sciruby 0.1.3 → 0.2.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +2 -0
- data/CHANGES +3 -0
- data/CONTRIBUTING.md +46 -0
- data/Gemfile +34 -0
- data/LICENSE.txt +21 -0
- data/README.rdoc +28 -0
- data/lib/sciruby/gems.rb +27 -0
- data/lib/sciruby/version.rb +3 -0
- data/lib/sciruby.rb +2 -77
- data/sciruby.gemspec +35 -0
- metadata +51 -413
- data/.autotest +0 -23
- data/.gemtest +0 -0
- data/History.txt +0 -6
- data/Manifest.txt +0 -119
- data/Rakefile +0 -178
- data/bin/sciruby-plotter +0 -12
- data/data/r/man/AirPassengers.Rd +0 -51
- data/data/r/man/BJsales.Rd +0 -34
- data/data/r/man/BOD.Rd +0 -53
- data/data/r/man/ChickWeight.Rd +0 -68
- data/data/r/man/DNase.Rd +0 -63
- data/data/r/man/EuStockMarkets.Rd +0 -28
- data/data/r/man/Formaldehyde.Rd +0 -44
- data/data/r/man/HairEyeColor.Rd +0 -77
- data/data/r/man/Harman23.cor.Rd +0 -25
- data/data/r/man/Harman74.cor.Rd +0 -28
- data/data/r/man/Indometh.Rd +0 -57
- data/data/r/man/InsectSprays.Rd +0 -45
- data/data/r/man/JohnsonJohnson.Rd +0 -37
- data/data/r/man/LakeHuron.Rd +0 -27
- data/data/r/man/LifeCycleSavings.Rd +0 -54
- data/data/r/man/Loblolly.Rd +0 -56
- data/data/r/man/Nile.Rd +0 -78
- data/data/r/man/Orange.Rd +0 -57
- data/data/r/man/OrchardSprays.Rd +0 -62
- data/data/r/man/PlantGrowth.Rd +0 -39
- data/data/r/man/Puromycin.Rd +0 -84
- data/data/r/man/Theoph.Rd +0 -84
- data/data/r/man/Titanic.Rd +0 -73
- data/data/r/man/ToothGrowth.Rd +0 -40
- data/data/r/man/UCBAdmissions.Rd +0 -68
- data/data/r/man/UKDriverDeaths.Rd +0 -72
- data/data/r/man/UKLungDeaths.Rd +0 -40
- data/data/r/man/UKgas.Rd +0 -25
- data/data/r/man/USAccDeaths.Rd +0 -23
- data/data/r/man/USArrests.Rd +0 -45
- data/data/r/man/USJudgeRatings.Rd +0 -38
- data/data/r/man/USPersonalExpenditure.Rd +0 -33
- data/data/r/man/VADeaths.Rd +0 -51
- data/data/r/man/WWWusage.Rd +0 -41
- data/data/r/man/WorldPhones.Rd +0 -40
- data/data/r/man/ability.cov.Rd +0 -50
- data/data/r/man/airmiles.Rd +0 -29
- data/data/r/man/airquality.Rd +0 -56
- data/data/r/man/anscombe.Rd +0 -62
- data/data/r/man/attenu.Rd +0 -66
- data/data/r/man/attitude.Rd +0 -48
- data/data/r/man/austres.Rd +0 -22
- data/data/r/man/beavers.Rd +0 -73
- data/data/r/man/cars.Rd +0 -59
- data/data/r/man/chickwts.Rd +0 -47
- data/data/r/man/co2.Rd +0 -43
- data/data/r/man/crimtab.Rd +0 -129
- data/data/r/man/datasets-package.Rd +0 -24
- data/data/r/man/discoveries.Rd +0 -30
- data/data/r/man/esoph.Rd +0 -66
- data/data/r/man/euro.Rd +0 -56
- data/data/r/man/eurodist.Rd +0 -25
- data/data/r/man/faithful.Rd +0 -63
- data/data/r/man/freeny.Rd +0 -56
- data/data/r/man/infert.Rd +0 -56
- data/data/r/man/iris.Rd +0 -62
- data/data/r/man/islands.Rd +0 -29
- data/data/r/man/lh.Rd +0 -22
- data/data/r/man/longley.Rd +0 -56
- data/data/r/man/lynx.Rd +0 -33
- data/data/r/man/morley.Rd +0 -50
- data/data/r/man/mtcars.Rd +0 -44
- data/data/r/man/nhtemp.Rd +0 -30
- data/data/r/man/nottem.Rd +0 -30
