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

Update test_dataset

Browse Source
This commit is contained in:
lwwang1995
2020-12-05 22:36:04 +08:00
committed by you-n-g
parent d2d865fb7a
commit 60f62482b7
1 changed files with 37 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

38
tests/test_dataset.py Normal file → Executable file
View File

@@ -6,6 +6,8 @@ import sys
from qlib.tests import TestAutoData from qlib.tests import TestAutoData
from qlib.data.dataset import TSDatasetH from qlib.data.dataset import TSDatasetH
import numpy as np import numpy as np
from torch.utils.data import DataLoader
import time
class TestDataset(TestAutoData): class TestDataset(TestAutoData):
@@ -20,6 +22,36 @@ class TestDataset(TestAutoData):
"fit_start_time": "2008-01-01", "fit_start_time": "2008-01-01",
"fit_end_time": "2014-12-31", "fit_end_time": "2014-12-31",
"instruments": "csi300", "instruments": "csi300",
"infer_processors": [
{
"class" : "DropCol",
"kwargs":{"col_list": ["VWAP0"]}
},
{
"class" : "FilterCol",
"kwargs":{"col_list": ["RESI5", "WVMA5", "RSQR5"]}
},
{
"class" : "CSZFillna",
"kwargs":{"fields_group": "feature"}
}
],
"learn_processors": [
{
"class" : "DropCol",
"kwargs":{"col_list": ["VWAP0"]}
},
{
"class" : "DropnaProcessor",
"kwargs":{"fields_group": "feature"}
},
"DropnaLabel",
{
"class": "CSZScoreNorm",
"kwargs": {"fields_group": "label"}
}
],
"process_type": "independent"
}, },
}, },
segments={ segments={
@@ -28,8 +60,12 @@ class TestDataset(TestAutoData):
"test": ("2017-01-01", "2020-08-01"), "test": ("2017-01-01", "2020-08-01"),
}, },
) )
_ = tsdh.prepare("train") # Test the correctness tsds_train = tsdh.prepare("train") # Test the correctness
tsds = tsdh.prepare("valid") # prepare a dataset with is friendly to converting tabular data to time-series tsds = tsdh.prepare("valid") # prepare a dataset with is friendly to converting tabular data to time-series
train_loader = DataLoader(tsds_train, batch_size=800, shuffle=True)
for data in train_loader:
now = time.localtime()
print(time.strftime("%Y-%m-%d-%H_%M_%S", now))
# The dimension of sample is same as tabular data, but it will return timeseries data of the sample # The dimension of sample is same as tabular data, but it will return timeseries data of the sample