bam {mgcv}  R Documentation 
Generalized additive models for very large datasets
Description
Fits a generalized additive model (GAM) to a very large
data set, the term ‘GAM’ being taken to include any quadratically penalized GLM (the extended families
listed in family.mgcv
can also be used).
The degree of smoothness of model terms is estimated as part of
fitting. In use the function is much like gam
, except that the numerical methods
are designed for datasets containing upwards of several tens of thousands of data (see Wood, Goude and Shaw, 2015). The advantage
of bam
is much lower memory footprint than gam
, but it can also be much faster,
for large datasets. bam
can also compute on a cluster set up by the parallel package.
An alternative fitting approach (Wood et al. 2017, Li and Wood, 2019) is provided by the discrete==TRUE
method. In this case a method based on discretization of covariate values and C code level parallelization (controlled by the nthreads
argument instead of the cluster
argument) is used. This extends both the data set and model size that are practical.
Usage
bam(formula,family=gaussian(),data=list(),weights=NULL,subset=NULL,
na.action=na.omit, offset=NULL,method="fREML",control=list(),
select=FALSE,scale=0,gamma=1,knots=NULL,sp=NULL,min.sp=NULL,
paraPen=NULL,chunk.size=10000,rho=0,AR.start=NULL,discrete=FALSE,
cluster=NULL,nthreads=1,gc.level=0,use.chol=FALSE,samfrac=1,
coef=NULL,drop.unused.levels=TRUE,G=NULL,fit=TRUE,drop.intercept=NULL,
in.out=NULL,...)
Arguments
formula 
A GAM formula (see 
family 
This is a family object specifying the distribution and link to use in
fitting etc. See 
data 
A data frame or list containing the model response variable and
covariates required by the formula. By default the variables are taken
from 
weights 
prior weights on the contribution of the data to the log likelihood. Note that a weight of 2, for example,
is equivalent to having made exactly the same observation twice. If you want to reweight the contributions
of each datum without changing the overall magnitude of the log likelihood, then you should normalize the weights
(e.g. 
subset 
an optional vector specifying a subset of observations to be used in the fitting process. 
na.action 
a function which indicates what should happen when the data contain ‘NA’s. The default is set by the ‘na.action’ setting of ‘options’, and is ‘na.fail’ if that is unset. The “factoryfresh” default is ‘na.omit’. 
offset 
Can be used to supply a model offset for use in fitting. Note
that this offset will always be completely ignored when predicting, unlike an offset
included in 
method 
The smoothing parameter estimation method. 
control 
A list of fit control parameters to replace defaults returned by

select 
Should selection penalties be added to the smooth effects, so that they can in principle be
penalized out of the model? See 
scale 
If this is positive then it is taken as the known scale parameter. Negative signals that the scale paraemter is unknown. 0 signals that the scale parameter is 1 for Poisson and binomial and unknown otherwise. Note that (RE)ML methods can only work with scale parameter 1 for the Poisson and binomial cases. 
gamma 
Increase above 1 to force smoother fits. 
knots 
this is an optional list containing user specified knot values to be used for basis construction.
For most bases the user simply supplies the knots to be used, which must match up with the 
sp 
A vector of smoothing parameters can be provided here.
Smoothing parameters must be supplied in the order that the smooth terms appear in the model
formula. Negative elements indicate that the parameter should be estimated, and hence a mixture
of fixed and estimated parameters is possible. If smooths share smoothing parameters then 
min.sp 
Lower bounds can be supplied for the smoothing parameters. Note
that if this option is used then the smoothing parameters 
paraPen 
optional list specifying any penalties to be applied to parametric model terms.

chunk.size 
The model matrix is created in chunks of this size, rather than ever being formed whole.
Reset to 
rho 
An AR1 error model can be used for the residuals (based on dataframe order), of Gaussianidentity
link models. This is the AR1 correlation parameter. Standardized residuals (approximately
uncorrelated under correct model) returned in

AR.start 
logical variable of same length as data, 
discrete 
with 
cluster 

nthreads 
Number of threads to use for noncluster computation (e.g. combining results from cluster nodes).
