make_confusions

rectools.metrics.classification.make_confusions(reco: DataFrame, interactions: DataFrame, k: int) → DataFrame[source]

Calculate some intermediate metrics from raw data (it’s a helper function).

For each user the following metrics are calculated:

  • LIKED - number of items the user has interacted (bought, liked) with;

  • TP - number of relevant recommendations among the first k items at the top of recommendation list;

  • FP - number of non-relevant recommendations among the first k items of recommendation list;

  • FN - number of items the user has interacted with but that weren’t recommended (in top-k).

Parameters

  • reco (pd.DataFrame) – Recommendations table with columns Columns.User, Columns.Item, Columns.Rank.

  • interactions (pd.DataFrame) – Interactions table with columns Columns.User, Columns.Item.

  • k (int) – Number of items at the top of recommendations list that will be used to calculate metric.

Returns

Table with columns: Columns.User, LIKED, TP, FP, FN.

Return type

pd.DataFrame