'trainSPNetOnlyIfRequested': False,
},
}
# 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['aggregationInfo'])))
assert (predictionSteps >= 1)
config['modelParams']['clParams']['steps'] = str(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)
dataPath = os.path.abspath(os.path.join(os.path.dirname(__file__),
'data.csv'))
control = {
# The environment that the current model is being run in
},
"trainSPNetOnlyIfRequested": False,
},
}
# 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["aggregationInfo"])))
assert predictionSteps >= 1
config["modelParams"]["clParams"]["steps"] = str(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)
control = {
# The environment that the current model is being run in
"environment": "nupic",
# Input stream specification per py/nupicengine/cluster/database/StreamDef.json.
#
},
'claTrainSPNetOnlyIfRequested': True,
'dataSource': 'fillInBySubExperiment',
}
# 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['aggregationInfo'])))
assert (predictionSteps >= 1)
config['modelParams']['clParams']['steps'] = str(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)
# With no TP, there are no columns
if not config['modelParams']['tpEnable']:
config['modelParams']['clParams']['cellsPerCol'] = 0
################################################################################
control = {
# The environment that the current model is being run in
},
}
# 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['aggregationInfo'])))
assert (predictionSteps >= 1)
config['modelParams']['clParams']['steps'] = str(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)
# [optional] A sequence of one or more tasks that describe what to do with the
# model. Each task consists of a task label, an input spec., iteration count,
# and a task-control spec per opfTaskSchema.json
#
},
'trainSPNetOnlyIfRequested': False,
},
}
# 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['aggregationInfo'])))
assert (predictionSteps >= 1)
config['modelParams']['clParams']['steps'] = str(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)
################################################################################
# [optional] A sequence of one or more tasks that describe what to do with the
# model. Each task consists of a task label, an input spec., iteration count,
# and a task-control spec per opfTaskSchema.json
#
# NOTE: The tasks are intended for OPF clients that make use of OPFTaskDriver.
