def test_to_df_fails_with_mismatched_inputs(sample_dataset):
users, items = sample_dataset[:, 0], sample_dataset[:, 1]
d = DatasetEncoder()
d.fit(users=users, items=items)
encoded = d.transform(users=users, items=items)
recommended = [
np.random.choice(encoded["items"], 10, replace=False)
for _ in range(int(len(users) / 2))
]
with pytest.raises(ValueError):
d.to_df(users, recommended)
def test_to_df_succeeds(sample_dataset):
users, items = sample_dataset[:, 0], sample_dataset[:, 1]
d = DatasetEncoder()
d.fit(users=users, items=items)
encoded = d.transform(users=users, items=items)
recommended = [
np.random.choice(encoded["items"], 10, replace=False) for _ in users
]
rdf = d.to_df(encoded["users"], recommended, target_col="user")
assert np.all(rdf["user"].values == users)
for i, row in enumerate(rdf.values[:, 1:]):
assert np.all(row == d.inverse_transform(
items=recommended[i])["items"])
encoder.fit(ratings["user"], ratings["item"])
train_ds = Dataset.from_df(train_df,
normalize=utils.as_implicit,
encoder=encoder)
test_ds = Dataset.from_df(test_df,
normalize=utils.as_implicit,
encoder=encoder)
model = GMFModel(fit_params=dict(epochs=10, batch_size=256),
n_factors=32,
negative_samples=4)
model.fit(train_ds)
_, test_items, _ = test_ds.to_components(shuffle=False)
# evaluate
users, items = he_sampling(test_ds, train_ds, n_samples=200)
recommended = model.predict(test_ds, users=users, items=items, n=10)
print("t-nDCG", score(metrics.truncated_ndcg, test_items, recommended).mean())
print("HR@k", score(metrics.precision_at_k, test_items, recommended).mean())
# results
recommended = model.predict(users=users, items=items[:, 1:], n=3)
recommended_df = encoder.to_df(users, recommended)
recommended_df.to_csv("recs.csv", index=False)