- data/data/r/man/occupationalStatus.Rd +0 -44
- data/data/r/man/precip.Rd +0 -31
- data/data/r/man/presidents.Rd +0 -36
- data/data/r/man/pressure.Rd +0 -41
- data/data/r/man/quakes.Rd +0 -40
- data/data/r/man/randu.Rd +0 -46
- data/data/r/man/rivers.Rd +0 -21
- data/data/r/man/rock.Rd +0 -34
- data/data/r/man/sleep.Rd +0 -51
- data/data/r/man/stackloss.Rd +0 -77
- data/data/r/man/state.Rd +0 -80
- data/data/r/man/sunspot.month.Rd +0 -49
- data/data/r/man/sunspot.year.Rd +0 -26
- data/data/r/man/sunspots.Rd +0 -33
- data/data/r/man/swiss.Rd +0 -79
- data/data/r/man/treering.Rd +0 -38
- data/data/r/man/trees.Rd +0 -48
- data/data/r/man/uspop.Rd +0 -27
- data/data/r/man/volcano.Rd +0 -31
- data/data/r/man/warpbreaks.Rd +0 -56
- data/data/r/man/women.Rd +0 -40
- data/data/r/man/zCO2.Rd +0 -81
- data/lib/ext/csv.rb +0 -22
- data/lib/ext/shoes.rb +0 -131
- data/lib/ext/string.rb +0 -39
- data/lib/sciruby/analysis/suite.rb +0 -87
- data/lib/sciruby/analysis/suite_report_builder.rb +0 -44
- data/lib/sciruby/analysis.rb +0 -98
- data/lib/sciruby/config.rb +0 -93
- data/lib/sciruby/data/guardian.rb +0 -96
- data/lib/sciruby/data/r/base.rb +0 -110
- data/lib/sciruby/data/r/data_frame.rb +0 -24
- data/lib/sciruby/data/r/grouped_data.rb +0 -7
- data/lib/sciruby/data/r/list.rb +0 -20
- data/lib/sciruby/data/r/multi_time_series.rb +0 -24
- data/lib/sciruby/data/r/r_matrix.rb +0 -7
- data/lib/sciruby/data/r/time_series.rb +0 -19
- data/lib/sciruby/data/r/time_series_base.rb +0 -40
- data/lib/sciruby/data/r/vector.rb +0 -125
- data/lib/sciruby/data/r.rb +0 -155
- data/lib/sciruby/data.rb +0 -168
- data/lib/sciruby/editor.rb +0 -82
- data/lib/sciruby/plotter.rb +0 -128
- data/lib/sciruby/recommend.rb +0 -70
- data/lib/sciruby/validation.rb +0 -368
- data/readme.md +0 -75
- data/static/sciruby-icon.png +0 -0
- data/test/helpers_tests.rb +0 -58
- data/test/test_recommend.rb +0 -16
data/data/r/man/esoph.Rd
DELETED
@@ -1,66 +0,0 @@
|
|
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
DELETED
@@ -1,56 +0,0 @@
|
|
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}
|
data/data/r/man/eurodist.Rd
DELETED
@@ -1,25 +0,0 @@
|
|
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}
|
data/data/r/man/faithful.Rd
DELETED
@@ -1,63 +0,0 @@
|
|
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$waiting, f = 2/3, iter = 3),
|
61
|
-
col = "red")
|
62
|
-
}
|
63
|
-
\keyword{datasets}
|
data/data/r/man/freeny.Rd
DELETED
@@ -1,56 +0,0 @@
|
|
1
|
-
% File src/library/datasets/man/freeny.Rd
|
2
|
-
% Part of the R package, http://www.R-project.org
|
3
|
-
% Copyright 1995-2007 R Core Development Team
|
4
|
-
% Distributed under GPL 2 or later
|
5
|
-
|
6
|
-
\name{freeny}
|
7
|
-
\docType{data}
|
8
|
-
\alias{freeny}
|
9
|
-
\alias{freeny.x}
|
10
|
-
\alias{freeny.y}
|
11
|
-
\title{Freeny's Revenue Data}
|
12
|
-
\description{
|
13
|
-
Freeny's data on quarterly revenue and explanatory variables.
