liuyu/qlib
1
0
Fork 0
mirror of https://github.com/microsoft/qlib.git synced 2026-07-14 08:16:54 +08:00
Code Activity

Merge branch 'main' of https://github.com/you-n-g/qlib into main

Browse Source
This commit is contained in:
Alex Wang
2020-11-26 14:35:35 +08:00
parent 28b11886dd 305b9372c7
commit 7a5153f7c7
39 changed files with 809 additions and 637 deletions
Download Patch File Download Diff File Expand all files Collapse all files

84
qlib/contrib/data/handler.py
View File

@@ -10,6 +10,28 @@ from inspect import getfullargspec
import copy
def check_transform_proc(proc_l, fit_start_time, fit_end_time):
new_l = []
for p in proc_l:
if not isinstance(p, Processor):
klass, pkwargs = get_cls_kwargs(p, processor_module)
args = getfullargspec(klass).args
if "fit_start_time" in args and "fit_end_time" in args:
assert (
fit_start_time is not None and fit_end_time is not None
), "Make sure `fit_start_time` and `fit_end_time` are 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)
return new_l
class ALPHA360_Denoise(DataHandlerLP):
def __init__(self, instruments="csi500", start_time=None, end_time=None, fit_start_time=None, fit_end_time=None):
data_loader = {
@@ -83,8 +105,31 @@ class ALPHA360_Denoise(DataHandlerLP):
return fields, names
_DEFAULT_LEARN_PROCESSORS = [
{"class": "DropnaLabel"},
{"class": "CSZScoreNorm", "kwargs": {"fields_group": "label"}},
]
_DEFAULT_INFER_PROCESSORS = [
{"class": "ProcessInf", "kwargs": {}},
{"class": "ZScoreNorm", "kwargs": {}},
{"class": "Fillna", "kwargs": {}},
]
class ALPHA360(DataHandlerLP):
def __init__(self, instruments="csi500", start_time=None, end_time=None, fit_start_time=None, fit_end_time=None):
def __init__(
self,
instruments="csi500",
start_time=None,
end_time=None,
infer_processors=_DEFAULT_INFER_PROCESSORS,
learn_processors=_DEFAULT_LEARN_PROCESSORS,
fit_start_time=None,
fit_end_time=None,
):
infer_processors = check_transform_proc(infer_processors, fit_start_time, fit_end_time)
learn_processors = check_transform_proc(learn_processors, fit_start_time, fit_end_time)
data_loader = {
"class": "QlibDataLoader",
"kwargs": {
@@ -95,16 +140,6 @@ class ALPHA360(DataHandlerLP):
},
}
learn_processors = [
{"class": "DropnaLabel", "kwargs": {"fields_group": "label"}},
{"class": "CSZScoreNorm", "kwargs": {"fields_group": "label"}},
]
infer_processors = [
{"class": "ProcessInf", "kwargs": {}},
{"class": "ZscoreNorm", "kwargs": {"fit_start_time": fit_start_time, "fit_end_time": fit_end_time}},
{"class": "Fillna", "kwargs": {}},
]
super().__init__(
instruments,
start_time,
@@ -168,33 +203,12 @@ class Alpha158(DataHandlerLP):
start_time=None,
end_time=None,
infer_processors=[],
learn_processors=["DropnaLabel", {"class": "CSZScoreNorm", "kwargs": {"fields_group": "label"}}],
learn_processors=_DEFAULT_LEARN_PROCESSORS,
fit_start_time=None,
fit_end_time=None,
):
def check_transform_proc(proc_l):
new_l = []
for p in proc_l:
if not isinstance(p, Processor):
klass, pkwargs = get_cls_kwargs(p, processor_module)
args = getfullargspec(klass).args
if "fit_start_time" in args and "fit_end_time" in args:
assert (
fit_start_time is not None and fit_end_time is not None
), "Make sure `fit_start_time` and `fit_end_time` are 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)
return new_l
infer_processors = check_transform_proc(infer_processors)
learn_processors = check_transform_proc(learn_processors)
infer_processors = check_transform_proc(infer_processors, fit_start_time, fit_end_time)
learn_processors = check_transform_proc(learn_processors, fit_start_time, fit_end_time)
data_loader = {
"class": "QlibDataLoader",

