train model Returns ------- pred_score: pandas.DataFrame predict scores performance: dict model performance
(uri_path: str = None)
| 17 | |
| 18 | |
| 19 | def train(uri_path: str = None): |
| 20 | """train model |
| 21 | |
| 22 | Returns |
| 23 | ------- |
| 24 | pred_score: pandas.DataFrame |
| 25 | predict scores |
| 26 | performance: dict |
| 27 | model performance |
| 28 | """ |
| 29 | |
| 30 | # model initialization |
| 31 | model = init_instance_by_config(CSI300_GBDT_TASK["model"]) |
| 32 | dataset = init_instance_by_config(CSI300_GBDT_TASK["dataset"]) |
| 33 | # To test __repr__ |
| 34 | print(dataset) |
| 35 | print(R) |
| 36 | |
| 37 | # start exp |
| 38 | with R.start(experiment_name="workflow", uri=uri_path): |
| 39 | R.log_params(**flatten_dict(CSI300_GBDT_TASK)) |
| 40 | model.fit(dataset) |
| 41 | R.save_objects(trained_model=model) |
| 42 | # prediction |
| 43 | recorder = R.get_recorder() |
| 44 | # To test __repr__ |
| 45 | print(recorder) |
| 46 | # To test get_local_dir |
| 47 | print(recorder.get_local_dir()) |
| 48 | rid = recorder.id |
| 49 | sr = SignalRecord(model, dataset, recorder) |
| 50 | sr.generate() |
| 51 | pred_score = sr.load("pred.pkl") |
| 52 | |
| 53 | # calculate ic and ric |
| 54 | sar = SigAnaRecord(recorder) |
| 55 | sar.generate() |
| 56 | ic = sar.load("ic.pkl") |
| 57 | ric = sar.load("ric.pkl") |
| 58 | |
| 59 | uri_path = R.get_uri() |
| 60 | return pred_score, {"ic": ic, "ric": ric}, rid, uri_path |
| 61 | |
| 62 | |
| 63 | def fake_experiment(): |
no test coverage detected