|
14
|
-
}
|
15
|
-
\usage{
|
16
|
-
freeny
|
17
|
-
freeny.x
|
18
|
-
freeny.y
|
19
|
-
}
|
20
|
-
\format{
|
21
|
-
There are three \sQuote{freeny} data sets.
|
22
|
-
|
23
|
-
\code{freeny.y} is a time series with 39 observations on quarterly
|
24
|
-
revenue from (1962,2Q) to (1971,4Q).
|
25
|
-
|
26
|
-
\code{freeny.x} is a matrix of explanatory variables. The columns
|
27
|
-
are \code{freeny.y} lagged 1 quarter, price index, income level, and
|
28
|
-
market potential.
|
29
|
-
|
30
|
-
Finally, \code{freeny} is a data frame with variables \code{y},
|
31
|
-
\code{lag.quarterly.revenue}, \code{price.index}, \code{income.level},
|
32
|
-
and \code{market.potential} obtained from the above two data objects.
|
33
|
-
}
|
34
|
-
\source{
|
35
|
-
A. E. Freeny (1977)
|
36
|
-
\emph{A Portable Linear Regression Package with Test Programs}.
|
37
|
-
Bell Laboratories memorandum.
|
38
|
-
}
|
39
|
-
\references{
|
40
|
-
Becker, R. A., Chambers, J. M. and Wilks, A. R. (1988)
|
41
|
-
\emph{The New S Language}.
|
42
|
-
Wadsworth & Brooks/Cole.
|
43
|
-
}
|
44
|
-
\examples{
|
45
|
-
require(stats); require(graphics)
|
46
|
-
summary(freeny)
|
47
|
-
pairs(freeny, main = "freeny data")
|
48
|
-
# gives warning: freeny$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}
|
data/data/r/man/infert.Rd
DELETED
@@ -1,56 +0,0 @@
|
|
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
DELETED
@@ -1,62 +0,0 @@
|
|
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}
|
data/data/r/man/islands.Rd
DELETED
@@ -1,29 +0,0 @@
|
|
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}
|
data/data/r/man/lh.Rd
DELETED
@@ -1,22 +0,0 @@
|
|
1
|
-
% File src/library/datasets/man/lh.Rd
|
2
|
-
% Part of the R package, http://www.R-project.org
|
3
|
-
% Copyright 1994-9 W. N. Venables and B. D. Ripley
|
4
|
-
% Distributed under GPL 2 or later
|
5
|
-
|
6
|
-
\name{lh}
|
7
|
-
\docType{data}
|
8
|
-
\alias{lh}
|
9
|
-
\title{
|
10
|
-
Luteinizing Hormone in Blood Samples
|
11
|
-
}
|
12
|
-
\description{
|
13
|
-
A regular time series giving the luteinizing hormone in blood
|
14
|
-
samples at 10 mins intervals from a human female, 48 samples.