84
qlib/contrib/evaluate.py
View File

@@ -26,9 +26,9 @@ def risk_analysis(r, N=252):
Parameters
----------
r : pandas.Series
daily return series
daily return series.
N: int
scaler for annualizing information_ratio (day: 250, week: 50, month: 12)
scaler for annualizing information_ratio (day: 250, week: 50, month: 12).
"""
mean = r.mean()
std = r.std(ddof=1)
@@ -61,7 +61,7 @@ def get_strategy(
----------
strategy : Strategy()
strategy used in backtest
strategy used in backtest.
topk : int (Default value: 50)
top-N stocks to buy.
margin : int or float(Default value: 0.5)
@@ -73,14 +73,14 @@ def get_strategy(
sell_limit = pred_in_a_day.count() * margin
buffer margin, in single score_mode, continue holding stock if it is in nlargest(sell_limit)
sell_limit should be no less than topk
buffer margin, in single score_mode, continue holding stock if it is in nlargest(sell_limit).
sell_limit should be no less than topk.
n_drop : int
number of stocks to be replaced in each trading date
number of stocks to be replaced in each trading date.
risk_degree: float
0-1, 0.95 for example, use 95% money to trade
0-1, 0.95 for example, use 95% money to trade.
str_type: 'amount', 'weight' or 'dropout'
strategy type: TopkAmountStrategy ,TopkWeightStrategy or TopkDropoutStrategy
strategy type: TopkAmountStrategy ,TopkWeightStrategy or TopkDropoutStrategy.
Returns
-------
@@ -126,21 +126,21 @@ def get_exchange(
----------
# exchange related arguments
exchange: Exchange()
exchange: Exchange().
subscribe_fields: list
subscribe fields
subscribe fields.
open_cost : float
open transaction cost
open transaction cost.
close_cost : float
close transaction cost
close transaction cost.
min_cost : float
min transaction cost
min transaction cost.
trade_unit : int
100 for China A
100 for China A.
deal_price: str
dealing price type: 'close', 'open', 'vwap'
dealing price type: 'close', 'open', 'vwap'.
limit_threshold : float
limit move 0.1 (10%) for example, long and short with same limit
limit move 0.1 (10%) for example, long and short with same limit.
extract_codes: bool
will we pass the codes extracted from the pred to the exchange.
NOTE: This will be faster with offline qlib.
@@ -193,20 +193,20 @@ def backtest(pred, account=1e9, shift=1, benchmark="SH000905", verbose=True, **k
- **backtest workflow related or commmon arguments**
pred : pandas.DataFrame
predict should has <datetime, instrument> index and one `score` column
predict should has <datetime, instrument> index and one `score` column.
account : float
init account value
init account value.
shift : int
whether to shift prediction by one day
whether to shift prediction by one day.
benchmark : str
benchmark code, default is SH000905 CSI 500
benchmark code, default is SH000905 CSI 500.
verbose : bool
whether to print log
whether to print log.
- **strategy related arguments**
strategy : Strategy()
strategy used in backtest
strategy used in backtest.
topk : int (Default value: 50)
top-N stocks to buy.
margin : int or float(Default value: 0.5)
@@ -218,33 +218,33 @@ def backtest(pred, account=1e9, shift=1, benchmark="SH000905", verbose=True, **k
sell_limit = pred_in_a_day.count() * margin
buffer margin, in single score_mode, continue holding stock if it is in nlargest(sell_limit)
sell_limit should be no less than topk
buffer margin, in single score_mode, continue holding stock if it is in nlargest(sell_limit).
sell_limit should be no less than topk.
n_drop : int
number of stocks to be replaced in each trading date
number of stocks to be replaced in each trading date.
risk_degree: float
0-1, 0.95 for example, use 95% money to trade
0-1, 0.95 for example, use 95% money to trade.
str_type: 'amount', 'weight' or 'dropout'
strategy type: TopkAmountStrategy ,TopkWeightStrategy or TopkDropoutStrategy
strategy type: TopkAmountStrategy ,TopkWeightStrategy or TopkDropoutStrategy.
- **exchange related arguments**
exchange: Exchange()
pass the exchange for speeding up.
subscribe_fields: list
subscribe fields
subscribe fields.
open_cost : float
open transaction cost. The default value is 0.002(0.2%).
close_cost : float
close transaction cost. The default value is 0.002(0.2%).
min_cost : float
min transaction cost
min transaction cost.
trade_unit : int
100 for China A
100 for China A.
deal_price: str
dealing price type: 'close', 'open', 'vwap'
dealing price type: 'close', 'open', 'vwap'.
limit_threshold : float
limit move 0.1 (10%) for example, long and short with same limit
limit move 0.1 (10%) for example, long and short with same limit.
extract_codes: bool
will we pass the codes extracted from the pred to the exchange.
@@ -291,17 +291,17 @@ def long_short_backtest(
"""
A backtest for long-short strategy
:param pred: The trading signal produced on day `T`
:param topk: The short topk securities and long topk securities
:param deal_price: The price to deal the trading
:param pred: The trading signal produced on day `T`.
:param topk: The short topk securities and long topk securities.
:param deal_price: The price to deal the trading.
:param shift: Whether to shift prediction by one day. The trading day will be T+1 if shift==1.
:param open_cost: open transaction cost
:param close_cost: close transaction cost
:param trade_unit: 100 for China A
:param limit_threshold: limit move 0.1 (10%) for example, long and short with same limit
:param min_cost: min transaction cost
:param subscribe_fields: subscribe fields
:param extract_codes: bool
:param open_cost: open transaction cost.
:param close_cost: close transaction cost.
:param trade_unit: 100 for China A.
:param limit_threshold: limit move 0.1 (10%) for example, long and short with same limit.
:param min_cost: min transaction cost.
:param subscribe_fields: subscribe fields.
:param extract_codes: bool.
will we pass the codes extracted from the pred to the exchange.
NOTE: This will be faster with offline qlib.
:return: The result of backtest, it is represented by a dict.

