sciruby 0.1.0 → 0.1.3

data/data/r/man/randu.Rd

@@ -0,0 +1,46 @@
+% File src/library/datasets/man/randu.Rd
+% Part of the R package, http://www.R-project.org
+% Copyright 1995-2007 R Core Development Team
+% Distributed under GPL 2 or later
+
+\name{randu}
+\docType{data}
+\alias{randu}
+\title{Random Numbers from Congruential Generator RANDU}
+\description{
+  400 triples of successive random numbers were taken from the VAX
+  FORTRAN function RANDU running under VMS 1.5.
+}
+\usage{randu}
+\details{
+  In three dimensional displays it is evident that the triples fall on
+  15 parallel planes in 3-space. This can be shown theoretically to be
+  true for all triples from the RANDU generator.
+
+  These particular 400 triples start 5 apart in the sequence, that is
+  they are ((U[5i+1], U[5i+2], U[5i+3]), i= 0, \dots, 399), and they
+  are rounded to 6 decimal places.
+
+  Under VMS versions 2.0 and higher, this problem has been fixed.
+}
+\format{
+  A data frame with 400 observations on 3 variables named \code{x},
+  \code{y} and \code{z} which give the first, second and third random
+  number in the triple.
+}
+\source{
+  David Donoho
+}
+\examples{
+\dontrun{## We could re-generate the dataset by the following R code
+seed <- as.double(1)
+RANDU <- function() {
+    seed <<- ((2^16 + 3) * seed) \%\% (2^31)
+    seed/(2^31)
+}
+for(i in 1:400) {
+    U <- c(RANDU(), RANDU(), RANDU(), RANDU(), RANDU())
+    print(round(U[1:3], 6))
+}}
+}
+\keyword{datasets}

data/data/r/man/rivers.Rd

@@ -0,0 +1,21 @@
+% File src/library/datasets/man/rivers.Rd
+% Part of the R package, http://www.R-project.org
+% Copyright 1995-2007 R Core Development Team
+% Distributed under GPL 2 or later
+
+\name{rivers}
+\docType{data}
+\alias{rivers}
+\title{Lengths of Major North American Rivers}
+\description{
+  This data set gives the lengths (in miles) of 141 \dQuote{major}
+  rivers in North America, as compiled by the US Geological Survey.
+}
+\usage{rivers}
+\format{A vector containing 141 observations.}
+\source{World Almanac and Book of Facts, 1975, page 406.}
+\references{
+  McNeil, D. R. (1977) \emph{Interactive Data Analysis}.
+  New York: Wiley.
+}
+\keyword{datasets}

data/data/r/man/rock.Rd

@@ -0,0 +1,34 @@
+% File src/library/datasets/man/rock.Rd
+% Part of the R package, http://www.R-project.org
+% Copyright 1994-8 W. N. Venables and B. D. Ripley
+% Distributed under GPL 2 or later
+
+% Manually converted to Rd data file description format by KH.
+\name{rock}
+\docType{data}
+\alias{rock}
+\title{Measurements on Petroleum Rock Samples}
+\description{
+    Measurements on 48 rock samples from a petroleum reservoir.}
+\usage{rock}
+\format{
+    A data frame with 48 rows and 4 numeric columns.
+
+    \tabular{rll}{
+        [,1] \tab area  \tab area of pores space, in pixels
+        out of 256 by 256 \cr
+        [,2] \tab peri  \tab perimeter in pixels \cr
+        [,3] \tab shape \tab perimeter/sqrt(area) \cr
+        [,4] \tab perm  \tab permeability in milli-Darcies
+    }
+}
+\details{
+    Twelve core samples from petroleum reservoirs were sampled by 4
+    cross-sections.  Each core sample was measured for permeability, and
+    each cross-section has total area of pores, total perimeter of
+    pores, and shape.
+}
+\source{
+    Data from BP Research, image analysis by Ronit Katz, U. Oxford.
+}
+\keyword{datasets}

