Description
|
def recommend_k_items( |
|
self, |
|
data, |
|
top_k=None, |
|
remove_seen=False, |
|
col_user=DEFAULT_USER_COL, |
|
col_item=DEFAULT_ITEM_COL, |
|
col_prediction=DEFAULT_PREDICTION_COL, |
|
): |
|
"""Computes top-k predictions of recommender model from Cornac on all users in data. |
|
It can be used for computing ranking metrics like NDCG. |
|
|
|
Args: |
|
data (pandas.DataFrame): The data from which to get the users and items. |
|
top_k (int): Number of items to recommend per user. |
|
remove_seen (bool): Flag to remove (user, item) pairs seen in the training data. |
|
col_user (str): Name of the user column. |
|
col_item (str): Name of the item column. |
|
col_rating (str): Name of the prediction column. |
The function signature has col_prediction but the docstring refers to col_rating
Willingness to contribute
Description
recommenders/recommenders/models/cornac/bpr.py
Lines 20 to 38 in c98accb
The function signature has
col_predictionbut the docstring refers tocol_ratingWillingness to contribute