20
qlib/contrib/model/catboost_model.py
View File

@@ -34,14 +34,14 @@ class CatBoostModel(Model):
def fit(
self,
dataset: DatasetH,
num_boost_round=1000,
early_stopping_rounds=50,
verbose_eval=20,
evals_result=dict(),
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
["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"]
@@ -52,8 +52,8 @@ class CatBoostModel(Model):
else:
raise ValueError("CatBoost doesn't support multi-label training")
train_pool = Pool(data=x_train, label=y_train_1d)
valid_pool = Pool(data=x_valid, label=y_valid_1d)
train_pool = Pool(data = x_train, label = y_train_1d)
valid_pool = Pool(data = x_valid, label = y_valid_1d)
# Initialize the catboost model
self._params["iterations"] = num_boost_round
@@ -63,7 +63,7 @@ class CatBoostModel(Model):
self.model = CatBoost(self._params, **kwargs)
# train the model
self.model.fit(train_pool, eval_set=valid_pool, use_best_model=True, **kwargs)
self.model.fit(train_pool, eval_set = valid_pool, use_best_model = True, **kwargs)
evals_result = self.model.get_evals_result()
evals_result["train"] = list(evals_result["learn"].values())[0]
@@ -72,8 +72,8 @@ class CatBoostModel(Model):
def predict(self, dataset):
if self.model is None:
raise ValueError("model is not fitted yet!")
x_test = dataset.prepare("test", col_set="feature")
return pd.Series(self.model.predict(x_test.values), index=x_test.index)
x_test = dataset.prepare("test", col_set = "feature")
return pd.Series(self.model.predict(x_test.values), index = x_test.index)
if __name__ == "__main__":

