knn_recsys.py 文件源码

def train_and_score(metric, training, testing, ks):
    print "Training and scoring"
    scores = []
    knn = NearestNeighbors(metric=metric, algorithm="brute")
    knn.fit(training)
    for k in ks:
        print "Evaluating for", k, "neighbors"
        neighbor_indices = knn.kneighbors(testing,
                                          n_neighbors=k,
                                          return_distance=False)

        all_predicted_scores = []
        all_labels = []
        for user_id in xrange(testing.shape[0]):
            user_row = testing[user_id, :]

            _, interaction_indices = user_row.nonzero()
            interacted = set(interaction_indices)
            non_interacted = set(xrange(testing.shape[1])) - interacted

            n_samples = min(len(non_interacted), len(interacted))
            sampled_interacted = random.sample(interacted, n_samples)
            sampled_non_interacted = random.sample(non_interacted, n_samples)

            indices = list(sampled_interacted)
            indices.extend(sampled_non_interacted)
            labels = [1] * n_samples
            labels.extend([0] * n_samples)

            neighbors = training[neighbor_indices[user_id, :], :]
            predicted_scores = neighbors.mean(axis=0)
            for idx in indices:
                all_predicted_scores.append(predicted_scores[0, idx])
            all_labels.extend(labels)

        print len(all_labels), len(all_predicted_scores)

        auc = roc_auc_score(all_labels, all_predicted_scores)

        print "k", k, "AUC", auc