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
data/data/r/man/randu.Rd
ADDED
@@ -0,0 +1,46 @@
|
|
1
|
+
% File src/library/datasets/man/randu.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{randu}
|
7
|
+
\docType{data}
|
8
|
+
\alias{randu}
|
9
|
+
\title{Random Numbers from Congruential Generator RANDU}
|
10
|
+
\description{
|
11
|
+
400 triples of successive random numbers were taken from the VAX
|
12
|
+
FORTRAN function RANDU running under VMS 1.5.
|
13
|
+
}
|
14
|
+
\usage{randu}
|
15
|
+
\details{
|
16
|
+
In three dimensional displays it is evident that the triples fall on
|
17
|
+
15 parallel planes in 3-space. This can be shown theoretically to be
|
18
|
+
true for all triples from the RANDU generator.
|
19
|
+
|
20
|
+
These particular 400 triples start 5 apart in the sequence, that is
|
21
|
+
they are ((U[5i+1], U[5i+2], U[5i+3]), i= 0, \dots, 399), and they
|
22
|
+
are rounded to 6 decimal places.
|
23
|
+
|
24
|
+
Under VMS versions 2.0 and higher, this problem has been fixed.
|
25
|
+
}
|
26
|
+
\format{
|
27
|
+
A data frame with 400 observations on 3 variables named \code{x},
|
28
|
+
\code{y} and \code{z} which give the first, second and third random
|
29
|
+
number in the triple.
|
30
|
+
}
|
31
|
+
\source{
|
32
|
+
David Donoho
|
33
|
+
}
|
34
|
+
\examples{
|
35
|
+
\dontrun{## We could re-generate the dataset by the following R code
|
36
|
+
seed <- as.double(1)
|
37
|
+
RANDU <- function() {
|
38
|
+
seed <<- ((2^16 + 3) * seed) \%\% (2^31)
|
39
|
+
seed/(2^31)
|
40
|
+
}
|
41
|
+
for(i in 1:400) {
|
42
|
+
U <- c(RANDU(), RANDU(), RANDU(), RANDU(), RANDU())
|
43
|
+
print(round(U[1:3], 6))
|
44
|
+
}}
|
45
|
+
}
|
46
|
+
\keyword{datasets}
|
@@ -0,0 +1,21 @@
|
|
1
|
+
% File src/library/datasets/man/rivers.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{rivers}
|
7
|
+
\docType{data}
|
8
|
+
\alias{rivers}
|
9
|
+
\title{Lengths of Major North American Rivers}
|
10
|
+
\description{
|
11
|
+
This data set gives the lengths (in miles) of 141 \dQuote{major}
|
12
|
+
rivers in North America, as compiled by the US Geological Survey.
|
13
|
+
}
|
14
|
+
\usage{rivers}
|
15
|
+
\format{A vector containing 141 observations.}
|
16
|
+
\source{World Almanac and Book of Facts, 1975, page 406.}
|
17
|
+
\references{
|
18
|
+
McNeil, D. R. (1977) \emph{Interactive Data Analysis}.
|
19
|
+
New York: Wiley.
|
20
|
+
}
|
21
|
+
\keyword{datasets}
|
data/data/r/man/rock.Rd
ADDED
@@ -0,0 +1,34 @@
|
|
1
|
+
% File src/library/datasets/man/rock.Rd
|
2
|
+
% Part of the R package, http://www.R-project.org
|
3
|
+
% Copyright 1994-8 W. N. Venables and B. D. Ripley
|
4
|
+
% Distributed under GPL 2 or later
|
5
|
+
|
6
|
+
% Manually converted to Rd data file description format by KH.
|
7
|
+
\name{rock}
|
8
|
+
\docType{data}
|
9
|
+
\alias{rock}
|
10
|
+
\title{Measurements on Petroleum Rock Samples}
|
11
|
+
\description{
|
12
|
+
Measurements on 48 rock samples from a petroleum reservoir.}
|
13
|
+
\usage{rock}
|
14
|
+
\format{
|
15
|
+
A data frame with 48 rows and 4 numeric columns.
