NEWS | R Documentation |
A generic mplot
and several instances have been
added to make a number of plots easy to generate. There are methods
for objects of classes
"data.frame"
,
"lm"
,
"summary.lm"
,
"glm"
,
"summary.glm"
,
"TukeyHSD"
, and
"hclust"
. For several of these there are also
fortify
methods that return the data frame created to
facilitate plotting.
read.file
now handles https URLs and accepts
an optional argument filetype
that can be used to
declare the type of data file when it is not identified
by extension.
The default for useNA
in the tally
function
has changed to "ifany"
.
mosaic now depends on dplyr both to use some
of its functionality and to avoid naming collisions with functions
like tally
and do
, allowing mosaic and dplyr
to coexist more happily.
some improvements to dot plots with dotPlot
. In particular,
the size of the dots is determined differently and works better
more of the time. Dots were also shifted down by .5 units so that they
don't hover above the x-axis so much. This means that (with default
sizing) the tops of the dots are approximately located at a height
equivalent to the number of dots rather than the center of the dots.
fixed a bug in do
that caused it to scope incorrectly
in some edge cases when a variable had the same name as a function.
ntiles
has been reimplemented and now has more
formatting options.
introduction of derivedFactor
for creating factors
from logical "cases".
The HELP
data set has been removed from the package.
It was deprecated in version 0.5. Use HELPrct
instead.
plotDist
now accepts add=TRUE
and under=TRUE
, making it easy to add
plots of distributions over (or under) plots of data (e.g., histograms, densityplots, etc.)
or other distributions.
Plotting funcitons with with the option add=TRUE
have been reimplemented using
layer
from latticeExtra. See documentaiton of these functions for details.
ladd
has been completely reimplemented using layer()
from latticeExtra. See
documentation of ladd()
for details, including some behavior changes.
aggregating functions (mean
, sd
, var
, et al) now use getOptions("na.rm")
to determine the default value of na.rm
. Use options(na.rm=TRUE)
to
change the default behavior to remove NA
s and options(na.rm=NULL) to restore
defaults.
do
has been largely rewritten with an eye toward improved
efficiency. In particular, do
will take advantage of multiple cores
if the parallel package is availalbe. At this point, sluggishness in applications of do
are
mostly likely due to the sluggishness of what is being done, not to do
itself.
Added an additional method to deltaMethod
from the car package to make it easier to do propagation of uncertainty is some situations
that arrise commonly in the physical sciences and engineering.
Added cdist
to compute critical values for the central portion
of a distribution.
Some changes to the API for qdata
. For interactive use, this
not cause any problem, but old programmatic uses of qdata
should be
checked as the object returned is now different.
Fixed a bug that caused aggregating functions (sum
, mean
, sd
, etc.) to produce counter-intuititve results (but with a warning). The results are now what one would expect (and the warning is removed).
Added rsquared
for extracting r-squared from models and model-like objects (r.squared
has been deprecated).
do
now handles ANOVA-like objects better
maggregate
is now built on some improved behind the scenes functions. Among
other features, the groups
argument is now incorporated as an alternative method
of specifying the goups to aggregate over and the method
argument can be set to
"ddply"
to use ddply
from the plyr package for aggregation. This results
in a different output format that may be desired in some applications.
The cdata
, pdata
and qdata
functions have been largely rewritten. In addition,
cdata_f
, pdata_f
and qdata_f
are provided which produce similar results
but have a formula in the first arguemnt slot.
Fixed bug in vignette generation. Static PDFs are now installed in doc/
and so
are available from within the package as well as via links to external files.
Added fetchGapminder
for fetching data sets originally from
Gapminder.
Added cdata
for finding end points of a central portion of a variable.
Name changes in functions like prop
to avoid internal :
which makes downstream processing messier.
Improved detection of the availability of manipulate
(RStudio)
Surface plots produced by plotFun
can be used without
manipulate
. This makes it possible to put surface plots into RMarkdown or Rnw files or to generate them outside of RStudio.
do() * rflip()
now records proportion heads as well
as counts of heads and tails.
