near_recommender package

Subpackages

• near_recommender.src.data package
  • Subpackages
    • near_recommender.src.data.queries package
      • Submodules
      • near_recommender.src.data.queries.query_all_users module
      • near_recommender.src.data.queries.query_get_post_text module
      • near_recommender.src.data.queries.query_get_profile_tags module
      • near_recommender.src.data.queries.query_get_trending_users module
      • Module contents
  • Submodules
  • near_recommender.src.data.get_dataframe module
    • get_dataframe()
  • Module contents
• near_recommender.src.features package
  • Submodules
  • near_recommender.src.features.preprocessors module
    • normalize_corpus()
    • normalize_document()
  • near_recommender.src.features.related_profile_tags module
    • find_similar_users()
  • near_recommender.src.features.top_sentences module
    • return_similar_sentences()
  • near_recommender.src.features.utils module
    • filter_last_post()
    • get_index_from_signer_id()
    • load_pretrained_model()
    • run_update_model()
    • save_pretrained_model()
  • Module contents
• near_recommender.src.models package
  • Submodules
  • near_recommender.src.models.friends_friends module
    • get_friends_of_friends()
  • near_recommender.src.models.similar_posts module
    • get_similar_post_users()
    • load_corpus_embeddings()
    • update_corpus()
  • near_recommender.src.models.similar_tags module
    • get_similar_tags_users()
  • near_recommender.src.models.trending_users module
    • get_trending_users()
  • Module contents

Submodules

near_recommender.recommender module

near_recommender.src.recommender.get_recommendations_per_user(idx, user, address_age=7, top_k=5)

Gets all applicable recommendations for a given user.

Recommendation system logic:

• If the user is new (< 1 week, < 3 days): appends trending users

• If the user is not active: appends trending users

• If the user is active: appends friends-of-friends

• If the user has a tag: appends tag similarity

• If the user has posted: appends post similarity

• If the user was inactive for some period: appends trending users

Returns a list of dictionaries with signer_id and recommended users.

Parameters:

• idx (int) –

• user (Series) –

• address_age (int) –

• top_k (int) –

Return type:

List[Dict]

near_recommender.process_recommendations module