|
16
|
+
|
17
|
+
\tabular{rll}{
|
18
|
+
[,1] \tab area \tab area of pores space, in pixels
|
19
|
+
out of 256 by 256 \cr
|
20
|
+
[,2] \tab peri \tab perimeter in pixels \cr
|
21
|
+
[,3] \tab shape \tab perimeter/sqrt(area) \cr
|
22
|
+
[,4] \tab perm \tab permeability in milli-Darcies
|
23
|
+
}
|
24
|
+
}
|
25
|
+
\details{
|
26
|
+
Twelve core samples from petroleum reservoirs were sampled by 4
|
27
|
+
cross-sections. Each core sample was measured for permeability, and
|
28
|
+
each cross-section has total area of pores, total perimeter of
|
29
|
+
pores, and shape.
|
30
|
+
}
|
31
|
+
\source{
|
32
|
+
Data from BP Research, image analysis by Ronit Katz, U. Oxford.
|
33
|
+
}
|
34
|
+
\keyword{datasets}
|
data/data/r/man/sleep.Rd
ADDED
@@ -0,0 +1,51 @@
|
|
1
|
+
% File src/library/datasets/man/sleep.Rd
|
2
|
+
% Part of the R package, http://www.R-project.org
|
3
|
+
% Copyright 1995-2010 R Core Development Team
|
4
|
+
% Copyright 1999-2010 The R Foundation
|
5
|
+
% Distributed under GPL 2 or later
|
6
|
+
|
7
|
+
\name{sleep}
|
8
|
+
\docType{data}
|
9
|
+
\encoding{UTF-8}
|
10
|
+
\alias{sleep}
|
11
|
+
\title{Student's Sleep Data}
|
12
|
+
\description{
|
13
|
+
Data which show the effect of two soporific drugs (increase in hours
|
14
|
+
of sleep compared to control) on 10 patients.
|
15
|
+
}
|
16
|
+
\usage{sleep}
|
17
|
+
\format{
|
18
|
+
A data frame with 20 observations on 3 variables.
|
19
|
+
\tabular{rlll}{
|
20
|
+
[, 1] \tab extra \tab numeric \tab increase in hours of sleep\cr
|
21
|
+
[, 2] \tab group \tab factor \tab drug given\cr
|
22
|
+
[, 3] \tab ID \tab factor \tab patient ID
|
23
|
+
}
|
24
|
+
}
|
25
|
+
\source{
|
26
|
+
Cushny, A. R. and Peebles, A. R. (1905)
|
27
|
+
The action of optical isomers: II hyoscines.
|
28
|
+
\emph{The Journal of Physiology} \bold{32}, 501--510.
|
29
|
+
|
30
|
+
Student (1908)
|
31
|
+
The probable error of the mean.
|
32
|
+
\emph{Biometrika}, \bold{6}, 20.
|
33
|
+
}
|
34
|
+
\details{
|
35
|
+
The \code{group} variable name may be misleading about the data:
|
36
|
+
They represent measurements on 10 persons, not in groups.
|
37
|
+
%% But we keep it (as [,2]) for back compatibility.
|
38
|
+
}
|
39
|
+
\references{
|
40
|
+
\enc{Scheffé}{Scheffe}, Henry (1959)
|
41
|
+
\emph{The Analysis of Variance}.
|
42
|
+
New York, NY: Wiley.
|
43
|
+
}
|
44
|
+
\examples{
|
45
|
+
require(stats)
|
46
|
+
## Student's paired t-test
|
47
|
+
with(sleep,
|
48
|
+
t.test(extra[group == 1],
|
49
|
+
extra[group == 2], paired = TRUE))
|
50
|
+
}
|
51
|
+
\keyword{datasets}
|
@@ -0,0 +1,77 @@
|
|
1
|
+
% File src/library/datasets/man/stackloss.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{stackloss}
|
7
|
+
\docType{data}
|
8
|
+
\alias{stackloss}
|
9
|
+
\alias{stack.loss}
|
10
|
+
\alias{stack.x}
|
11
|
+
\title{Brownlee's Stack Loss Plant Data}
|
12
|
+
\description{
|
13
|
+
Operational data of a plant for the oxidation of ammonia to nitric
|
14
|
+
acid.
|
15
|
+
}
|
16
|
+
\usage{
|
17
|
+
stackloss
|
18
|
+
|
19
|
+
stack.x
|
20
|
+
stack.loss
|
21
|
+
}
|
22
|
+
\format{
|
23
|
+
\code{stackloss} is a data frame with 21 observations on 4 variables.
