# ----------------------------------------------------------------------
# Numenta Platform for Intelligent Computing (NuPIC)
# Copyright (C) 2013, Numenta, Inc. Unless you have an agreement
# with Numenta, Inc., for a separate license for this software code, the
# following terms and conditions apply:
#
# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU Affero Public License version 3 as
# published by the Free Software Foundation.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
# See the GNU Affero Public License for more details.
#
# You should have received a copy of the GNU Affero Public License
# along with this program. If not, see http://www.gnu.org/licenses.
#
# http://numenta.org/licenses/
# ----------------------------------------------------------------------
"""
Template file used by the OPF Experiment Generator to generate the actual
description.py file by replacing $XXXXXXXX tokens with desired values.
This description.py file was generated by:
$EXP_GENERATOR_PROGRAM_PATH
"""
from nupic.frameworks.opf.exp_description_api import ExperimentDescriptionAPI
from nupic.frameworks.opf.exp_description_helpers import (
updateConfigFromSubConfig,
applyValueGettersToContainer,
DeferredDictLookup)
from nupic.frameworks.opf.htm_prediction_model_callbacks import *
from nupic.frameworks.opf.metrics import MetricSpec
from nupic.swarming.experiment_utils import (InferenceType, InferenceElement)
from nupic.support import aggregationDivide
from nupic.frameworks.opf.opf_task_driver import (
IterationPhaseSpecLearnOnly,
IterationPhaseSpecInferOnly,
IterationPhaseSpecLearnAndInfer)