If 
gc.level 
to keep the memory footprint down, it can help to call the garbage collector often, but this takes a substatial amount of time. Setting this to zero means that garbage collection only happens when R decides it should. Setting to 2 gives frequent garbage collection. 1 is in between. Not as much of a problem as it used to be. 
use.chol 
By default 
samfrac 
For very large sample size Generalized additive models the number of iterations needed for the model fit can
be reduced by first fitting a model to a random sample of the data, and using the results to supply starting values. This initial fit is run with sloppy convergence tolerances, so is typically very low cost. 
coef 
initial values for model coefficients 
drop.unused.levels 
by default unused levels are dropped from factors before fitting. For some smooths involving factor variables you might want to turn this off. Only do so if you know what you are doing. 
G 
if not 
fit 
if 
drop.intercept 
Set to 
in.out 
If supplied then this is a two item list of intial values. 
... 
further arguments for
passing on e.g. to 
Details
When discrete=FALSE
, bam
operates by first setting up the basis characteristics for the smooths, using a representative subsample of the data. Then the model matrix is constructed in blocks using predict.gam
. For each block the factor R,
from the QR decomposition of the whole model matrix is updated, along with Q'y. and the sum of squares of y. At the end of
block processing, fitting takes place, without the need to ever form the whole model matrix.
In the generalized case, the same trick is used with the weighted model matrix and weighted pseudodata, at each step of the PIRLS. Smoothness selection is performed on the working model at each stage (performance oriented iteration), to maintain the small memory footprint. This is trivial to justify in the case of GCV or Cp/UBRE/AIC based model selection, and for REML/ML is justified via the asymptotic multivariate normality of Q'z where z is the IRLS pseudodata.
For full method details see Wood, Goude and Shaw (2015).
Note that POI is not as stable as the default nested iteration used with gam
, but that for very large, information rich,
datasets, this is unlikely to matter much.
Note also that it is possible to spend most of the computational time on basis evaluation, if an expensive basis is used. In practice this means that the default "tp"
basis should be avoided: almost any other basis (e.g. "cr"
or "ps"
)
can be used in the 1D case, and tensor product smooths (te
) are typically much less costly in the multidimensional case.
If cluster
is provided as a cluster set up using makeCluster
(or makeForkCluster
) from the parallel
package, then the rate limiting QR decomposition of the model matrix is performed in parallel using this cluster. Note that the speed ups are often not that great. On a multicore machine it is usually best to set the cluster size to the number of physical cores, which is often less than what is reported by detectCores
. Using more than the number of physical cores can result in no speed up at all (or even a slow down). Note that a highly parallel BLAS may negate all advantage from using a cluster of cores. Computing in parallel of course requires more memory than computing in series. See examples.
When discrete=TRUE
the covariate data are first discretized. Discretization takes place on a smooth by smooth basis, or in the case of tensor product smooths (or any smooth that can be represented as such, such as random effects), separately for each marginal smooth. The required spline bases are then evaluated at the discrete values, and stored, along with index vectors indicating which original observation they relate to. Fitting is by a version of performance oriented iteration/PQL using REML smoothing parameter selection on each iterative working model (as for the default method). The iteration is based on the derivatives of the REML score, without computing the score itself, allowing the expensive computations to be reduced to one parallel block Cholesky decomposition per iteration (plus two basic operations of equal cost, but easily parallelized). Unlike standard POI/PQL, only one step of the smoothing parameter update for the working model is taken at each step (rather than iterating to the optimal set of smoothing parameters for each working model). At each step a weighted model matrix crossproduct of the model matrix is required  this is efficiently computed from the precomputed basis functions evaluated at the discretized covariate values. Efficient computation with tensor product terms means that some terms within a tensor product may be reordered for maximum efficiency. See Wood et al (2017) and Li and Wood (2019) for full details.
When discrete=TRUE
parallel computation is controlled using the nthreads
argument. For this method no cluster computation is used, and the parallel
package is not required. Note that actual speed up from parallelization depends on the BLAS installed and your hardware. With the (R default) reference BLAS using several threads can make a substantial difference, but with a single threaded tuned BLAS, such as openblas, the effect is less marked (since cache use is typically optimized for one thread, and is then sub optimal for several). However the tuned BLAS is usually much faster than using the reference BLAS, however many threads you use. If you have a multithreaded BLAS installed then you should leave nthreads
at 1, since calling a multithreaded BLAS from multiple threads usually slows things down: the only exception to this is that you might choose to form discrete matrix cross products (the main cost in the fitting routine) in a multithreaded way, but use single threaded code for other computations: this can be achieved by e.g. nthreads=c(2,1)
, which would use 2 threads for discrete inner products, and 1 for most code calling BLAS. Not that the basic reason that multithreaded performance is often disappointing is that most computers are heavily memory bandwidth limited, not flop rate limited. It is hard to get data to one core fast enough, let alone trying to get data simultaneously to several cores.