|
24
|
+
|
25
|
+
\tabular{rll}{
|
26
|
+
[,1] \tab \code{Air Flow} \tab Flow of cooling air\cr
|
27
|
+
[,2] \tab \code{Water Temp} \tab Cooling Water Inlet
|
28
|
+
Temperature\cr
|
29
|
+
[,3] \tab \code{Acid Conc.} \tab Concentration of acid [per
|
30
|
+
1000, minus 500]\cr
|
31
|
+
[,4] \tab \code{stack.loss} \tab Stack loss\cr
|
32
|
+
}
|
33
|
+
|
34
|
+
For compatibility with S-PLUS, the data sets \code{stack.x}, a matrix
|
35
|
+
with the first three (independent) variables of the data frame, and
|
36
|
+
\code{stack.loss}, the numeric vector giving the fourth (dependent)
|
37
|
+
variable, are provided as well.
|
38
|
+
}
|
39
|
+
\source{
|
40
|
+
Brownlee, K. A. (1960, 2nd ed. 1965)
|
41
|
+
\emph{Statistical Theory and Methodology in Science and Engineering}.
|
42
|
+
New York: Wiley. pp. 491--500.
|
43
|
+
}
|
44
|
+
\details{
|
45
|
+
\dQuote{Obtained from 21 days of operation of a plant for the
|
46
|
+
oxidation of ammonia (NH\eqn{_3}{3}) to nitric acid
|
47
|
+
(HNO\eqn{_3}{3}). The nitric oxides produced are absorbed in a
|
48
|
+
countercurrent absorption tower}.
|
49
|
+
(Brownlee, cited by Dodge, slightly reformatted by MM.)
|
50
|
+
|
51
|
+
\code{Air Flow} represents the rate of operation of the plant.
|
52
|
+
\code{Water Temp} is the temperature of cooling water circulated
|
53
|
+
through coils in the absorption tower.
|
54
|
+
\code{Acid Conc.} is the concentration of the acid circulating, minus
|
55
|
+
50, times 10: that is, 89 corresponds to 58.9 per cent acid.
|
56
|
+
\code{stack.loss} (the dependent variable) is 10 times the percentage
|
57
|
+
of the ingoing ammonia to the plant that escapes from the absorption
|
58
|
+
column unabsorbed; that is, an (inverse) measure of the over-all
|
59
|
+
efficiency of the plant.
|
60
|
+
}
|
61
|
+
\references{
|
62
|
+
Becker, R. A., Chambers, J. M. and Wilks, A. R. (1988)
|
63
|
+
\emph{The New S Language}.
|
64
|
+
Wadsworth & Brooks/Cole.
|
65
|
+
|
66
|
+
Dodge, Y. (1996)
|
67
|
+
The guinea pig of multiple regression. In:
|
68
|
+
\emph{Robust Statistics, Data Analysis, and Computer Intensive
|
69
|
+
Methods; In Honor of Peter Huber's 60th Birthday}, 1996,
|
70
|
+
\emph{Lecture Notes in Statistics} \bold{109}, Springer-Verlag, New York.
|
71
|
+
}
|
72
|
+
\examples{
|
73
|
+
require(stats)
|
74
|
+
summary(lm.stack <- lm(stack.loss ~ stack.x))
|
75
|
+
}
|
76
|
+
\keyword{datasets}
|
77
|
+
|
data/data/r/man/state.Rd
ADDED
@@ -0,0 +1,80 @@
|
|
1
|
+
% File src/library/datasets/man/state.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{state}
|
7
|
+
\docType{data}
|
8
|
+
\alias{state}
|
9
|
+
\alias{state.abb}
|
10
|
+
\alias{state.area}
|
11
|
+
\alias{state.center}
|
12
|
+
\alias{state.division}
|
13
|
+
\alias{state.name}
|
14
|
+
\alias{state.region}
|
15
|
+
\alias{state.x77}
|
16
|
+
\title{US State Facts and Figures}
|
17
|
+
\description{Data sets related to the 50 states of the United States of
|
18
|
+
America.}
|
19
|
+
\usage{
|
20
|
+
state.abb
|
21
|
+
state.area
|
22
|
+
state.center
|
23
|
+
state.division
|
24
|
+
state.name
|
25
|
+
state.region
|
26
|
+
state.x77
|
27
|
+
}
|
28
|
+
\details{
|
29
|
+
\R currently contains the following \dQuote{state} data sets. Note
|
30
|
+
that all data are arranged according to alphabetical order of the
|
31
|
+
state names.
