dataset_pseudo_generator module

dataset_pseudo_generator.dataset_generate(model_name='en_core_web_sm', suggestions=[], max_similar_amount=100)

dataset_pseudo_generator.gensim_initialize(model_name)

dataset_pseudo_generator.similar_set_spacy(model, word_list, max_similar_amount=100)

Return the List of similar words using the spacy model and suggested word_list

Parameters:

• model (spacy model object) – The spacy model
• word_list (list) – The list of suggestive words
• max_similar_amount (int) – The maximum number of words to look for

Returns:

list of similar words

Return type:

dataset (list)

dataset_pseudo_generator.spacy_initialize(model_name)

Initialize a spacy model with name

Parameters:model_name (str) – The designated model name Returns:spacy model Return type:model (spacy model object)