mindmeld.components.intent_classifier module

This module contains the intent classifier component of the MindMeld natural language processor.

class mindmeld.components.intent_classifier.IntentClassifier(resource_loader, domain)

Bases: mindmeld.components.classifier.Classifier

An intent classifier is used to determine the target intent for a given query. It is trained using all of the labeled queries across all intents for a domain in an application. The labels for the training data are the intent names associated with each query.

domain

str -- The domain that this intent classifier belongs to.

dump(*args, **kwargs)

Persists the trained intent classification model to disk.

Parameters:model_path (str) -- The location on disk where the model should be stored.

fit(*args, **kwargs)

Trains the intent classification model using the provided training queries.

Parameters:

• model_type (str) -- The type of machine learning model to use. If omitted, the default model type will be used.
• features (dict) -- Features to extract from each example instance to form the feature vector used for model training. If omitted, the default feature set for the model type will be used.
• params_grid (dict) -- The grid of hyper-parameters to search, for finding the optimal hyper-parameter settings for the model. If omitted, the default hyper-parameter search grid will be used.
• queries (list[ProcessedQuery]) -- The labeled queries to use as training data.
• cv (optional) -- Cross-validation settings.

inspect(query, intent=None, dynamic_resource=None)

Inspects the query.

Parameters:

• query (Query) -- The query to be predicted.
• intent (str) -- The expected intent label for this query.
• dynamic_resource (dict, optional) -- A dynamic resource to aid NLP inference.

Returns:

2D list that includes every feature, their value, weight and probability.

Return type:

(list of lists)

load(*args, **kwargs)

Loads the trained intent classification model from disk.

Parameters:model_path (str) -- The location on disk where the model is stored.

unload()

Unloads the model from memory. This helps reduce memory requirements while training other models.

CLF_TYPE = 'intent'

The classifier type.