|
32
|
+
\describe{
|
33
|
+
\item{\code{state.abb}:}{character vector of 2-letter abbreviations
|
34
|
+
for the state names.}
|
35
|
+
\item{\code{state.area}:}{numeric vector of state areas (in square
|
36
|
+
miles).}
|
37
|
+
\item{\code{state.center}:}{ list with components named \code{x} and
|
38
|
+
\code{y} giving the approximate geographic center of each state in
|
39
|
+
negative longitude and latitude. Alaska and Hawaii are placed
|
40
|
+
just off the West Coast.}
|
41
|
+
\item{\code{state.division}:}{factor giving state divisions (New
|
42
|
+
England, Middle Atlantic, South Atlantic, East South Central, West
|
43
|
+
South Central, East North Central, West North Central, Mountain,
|
44
|
+
and Pacific).}
|
45
|
+
\item{\code{state.name}:}{character vector giving the full state
|
46
|
+
names.}
|
47
|
+
\item{\code{state.region}:}{factor giving the region (Northeast,
|
48
|
+
South, North Central, West) that each state belongs to.}
|
49
|
+
\item{\code{state.x77}:}{matrix with 50 rows and 8 columns giving
|
50
|
+
the following statistics in the respective columns.
|
51
|
+
\describe{
|
52
|
+
\item{\code{Population}:}{population estimate as of July 1,
|
53
|
+
1975}
|
54
|
+
\item{\code{Income}:}{per capita income (1974)}
|
55
|
+
\item{\code{Illiteracy}:}{illiteracy (1970, percent of
|
56
|
+
population)}
|
57
|
+
\item{\code{Life Exp}:}{life expectancy in years (1969--71)}
|
58
|
+
\item{\code{Murder}:}{murder and non-negligent manslaughter rate
|
59
|
+
per 100,000 population (1976)}
|
60
|
+
\item{\code{HS Grad}:}{percent high-school graduates (1970)}
|
61
|
+
\item{\code{Frost}:}{mean number of days with minimum
|
62
|
+
temperature below freezing (1931--1960) in capital or large
|
63
|
+
city}
|
64
|
+
\item{\code{Area}:}{land area in square miles}
|
65
|
+
}}
|
66
|
+
}
|
67
|
+
}
|
68
|
+
\source{
|
69
|
+
U.S. Department of Commerce, Bureau of the Census (1977)
|
70
|
+
\emph{Statistical Abstract of the United States}.
|
71
|
+
|
72
|
+
U.S. Department of Commerce, Bureau of the Census (1977)
|
73
|
+
\emph{County and City Data Book}.
|
74
|
+
}
|
75
|
+
\references{
|
76
|
+
Becker, R. A., Chambers, J. M. and Wilks, A. R. (1988)
|
77
|
+
\emph{The New S Language}.
|
78
|
+
Wadsworth & Brooks/Cole.
|
79
|
+
}
|
80
|
+
\keyword{datasets}
|
@@ -0,0 +1,49 @@
|
|
1
|
+
% File src/library/datasets/man/sunspot.month.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{sunspot.month}
|
7
|
+
\docType{data}
|
8
|
+
\alias{sunspot.month}
|
9
|
+
\title{
|
10
|
+
Monthly Sunspot Data, 1749--1997
|
11
|
+
}
|
12
|
+
\description{
|
13
|
+
Monthly numbers of sunspots.
|
14
|
+
}
|
15
|
+
\usage{
|
16
|
+
sunspot.month
|
17
|
+
}
|
18
|
+
\format{
|
19
|
+
The univariate time series \code{sunspot.year} and
|
20
|
+
\code{sunspot.month} contain 289 and 2988 observations, respectively.
|
21
|
+
The objects are of class \code{"ts"}.
|
22
|
+
}
|
23
|
+
\seealso{
|
24
|
+
\code{sunspot.month} is a longer version of \code{\link{sunspots}}
|
25
|
+
that runs until 1988 rather than 1983.