data/data/r/man/sleep.Rd

@@ -0,0 +1,51 @@
+% File src/library/datasets/man/sleep.Rd
+% Part of the R package, http://www.R-project.org
+% Copyright 1995-2010 R Core Development Team
+% Copyright 1999-2010 The R Foundation
+% Distributed under GPL 2 or later
+
+\name{sleep}
+\docType{data}
+\encoding{UTF-8}
+\alias{sleep}
+\title{Student's Sleep Data}
+\description{
+  Data which show the effect of two soporific drugs (increase in hours
+  of sleep compared to control) on 10 patients.
+}
+\usage{sleep}
+\format{
+  A data frame with 20 observations on 3 variables.
+  \tabular{rlll}{
+    [, 1] \tab extra \tab numeric \tab increase in hours of sleep\cr
+    [, 2] \tab group \tab factor  \tab drug given\cr
+    [, 3] \tab ID    \tab factor  \tab patient ID
+  }
+}
+\source{
+  Cushny, A. R. and Peebles, A. R. (1905)
+  The action of optical isomers: II hyoscines.
+  \emph{The Journal of Physiology} \bold{32}, 501--510.
+
+  Student (1908)
+  The probable error of the mean.
+  \emph{Biometrika}, \bold{6}, 20.
+}
+\details{
+  The \code{group} variable name may be misleading about the data:
+  They represent measurements on 10 persons, not in groups.
+  %% But we keep it (as [,2]) for back compatibility.
+}
+\references{
+  \enc{Scheffé}{Scheffe}, Henry (1959)
+  \emph{The Analysis of Variance}.
+  New York, NY: Wiley.
+}
+\examples{
+require(stats)
+## Student's paired t-test
+with(sleep,
+     t.test(extra[group == 1],
+            extra[group == 2], paired = TRUE))
+}
+\keyword{datasets}

data/data/r/man/stackloss.Rd

@@ -0,0 +1,77 @@
+% File src/library/datasets/man/stackloss.Rd
+% Part of the R package, http://www.R-project.org
+% Copyright 1995-2007 R Core Development Team
+% Distributed under GPL 2 or later
+
+\name{stackloss}
+\docType{data}
+\alias{stackloss}
+\alias{stack.loss}
+\alias{stack.x}
+\title{Brownlee's Stack Loss Plant Data}
+\description{
+  Operational data of a plant for the oxidation of ammonia to nitric
+  acid.
+}
+\usage{
+stackloss
+
+stack.x
+stack.loss
+}
+\format{
+  \code{stackloss} is a data frame with 21 observations on 4 variables.
+
+  \tabular{rll}{
+    [,1] \tab \code{Air Flow}   \tab Flow of cooling air\cr
+    [,2] \tab \code{Water Temp} \tab Cooling Water Inlet
+    Temperature\cr
+    [,3] \tab  \code{Acid Conc.} \tab Concentration of acid [per
+    1000, minus 500]\cr
+    [,4] \tab  \code{stack.loss} \tab Stack loss\cr
+  }
+
+  For compatibility with S-PLUS, the data sets \code{stack.x}, a matrix
+  with the first three (independent) variables of the data frame, and
+  \code{stack.loss}, the numeric vector giving the fourth (dependent)
+  variable, are provided as well.
+}
+\source{
+  Brownlee, K. A. (1960, 2nd ed. 1965)
+  \emph{Statistical Theory and Methodology in Science and Engineering}.
+  New York: Wiley. pp. 491--500.
+}
+\details{
+  \dQuote{Obtained from 21 days of operation of a plant for the
+    oxidation of ammonia (NH\eqn{_3}{3}) to nitric acid
+    (HNO\eqn{_3}{3}).  The nitric oxides produced are absorbed in a
+    countercurrent absorption tower}.
+  (Brownlee, cited by Dodge, slightly reformatted by MM.)
+
+  \code{Air Flow} represents the rate of operation of the plant.
+  \code{Water Temp} is the temperature of cooling water circulated
+  through coils in the absorption tower.
+  \code{Acid Conc.} is the concentration of the acid circulating, minus
+  50, times 10: that is, 89 corresponds to 58.9 per cent acid.
+  \code{stack.loss} (the dependent variable) is 10 times the percentage
+  of the ingoing ammonia to the plant that escapes from the absorption
+  column unabsorbed; that is, an (inverse) measure of the over-all
+  efficiency of the plant.
+}
+\references{
+  Becker, R. A., Chambers, J. M. and Wilks, A. R. (1988)
+  \emph{The New S Language}.
+  Wadsworth & Brooks/Cole.
+
+  Dodge, Y. (1996)
+  The guinea pig of multiple regression. In:
+  \emph{Robust Statistics, Data Analysis, and Computer Intensive
+    Methods; In Honor of Peter Huber's 60th Birthday}, 1996,
+  \emph{Lecture Notes in Statistics} \bold{109}, Springer-Verlag, New York.
+}
+\examples{
+require(stats)
+summary(lm.stack <- lm(stack.loss ~ stack.x))
+}
+\keyword{datasets}
+

