liuyu/qlib
1
0
Fork 0
mirror of https://github.com/microsoft/qlib.git synced 2026-07-15 00:36:55 +08:00
Code Activity

Test CSRankNorm.

Browse Source
This commit is contained in:
lwwang1995
2020-12-06 17:24:58 +08:00
committed by you-n-g
parent d2107c9957
commit a88697151a
1 changed files with 6 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
tests/test_dataset.py
View File

@@ -8,7 +8,7 @@ from qlib.data.dataset import TSDatasetH
import numpy as np import numpy as np
from torch.utils.data import DataLoader from torch.utils.data import DataLoader
import time import time
from qlib.data.dataset.handler import DataHandlerLP
class TestDataset(TestAutoData): class TestDataset(TestAutoData):
def testTSDataset(self): def testTSDataset(self):
@@ -23,17 +23,14 @@ class TestDataset(TestAutoData):
"fit_end_time": "2014-12-31", "fit_end_time": "2014-12-31",
"instruments": "csi300", "instruments": "csi300",
"infer_processors": [ "infer_processors": [
{"class": "DropCol", "kwargs": {"col_list": ["VWAP0"]}},
{"class": "FilterCol", "kwargs": {"col_list": ["RESI5", "WVMA5", "RSQR5"]}}, {"class": "FilterCol", "kwargs": {"col_list": ["RESI5", "WVMA5", "RSQR5"]}},
{"class": "CSZFillna", "kwargs": {"fields_group": "feature"}}, {"class": "RobustZScoreNorm", "kwargs": {"fields_group": "feature", "clip_outlier":"true"}},
{"class": "Fillna", "kwargs": {"fields_group": "feature"}},
], ],
"learn_processors": [ "learn_processors": [
{"class": "DropCol", "kwargs": {"col_list": ["VWAP0"]}},
{"class": "DropnaProcessor", "kwargs": {"fields_group": "feature"}},
"DropnaLabel", "DropnaLabel",
{"class": "CSZScoreNorm", "kwargs": {"fields_group": "label"}}, {"class": "CSZScoreNorm", "kwargs": {"fields_group": "label"}}, # CSRankNorm
], ],
"process_type": "independent",
}, },
}, },
segments={ segments={
@@ -42,8 +39,8 @@ class TestDataset(TestAutoData):
"test": ("2017-01-01", "2020-08-01"), "test": ("2017-01-01", "2020-08-01"),
}, },
) )
tsds_train = tsdh.prepare("train") # Test the correctness tsds_train = tsdh.prepare("train", data_key=DataHandlerLP.DK_L) # Test the correctness
tsds = tsdh.prepare("valid") # prepare a dataset with is friendly to converting tabular data to time-series tsds = tsdh.prepare("valid", data_key=DataHandlerLP.DK_L)
t = time.time() t = time.time()
for idx in np.random.randint(0, len(tsds_train), size=2000): for idx in np.random.randint(0, len(tsds_train), size=2000):