|
26
|
+
}
|
27
|
+
\source{
|
28
|
+
World Data Center-C1 For Sunspot Index
|
29
|
+
Royal Observatory of Belgium, Av. Circulaire, 3, B-1180 BRUSSELS
|
30
|
+
\url{http://www.oma.be/KSB-ORB/SIDC/sidc_txt.html}
|
31
|
+
}
|
32
|
+
\examples{
|
33
|
+
require(stats); require(graphics)
|
34
|
+
## Compare the monthly series
|
35
|
+
plot (sunspot.month, main = "sunspot.month [stats]", col = 2)
|
36
|
+
lines(sunspots) # "very barely" see something
|
37
|
+
|
38
|
+
## Now look at the difference :
|
39
|
+
all(tsp(sunspots) [c(1,3)] ==
|
40
|
+
tsp(sunspot.month)[c(1,3)]) ## Start & Periodicity are the same
|
41
|
+
n1 <- length(sunspots)
|
42
|
+
table(eq <- sunspots == sunspot.month[1:n1]) #> 132 are different !
|
43
|
+
i <- which(!eq)
|
44
|
+
rug(time(eq)[i])
|
45
|
+
s1 <- sunspots[i] ; s2 <- sunspot.month[i]
|
46
|
+
cbind(i = i, sunspots = s1, ss.month = s2,
|
47
|
+
perc.diff = round(100*2*abs(s1-s2)/(s1+s2), 1))
|
48
|
+
}
|
49
|
+
\keyword{datasets}
|
@@ -0,0 +1,26 @@
|
|
1
|
+
% File src/library/datasets/man/sunspot.year.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{sunspot.year}
|
7
|
+
\docType{data}
|
8
|
+
\alias{sunspot.year}
|
9
|
+
\title{
|
10
|
+
Yearly Sunspot Data, 1700--1988
|
11
|
+
}
|
12
|
+
\description{
|
13
|
+
Yearly numbers of sunspots.
|
14
|
+
}
|
15
|
+
\usage{
|
16
|
+
sunspot.year
|
17
|
+
}
|
18
|
+
\format{
|
19
|
+
The univariate time series \code{sunspot.year} contains 289
|
20
|
+
observations, and is of class \code{"ts"}.
|
21
|
+
}
|
22
|
+
\source{
|
23
|
+
H. Tong (1996)
|
24
|
+
\emph{Non-Linear Time Series}. Clarendon Press, Oxford, p. 471.
|
25
|
+
}
|
26
|
+
\keyword{datasets}
|
@@ -0,0 +1,33 @@
|
|
1
|
+
% File src/library/datasets/man/sunspots.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{sunspots}
|
7
|
+
\docType{data}
|
8
|
+
\alias{sunspots}
|
9
|
+
\title{Monthly Sunspot Numbers, 1749--1983}
|
10
|
+
\description{
|
11
|
+
Monthly mean relative sunspot numbers from 1749 to 1983. Collected at
|
12
|
+
Swiss Federal Observatory, Zurich until 1960, then Tokyo Astronomical
|
13
|
+
Observatory.
|
14
|
+
}
|
15
|
+
\usage{sunspots}
|
16
|
+
\format{
|
17
|
+
A time series of monthly data from 1749 to 1983.
|
18
|
+
}
|
19
|
+
\source{
|
20
|
+
Andrews, D. F. and Herzberg, A. M. (1985)
|
21
|
+
\emph{Data: A Collection of Problems from Many Fields for the
|
22
|
+
Student and Research Worker}.
|
23
|
+
New York: Springer-Verlag.
|
24
|
+
}
|
25
|
+
\seealso{
|
26
|
+
\code{\link{sunspot.month}} has a longer (and a bit different) series.