data/data/r/man/state.Rd

@@ -0,0 +1,80 @@
+% File src/library/datasets/man/state.Rd
+% Part of the R package, http://www.R-project.org
+% Copyright 1995-2007 R Core Development Team
+% Distributed under GPL 2 or later
+
+\name{state}
+\docType{data}
+\alias{state}
+\alias{state.abb}
+\alias{state.area}
+\alias{state.center}
+\alias{state.division}
+\alias{state.name}
+\alias{state.region}
+\alias{state.x77}
+\title{US State Facts and Figures}
+\description{Data sets related to the 50 states of the United States of
+  America.}
+\usage{
+state.abb
+state.area
+state.center
+state.division
+state.name
+state.region
+state.x77
+}
+\details{
+  \R currently contains the following \dQuote{state} data sets.  Note
+  that all data are arranged according to alphabetical order of the
+  state names.
+  \describe{
+    \item{\code{state.abb}:}{character vector of 2-letter abbreviations
+      for the state names.}
+    \item{\code{state.area}:}{numeric vector of state areas (in square
+      miles).}
+    \item{\code{state.center}:}{ list with components named \code{x} and
+      \code{y} giving the approximate geographic center of each state in
+      negative longitude and latitude.  Alaska and Hawaii are placed
+      just off the West Coast.}
+    \item{\code{state.division}:}{factor giving state divisions (New
+      England, Middle Atlantic, South Atlantic, East South Central, West
+      South Central, East North Central, West North Central, Mountain,
+      and Pacific).}
+    \item{\code{state.name}:}{character vector giving the full state
+      names.}
+    \item{\code{state.region}:}{factor giving the region (Northeast,
+      South, North Central, West) that each state belongs to.}
+    \item{\code{state.x77}:}{matrix with 50 rows and 8 columns giving
+      the following statistics in the respective columns.
+      \describe{
+        \item{\code{Population}:}{population estimate as of July 1,
+          1975}
+        \item{\code{Income}:}{per capita income (1974)}
+        \item{\code{Illiteracy}:}{illiteracy (1970, percent of
+          population)}
+        \item{\code{Life Exp}:}{life expectancy in years (1969--71)}
+        \item{\code{Murder}:}{murder and non-negligent manslaughter rate
+          per 100,000 population (1976)}
+        \item{\code{HS Grad}:}{percent high-school graduates (1970)}
+        \item{\code{Frost}:}{mean number of days with minimum
+          temperature below freezing (1931--1960) in capital or large
+          city}
+       \item{\code{Area}:}{land area in square miles}
+    }}
+  }
+}
+\source{
+  U.S. Department of Commerce, Bureau of the Census (1977)
+  \emph{Statistical Abstract of the United States}.
+
+  U.S. Department of Commerce, Bureau of the Census (1977)
+  \emph{County and City Data Book}.
+}
+\references{
+  Becker, R. A., Chambers, J. M. and Wilks, A. R. (1988)
+  \emph{The New S Language}.
+  Wadsworth & Brooks/Cole.
+}
+\keyword{datasets}