23
qlib/contrib/model/pytorch_gats.py
View File

@@ -28,14 +28,12 @@ class GAT(Model):
Parameters
----------
input_dim : int
input dimension
output_dim : int
output dimension
layers : tuple
layer sizes
lr : float
learning rate
d_feat : int
input dimensions for each time step
metric : str
the evaluate metric used in early stop
optimizer : str
optimizer name
GPU : str
@@ -119,11 +117,7 @@ class GAT(Model):
seed,
)
)
if loss not in {"mse", "binary"}:
raise NotImplementedError("loss {} is not supported!".format(loss))
self._scorer = mean_squared_error if loss == "mse" else roc_auc_score
self.GAT_model = GATModel(
d_feat=self.d_feat,
hidden_size=self.hidden_size,
@@ -213,7 +207,6 @@ class GAT(Model):
losses = []
indices = np.arange(len(x_values))
np.random.shuffle(indices)
for i in range(len(indices))[:: self.batch_size]:
@@ -377,7 +370,6 @@ class GATModel(nn.Module):
self.fc_out = nn.Linear(hidden_size, 1)
self.leaky_relu = nn.LeakyReLU()
self.softmax = nn.Softmax(dim=1)
self.d_feat = d_feat
def cal_convariance(self, x, y): # the 2nd dimension of x and y are the same
@@ -396,12 +388,7 @@ class GATModel(nn.Module):
out, _ = self.rnn(x)
hidden = out[:, -1, :]
hidden = self.bn1(hidden)
gamma = self.cal_convariance(hidden, hidden)
# gamma = hidden.mm(torch.t(hidden))
# gamma = self.leaky_relu(gamma)
# gamma = self.softmax(gamma)
# gamma = gamma * (torch.ones(x.shape[0], x.shape[0]).to(device) - torch.diag(torch.ones(x.shape[0])).to(device))
output = gamma.mm(hidden)
output = self.fc(output)
output = self.bn2(output)

17
qlib/contrib/model/pytorch_gru.py
View File

@@ -28,14 +28,10 @@ class GRU(Model):
Parameters
----------
input_dim : int
input dimension
output_dim : int
output dimension
layers : tuple
layer sizes
lr : float
learning rate
d_feat : int
input dimension for each time step
metric: str
the evaluate metric used in early stop
optimizer : str
optimizer name
GPU : str
@@ -112,10 +108,6 @@ class GRU(Model):
)
)
if loss not in {"mse", "binary"}:
raise NotImplementedError("loss {} is not supported!".format(loss))
self._scorer = mean_squared_error if loss == "mse" else roc_auc_score
self.gru_model = GRUModel(
d_feat=self.d_feat, hidden_size=self.hidden_size, num_layers=self.num_layers, dropout=self.dropout
)
@@ -251,7 +243,6 @@ class GRU(Model):
# train
self.logger.info("training...")
self._fitted = True
# return
for step in range(self.n_epochs):
self.logger.info("Epoch%d:", step)

17
qlib/contrib/model/pytorch_lstm.py
View File

@@ -28,14 +28,10 @@ class LSTM(Model):
Parameters
----------
input_dim : int
input dimension
output_dim : int
output dimension
layers : tuple
layer sizes
lr : float
learning rate
d_feat : int
input dimension for each time step
metric: str
the evaluate metric used in early stop
optimizer : str
optimizer name
GPU : str
@@ -112,10 +108,6 @@ class LSTM(Model):
)
)
if loss not in {"mse", "binary"}:
raise NotImplementedError("loss {} is not supported!".format(loss))
self._scorer = mean_squared_error if loss == "mse" else roc_auc_score
self.lstm_model = LSTMModel(
d_feat=self.d_feat, hidden_size=self.hidden_size, num_layers=self.num_layers, dropout=self.dropout
)
@@ -251,7 +243,6 @@ class LSTM(Model):
# train
self.logger.info("training...")
self._fitted = True
# return
for step in range(self.n_epochs):
self.logger.info("Epoch%d:", step)

36
qlib/contrib/model/xgboost.py
View File

@@ -22,25 +22,23 @@ from ...data.dataset.handler import DataHandlerLP
class XGBModel(Model):
"""XGBModel Model"""
def __init__(self, obj="mse", **kwargs):
if obj not in {"mse", "binary"}:
raise NotImplementedError
self._params = {"obj": obj}
def __init__(self, **kwargs):
self._params = {}
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(),
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
["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"]
@@ -51,16 +49,16 @@ class XGBModel(Model):
else:
raise ValueError("XGBoost doesn't support multi-label training")
dtrain = xgb.DMatrix(x_train.values, label=y_train_1d)
dvalid = xgb.DMatrix(x_valid.values, label=y_valid_1d)
dtrain = xgb.DMatrix(x_train.values, label = y_train_1d)
dvalid = xgb.DMatrix(x_valid.values, label = y_valid_1d)
self.model = xgb.train(
self._params,
dtrain=dtrain,
num_boost_round=num_boost_round,
evals=[(dtrain, "train"), (dvalid, "valid")],
early_stopping_rounds=early_stopping_rounds,
verbose_eval=verbose_eval,
evals_result=evals_result,
dtrain = dtrain,
num_boost_round = num_boost_round,
evals = [(dtrain, "train"), (dvalid, "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]
@@ -69,5 +67,5 @@ class XGBModel(Model):
def predict(self, dataset):
if self.model is None:
raise ValueError("model is not fitted yet!")
x_test = dataset.prepare("test", col_set="feature")
return pd.Series(self.model.predict(xgb.DMatrix(x_test.values)), index=x_test.index)
x_test = dataset.prepare("test", col_set = "feature")
return pd.Series(self.model.predict(xgb.DMatrix(x_test.values)), index = x_test.index)