|
15
|
-
}
|
16
|
-
\usage{lh}
|
17
|
-
\source{
|
18
|
-
P.J. Diggle (1990)
|
19
|
-
\emph{Time Series: A Biostatistical Introduction.}
|
20
|
-
Oxford, table A.1, series 3
|
21
|
-
}
|
22
|
-
\keyword{datasets}
|
data/data/r/man/longley.Rd
DELETED
@@ -1,56 +0,0 @@
|
|
1
|
-
% File src/library/datasets/man/longley.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{longley}
|
7
|
-
\docType{data}
|
8
|
-
\alias{longley}
|
9
|
-
\title{Longley's Economic Regression Data}
|
10
|
-
\description{
|
11
|
-
A macroeconomic data set which provides a well-known example for a
|
12
|
-
highly collinear regression.
|
13
|
-
}
|
14
|
-
\usage{longley}
|
15
|
-
\format{
|
16
|
-
A data frame with 7 economical variables, observed yearly from 1947 to
|
17
|
-
1962 (\eqn{n=16}).
|
18
|
-
\describe{
|
19
|
-
\item{GNP.deflator:}{GNP implicit price deflator (\eqn{1954=100})}
|
20
|
-
\item{GNP:}{Gross National Product.}
|
21
|
-
\item{Unemployed:}{number of unemployed.}
|
22
|
-
\item{Armed.Forces:}{number of people in the armed forces.}
|
23
|
-
\item{Population:}{\sQuote{noninstitutionalized} population
|
24
|
-
\eqn{\ge} 14 years of age.}
|
25
|
-
\item{Year:}{the year (time).}
|
26
|
-
\item{Employed:}{number of people employed.}
|
27
|
-
}
|
28
|
-
|
29
|
-
The regression \code{lm(Employed ~ .)} is known to be highly
|
30
|
-
collinear.
|
31
|
-
}
|
32
|
-
\source{
|
33
|
-
J. W. Longley (1967)
|
34
|
-
An appraisal of least-squares programs from the point of view of the
|
35
|
-
user.
|
36
|
-
\emph{Journal of the American Statistical Association}, \bold{62},
|
37
|
-
819--841.
|
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
|
-
## give the data set in the form it is used in S-PLUS:
|
47
|
-
longley.x <- data.matrix(longley[, 1:6])
|
48
|
-
longley.y <- longley[, "Employed"]
|
49
|
-
pairs(longley, main = "longley data")
|
50
|
-
summary(fm1 <- lm(Employed ~ ., data = longley))
|
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}
|
data/data/r/man/lynx.Rd
DELETED
@@ -1,33 +0,0 @@
|
|
1
|
-
% File src/library/datasets/man/lynx.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{lynx}
|
7
|
-
\docType{data}
|
8
|
-
\alias{lynx}
|
9
|
-
\title{Annual Canadian Lynx trappings 1821--1934}
|
10
|
-
\description{
|
11
|
-
Annual numbers of lynx trappings for 1821--1934 in Canada. Taken from
|
12
|
-
Brockwell & Davis (1991), this appears to be the series considered
|
13
|
-
by Campbell & Walker (1977).
|
14
|
-
}
|
15
|
-
\usage{lynx}
|
16
|
-
\source{
|
17
|
-
Brockwell, P. J. and Davis, R. A. (1991) \emph{Time
|
18
|
-
Series and Forecasting Methods.} Second edition.
|
19
|
-
Springer. Series G (page 557).
|
20
|
-
}
|
21
|
-
\references{
|
22
|
-
Becker, R. A., Chambers, J. M. and Wilks, A. R. (1988)
|
23
|
-
\emph{The New S Language}.
|
24
|
-
Wadsworth & Brooks/Cole.
|
25
|
-
|
26
|
-
Campbell, M. J.and A. M. Walker (1977). A Survey of
|
27
|
-
statistical work on the Mackenzie River series of annual
|
28
|
-
Canadian lynx trappings for the years 1821--1934 and
|
29
|
-
a new analysis.
|
30
|
-
\emph{Journal of the Royal Statistical Society series A},
|
31
|
-
\bold{140}, 411--431.