Added functions mosaicLatticeOptions
and restoreLatticeOptions
to switch back and forth between lattice
defaults and
mosaic
defaults.
dotPlot
uses a different algorithm to determine dot sizes.
(Still not perfect, but cex
can be used to further scale the dots.)
adjustments to histogram
so that nint
matches the number of bins used more accurately.
fixed coding error in the HELP datasets so that i2
: max number of drinks is at least as large as i1
: the average number of drinks.
removed the deprecated HELP dataset (now called HELPrct)
Various minor bug fixes and internal improvements.
Various improvements and bug fixes to D
and antiD
.
In RStudio, mPlot
provides an interactive environment for
creating lattice and ggplot2 plots.
Some support for producing maps has been introduced, notably sp2df
for converting SpatialPolygonDataFrames to regular data frames (which is useful for plotting with ggplot2, for example). Also the Countries
data frame facilitates
mapping country names among different sources of map data.
Data frames returned by do
are now marked as such so that confint
can behave differently for such data frames and for "regular" data frames.
t.test
can now do 1-sample t-test described using a formula.
Aggregating functions (e.g. mean
, var
, etc. using a formula
interface) have been completely
reimplemented and additional aggregating functions are provided.
An ntiles
function has been added to facilitate creating
factors based on quantile ranges.
Changes in format to RailTrail
dataset.
Minor changes in documentation.
Added vignettes: Starting with R and A Compendium of Commands to Teach Statistics.
Plan to deprecate datasets from the Carnegie Melon University Online Learning Initiative Statistics Modules in next release.
xhistogram
is now deprecated. Use histogram
instead.
Added vignette: Minimal R for Intro Stats.
Implemented symbolic integration for simple functions.
Aggregating functions (mean
, max
, median
, var
, etc.) now use getOption('na.rm')
to determine default behavior.
Various bug fixes in var()
allow it to work in a wider range of situations.
Augmented TukeyHSD
so that explicit use of aov
is no longer required
Added panel.lmbands
for plotting confidence and prediction bands in linear regression
Some data cleaning in the Carnegie Melon University Online Learning Initiative Statistics Modules. In particular
the name collision with Animals
from MASS
has been
removed by renaming the data set GestationLongevity
.
Added freqpolygon
for making frequency polygons.
Added r.squared
for extracting r-squared from models and model-like objects.
Modified names of data frame produced by do
so that hyphens ('-') are turned into dots ('.')
Improvements to fetchData
.
We're still in beta, but we hope things are beginning to stabilize as we settle on syntax and coding idioms for the package. Here are some of the key updates since 0.4:
removed dependency on RCurl since it caused installation problems for some PC users. (Code requiring RCurl now checks at run time whether the package is available.)
further improvements to formula interfaces to common functions. The conditional | now works in more situations and & has been replaced by + so that formulas look more like the formulas
used in lm()
and its cousins.
inclusion of the datasets from the Carnegie Mellon University Online Learning Initiative Statistics modules. These are in alpha form and some additional data cleaning and renaming may happen in the near future.
makeFun()
now has methods for glm and nls objects
D()
improved to use symbolic differentiation in more cases and allow pass through to
stats::D()
when that makes sense. This allows functions like deltaMethod() from the car package
to work properly even when the mosaic package is loaded.
The API for antiD()
has been modified somewhat. This may go through another revision
if/when we add in symbolic differentiation, but we think we are now close to the end state.
The HELP dataset has been replaced by the HELPrct dataset, and the former will be deprecated in the next release.
The CPS data set has been renamed CPS85.
fitSpline()
and fitModel()
have been added as wrappers around linear models using ns(), bs(), and nls().
Each of these returns the model fit as a function.
improvements to the vignettes.
renamed mtable() to tally(), added new functionality
reimplemented D() and antiD()
improvements to statTally()
new confint() functionality
makeFun() and plotFun() interface to plotting using formulas
added new vignette on Teaching Calculus using R
added new vignette on Resampling-Based Inference using R
changed default behavior for aggregating functions na.rm option so that it defaults to usual behavior unless given a formula as argument