16
qlib/contrib/report/analysis_model/analysis_model_performance.py
View File

@@ -252,7 +252,7 @@ def model_performance_graph(
"""Model performance
:param pred_label: index is **pd.MultiIndex**, index name is **[instrument, datetime]**; columns names is **[score,
label]**. It is usually same as the label of model training(e.g. "Ref($close, -2)/Ref($close, -1) - 1")
label]**. It is usually same as the label of model training(e.g. "Ref($close, -2)/Ref($close, -1) - 1").
.. code-block:: python
@@ -266,13 +266,13 @@ def model_performance_graph(
:param lag: `pred.groupby(level='instrument')['score'].shift(lag)`. It will be only used in the auto-correlation computing.
:param N: group number, default 5
:param reverse: if `True`, `pred['score'] *= -1`
:param rank: if **True**, calculate rank ic
:param graph_names: graph names; default ['cumulative_return', 'pred_ic', 'pred_autocorr', 'pred_turnover']
:param show_notebook: whether to display graphics in notebook, the default is `True`
:param show_nature_day: whether to display the abscissa of non-trading day
:return: if show_notebook is True, display in notebook; else return `plotly.graph_objs.Figure` list
:param N: group number, default 5.
:param reverse: if `True`, `pred['score'] *= -1`.
:param rank: if **True**, calculate rank ic.
:param graph_names: graph names; default ['cumulative_return', 'pred_ic', 'pred_autocorr', 'pred_turnover'].
:param show_notebook: whether to display graphics in notebook, the default is `True`.
:param show_nature_day: whether to display the abscissa of non-trading day.
:return: if show_notebook is True, display in notebook; else return `plotly.graph_objs.Figure` list.
"""
figure_list = []
for graph_name in graph_names:

6
qlib/contrib/report/analysis_position/cumulative_return.py
View File

@@ -218,10 +218,10 @@ def cumulative_return_graph(
Graph desc:
- Axis X: Trading day
- Axis X: Trading day.
- Axis Y:
- Above axis Y: `(((Ref($close, -1)/$close - 1) * weight).sum() / weight.sum()).cumsum()`
- Below axis Y: Daily weight sum
- Above axis Y: `(((Ref($close, -1)/$close - 1) * weight).sum() / weight.sum()).cumsum()`.
- Below axis Y: Daily weight sum.
- In the **sell** graph, `y < 0` stands for profit; in other cases, `y > 0` stands for profit.
- In the **buy_minus_sell** graph, the **y** value of the **weight** graph at the bottom is `buy_weight + sell_weight`.
- In each graph, the **red line** in the histogram on the right represents the average.

6
qlib/contrib/report/analysis_position/rank_label.py
View File

@@ -97,9 +97,9 @@ def rank_label_graph(
qcr.rank_label_graph(positions, features_df, pred_df_dates.min(), pred_df_dates.max())
:param position: position data; **qlib.contrib.backtest.backtest.backtest** result
:param position: position data; **qlib.contrib.backtest.backtest.backtest** result.
:param label_data: **D.features** result; index is **pd.MultiIndex**, index name is **[instrument, datetime]**; columns names is **[label]**.
**The label T is the change from T to T+1**, it is recommended to use ``close``, example: `D.features(D.instruments('csi500'), ['Ref($close, -1)/$close-1'])`
**The label T is the change from T to T+1**, it is recommended to use ``close``, example: `D.features(D.instruments('csi500'), ['Ref($close, -1)/$close-1'])`.
.. code-block:: python
@@ -115,7 +115,7 @@ def rank_label_graph(
:param start_date: start date
:param end_date: end_date
:param show_notebook: **True** or **False**. If True, show graph in notebook, else return figures
:param show_notebook: **True** or **False**. If True, show graph in notebook, else return figures.
:return:
"""
position = copy.deepcopy(position)

