liuyu/qlib
1
0
Fork 0
mirror of https://github.com/microsoft/qlib.git synced 2026-07-12 23:36:54 +08:00
Code Activity

Format with black

Browse Source
This commit is contained in:
Jactus
2020-10-29 13:22:49 +08:00
parent 490dbd908b
commit da9d1c8ac6
20 changed files with 290 additions and 251 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
qlib/contrib/backtest/backtest.py
View File

@@ -46,10 +46,10 @@ def backtest(pred, strategy, trade_exchange, shift, verbose, account, benchmark)
benchmark code, default is SH000905 CSI500
"""
# Convert format if the input format is not expected
if get_level_index(pred, level='datetime') == 1:
if get_level_index(pred, level="datetime") == 1:
pred = pred.swaplevel().sort_index()
if isinstance(pred, pd.Series):
pred = pred.to_frame('score')
pred = pred.to_frame("score")
trade_account = Account(init_cash=account)
_pred_dates = pred.index.get_level_values(level="datetime")
@@ -80,8 +80,9 @@ def backtest(pred, strategy, trade_exchange, shift, verbose, account, benchmark)
# 1. Load the score_series at pred_date
try:
score = pred.loc(axis=0)[pred_date, :] # (trade_date, stock_id) multi_index, score in pdate
score_series = score.reset_index(level="datetime",
drop=True)["score"] # pd.Series(index:stock_id, data: score)
score_series = score.reset_index(level="datetime", drop=True)[
"score"
] # pd.Series(index:stock_id, data: score)
except KeyError:
LOG.warning("No score found on predict date[{:%Y-%m-%d}]".format(trade_date))
score_series = None

76
qlib/contrib/data/handler.py
View File

@@ -16,21 +16,16 @@ class ALPHA360(DataHandlerLP):
"kwargs": {
"config": {
"feature": {
"price": {
"windows": range(60)
},
"volume": {
"windows": range(60)
},
"price": {"windows": range(60)},
"volume": {"windows": range(60)},
},
"label": self.get_label_config()
"label": self.get_label_config(),
},
}
},
}
infer_processors = [{
"class": "ConfigSectionProcessor",
"module_path": "qlib.contrib.data.processor"
}] # ConfigSectionProcessor will normalize LABEL0
infer_processors = [
{"class": "ConfigSectionProcessor", "module_path": "qlib.contrib.data.processor"}
] # ConfigSectionProcessor will normalize LABEL0
super().__init__(instruments, start_time, end_time, data_loader=data_loader, infer_processors=infer_processors)
def get_label_config(self):
@@ -49,12 +44,7 @@ class Alpha158(DataHandlerLP):
start_time=None,
end_time=None,
infer_processors=[],
learn_processors=["DropnaLabel", {
"class": "CSZScoreNorm",
"kwargs": {
"fields_group": "label"
}
}],
learn_processors=["DropnaLabel", {"class": "CSZScoreNorm", "kwargs": {"fields_group": "label"}}],
fit_start_time=None,
fit_end_time=None,
):
@@ -65,11 +55,13 @@ class Alpha158(DataHandlerLP):
klass, pkwargs = get_cls_kwargs(p, processor_module)
# FIXME: It's hard code here!!!!!
if isinstance(klass, (MinMaxNorm, ZscoreNorm)):
assert (fit_start_time is not None and fit_end_time is not None)
pkwargs.update({
"fit_start_time": fit_start_time,
"fit_end_time": fit_end_time,
})
assert fit_start_time is not None and fit_end_time is not None
pkwargs.update(
{
"fit_start_time": fit_start_time,
"fit_end_time": fit_end_time,
}
)
new_l.append({"class": klass.__name__, "kwargs": pkwargs})
else:
new_l.append(p)
@@ -81,18 +73,17 @@ class Alpha158(DataHandlerLP):
data_loader = {
"class": "QlibDataLoader",
"kwargs": {
"config": {
"feature": self.get_feature_config(),
"label": self.get_label_config()
},
}
"config": {"feature": self.get_feature_config(), "label": self.get_label_config()},
},
}
super().__init__(instruments,
start_time,
end_time,
data_loader=data_loader,
infer_processors=infer_processors,
learn_processors=learn_processors)
super().__init__(
instruments,
start_time,
end_time,
data_loader=data_loader,
infer_processors=infer_processors,
learn_processors=learn_processors,
)
def get_feature_config(self):
conf = {
@@ -247,7 +238,8 @@ class Alpha158(DataHandlerLP):
if use("SUMD"):
fields += [
"(Sum(Greater($close-Ref($close, 1), 0), %d)-Sum(Greater(Ref($close, 1)-$close, 0), %d))"
"/(Sum(Abs($close-Ref($close, 1)), %d)+1e-12)" % (d, d, d) for d in windows
"/(Sum(Abs($close-Ref($close, 1)), %d)+1e-12)" % (d, d, d)
for d in windows
]
names += ["SUMD%d" % d for d in windows]
if use("VMA"):
@@ -258,26 +250,30 @@ class Alpha158(DataHandlerLP):
names += ["VSTD%d" % d for d in windows]
if use("WVMA"):
fields += [
"Std(Abs($close/Ref($close, 1)-1)*$volume, %d)/(Mean(Abs($close/Ref($close, 1)-1)*$volume, %d)+1e-12)" %
(d, d) for d in windows
"Std(Abs($close/Ref($close, 1)-1)*$volume, %d)/(Mean(Abs($close/Ref($close, 1)-1)*$volume, %d)+1e-12)"
% (d, d)
for d in windows
]
names += ["WVMA%d" % d for d in windows]
if use("VSUMP"):
fields += [
"Sum(Greater($volume-Ref($volume, 1), 0), %d)/(Sum(Abs($volume-Ref($volume, 1)), %d)+1e-12)" % (d, d)
"Sum(Greater($volume-Ref($volume, 1), 0), %d)/(Sum(Abs($volume-Ref($volume, 1)), %d)+1e-12)"
% (d, d)
for d in windows
]
names += ["VSUMP%d" % d for d in windows]
if use("VSUMN"):
fields += [
"Sum(Greater(Ref($volume, 1)-$volume, 0), %d)/(Sum(Abs($volume-Ref($volume, 1)), %d)+1e-12)" % (d, d)
"Sum(Greater(Ref($volume, 1)-$volume, 0), %d)/(Sum(Abs($volume-Ref($volume, 1)), %d)+1e-12)"
% (d, d)
for d in windows
]
names += ["VSUMN%d" % d for d in windows]
if use("VSUMD"):
fields += [
"(Sum(Greater($volume-Ref($volume, 1), 0), %d)-Sum(Greater(Ref($volume, 1)-$volume, 0), %d))"
"/(Sum(Abs($volume-Ref($volume, 1)), %d)+1e-12)" % (d, d, d) for d in windows
"/(Sum(Abs($volume-Ref($volume, 1)), %d)+1e-12)" % (d, d, d)
for d in windows
]
names += ["VSUMD%d" % d for d in windows]

