Configuration Parameters Reference

Here are the configuration parameters supported by pebl. These can set in a configuration file or via the config.set() function.

data

data.discretize

Number of bins used to discretize data. Specify 0 to indicate that data should not be discretized. default=0

data.filename

File to read data from. default=None

data.text

The text of a dataset included in config file. default=

learner

learner.numtasks

Number of learner tasks to run. default=1

learner.type

Type of learner to use.

The following learners are included with pebl:

• greedy.GreedyLearner
• simanneal.SimulatedAnnealingLearner
• exhaustive.ListLearner

default=greedy.GreedyLearner

greedy

greedy.max_iterations

Maximum number of iterations to run. default=1000

greedy.max_time

Maximum learner runtime in seconds. default=0

greedy.max_unimproved_iterations

Maximum number of iterations without score improvement before a restart. default=500

greedy.seed

Starting network for a greedy search. default=

simanneal

simanneal.delta_temp

Change in temp between steps. default=0.5

simanneal.max_iters_at_temp

Max iterations at any temperature. default=100

simanneal.seed

Starting network for a greedy search. default=

simanneal.start_temp

Starting temperature for a run. default=100.0

listlearner

listlearner.networks

List of networks to score. default=

localscore_cache

localscore_cache.maxsize

Max number of localscores to cache. Default=-1 means unlimited size. default=-1

result

result.filename

The name of the result output file default=result.pebl

result.format

The format for the pebl result file (pickle or html). default=pickle

result.size

Number of top-scoring networks to save. Specify 0 to indicate that all scored networks should be saved. default=1000

gibbs.burnin

Burn-in period for the gibbs sampler (specified as a multiple of the number of missing values) default=10

gibbs.max_iterations

Stopping criteria for the gibbs sampler.

The number of Gibb’s sampler iterations to run. Should be a valid python expression using the variable n (number of missing values). Examples:

• n**2 (for n-squared iterations)
• 100 (for 100 iterations)

default=n**2

taskcontroller

taskcontroller.type

The task controller to use. default=serial

multiprocess

multiprocess.poolsize

Number of processes to run concurrently (0 means no limit) default=0

xgrid

xgrid.controller

Hostname or IP of the Xgrid controller. default=

xgrid.grid

Id of the grid to use at the Xgrid controller. default=0

xgrid.password

Password for the Xgrid controller. default=

xgrid.peblpath

Full path to the pebl script on Xgrid agents default=pebl

xgrid.pollinterval

Time (in secs) to wait between polling the Xgrid controller. default=60.0

ipython1

ipython1.controller

IPython1 TaskController (default is 127.0.0.1:10113) default=127.0.0.1:10113

ec2

ec2.config

EC2 config file. This is kept seperate from pebl config because it contains authentication keys, etc. default=

ec2.max_count

Maximum number of EC2 instances to create (default=0 means the same number as ec2.min_count). default=0

ec2.min_count

Minimum number of EC2 instances to create (default=1). default=1