6
qlib/contrib/report/analysis_position/report.py
View File

@@ -186,7 +186,7 @@ def report_graph(report_df: pd.DataFrame, show_notebook: bool = True) -> [list,
qcr.report_graph(report_normal_df)
:param report_df: **df.index.name** must be **date**, **df.columns** must contain **return**, **turnover**, **cost**, **bench**
:param report_df: **df.index.name** must be **date**, **df.columns** must contain **return**, **turnover**, **cost**, **bench**.
.. code-block:: python
@@ -200,8 +200,8 @@ def report_graph(report_df: pd.DataFrame, show_notebook: bool = True) -> [list,
2017-01-10 -0.000416 0.000440 -0.003350 0.208396
:param show_notebook: whether to display graphics in notebook, the default is **True**
:return: if show_notebook is True, display in notebook; else return **plotly.graph_objs.Figure** list
:param show_notebook: whether to display graphics in notebook, the default is **True**.
:return: if show_notebook is True, display in notebook; else return **plotly.graph_objs.Figure** list.
"""
report_df = report_df.copy()
fig_list = _report_figure(report_df)

6
qlib/contrib/report/analysis_position/risk_analysis.py
View File

@@ -218,7 +218,7 @@ def risk_analysis_graph(
max_drawdown -0.088263
:param report_normal_df: **df.index.name** must be **date**, df.columns must contain **return**, **turnover**, **cost**, **bench**
:param report_normal_df: **df.index.name** must be **date**, df.columns must contain **return**, **turnover**, **cost**, **bench**.
.. code-block:: python
@@ -232,7 +232,7 @@ def risk_analysis_graph(
2017-01-10 -0.000416 0.000440 -0.003350 0.208396
:param report_long_short_df: **df.index.name** must be **date**, df.columns contain **long**, **short**, **long_short**
:param report_long_short_df: **df.index.name** must be **date**, df.columns contain **long**, **short**, **long_short**.
.. code-block:: python
@@ -246,7 +246,7 @@ def risk_analysis_graph(
2017-01-10 0.000824 -0.001944 -0.001120
:param show_notebook: Whether to display graphics in a notebook, default **True**
:param show_notebook: Whether to display graphics in a notebook, default **True**.
If True, show graph in notebook
If False, return graph figure
:return:

6
qlib/contrib/report/analysis_position/score_ic.py
View File

@@ -36,7 +36,7 @@ def score_ic_graph(pred_label: pd.DataFrame, show_notebook: bool = True) -> [lis
analysis_position.score_ic_graph(pred_label)
:param pred_label: index is **pd.MultiIndex**, index name is **[instrument, datetime]**; columns names is **[score, label]**
:param pred_label: index is **pd.MultiIndex**, index name is **[instrument, datetime]**; columns names is **[score, label]**.
.. code-block:: python
@@ -49,8 +49,8 @@ def score_ic_graph(pred_label: pd.DataFrame, show_notebook: bool = True) -> [lis
2017-12-15 -0.102778 -0.102778
:param show_notebook: whether to display graphics in notebook, the default is **True**
:return: if show_notebook is True, display in notebook; else return **plotly.graph_objs.Figure** list
:param show_notebook: whether to display graphics in notebook, the default is **True**.
:return: if show_notebook is True, display in notebook; else return **plotly.graph_objs.Figure** list.
"""
_ic_df = _get_score_ic(pred_label)
# FIXME: support HIGH-FREQ

