Bowman version.
|
44
|
+
}
|
45
|
+
\examples{
|
46
|
+
require(stats); require(graphics)
|
47
|
+
f.tit <- "faithful data: Eruptions of Old Faithful"
|
48
|
+
|
49
|
+
ne60 <- round(e60 <- 60 * faithful$eruptions)
|
50
|
+
all.equal(e60, ne60) # relative diff. ~ 1/10000
|
51
|
+
table(zapsmall(abs(e60 - ne60))) # 0, 0.02 or 0.04
|
52
|
+
faithful$better.eruptions <- ne60 / 60
|
53
|
+
te <- table(ne60)
|
54
|
+
te[te >= 4] # (too) many multiples of 5 !
|
55
|
+
plot(names(te), te, type="h", main = f.tit, xlab = "Eruption time (sec)")
|
56
|
+
|
57
|
+
plot(faithful[, -3], main = f.tit,
|
58
|
+
xlab = "Eruption time (min)",
|
59
|
+
ylab = "Waiting time to next eruption (min)")
|
60
|
+
lines(lowess(faithful$eruptions, faithful$waiting, f = 2/3, iter = 3),
|
61
|
+
col = "red")
|
62
|
+
}
|
63
|
+
\keyword{datasets}
|
@@ -0,0 +1,56 @@
|
|
1
|
+
% File src/library/datasets/man/freeny.Rd
|
2
|
+
% Part of the R package, http://www.R-project.org
|
3
|
+
% Copyright 1995-2007 R Core Development Team
|
4
|
+
% Distributed under GPL 2 or later
|
5
|
+
|
6
|
+
\name{freeny}
|
7
|
+
\docType{data}
|
8
|
+
\alias{freeny}
|
9
|
+
\alias{freeny.x}
|
10
|
+
\alias{freeny.y}
|
11
|
+
\title{Freeny's Revenue Data}
|
12
|
+
\description{
|
13
|
+
Freeny's data on quarterly revenue and explanatory variables.
|
14
|
+
}
|
15
|
+
\usage{
|
16
|
+
freeny
|
17
|
+
freeny.x
|
18
|
+
freeny.y
|
19
|
+
}
|
20
|
+
\format{
|
21
|
+
There are three \sQuote{freeny} data sets.
|
22
|
+
|
23
|
+
\code{freeny.y} is a time series with 39 observations on quarterly
|
24
|
+
revenue from (1962,2Q) to (1971,4Q).
|
25
|
+
|
26
|
+
\code{freeny.x} is a matrix of explanatory variables. The columns
|
27
|
+
are \code{freeny.y} lagged 1 quarter, price index, income level, and
|
28
|
+
market potential.
|
29
|
+
|
30
|
+
Finally, \code{freeny} is a data frame with variables \code{y},
|
31
|
+
\code{lag.quarterly.revenue}, \code{price.index}, \code{income.level},
|
32
|
+
and \code{market.potential} obtained from the above two data objects.
|
33
|
+
}
|
34
|
+
\source{
|
35
|
+
A. E. Freeny (1977)
|
36
|
+
\emph{A Portable Linear Regression Package with Test Programs}.
|
37
|
+
Bell Laboratories memorandum.
|
38
|
+
}
|
39
|
+
\references{
|
40
|
+
Becker, R. A., Chambers, J. M. and Wilks, A. R. (1988)
|
41
|
+
\emph{The New S Language}.
|
42
|
+
Wadsworth & Brooks/Cole.
|
43
|
+
}
|
44
|
+
\examples{
|
45
|
+
require(stats); require(graphics)
|
46
|
+
summary(freeny)
|
47
|
+
pairs(freeny, main = "freeny data")
|
48
|
+
# gives warning: freeny$y has class "ts"
|
49
|
+
|
50
|
+
summary(fm1 <- lm(y ~ ., data = freeny))
|
51
|
+
opar <- par(mfrow = c(2, 2), oma = c(0, 0, 1.1, 0),
|
52
|
+
mar = c(4.1, 4.1, 2.1, 1.1))
|
53
|
+
plot(fm1)
|
54
|
+
par(opar)
|
55
|
+
}
|
56
|
+
\keyword{datasets}
|
@@ -0,0 +1,56 @@
|
|
1
|
+
% File src/library/datasets/man/infert.Rd
|
2
|
+
% Part of the R package, http://www.R-project.org
|
3
|
+
% Copyright 1995-2007 R Core Development Team
|
4
|
+
% Distributed under GPL 2 or later
|
5
|
+
|
6
|
+
\name{infert}
|
7
|
+
\docType{data}
|
8
|
+
\alias{infert}
|
9
|
+
\title{Infertility after Spontaneous and Induced Abortion}
|
10
|
+
\description{
|
11
|
+
This is a matched case-control study dating from before the
|
12
|
+
availability of conditional logistic regression.
