Skip to main content

Model for tracking context of utterance and predicting future characters.

Project description

To use, first create CharPredictor object:

>>> predictor = CharPredictor()

This may take a while as model is being downloaded and loaded.

Then, to track utterance context, you can add letter index to context:

>>> letter_index = 1    # 1 -> a,   letters should be indexed in order: ' abcdefghijklmnopqrstuvwxyz' (0 -> space)
>>> predictor.add_to_context(letter_index)

or you can add letter as string of length 1 (make sure it is one of AsciiEncoder.AVAILABLE_CHARS):

>>> letter = 'a'
>>> predictor.add_to_context(letter)

or you can add probability distribution for all AsciiEncoder.AVAILABLE_CHARS letters:

>>> import numpy as np
>>> import AsciiEncoder as AE
>>>
>>> num_chars = len(AE.AVAILABLE_CHARS)
>>> letter_distr = np.random.random((1, num_chars)) # random proba distribution
>>> predictor.add_to_context(letter_distr)

And finally - you can predict probabilities of each letter coming next after text stored in context. (Letters are indexed in order shown below):

>>> predictor.transform()

Letters order:

' abcdefghijklmnopqrstuvwxyz' # space character comes at index 0, then alphabetical order for indices from 1 to 26

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

dictionary-model-0.2.4.tar.gz (3.0 kB view hashes)

Uploaded source

Supported by

AWS AWS Cloud computing Datadog Datadog Monitoring Facebook / Instagram Facebook / Instagram PSF Sponsor Fastly Fastly CDN Google Google Object Storage and Download Analytics Huawei Huawei PSF Sponsor Microsoft Microsoft PSF Sponsor NVIDIA NVIDIA PSF Sponsor Pingdom Pingdom Monitoring Salesforce Salesforce PSF Sponsor Sentry Sentry Error logging StatusPage StatusPage Status page