# ------------------------------------------------------------------------------
# Model Configuration Dictionary:
#
# Define the model parameters and adjust for any modifications if imported
# from a sub-experiment.
#
# These fields might be modified by a sub-experiment; this dict is passed between
# the sub-experiment and base experiment
#
#
# NOTE: Use of DEFERRED VALUE-GETTERs: dictionary fields and list elements
# within the config dictionary may be assigned futures derived from the
# ValueGetterBase class, such as DeferredDictLookup.
# This facility is particularly handy for enabling substitution of values in
# the config dictionary from other values in the config dictionary, which is
# needed by permutation.py-based experiments. These values will be resolved
# during the call to applyValueGettersToContainer(),
# which we call after the base experiment's config dictionary is updated from
# the sub-experiment. See ValueGetterBase and
# DeferredDictLookup for more details about value-getters.
#
# For each custom encoder parameter to be exposed to sub-experiment/permutation
# overrides, define a variable in this section, using key names beginning with a
# single underscore character to avoid collisions with pre-defined keys (e.g.,
# _dsEncoderFieldName2_N).
#
# Example:
# config = dict(
# _dsEncoderFieldName2_N = 70,
# _dsEncoderFieldName2_W = 5,
# dsEncoderSchema = [
# base=dict(
# fieldname='Name2', type='ScalarEncoder',
# name='Name2', minval=0, maxval=270, clipInput=True,
# n=DeferredDictLookup('_dsEncoderFieldName2_N'),
# w=DeferredDictLookup('_dsEncoderFieldName2_W')),
# ],
# )
# updateConfigFromSubConfig(config)
# applyValueGettersToContainer(config)
#
config = {
# Type of model that the rest of these parameters apply to
'model' : "HTMPrediction",
# The type of inference that this model will perform
'inferenceType': $INFERENCE_TYPE,
# How much in advance we want to predict. Used only when swarming over
# aggregations
'predictAheadTime': $PREDICT_AHEAD_TIME,
# The number of prediction steps to use. When swarming over aggregations, this
# is computed and filled in by the logic that follows this config
# declaration. It is computed based on the chosen aggreation and the
# above predictAheadTime.
'predictionSteps': 'FilledInBelow',
##############################################################################
# Dataset Aggregation Parameters (for training and inference datasets)
##############################################################################
# Time-based Dataset Aggregation rules;
#
# Usage details and additional options: see
# nupic.data.aggregator.generateDataset()
#
# Aggregation presently begins at the start of the dataset. For every
# aggregation period, the records within the period are coalesced into a
# single record per rules specified via the aggregationInfo property.
#
# Value schema:
# {
# 'periodUnit1':value1, 'periodUnit2':value2, ...,
# 'fields':[('fieldNameA', aggFuncNameA), ('fieldNameB', aggFuncNameB)]
# }
#
# Aggregation period units: combination of 0 or more unit/value properties:
# [years months] | [weeks days hours minutes seconds milliseconds microseconds]
# NOTE: years and months are mutually-exclusive with the other units.
# Example2: hours=1, minutes=30,
#
# Aggregation is disabled if the aggregationInfo key is omitted or all
# expressed period unit values evaluate to 0
#
# Aggregation fields: list of field-name/aggregationFunctionName tuples;
# e.g.: ("consumpion", "mean").
#
# Supported function names: "first", "last", "mean", "sum" (per
# nupic.data.aggregator.py)
#
# NOTE: Designated Sequence id, Reset, and Timestamp fields are included
# automatically if not specified in aggregation fields.
#
# Aggregation period can be permuted over, so is separated out
# (generated from AGGREGATION_PERIOD)
'__aggregationPeriod' : $AGGREGATION_PERIOD
# (value generated from AGGREGATION_INFO)
'aggregationInfo' : $AGGREGATION_INFO,
##############################################################################
# Sensor Region Parameters
##############################################################################
# Sensor diagnostic output verbosity control;
# if > 0: sensor region will print out on screen what it's sensing at each step
# 0: silent; >=1: some info; >=2: more info; >=3: even more info
# (see compute() in py/regions/RecordSensor.py)
#
'sensorVerbosity' : 0,
# A dictionary specifying the period for automatically-generated resets from
# a RecordSensor;
#
# None = disable automatically-generated resets (also disabled if all of the
# specified values evaluate to 0).
# Valid keys is the desired combination of the following:
# days, hours, minutes, seconds, milliseconds, microseconds, weeks
#
# Example for 1.5 days: sensorAutoReset = dict(days=1,hours=12),
#
# (value generated from SENSOR_AUTO_RESET)
'sensorAutoReset' : $SENSOR_AUTO_RESET,
# Dataset Encoder consists of field encoders that convert dataset record fields
# to the internal representations suitable for input to the Sensor Region.
#
# Each field encoder dict must have the following keys per
# nupic.encoders.MultiEncoder (multi.py):
# 1) data fieldname ('fieldname')
# 2) an encoder type ('type')
# 3) and the encoder params (all other keys)
#
# See specific encoder modules (e.g., sdrcateogry.py, scalar.py,
# date.py, etc.) for encoder type values and descriptions of their specific params.
#
# Schema that describes how to build the encoder configuration.
#
# dsEncoderSchema: [encoderSpec1, encoderSpec2, ...]
# encoderSpec: dictionary of parameters describing the field encoder
#
# In this dsEncoderSchema example, the field name "Name1" is a timestamp,
# "Name2" is a scalar quantity, and "Name3" is a category
#
# Encoder specs;
# Example:
# __field_name_encoder = dict(
# type = SDRCategoryEncoder',
# fieldname = name',
# name = 'name',
# n = 1000,
# w = DeferredDictLookup('spNumActivePerInhArea'),
# )
# Generated from ENCODER_SPECS
#
$ENCODER_SPECS,
# Example:
# dsEncoderSchema = [
# DeferredDictLookup('__field_name_encoder'),
# ],
#
# (value generated from DS_ENCODER_SCHEMA)
#
'dsEncoderSchema' : $DS_ENCODER_SCHEMA,
