spec2vec.serialization.model_exporting module¶
- spec2vec.serialization.model_exporting.export_model(model: Word2Vec, output_model_file: Union[str, PathLike], output_weights_file: Union[str, PathLike])[source]¶
Write a lightweight version of a
Word2Vec
model to disk. Such a model can be read to calculate scores but is not capable of further training.- Parameters
model –
Word2Vec
trained model.output_model_file – A path of json file to save the model.
output_weights_file – A path of .npy file to save the model’s weights.
- spec2vec.serialization.model_exporting.extract_keyedvectors(model: Word2Vec) dict [source]¶
Extract
KeyedVectors
object from the model, convert it to a dictionary and remove redundant keys.- Parameters
model –
Word2Vec
trained model.- Returns
Dictionary representation of
KeyedVectors
without redundant keys.- Return type
keyedvectors
- spec2vec.serialization.model_exporting.get_weights_format(weights: Union[ndarray, csr_matrix, csc_matrix]) str [source]¶
Get the array format of the model’s weights.
- Parameters
weights – Model’s weights.
- Returns
Format of the model’s weights.
- Return type
weights_format
- spec2vec.serialization.model_exporting.save_model(keyedvectors: dict, output_model_file: Union[str, PathLike])[source]¶
Write model’s metadata to disk in json format.
- spec2vec.serialization.model_exporting.save_weights(weights: Union[ndarray, csr_matrix, csc_matrix], output_weights_file: Union[str, PathLike])[source]¶
Write model’s weights to disk in .npy dense array format. If the weights are sparse, they are converted to dense prior to saving.