data/data/r/man/sunspot.month.Rd

@@ -0,0 +1,49 @@
+% File src/library/datasets/man/sunspot.month.Rd
+% Part of the R package, http://www.R-project.org
+% Copyright 1995-2007 R Core Development Team
+% Distributed under GPL 2 or later
+
+\name{sunspot.month}
+\docType{data}
+\alias{sunspot.month}
+\title{
+  Monthly Sunspot Data, 1749--1997
+}
+\description{
+  Monthly numbers of sunspots. 
+}
+\usage{
+sunspot.month
+}
+\format{
+  The univariate time series \code{sunspot.year} and
+  \code{sunspot.month} contain 289 and 2988 observations, respectively.
+  The objects are of class \code{"ts"}.
+}
+\seealso{
+  \code{sunspot.month} is a longer version of \code{\link{sunspots}}
+  that runs until 1988 rather than 1983.
+}
+\source{
+  World Data Center-C1 For Sunspot Index
+  Royal Observatory of Belgium, Av. Circulaire, 3, B-1180 BRUSSELS
+  \url{http://www.oma.be/KSB-ORB/SIDC/sidc_txt.html}
+}
+\examples{
+require(stats); require(graphics)
+## Compare the monthly series 
+plot (sunspot.month, main = "sunspot.month [stats]", col = 2)
+lines(sunspots) # "very barely" see something
+
+## Now look at the difference :
+all(tsp(sunspots)     [c(1,3)] ==
+    tsp(sunspot.month)[c(1,3)]) ## Start & Periodicity are the same
+n1 <- length(sunspots)
+table(eq <- sunspots == sunspot.month[1:n1]) #>  132  are different !
+i <- which(!eq) 
+rug(time(eq)[i])
+s1 <- sunspots[i] ; s2 <- sunspot.month[i]
+cbind(i = i, sunspots = s1, ss.month = s2,
+      perc.diff = round(100*2*abs(s1-s2)/(s1+s2), 1))
+}
+\keyword{datasets}

data/data/r/man/sunspot.year.Rd

@@ -0,0 +1,26 @@
+% File src/library/datasets/man/sunspot.year.Rd
+% Part of the R package, http://www.R-project.org
+% Copyright 1995-2007 R Core Development Team
+% Distributed under GPL 2 or later
+
+\name{sunspot.year}
+\docType{data}
+\alias{sunspot.year}
+\title{
+  Yearly Sunspot Data, 1700--1988
+}
+\description{
+  Yearly numbers of sunspots. 
+}
+\usage{
+sunspot.year
+}
+\format{
+  The univariate time series \code{sunspot.year} contains 289
+  observations, and is of class \code{"ts"}.
+}
+\source{
+  H. Tong (1996)
+  \emph{Non-Linear Time Series}. Clarendon Press, Oxford, p. 471. 
+}
+\keyword{datasets}

data/data/r/man/sunspots.Rd

@@ -0,0 +1,33 @@
+% File src/library/datasets/man/sunspots.Rd
+% Part of the R package, http://www.R-project.org
+% Copyright 1995-2007 R Core Development Team
+% Distributed under GPL 2 or later
+
+\name{sunspots}
+\docType{data}
+\alias{sunspots}
+\title{Monthly Sunspot Numbers, 1749--1983}
+\description{
+  Monthly mean relative sunspot numbers from 1749 to 1983.  Collected at
+  Swiss Federal Observatory, Zurich until 1960, then Tokyo Astronomical
+  Observatory.
+}
+\usage{sunspots}
+\format{
+  A time series of monthly data from 1749 to 1983.
+}
+\source{
+  Andrews, D. F. and Herzberg, A. M. (1985)
+  \emph{Data: A Collection of Problems from Many Fields for the
+    Student and Research Worker}.
+  New York: Springer-Verlag.
+}
+\seealso{
+  \code{\link{sunspot.month}} has a longer (and a bit different) series.
+} 
+\examples{
+require(graphics)
+plot(sunspots, main = "sunspots data", xlab = "Year",
+     ylab = "Monthly sunspot numbers")
+}
+\keyword{datasets}

