def test_explicit_to_implicit(explicit_df):
expected = pd.DataFrame(data={
'userId': [3, 1],
'itemId': [1, 3],
'rating': [1, 1]
})
actual = convert_to_implicit(explicit_df, user_col='userId', item_col='itemId')
pd.testing.assert_frame_equal(actual, expected)
def test_explicit_to_implicit_with_duplicate_user_id_item_id_pairs(
explicit_df_with_duplicate_user_item_pairs
):
expected = pd.DataFrame(data={
'userId': [3, 2, 1],
'itemId': [1, 0, 3],
'rating': [1, 1, 1]
})
actual = convert_to_implicit(explicit_df_with_duplicate_user_item_pairs,
user_col='userId',
item_col='itemId')
pd.testing.assert_frame_equal(actual, expected)
def movielens_implicit_df(movielens_explicit_df):
return convert_to_implicit(movielens_explicit_df)
def run_movielens_example(epochs: int = 20, gpus: int = 0) -> None:
"""
Retrieve and split data, train and evaluate a model, and save it.
From the terminal, you can run this script with:
.. code-block:: bash
python collie_recs/movielens/run.py --epochs 20
Parameters
-------------
epochs: int
Number of epochs for model training
gpus: int
Number of gpus to train on
"""
t = Timer()
t.timecheck(' 1.0 - retrieving MovieLens 100K dataset')
df = read_movielens_df(decrement_ids=True)
t.timecheck(' 1.0 complete')
t.timecheck(' 2.0 - splitting data')
df_imp = convert_to_implicit(df)
interactions = Interactions(users=df_imp['user_id'],
items=df_imp['item_id'],
allow_missing_ids=True)
train, val, test = stratified_split(interactions, val_p=0.1, test_p=0.1)
train_loader = InteractionsDataLoader(train, batch_size=1024, shuffle=True)
val_loader = InteractionsDataLoader(val, batch_size=1024, shuffle=False)
t.timecheck(' 2.0 complete')
t.timecheck(' 3.0 - training the model')
model = MatrixFactorizationModel(train=train_loader,
val=val_loader,
dropout_p=0.05,
loss='adaptive',
lr=5e-2,
embedding_dim=10,
optimizer='adam',
weight_decay=1e-7)
trainer = CollieTrainer(
model=model,
gpus=gpus,
max_epochs=epochs,
deterministic=True,
logger=False,
checkpoint_callback=False,
callbacks=[EarlyStopping(monitor='val_loss_epoch', mode='min')],
weights_summary='full',
terminate_on_nan=True)
trainer.fit(model)
model.eval()
t.timecheck('\n 3.0 complete')
t.timecheck(' 4.0 - evaluating model')
auc_score, mrr_score, mapk_score = evaluate_in_batches([auc, mrr, mapk],
test,
model,
k=10)
print(f'AUC: {auc_score}')
print(f'MRR: {mrr_score}')
print(f'MAP@10: {mapk_score}')
t.timecheck(' 4.0 complete')
t.timecheck(' 5.0 - saving model')
absolute_data_path = DATA_PATH / 'fitted_model'
model.save_model(absolute_data_path)
t.timecheck(' 5.0 complete')