5
qlib/contrib/data/processor.py
View File

@@ -8,9 +8,10 @@ from ...data.dataset.processor import Processor, get_group_columns
class ConfigSectionProcessor(Processor):
'''
"""
This processor is designed for Alpha158. And will be replaced by simple processors in the future
'''
"""
def __init__(self, fields_group=None, **kwargs):
super().__init__()
# Options

6
qlib/contrib/evaluate.py
View File

@@ -159,11 +159,11 @@ def get_exchange(
if deal_price[0] != "$":
deal_price = "$" + deal_price
if extract_codes:
codes = sorted(pred.index.get_level_values('instrument').unique())
codes = sorted(pred.index.get_level_values("instrument").unique())
else:
codes = "all" # TODO: We must ensure that 'all.txt' includes all the stocks
dates = sorted(pred.index.get_level_values('datetime').unique())
dates = sorted(pred.index.get_level_values("datetime").unique())
dates = np.append(dates, get_date_range(dates[-1], shift=shift))
exchange = Exchange(
@@ -298,7 +298,7 @@ def long_short_backtest(
"short": short_returns(excess),
"long_short": long_short_returns}
"""
if get_level_index(pred, level='datetime') == 1:
if get_level_index(pred, level="datetime") == 1:
pred = pred.swaplevel().sort_index()
if trade_unit is None:

51
qlib/contrib/model/gbdt.py
View File

@@ -12,26 +12,29 @@ from ...data.dataset.handler import DataHandlerLP
class LGBModel(Model):
"""LightGBM Model"""
def __init__(self, loss="mse", **kwargs):
if loss not in {"mse", "binary"}:
raise NotImplementedError
self._params = {'objective': loss}
self._params = {"objective": loss}
self._params.update(kwargs)
self.model = None
def fit(self,
dataset: DatasetH,
num_boost_round=1000,
early_stopping_rounds=50,
verbose_eval=20,
evals_result=dict(),
**kwargs):
def fit(
self,
dataset: DatasetH,
num_boost_round=1000,
early_stopping_rounds=50,
verbose_eval=20,
evals_result=dict(),
**kwargs
):
df_train, df_valid = dataset.prepare(['train', 'valid'],
col_set=['feature', 'label'],
data_key=DataHandlerLP.DK_L)
x_train, y_train = df_train['feature'], df_train['label']
x_valid, y_valid = df_valid['feature'], df_valid['label']
df_train, df_valid = dataset.prepare(
["train", "valid"], col_set=["feature", "label"], data_key=DataHandlerLP.DK_L
)
x_train, y_train = df_train["feature"], df_train["label"]
x_valid, y_valid = df_valid["feature"], df_valid["label"]
# Lightgbm need 1D array as its label
if y_train.values.ndim == 2 and y_train.values.shape[1] == 1:
@@ -41,20 +44,22 @@ class LGBModel(Model):
dtrain = lgb.Dataset(x_train.values, label=y_train_1d)
dvalid = lgb.Dataset(x_valid.values, label=y_valid_1d)
self.model = lgb.train(self._params,
dtrain,
num_boost_round=num_boost_round,
valid_sets=[dtrain, dvalid],
valid_names=["train", "valid"],
early_stopping_rounds=early_stopping_rounds,
verbose_eval=verbose_eval,
evals_result=evals_result,
**kwargs)
self.model = lgb.train(
self._params,
dtrain,
num_boost_round=num_boost_round,
valid_sets=[dtrain, dvalid],
valid_names=["train", "valid"],
early_stopping_rounds=early_stopping_rounds,
verbose_eval=verbose_eval,
evals_result=evals_result,
**kwargs
)
evals_result["train"] = list(evals_result["train"].values())[0]
evals_result["valid"] = list(evals_result["valid"].values())[0]
def predict(self, dataset):
if self.model is None:
raise ValueError("model is not fitted yet!")
x_test = dataset.prepare('test', col_set='feature')
x_test = dataset.prepare("test", col_set="feature")
return pd.Series(self.model.predict(np.squeeze(x_test.values)), index=x_test.index)