data/data/r/man/swiss.Rd

@@ -0,0 +1,79 @@
+% File src/library/datasets/man/swiss.Rd
+% Part of the R package, http://www.R-project.org
+% Copyright 1995-2007 R Core Development Team
+% Distributed under GPL 2 or later
+
+\name{swiss}
+\docType{data}
+\alias{swiss}
+\title{Swiss Fertility and Socioeconomic Indicators (1888) Data}
+\description{
+  Standardized fertility measure and socio-economic indicators for each
+  of 47 French-speaking provinces of Switzerland at about 1888.
+}
+\usage{swiss}
+\format{
+  A data frame with 47 observations on 6 variables, \emph{each} of which
+  is in percent, i.e., in \eqn{[0, 100]}.
+
+  \tabular{rll}{
+    [,1] \tab Fertility \tab \eqn{I_g}{Ig}, \sQuote{common standardized
+    fertility measure}\cr
+    [,2] \tab Agriculture\tab \% of males involved in agriculture
+    as occupation\cr
+    [,3] \tab Examination\tab \% draftees receiving highest mark
+    on army examination\cr
+    [,4] \tab Education \tab \% education beyond primary school for draftees.\cr
+    [,5] \tab Catholic \tab \% \sQuote{catholic} (as opposed to \sQuote{protestant}).\cr
+    [,6] \tab Infant.Mortality\tab live births who live less than 1
+    year.
+  }
+
+  All variables but \sQuote{Fertility} give proportions of the
+  population.
+}
+\details{
+  (paraphrasing Mosteller and Tukey):
+
+  Switzerland, in 1888, was entering a period known as the
+  \emph{demographic transition}; i.e., its fertility was beginning to
+  fall from the high level typical of underdeveloped countries.
+
+  The data collected are for 47 French-speaking \dQuote{provinces} at
+  about 1888.
+
+  Here, all variables are scaled to \eqn{[0, 100]}, where in the
+  original, all but \code{"Catholic"} were scaled to \eqn{[0, 1]}.
+}
+\source{
+  Project \dQuote{16P5}, pages 549--551 in
+
+  Mosteller, F. and Tukey, J. W. (1977)
+  \emph{Data Analysis and Regression: A Second Course in Statistics}.
+  Addison-Wesley, Reading Mass.
+
+  indicating their source as
+  \dQuote{Data used by permission of Franice van de Walle. Office of
+  Population Research, Princeton University, 1976.  Unpublished data
+  assembled under NICHD contract number No 1-HD-O-2077.}
+}
+\references{
+  Becker, R. A., Chambers, J. M. and Wilks, A. R. (1988)
+  \emph{The New S Language}.
+  Wadsworth & Brooks/Cole.
+}
+\note{
+  Files for all 182 districts in 1888 and other years have been available at
+  \url{http://opr.princeton.edu/archive/eufert/switz.html} or
+  \url{http://opr.princeton.edu/archive/pefp/switz.asp}.
+
+  They state that variables \code{Examination} and \code{Education}
+  are averages for 1887, 1888 and 1889.
+}
+\examples{
+require(stats); require(graphics)
+pairs(swiss, panel = panel.smooth, main = "swiss data",
+      col = 3 + (swiss$Catholic > 50))
+summary(lm(Fertility ~ . , data = swiss))
+}
+\keyword{datasets}