|
13
|
+
}
|
14
|
+
\usage{infert}
|
15
|
+
\format{
|
16
|
+
\tabular{rll}{
|
17
|
+
1. \tab Education \tab 0 = 0-5 years \cr
|
18
|
+
\tab \tab 1 = 6-11 years \cr
|
19
|
+
\tab \tab 2 = 12+ years \cr
|
20
|
+
2. \tab age \tab age in years of case \cr
|
21
|
+
3. \tab parity \tab count \cr
|
22
|
+
4. \tab number of prior \tab 0 = 0 \cr
|
23
|
+
\tab induced abortions \tab 1 = 1 \cr
|
24
|
+
\tab \tab 2 = 2 or more \cr
|
25
|
+
5. \tab case status\tab 1 = case \cr
|
26
|
+
\tab \tab 0 = control \cr
|
27
|
+
6. \tab number of prior \tab 0 = 0 \cr
|
28
|
+
\tab spontaneous abortions \tab 1 = 1 \cr
|
29
|
+
\tab \tab 2 = 2 or more \cr
|
30
|
+
7. \tab matched set number \tab 1-83 \cr
|
31
|
+
8. \tab stratum number \tab 1-63}
|
32
|
+
}
|
33
|
+
\source{
|
34
|
+
Trichopoulos et al. (1976)
|
35
|
+
\emph{Br. J. of Obst. and Gynaec.} \bold{83}, 645--650.
|
36
|
+
}
|
37
|
+
\note{
|
38
|
+
One case with two prior spontaneous abortions and two prior induced
|
39
|
+
abortions is omitted.
|
40
|
+
}
|
41
|
+
\examples{
|
42
|
+
require(stats)
|
43
|
+
model1 <- glm(case ~ spontaneous+induced, data=infert,family=binomial())
|
44
|
+
summary(model1)
|
45
|
+
## adjusted for other potential confounders:
|
46
|
+
summary(model2 <- glm(case ~ age+parity+education+spontaneous+induced,
|
47
|
+
data=infert,family=binomial()))
|
48
|
+
## Really should be analysed by conditional logistic regression
|
49
|
+
## which is in the survival package
|
50
|
+
if(require(survival)){
|
51
|
+
model3 <- clogit(case~spontaneous+induced+strata(stratum),data=infert)
|
52
|
+
print(summary(model3))
|
53
|
+
detach()# survival (conflicts)
|
54
|
+
}
|
55
|
+
}
|
56
|
+
\keyword{datasets}
|
data/data/r/man/iris.Rd
ADDED
@@ -0,0 +1,62 @@
|
|
1
|
+
% File src/library/datasets/man/iris.Rd
|
2
|
+
% Part of the R package, http://www.R-project.org
|
3
|
+
% Copyright 1995-2007 R Core Development Team
|
4
|
+
% Distributed under GPL 2 or later
|
5
|
+
|
6
|
+
\name{iris}
|
7
|
+
\docType{data}
|
8
|
+
\alias{iris}
|
9
|
+
\alias{iris3}
|
10
|
+
\title{Edgar Anderson's Iris Data}
|
11
|
+
\description{
|
12
|
+
This famous (Fisher's or Anderson's) iris data set gives the
|
13
|
+
measurements in centimeters of the variables sepal length and width
|
14
|
+
and petal length and width, respectively, for 50 flowers from each
|
15
|
+
of 3 species of iris. The species are \emph{Iris setosa},
|
16
|
+
\emph{versicolor}, and \emph{virginica}.
