liuyu/qlib
1
0
Fork 0
mirror of https://github.com/microsoft/qlib.git synced 2026-07-10 14:26:56 +08:00
Code Activity

Add segment args for pred and refine MultiSegRecord

Browse Source
This commit is contained in:
D-X-Y
2021-03-28 08:30:16 +00:00
parent 9d04ae4676
commit 8a2e7b62af
5 changed files with 47 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files

30
qlib/contrib/workflow/record_temp.py
View File

@@ -1,13 +1,12 @@
# Copyright (c) Microsoft Corporation.
# Licensed under the MIT License.
import re
import pandas as pd
from sklearn.metrics import mean_squared_error
from pprint import pprint
from typing import Dict, Text, Any
import numpy as np
from ...contrib.eva.alpha import calc_ic
from ...workflow.record_temp import RecordTemp
from ...workflow.record_temp import SignalRecord
from ...data import dataset as qlib_dataset
@@ -30,16 +29,29 @@ class MultiSegRecord(RecordTemp):
self.dataset = dataset
def generate(self, segments: Dict[Text, Any], save: bool = False):
# generate prediciton
for key, segment in segments.items():
predics = self.model.predict(self.dataset, segment)
if isinstance(pred, pd.Series):
predics = predictions.to_frame("score")
# self.recorder.save_objects(**{"pred.pkl": pred})
if isinstance(predics, pd.Series):
predics = predics.to_frame("score")
labels = self.dataset.prepare(
segments=segment, col_set="label", data_key=dataset.handler.DataHandlerLP.DK_R
segments=segment, col_set="label", data_key=qlib_dataset.handler.DataHandlerLP.DK_R
)
# compute ic, rank_ic
# Compute the IC and Rank IC
ic, ric = calc_ic(predics.iloc[:, 0], labels.iloc[:, 0])
results = {"all-IC": ic, "mean-IC": ic.mean(), "all-Rank-IC": ric, "mean-Rank-IC": ric.mean()}
logger.info("--- Results for {:} ({:}) ---".format(key, segment))
ic_x100, ric_x100 = ic * 100, ric * 100
logger.info("IC: {:.4f}%".format(ic_x100.mean()))
logger.info("ICIR: {:.4f}%".format(ic_x100.mean() / ic_x100.std()))
logger.info("Rank IC: {:.4f}%".format(ric_x100.mean()))
logger.info("Rank ICIR: {:.4f}%".format(ric_x100.mean() / ric_x100.std()))
if save:
save_name = "results-{:}.pkl".format(key)
self.recorder.save_objects(**{save_name: results})
logger.info(
"The record '{save_name}' has been saved as the artifact of the Experiment {self.recorder.experiment_id}"
)
class SignalMseRecord(SignalRecord):
@@ -67,7 +79,7 @@ class SignalMseRecord(SignalRecord):
objects = {"mse.pkl": mse, "rmse.pkl": np.sqrt(mse)}
self.recorder.log_metrics(**metrics)
self.recorder.save_objects(**objects, artifact_path=self.get_path())
pprint(metrics)
logger.info("The evaluation results in SignalMseRecord is {:}".format(metrics))
def list(self):
paths = [self.get_path("mse.pkl"), self.get_path("rmse.pkl")]