|
32
|
-
}
|
33
|
-
\keyword{datasets}
|
data/data/r/man/morley.Rd
DELETED
@@ -1,50 +0,0 @@
|
|
1
|
-
% File src/library/datasets/man/morley.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{morley}
|
7
|
-
\docType{data}
|
8
|
-
\alias{morley}
|
9
|
-
\title{Michaelson-Morley Speed of Light Data}
|
10
|
-
\description{
|
11
|
-
The classical data of Michaelson and Morley on the speed of light.
|
12
|
-
The data consists of five experiments, each consisting of 20
|
13
|
-
consecutive \sQuote{runs}. The response is the speed of light
|
14
|
-
measurement, suitably coded.
|
15
|
-
}
|
16
|
-
\usage{morley}
|
17
|
-
\format{
|
18
|
-
A data frame contains the following components:
|
19
|
-
\describe{
|
20
|
-
\item{\code{Expt}}{The experiment number, from 1 to 5.}
|
21
|
-
\item{\code{Run}}{The run number within each experiment.}
|
22
|
-
\item{\code{Speed}}{Speed-of-light measurement.}
|
23
|
-
}
|
24
|
-
}
|
25
|
-
\details{
|
26
|
-
The data is here viewed as a randomized block experiment with
|
27
|
-
\sQuote{experiment} and \sQuote{run} as the factors. \sQuote{run} may
|
28
|
-
also be considered a quantitative variate to account for linear (or
|
29
|
-
polynomial) changes in the measurement over the course of a single
|
30
|
-
experiment.
|
31
|
-
}
|
32
|
-
\source{
|
33
|
-
A. J. Weekes (1986)
|
34
|
-
\emph{A Genstat Primer}.
|
35
|
-
London: Edward Arnold.
|
36
|
-
}
|
37
|
-
\examples{
|
38
|
-
require(stats); require(graphics)
|
39
|
-
morley$Expt <- factor(morley$Expt)
|
40
|
-
morley$Run <- factor(morley$Run)
|
41
|
-
|
42
|
-
xtabs(~ Expt + Run, data = morley)# 5 x 20 balanced (two-way)
|
43
|
-
plot(Speed ~ Expt, data = morley,
|
44
|
-
main = "Speed of Light Data", xlab = "Experiment No.")
|
45
|
-
fm <- aov(Speed ~ Run + Expt, data = morley)
|
46
|
-
summary(fm)
|
47
|
-
fm0 <- update(fm, . ~ . - Run)
|
48
|
-
anova(fm0, fm)
|
49
|
-
}
|
50
|
-
\keyword{datasets}
|
data/data/r/man/mtcars.Rd
DELETED
@@ -1,44 +0,0 @@
|
|
1
|
-
% File src/library/datasets/man/mtcars.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{mtcars}
|
7
|
-
\docType{data}
|
8
|
-
\alias{mtcars}
|
9
|
-
\title{Motor Trend Car Road Tests}
|
10
|
-
\description{
|
11
|
-
The data was extracted from the 1974 \emph{Motor Trend} US magazine,
|
12
|
-
and comprises fuel consumption and 10 aspects of
|
13
|
-
automobile design and performance for 32 automobiles (1973--74
|
14
|
-
models).
|
15
|
-
}
|
16
|
-
\usage{mtcars}
|
17
|
-
\format{
|
18
|
-
A data frame with 32 observations on 11 variables.
|
19
|
-
\tabular{rll}{
|
20
|
-
[, 1] \tab mpg \tab Miles/(US) gallon \cr
|
21
|
-
[, 2] \tab cyl \tab Number of cylinders \cr
|
22
|
-
[, 3] \tab disp \tab Displacement (cu.in.) \cr
|
23
|
-
[, 4] \tab hp \tab Gross horsepower \cr
|
24
|
-
[, 5] \tab drat \tab Rear axle ratio \cr
|
25
|
-
[, 6] \tab wt \tab Weight (lb/1000) \cr
|
26
|
-
[, 7] \tab qsec \tab 1/4 mile time \cr
|
27
|
-
[, 8] \tab vs \tab V/S \cr
|
28
|
-
[, 9] \tab am \tab Transmission (0 = automatic, 1 = manual) \cr
|
29
|
-
[,10] \tab gear \tab Number of forward gears \cr
|
30
|
-
[,11] \tab carb \tab Number of carburetors
|
31
|
-
}
|
32
|
-
}
|
33
|
-
\source{
|
34
|
-
Henderson and Velleman (1981),
|
35
|
-
Building multiple regression models interactively.
