recsys_user_knn_occupation

user_knn.py

def get_user_sim_values(train_set):
    users_age_gender = (users_df.
        assign(inner_id=lambda df: df['user_id'].apply(lambda x: train_set.to_inner_uid(x)),
               gender=lambda df: df['gender'].replace({'M': 0, 'F': 1}).astype('int')).
        sort_values('inner_id').
        filter(items=['age', 'gender'])
    )
    user_values_np = StandardScaler().fit_transform(users_age_gender.to_numpy())
    cosine_sim_user_values = cosine_similarity(user_values_np, user_values_np)
    return cosine_sim_user_values

cosine_sim_user_values_trainset = get_user_sim_values(trainset)
cosine_sim_user_values_train_loocv = get_user_sim_values(train_loocv)
get_algorithm_report(CustomSimKNNAlgorithm, trainset, testset, train_loocv, test_loocv, movies_df,
                     target_movie_id='movie_1', target_user_id='user_1', top_k=10,
                     algo_kwargs_trainset=dict(similarities=None,
                                               sim_options={'user_based': True}),
                     algo_kwargs_trainset_loocv=dict(similarities=cosine_sim_user_values_train_loocv,
                                                     sim_options={'user_based': True}), calc_most_similar=False)