|
27
|
+
}
|
28
|
+
\examples{
|
29
|
+
require(graphics)
|
30
|
+
plot(sunspots, main = "sunspots data", xlab = "Year",
|
31
|
+
ylab = "Monthly sunspot numbers")
|
32
|
+
}
|
33
|
+
\keyword{datasets}
|
data/data/r/man/swiss.Rd
ADDED
@@ -0,0 +1,79 @@
|
|
1
|
+
% File src/library/datasets/man/swiss.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{swiss}
|
7
|
+
\docType{data}
|
8
|
+
\alias{swiss}
|
9
|
+
\title{Swiss Fertility and Socioeconomic Indicators (1888) Data}
|
10
|
+
\description{
|
11
|
+
Standardized fertility measure and socio-economic indicators for each
|
12
|
+
of 47 French-speaking provinces of Switzerland at about 1888.
|
13
|
+
}
|
14
|
+
\usage{swiss}
|
15
|
+
\format{
|
16
|
+
A data frame with 47 observations on 6 variables, \emph{each} of which
|
17
|
+
is in percent, i.e., in \eqn{[0, 100]}.
|
18
|
+
|
19
|
+
\tabular{rll}{
|
20
|
+
[,1] \tab Fertility \tab \eqn{I_g}{Ig}, \sQuote{common standardized
|
21
|
+
fertility measure}\cr
|
22
|
+
[,2] \tab Agriculture\tab \% of males involved in agriculture
|
23
|
+
as occupation\cr
|
24
|
+
[,3] \tab Examination\tab \% draftees receiving highest mark
|
25
|
+
on army examination\cr
|
26
|
+
[,4] \tab Education \tab \% education beyond primary school for draftees.\cr
|
27
|
+
[,5] \tab Catholic \tab \% \sQuote{catholic} (as opposed to \sQuote{protestant}).\cr
|
28
|
+
[,6] \tab Infant.Mortality\tab live births who live less than 1
|
29
|
+
year.
|
30
|
+
}
|
31
|
+
|
32
|
+
All variables but \sQuote{Fertility} give proportions of the
|
33
|
+
population.
|
34
|
+
}
|
35
|
+
\details{
|
36
|
+
(paraphrasing Mosteller and Tukey):
|
37
|
+
|
38
|
+
Switzerland, in 1888, was entering a period known as the
|
39
|
+
\emph{demographic transition}; i.e., its fertility was beginning to
|
40
|
+
fall from the high level typical of underdeveloped countries.
|
41
|
+
|
42
|
+
The data collected are for 47 French-speaking \dQuote{provinces} at
|
43
|
+
about 1888.
|
44
|
+
|
45
|
+
Here, all variables are scaled to \eqn{[0, 100]}, where in the
|
46
|
+
original, all but \code{"Catholic"} were scaled to \eqn{[0, 1]}.
|
47
|
+
}
|
48
|
+
\source{
|
49
|
+
Project \dQuote{16P5}, pages 549--551 in
|
50
|
+
|
51
|
+
Mosteller, F. and Tukey, J. W. (1977)
|
52
|
+
\emph{Data Analysis and Regression: A Second Course in Statistics}.
|
53
|
+
Addison-Wesley, Reading Mass.
|
54
|
+
|
55
|
+
indicating their source as
|
56
|
+
\dQuote{Data used by permission of Franice van de Walle. Office of
|
57
|
+
Population Research, Princeton University, 1976. Unpublished data
|
58
|
+
assembled under NICHD contract number No 1-HD-O-2077.}
|
59
|
+
}
|
60
|
+
\references{
|
61
|
+
Becker, R. A., Chambers, J. M. and Wilks, A. R. (1988)
|
62
|
+
\emph{The New S Language}.
|
63
|
+
Wadsworth & Brooks/Cole.
|
64
|
+
}
|
65
|
+
\note{
|
66
|
+
Files for all 182 districts in 1888 and other years have been available at
|
67
|
+
\url{http://opr.princeton.edu/archive/eufert/switz.html} or
|
68
|
+
\url{http://opr.princeton.edu/archive/pefp/switz.asp}.
|
69
|
+
|
70
|
+
They state that variables \code{Examination} and \code{Education}
|
71
|
+
are averages for 1887, 1888 and 1889.
|
72
|
+
}
|
73
|
+
\examples{
|
74
|
+
require(stats); require(graphics)
|
75
|
+
pairs(swiss, panel = panel.smooth, main = "swiss data",
|
76
|
+
col = 3 + (swiss$Catholic > 50))
|
77
|
+
summary(lm(Fertility ~ . , data = swiss))
|
78
|
+
}
|
79
|
+
\keyword{datasets}
|