##############################################################################
# General CLA Region Parameters
##############################################################################
# Number of cell columns in the cortical region (same number for SP and TM)
# (see also tpNCellsPerCol)
# Replaces: spCoincCount
'claRegionNColumns' : 2048,
##############################################################################
# Spatial Pooler (SP) Parameters (SP is always enabled in OPF)
##############################################################################
# SP diagnostic output verbosity control;
# 0: silent; >=1: some info; >=2: more info;
#
'spVerbosity' : 0,
# Print/logs stats every N iterations; 0 = disable stats
'spPrintStatsPeriodIter' : 0,
# SP inhibition control (absolute value);
# Maximum number of active columns in the SP region's output (when there are more,
# the weaker ones are suppressed)
#
'spNumActivePerInhArea' : 40,
# potentialPct
# What percent of the columns's receptive field is available
# for potential synapses. At initialization time, we will
# choose potentialPct * (2*potentialRadius+1)^2
'spCoincInputPoolPct' : $SP_POOL_PCT,
# The default connected threshold. Any synapse whose
# permanence value is above the connected threshold is
# a "connected synapse", meaning it can contribute to the
# cell's firing. Typical value is 0.10. Cells whose activity
# level before inhibition falls below minDutyCycleBeforeInh
# will have their own internal synPermConnectedCell
# threshold set below this default value.
# (This concept applies to both SP and TM and so 'cells'
# is correct here as opposed to 'columns')
'spSynPermConnected' : $SP_PERM_CONNECTED,
##############################################################################
# Temporal Memory (TM) Parameters
##############################################################################
# TM diagnostic output verbosity control;
# 0: silent; [1..6]: increasing levels of verbosity
# (see verbosity in nupic/trunk/py/nupic/research/BacktrackingTM.py and BacktrackingTMCPP.py)
#
'tpVerbosity' : 0,
# Print stats every N iterations during training; 0 = disable stats
# TODO Why aren't experiments configuring stats for the inference phase? It seems
# like SP stats are dumped by SP Pooler directly regardless of whether it's
# in training or inference phase. (waiting for email from Ron)
# TODO: In LPF, these were accumulated/printed via iter/final callbacks installed
# by LPF; solve in OPF.
'tpTrainPrintStatsPeriodIter' : 0,
# Controls whether TM is enabled or disabled;
# TM is necessary for making temporal predictions, such as predicting the next
# inputs. Without TP, the model is only capable of reconstructing missing sensor
# inputs (via SP).
#
'tmEnable' : True,
# The number of cells (i.e., states), allocated per column
#
'tpNCellsPerCol' : 32,
# Initial Permanence
# TODO need better explanation
#
'tpInitialPerm' : 0.21,
# Permanence Increment
#
'tpPermanenceInc' : 0.1,
# Permanence Decrement
# If set to None, will automatically default to tpPermanenceInc value
#
'tpPermanenceDec' : None,
# Temporal Pooler implementation selector (see _getTPClass in CLARegion.py)
#
'tpImplementation' : 'cpp',
# Maximum number of segments per cell
# > 0 for fixed-size CLA
# -1 for non-fixed-size CLA
#
# TODO for Ron: once the appropriate value is placed in TM constructor, see if
# we should eliminate this parameter from description.py
#
'tpMaxSegmentsPerCell' : 128,
# Segment activation threshold.
# A segment is active if it has >= tpSegmentActivationThreshold connected
# synapses that are active due to infActiveState
# None=use default
# Replaces: tpActivationThreshold
'tpSegmentActivationThreshold' : None,
# Minimum number of active synapses for a segment to be considered during
# search for the best-matching segments.
# None=use default
# Replaces: tpMinThreshold
'tpMinSegmentMatchSynapseThreshold' : None,
# Maximum number of synapses per segment
# > 0 for fixed-size CLA
# -1 for non-fixed-size CLA
#
# TODO for Ron: once the appropriate value is placed in TM constructor, see if
# we should eliminate this parameter from description.py
#
'tpMaxSynapsesPerSegment' : 32,
# New Synapse formation count
# NOTE: If None, use spNumActivePerInhArea
#
# TODO need better explanation
#
'tpNewSynapseCount' : 20,
# "Pay Attention Mode" length. This tells the TM how many new elements
# to append to the end of a learned sequence at a time. Smaller values are
# better for datasets with short sequences, higher values are better for
# datasets with long sequences.
'tpPamLength': 1,
##############################################################################
# SDRClassifier parameters
##############################################################################
'clRegionName' : 'SDRClassifierRegion',
# Classifier diagnostic output verbosity control;
# 0: silent; [1..6]: increasing levels of verbosity
#
'verbosity' : 0,
# Comma separated list of steps ahead to learn in the classifier.
'clSteps': $PREDICTION_STEPS,
# This controls how fast the classifier learns/forgets. Higher values
# make it adapt faster and forget older patterns faster.
'clAlpha': None,
# This allows the user to specify custom classifier params
'clAdvancedParams' : {},
}
# end of config dictionary
# Adjust base config dictionary for any modifications if imported from a
# sub-experiment
updateConfigFromSubConfig(config)
# Compute predictionSteps based on the predictAheadTime and the aggregation
# period, which may be permuted over.
if config['predictAheadTime'] is not None:
predictionSteps = int(round(aggregationDivide(
config['predictAheadTime'], config['__aggregationPeriod'])))
assert (predictionSteps >= 1)
config['clSteps'] = '%s' % (predictionSteps)
# Adjust config by applying ValueGetterBase-derived
# futures. NOTE: this MUST be called after updateConfigFromSubConfig() in order
# to support value-getter-based substitutions from the sub-experiment (if any)
applyValueGettersToContainer(config)
