niml.model package

Submodules

niml.model.model module

class niml.model.model.Model(model_state=None, sdr_width=None, neurons=None, active_neurons=None, input_pct=None, learning=True, synapse_inc=None, synapse_dec=None, activity_reset_cnt=1, decay_cnt_target=None, seed=None, subclass_thresh=None, unknown_thresh=None, history_depth=None, min_overlap=None, enc_set_bits=None, feat_count=None, boost_max=None, boost_str=None, boost_tbl_size=None, boost_tbl_step=None, _clsfr_enabled=True)

Provides common access using familiar method names for performing fit, evaluate, and predict operations on iSDR data. The model class will not perform these operations directly, but will pass the data to the requisite functions in the pooler and classifier

Parameters

  • model_state (basestring or file-like object, optional) – A previously configured model state in the form of a file name string or python file handle

  • sdr_width (int, optional) – Indicates the full width of the input SDRs that will be submitted to the fit, evaluate, or predict methods

  • neurons (int, optional) – Indicates how many neurons to use for training the model

  • active_neurons (int, optional) – Indicates the number of neurons to use as the best representation of a class of data

  • input_pct (float, optional) – Indicates the percentage of iSDR bit width mapped to each neuron by a synapse.

  • learning (bool, optional) – Indicates to the model whether to update synapses and signatures with new information or maintain existing state and just evaluate/classify input SDR data

  • synapse_inc (int, optional) – Amount to strengthen a synapse to a winning neuron when the corresponding iSDR location is true. (only applies when learning is on)

  • synapse_dec (int, optional) – Amount to weaken a synapse to a winning neuron when the corresponding iSDR location is false. (only applies when learning is on)

  • activity_reset_cnt (int, optional) – Indicates to the model when to reset the strength by which the model encourage/discourages neurons that are losing or winning too frequently (affects boosting and only applies when learning is on)

  • decay_cnt_target (int) – Sets the number of iSDRs to process before triggering an adjustment to the outer activity_reset_cnt loop (only applies when learning and must be between 2 and 256 inclusive)

  • seed (int, optional) – Passed to the random initialization function to allow for repeatable output

  • subclass_thresh (float) – A value that directs the model when to create a new subclass during fit. Anything below the threshold will cause the creation of a new subclass

  • unknown_thresh (float, optional) – Indicates when the model needs to create a new subclass during continuous learning. Anything below the threshold will cause the creation of a new subclass (only applies when learning is on)

  • history_depth (int, optional) – Indicates the number of class signatures for the model to retain for determining class association

  • min_overlap (float, optional) – Indicates the minimum percentage of overlap between an output SDR and subclass signature to determine if the item represented by the output SDR should be considered a member of the subclass

  • enc_set_bits (int, optional) – The number of set-bits used per-feature during the encoding process. Should be the same value as provided to the encoder as the set_bits parameter

  • feat_count (int, optional) – The number of features present in the observation data, usually represented by the number of columns in a dataset minus the label column if labels are present

  • boost_max (int, optional) –

    Maximum boost value to be allowed in the boost table as a percentage of total SDR set bits across all features:

    max_boost_value = enc_set_bits * feature_count * boost_max

  • boost_str (int, optional) – Determines the x-intercept of the boost curve. a higher value will result in a higher x-intercept and lower will intercept lower

  • boost_tbl_size (int, optional) –

    Sets the total number of boost table steps. A higher value will result in a more gradual boosting profile and a lower number will cause boosting to change more rapidly:

    1 < boost_tbl_size <= 256

  • boost_tbl_step (int, optional) –

    Determines the distance along the boost curve between each value of the boost table:

    0.1 <= boost_tbl_size <= 1.0

Notes

All input parameters are marked as optional; however, either a model_state or all other parameters, except seed, are required

evaluate(encoder_state=None, labels=None, isdrs=None)

Provides measurement of the performance of the pooler/classifier by making predictions for the given observations, then generating statistics based on the predictions verses the ground-truth labels Requies either and encoder state or labels and isdrs

Parameters

  • encoder_state (dict, optional) – a state dictionary from the encoder

  • labels (list, optional) – ground-truth labels for iSDRs

  • isdrs (list of lists, optional) – encoded iSDRs

Returns

accuracy_results – contains results of f1 score, accuracy score, and confusion matrix calculations

Return type

dict

Raises

AttributeError – Raised if an error occurs while parsing the input parameters

Notes

All input parameters are marked as optional; however, either an encoder_state or list of labels and a list of isdrs is required, all parameters cannot be empty or None

fit(encoder_state=None, labels=None, isdrs=None, epochs=1, batch_size=1)

Given an encoder state or lists of labels and iSDRs, it will train the pooler by sending the iSDRs through the pooler for the requested number of epochs. It will then send the oSDRs generated from the final epoch to the classifier for signature createion

Parameters

  • encoder_state (dict, optional) – a state dictionary from the encoder

  • labels (list, optional) – ground-truth labels for iSDRs

  • isdrs (list of lists, optional) – encoded iSDRs

  • epochs (int, optional) – number of iterations the data should be processed through the pooler

  • batch_size (int, optional) – number SDRs to process between updates of boost factor and synaptic connection status.

Returns

signatures – Representation of the neurons that uniquely identify each label and sub-classification

Return type

dict of sets

Raises

AttributeError – Raised if an error occurs while parsing the input parameters

Notes

All input parameters are marked as optional; however, either an encoder_state or list of labels and a list of isdrs is required, all parameters except epochs cannot be empty or None

get_subclass_predictions()

Convenience method for accessing full predictions with subclass

Returns

predictions – Ordered list of (label, subclass index)

Return type

list of tuples

load_model(load_file)

Loads the current model state from load_file, which can be either a filename or a file-like object

Parameters

load_file (basestring or file-like object) – Either a string representing a file path or a file-like object where the json representation of the model state will loaded from

Raises

IOError – Raised if an error occurs and the json text cannot be read from the file

predict(encoder_state=None, isdrs=None)

Evaluates oSDR data against known class / subclass signatures and assigns the observation data row to the best matching signature if the match exceeds the subclass_thresh

Parameters

  • encoder_state (basestring or file-like object, optional) – Either a string representing a file path or a file-like object where the json representation of the encoder state can be loaded from

  • isdrs (list of lists, optional) – List of encoded observation data

Returns

predictions – List of class labels for each observation data row

Return type

list

Raises

AttributeError – Raised if an error occurs while parsing the input parameters

Notes

Both input parameters are marked as optional; however, either an encoder_state or list of isdrs is required, both parameters cannot be empty or None

reset_classifications()

Allows a user to clear the classifier signatures while retaining all the configuration parameters

save_model(output_file, indent=None)

Saves the current model state, which is simply the pooler state combined with the classifier state

Parameters

output_file (basestring or file-like object) – Either a string representing a file path or a file-like object where the json representation of the model state will be written

Raises

IOError – Raised if an error occurs and the json text cannot be written to the file