70
qlib/contrib/strategy/strategy.py
View File

@@ -31,16 +31,16 @@ class BaseStrategy:
Parameters
-----------
score_series : pd.Seires
stock_id , score
stock_id , score.
current : Position()
current state of position
DO NOT directly change the state of current
current state of position.
DO NOT directly change the state of current.
trade_exchange : Exchange()
trade exchange
trade exchange.
pred_date : pd.Timestamp
predict date
predict date.
trade_date : pd.Timestamp
trade date
trade date.
"""
pass
@@ -49,11 +49,11 @@ class BaseStrategy:
Parameters
-----------
score_series : pd.Series
stock_id , score
stock_id , score.
pred_date : pd.Timestamp
oredict date
oredict date.
trade_date : pd.Timestamp
trade date
trade date.
"""
pass
@@ -67,7 +67,7 @@ class BaseStrategy:
"""
This method only be used in 'online' module, it will generate the *args to initial the strategy.
:param
mode : model used in 'online' module
mode : model used in 'online' module.
"""
return {}
@@ -82,7 +82,7 @@ class StrategyWrapper:
def __init__(self, inner_strategy):
"""__init__
:param inner_strategy: set the inner strategy
:param inner_strategy: set the inner strategy.
"""
self.inner_strategy = inner_strategy
@@ -99,9 +99,9 @@ class AdjustTimer:
Responsible for timing of position adjusting
This is designed as multiple inheritance mechanism due to:
- the is_adjust may need access to the internel state of a strategy
- the is_adjust may need access to the internel state of a strategy.
- it can be reguard as a enhancement to the existing strategy
- it can be reguard as a enhancement to the existing strategy.
"""
# adjust position in each trade date
@@ -146,12 +146,12 @@ class WeightStrategyBase(BaseStrategy, AdjustTimer):
Parameters
-----------
score : pd.Series
pred score for this trade date, index is stock_id, contain 'score' column
pred score for this trade date, index is stock_id, contain 'score' column.
current : Position()
current position
current position.
trade_exchange : Exchange()
trade_date : pd.Timestamp
trade date
trade date.
"""
raise NotImplementedError()
@@ -160,13 +160,13 @@ class WeightStrategyBase(BaseStrategy, AdjustTimer):
Parameters
-----------
score_series : pd.Seires
stock_id , score
stock_id , score.
current : Position()
current of account
current of account.
trade_exchange : Exchange()
exchange
exchange.
trade_date : pd.Timestamp
date
date.
"""
# judge if to adjust
if not self.is_adjust(trade_date):
@@ -206,26 +206,26 @@ class TopkDropoutStrategy(BaseStrategy, ListAdjustTimer):
Parameters
-----------
topk : int
The number of stocks in the portfolio
the number of stocks in the portfolio.
n_drop : int
number of stocks to be replaced in each trading date
number of stocks to be replaced in each trading date.
method_sell : str
dropout method_sell, random/bottom
dropout method_sell, random/bottom.
method_buy : str
dropout method_buy, random/top
dropout method_buy, random/top.
risk_degree : float
position percentage of total value
position percentage of total value.
thresh : int
minimun holding days since last buy singal of the stock
minimun holding days since last buy singal of the stock.
hold_thresh : int
minimum holding days
before sell stock , will check current.get_stock_count(order.stock_id) >= self.thresh
before sell stock , will check current.get_stock_count(order.stock_id) >= self.thresh.
only_tradable : bool
will the strategy only consider the tradable stock when buying and selling.
if only_tradable:
strategy will make buy sell decision without checking the tradable state of the stock
strategy will make buy sell decision without checking the tradable state of the stock.
else:
strategy will make decision with the tradable state of the stock info and avoid buy and sell them
strategy will make decision with the tradable state of the stock info and avoid buy and sell them.
"""
super(TopkDropoutStrategy, self).__init__()
ListAdjustTimer.__init__(self, kwargs.get("adjust_dates", None))
@@ -245,7 +245,7 @@ class TopkDropoutStrategy(BaseStrategy, ListAdjustTimer):
def get_risk_degree(self, date):
"""get_risk_degree
Return the proportion of your total value you will used in investment.
Dynamically risk_degree will result in Market timing
Dynamically risk_degree will result in Market timing.
"""
# It will use 95% amoutn of your total value by default
return self.risk_degree
@@ -257,15 +257,15 @@ class TopkDropoutStrategy(BaseStrategy, ListAdjustTimer):
Parameters
-----------
score_series : pd.Series
stock_id , score
stock_id , score.
current : Position()
current of account
current of account.
trade_exchange : Exchange()
exchange
exchange.
pred_date : pd.Timestamp
predict date
predict date.
trade_date : pd.Timestamp
trade date
trade date.
"""
if not self.is_adjust(trade_date):
return []