def my_eval(eval_data_df, model):
u_indices = eval_data_df[Constants.DEFAULT_USER_COL].to_numpy()
i_indices = eval_data_df[Constants.DEFAULT_ITEM_COL].to_numpy()
r_preds = np.fromiter(
(model.score(user_idx, item_idx).item()
for user_idx, item_idx in zip(u_indices, i_indices)),
dtype=np.float,
count=len(u_indices),
)
pred_df = pd.DataFrame({
Constants.DEFAULT_USER_COL: u_indices,
Constants.DEFAULT_ITEM_COL: i_indices,
Constants.DEFAULT_PREDICTION_COL: r_preds,
})
result_dic = {}
TOP_K = [5, 10, 20]
if type(TOP_K) != list:
TOP_K = [TOP_K]
if 10 not in TOP_K:
TOP_K.append(10)
metrics = ["ndcg_at_k", "precision_at_k", "recall_at_k", "map_at_k"]
for k in TOP_K:
for metric in metrics:
eval_metric = getattr(eval_model, metric)
result = eval_metric(eval_data_df, pred_df, k=k)
result_dic[metric + "@" + str(k)] = result
result_dic.update(config)
result_df = pd.DataFrame(result_dic, index=[0])
save_to_csv(result_df, config["result_file"])
def test_eval_worker(testEngine, eval_data_df, prediction):
"""Start a worker for the evaluation during training.
Prediction and evaluation on the testing set.
"""
result_para = {
"run_time": [testEngine.config["run_time"]],
}
testEngine.n_worker += 1
for cfg in ["model", "dataset"]:
for col in testEngine.config[cfg]["result_col"]:
result_para[col] = [testEngine.config[cfg][col]]
test_result_dic = evaluate(eval_data_df, prediction, testEngine.metrics,
testEngine.k)
print_dict_as_table(
test_result_dic,
tag="performance on test",
columns=["metrics", "values"],
)
test_result_dic.update(result_para)
lock_test_eval.acquire() # need to be test
result_df = pd.DataFrame(test_result_dic)
save_to_csv(result_df, testEngine.config["system"]["result_file"])
lock_test_eval.release()
testEngine.n_worker -= 1
return test_result_dic
def test_eval_worker(testEngine, eval_data_df, prediction, k_li=[5, 10, 20]):
"""
Prediction and evaluation on the testing set
"""
result_para = {
"model": [testEngine.config["model"]],
"dataset": [testEngine.config["dataset"]],
"data_split": [testEngine.config["data_split"]],
"emb_dim": [int(testEngine.config["emb_dim"])],
"lr": [testEngine.config["lr"]],
"batch_size": [int(testEngine.config["batch_size"])],
"optimizer": [testEngine.config["optimizer"]],
"max_epoch": [testEngine.config["max_epoch"]],
"model_run_id": [testEngine.config["model_run_id"]],
"run_time": [testEngine.config["run_time"]],
}
if "late_dim" in testEngine.config:
result_para["late_dim"] = [int(testEngine.config["late_dim"])]
if "remark" in testEngine.config:
result_para["remark"] = [testEngine.config["remark"]]
if "alpha" in testEngine.config:
result_para["alpha"] = [testEngine.config["alpha"]]
if "activator" in testEngine.config:
result_para["activator"] = [testEngine.config["activator"]]
if "item_fea_type" in testEngine.config:
result_para["item_fea_type"] = [testEngine.config["item_fea_type"]]
if "n_sample" in testEngine.config:
result_para["n_sample"] = [testEngine.config["n_sample"]]
if "time_step" in testEngine.config:
result_para["time_step"] = [testEngine.config["time_step"]]
test_result_dic = evaluate(eval_data_df, prediction, testEngine.metrics,
k_li)
print_dict_as_table(
test_result_dic,
tag=f"performance on test",
columns=["metrics", "values"],
)
test_result_dic.update(result_para)
lock_test_eval.acquire() # need to be test
result_df = pd.DataFrame(test_result_dic)
save_to_csv(result_df, testEngine.config["result_file"])
lock_test_eval.release()
return test_result_dic