discrete=TRUE
will often produce identical results to the methods without discretization, since covariates often only take a modest number of discrete values anyway, so no approximation at all is involved in the discretization process. Even when some approximation is involved, the differences are often very small as the algorithms discretize marginally whenever possible. For example each margin of a tensor product smooth is discretized separately, rather than discretizing onto a grid of covariate values (for an equivalent isotropic smooth we would have to discretize onto a grid). The marginal approach allows quite fine scale discretization and hence very low approximation error. Note that when using the smooth id
mechanism to link smoothing parameters, the discrete method cannot force the linked bases to be identical, so some differences to the none discrete methods will be noticable.
The extended families given in family.mgcv
can also be used. The extra parameters of these are estimated by maximizing the penalized likelihood, rather than the restricted marginal likelihood as in gam
. So estimates may differ slightly from those returned by gam
. Estimation is accomplished by a Newton iteration to find the extra parameters (e.g. the theta parameter of the negative binomial or the degrees of freedom and scale of the scaled t) maximizing the log likelihood given the model coefficients at each iteration of the fitting procedure.
Value
An object of class "gam"
as described in gamObject
.
WARNINGS
The routine may be slower than optimal if the default "tp"
basis is used.
This routine is less stable than ‘gam’ for the same dataset.
With discrete=TRUE
, te
terms are efficiently computed, but t2
are not.
Author(s)
Simon N. Wood simon.wood@rproject.org
References
Wood, S.N., Goude, Y. & Shaw S. (2015) Generalized additive models for large datasets. Journal of the Royal Statistical Society, Series C 64(1): 139155. doi:10.1111/rssc.12068
Wood, S.N., Li, Z., Shaddick, G. & Augustin N.H. (2017) Generalized additive models for gigadata: modelling the UK black smoke network daily data. Journal of the American Statistical Association. 112(519):11991210 doi:10.1080/01621459.2016.1195744
Li, Z & S.N. Wood (2020) Faster model matrix crossproducts for large generalized linear models with discretized covariates. Statistics and Computing. 30:1925 doi:10.1007/s11222019098642
See Also
mgcv.parallel
,
mgcvpackage
, gamObject
, gam.models
, smooth.terms
,
linear.functional.terms
, s
,
te
predict.gam
,
plot.gam
, summary.gam
, gam.side
,
gam.selection
, gam.control
gam.check
, linear.functional.terms
negbin
, magic
,vis.gam
Examples
library(mgcv)
## See help("mgcvparallel") for using bam in parallel
## Sample sizes are small for fast run times.
set.seed(3)
dat < gamSim(1,n=25000,dist="normal",scale=20)
bs < "cr";k < 12
b < bam(y ~ s(x0,bs=bs)+s(x1,bs=bs)+s(x2,bs=bs,k=k)+
s(x3,bs=bs),data=dat)
summary(b)
plot(b,pages=1,rug=FALSE) ## plot smooths, but not rug
plot(b,pages=1,rug=FALSE,seWithMean=TRUE) ## `with intercept' CIs
ba < bam(y ~ s(x0,bs=bs,k=k)+s(x1,bs=bs,k=k)+s(x2,bs=bs,k=k)+
s(x3,bs=bs,k=k),data=dat,method="GCV.Cp") ## use GCV
summary(ba)
## A Poisson example...
k < 15
dat < gamSim(1,n=21000,dist="poisson",scale=.1)
system.time(b1 < bam(y ~ s(x0,bs=bs)+s(x1,bs=bs)+s(x2,bs=bs,k=k),
data=dat,family=poisson()))
b1
## Similar using faster discrete method...
system.time(b2 < bam(y ~ s(x0,bs=bs,k=k)+s(x1,bs=bs,k=k)+s(x2,bs=bs,k=k)+
s(x3,bs=bs,k=k),data=dat,family=poisson(),discrete=TRUE))
b2