|
17
|
+
}
|
18
|
+
\usage{
|
19
|
+
iris
|
20
|
+
iris3
|
21
|
+
}
|
22
|
+
\format{
|
23
|
+
\code{iris} is a data frame with 150 cases (rows) and 5 variables
|
24
|
+
(columns) named \code{Sepal.Length}, \code{Sepal.Width},
|
25
|
+
\code{Petal.Length}, \code{Petal.Width}, and \code{Species}.
|
26
|
+
|
27
|
+
\code{iris3} gives the same data arranged as a 3-dimensional array
|
28
|
+
of size 50 by 4 by 3, as represented by S-PLUS. The first dimension
|
29
|
+
gives the case number within the species subsample, the second the
|
30
|
+
measurements with names \code{Sepal L.}, \code{Sepal W.},
|
31
|
+
\code{Petal L.}, and \code{Petal W.}, and the third the species.
|
32
|
+
}
|
33
|
+
\source{
|
34
|
+
Fisher, R. A. (1936)
|
35
|
+
The use of multiple measurements in taxonomic problems.
|
36
|
+
\emph{Annals of Eugenics},
|
37
|
+
\bold{7}, Part II, 179--188.
|
38
|
+
|
39
|
+
The data were collected by
|
40
|
+
Anderson, Edgar (1935).
|
41
|
+
The irises of the Gaspe Peninsula,
|
42
|
+
\emph{Bulletin of the American Iris Society},
|
43
|
+
\bold{59}, 2--5.
|
44
|
+
}
|
45
|
+
\references{
|
46
|
+
Becker, R. A., Chambers, J. M. and Wilks, A. R. (1988)
|
47
|
+
\emph{The New S Language}.
|
48
|
+
Wadsworth & Brooks/Cole. (has \code{iris3} as \code{iris}.)
|
49
|
+
}
|
50
|
+
\seealso{
|
51
|
+
\code{\link{matplot}} some examples of which use
|
52
|
+
\code{iris}.
|
53
|
+
}
|
54
|
+
\examples{
|
55
|
+
dni3 <- dimnames(iris3)
|
56
|
+
ii <- data.frame(matrix(aperm(iris3, c(1,3,2)), ncol=4,
|
57
|
+
dimnames = list(NULL, sub(" L.",".Length",
|
58
|
+
sub(" W.",".Width", dni3[[2]])))),
|
59
|
+
Species = gl(3, 50, labels=sub("S", "s", sub("V", "v", dni3[[3]]))))
|
60
|
+
all.equal(ii, iris) # TRUE
|
61
|
+
}
|
62
|
+
\keyword{datasets}
|
@@ -0,0 +1,29 @@
|
|
1
|
+
% File src/library/datasets/man/islands.Rd
|
2
|
+
% Part of the R package, http://www.R-project.org
|
3
|
+
% Copyright 1995-2007 R Core Development Team
|
4
|
+
% Distributed under GPL 2 or later
|
5
|
+
|
6
|
+
\name{islands}
|
7
|
+
\docType{data}
|
8
|
+
\alias{islands}
|
9
|
+
\title{Areas of the World's Major Landmasses}
|
10
|
+
\description{
|
11
|
+
The areas in thousands of square miles of the landmasses which exceed
|
12
|
+
10,000 square miles.
|
13
|
+
}
|
14
|
+
\usage{islands}
|
15
|
+
\format{A named vector of length 48.}
|
16
|
+
\source{The World Almanac and Book of Facts, 1975, page 406.}
|
17
|
+
\references{
|
18
|
+
McNeil, D. R. (1977)
|
19
|
+
\emph{Interactive Data Analysis}.
|
20
|
+
Wiley.
|
21
|
+
}
|
22
|
+
\examples{
|
23
|
+
require(graphics)
|
24
|
+
dotchart(log(islands, 10),
|
25
|
+
main = "islands data: log10(area) (log10(sq. miles))")
|
26
|
+
dotchart(log(islands[order(islands)], 10),
|
27
|
+
main = "islands data: log10(area) (log10(sq. miles))")
|
28
|
+
}
|
29
|
+
\keyword{datasets}
|