Commit aa433049 authored by Oscar Araque's avatar Oscar Araque

added new embeddings: no seeds and 20 freq

parent 3500a032
{
"embeddings": [
{
"tensorName": "no seeds 20 freq",
"tensorShape": [
20018,
100
],
"tensorPath": "https://lab.gsi.upm.es/oaraque/incel-embeddings/raw/master/no_seed_20freq/neologisms_embeddings_2019-06-20_10-41.tsv",
"metadataPath": "https://lab.gsi.upm.es/oaraque/incel-embeddings/raw/master/no_seeds/neologisms_embeddings_words_2019-06-20_10-41.txt"
}
]
}
This diff is collapsed.
{"results": {"frequency_filtered_terms": 59147, "lda_topics": 60, "dictionary_filtered_terms": 3426, "embedding_pre_filtering": 3426, "embedding_expansion_factor": 5.244600116754232, "clean_filtered_terms": 51588, "embedding_post_filtering": 2865, "embedding_new_neo_candidates": 0, "lda_covered_topics": 60, "embedding_expansion_no_dict_words": 3426, "embedding_expansion_dict_words": 17968, "general_words": 302001, "terms_dataset": 1138898}, "parameters": {"frequency_threshold": 20, "lda_minimum_probability": 1e-05, "EMBEDDINGS_MODEL_PATH": "data/embeddings/fastext_100_10min_5epochs", "COMMENTS_PROCESSED_PATH": "data/comments_processed.csv", "LDA_DICT_PATH": "data/dict_10mn", "LDA_MODEL_PATH": "data/lda_models/lda_model_60topics_5passes", "LINKS_PROCESSED_PATH": "data/links_processed.csv", "SAVE_PATH": "export/no_seed_20/", "n_neighbours": 30, "similarity_threshold": 0.85, "levenshtein_distance_threshold": 3}}
\ No newline at end of file
This diff is collapsed.
This diff is collapsed.
This diff is collapsed.
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment