def prepare_training_ncf(train):
return NCFDataset(train=train,
col_user=DEFAULT_USER_COL,
col_item=DEFAULT_ITEM_COL,
col_rating=DEFAULT_RATING_COL,
col_timestamp=DEFAULT_TIMESTAMP_COL,
seed=SEED)
def ncf_training(params):
"""
Train NCF using the given hyper-parameters
"""
logger.debug("Start training...")
train_data = pd.read_pickle(
path=os.path.join(params["datastore"], params["train_datapath"])
)
validation_data = pd.read_pickle(
path=os.path.join(params["datastore"], params["validation_datapath"])
)
data = NCFDataset(train=train_data, test=validation_data, seed=DEFAULT_SEED)
model = NCF(
n_users=data.n_users,
n_items=data.n_items,
model_type="NeuMF",
n_factors=params["n_factors"],
layer_sizes=[16, 8, 4],
n_epochs=params["n_epochs"],
learning_rate=params["learning_rate"],
verbose=params["verbose"],
seed=DEFAULT_SEED,
)
model.fit(data)
logger.debug("Evaluating...")
metrics_dict = {}
rating_metrics = params["rating_metrics"]
if len(rating_metrics) > 0:
predictions = [
[row.userID, row.itemID, model.predict(row.userID, row.itemID)]
for (_, row) in validation_data.iterrows()
]
predictions = pd.DataFrame(
predictions, columns=["userID", "itemID", "prediction"]
)
predictions = predictions.astype(
{"userID": "int64", "itemID": "int64", "prediction": "float64"}
)
for metric in rating_metrics:
result = getattr(evaluation, metric)(validation_data, predictions)
metrics_dict = _update_metrics(metrics_dict, metric, params, result)
ranking_metrics = params["ranking_metrics"]
if len(ranking_metrics) > 0:
users, items, preds = [], [], []
item = list(train_data.itemID.unique())
for user in train_data.userID.unique():
user = [user] * len(item)
users.extend(user)
items.extend(item)
preds.extend(list(model.predict(user, item, is_list=True)))
all_predictions = pd.DataFrame(
data={"userID": users, "itemID": items, "prediction": preds}
)
merged = pd.merge(
train_data, all_predictions, on=["userID", "itemID"], how="outer"
)
all_predictions = merged[merged.rating.isnull()].drop("rating", axis=1)
for metric in ranking_metrics:
result = getattr(evaluation, metric)(
validation_data,
all_predictions,
col_prediction="prediction",
k=params["k"],
)
metrics_dict = _update_metrics(metrics_dict, metric, params, result)
if len(ranking_metrics) == 0 and len(rating_metrics) == 0:
raise ValueError("No metrics were specified.")
# Report the metrics
nni.report_final_result(metrics_dict)
# Save the metrics in a JSON file
output_dir = os.environ.get("NNI_OUTPUT_DIR")
with open(os.path.join(output_dir, "metrics.json"), "w") as fp:
temp_dict = metrics_dict.copy()
temp_dict[params["primary_metric"]] = temp_dict.pop("default")
json.dump(temp_dict, fp)
return model