|
36
|
-
\emph{Biometrics}, \bold{37}, 391--411.
|
37
|
-
}
|
38
|
-
\examples{
|
39
|
-
require(graphics)
|
40
|
-
pairs(mtcars, main = "mtcars data")
|
41
|
-
coplot(mpg ~ disp | as.factor(cyl), data = mtcars,
|
42
|
-
panel = panel.smooth, rows = 1)
|
43
|
-
}
|
44
|
-
\keyword{datasets}
|
data/data/r/man/nhtemp.Rd
DELETED
@@ -1,30 +0,0 @@
|
|
1
|
-
% File src/library/datasets/man/nhtemp.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{nhtemp}
|
7
|
-
\docType{data}
|
8
|
-
\alias{nhtemp}
|
9
|
-
\title{Average Yearly Temperatures in New Haven}
|
10
|
-
\description{
|
11
|
-
The mean annual temperature in degrees Fahrenheit in New Haven,
|
12
|
-
Connecticut, from 1912 to 1971.
|
13
|
-
}
|
14
|
-
\usage{nhtemp}
|
15
|
-
\format{A time series of 60 observations.}
|
16
|
-
\source{
|
17
|
-
Vaux, J. E. and Brinker, N. B. (1972)
|
18
|
-
\emph{Cycles}, \bold{1972}, 117--121.
|
19
|
-
}
|
20
|
-
\references{
|
21
|
-
McNeil, D. R. (1977)
|
22
|
-
\emph{Interactive Data Analysis}.
|
23
|
-
New York: Wiley.
|
24
|
-
}
|
25
|
-
\examples{
|
26
|
-
require(stats); require(graphics)
|
27
|
-
plot(nhtemp, main = "nhtemp data",
|
28
|
-
ylab = "Mean annual temperature in New Haven, CT (deg. F)")
|
29
|
-
}
|
30
|
-
\keyword{datasets}
|
data/data/r/man/nottem.Rd
DELETED
@@ -1,30 +0,0 @@
|
|
1
|
-
% File src/library/datasets/man/nottem.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{nottem}
|
7
|
-
\docType{data}
|
8
|
-
\alias{nottem}
|
9
|
-
\title{
|
10
|
-
Average Monthly Temperatures at Nottingham, 1920--1939
|
11
|
-
}
|
12
|
-
\description{
|
13
|
-
A time series object containing average air temperatures at
|
14
|
-
Nottingham Castle in degrees Fahrenheit for 20 years.
|
15
|
-
}
|
16
|
-
\usage{nottem}
|
17
|
-
\source{
|
18
|
-
Anderson, O. D. (1976)
|
19
|
-
\emph{Time Series Analysis and Forecasting: The Box-Jenkins approach.}
|
20
|
-
Butterworths. Series R.
|
21
|
-
}
|
22
|
-
\examples{
|
23
|
-
\dontrun{require(stats); require(graphics)
|
24
|
-
nott <- window(nottem, end=c(1936,12))
|
25
|
-
fit <- arima(nott,order=c(1,0,0), list(order=c(2,1,0), period=12))
|
26
|
-
nott.fore <- predict(fit, n.ahead=36)
|
27
|
-
ts.plot(nott, nott.fore$pred, nott.fore$pred+2*nott.fore$se,
|
28
|
-
nott.fore$pred-2*nott.fore$se, gpars=list(col=c(1,1,4,4)))
|
29
|
-
}}
|
30
|
-
\keyword{datasets}
|