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

Update doc strings and fix

Browse Source
This commit is contained in:
Jactus
2020-11-25 18:03:52 +08:00
parent 5ac90f25b3
commit b31480a06a
6 changed files with 94 additions and 64 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/benchmarks/DNN/workflow_config_dnn.yaml
View File

@@ -30,7 +30,7 @@ task:
module_path: qlib.contrib.model.pytorch_nn module_path: qlib.contrib.model.pytorch_nn
kwargs: kwargs:
loss: mse loss: mse
input_dim: 360 input_dim: 158
output_dim: 1 output_dim: 1
lr: 0.002 lr: 0.002
lr_decay: 0.96 lr_decay: 0.96

9
qlib/contrib/evaluate.py
View File

@@ -190,7 +190,8 @@ def backtest(pred, account=1e9, shift=1, benchmark="SH000905", verbose=True, **k
Parameters Parameters
---------- ----------
# backtest workflow related or commmon arguments - **backtest workflow related or commmon arguments**
pred : pandas.DataFrame 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 account : float
@@ -202,7 +203,8 @@ def backtest(pred, account=1e9, shift=1, benchmark="SH000905", verbose=True, **k
verbose : bool verbose : bool
whether to print log whether to print log
# strategy related arguments - **strategy related arguments**
strategy : Strategy() strategy : Strategy()
strategy used in backtest strategy used in backtest
topk : int (Default value: 50) topk : int (Default value: 50)
@@ -225,7 +227,8 @@ def backtest(pred, account=1e9, shift=1, benchmark="SH000905", verbose=True, **k
str_type: 'amount', 'weight' or 'dropout' str_type: 'amount', 'weight' or 'dropout'
strategy type: TopkAmountStrategy ,TopkWeightStrategy or TopkDropoutStrategy strategy type: TopkAmountStrategy ,TopkWeightStrategy or TopkDropoutStrategy
# exchange related arguments - **exchange related arguments**
exchange: Exchange() exchange: Exchange()
pass the exchange for speeding up. pass the exchange for speeding up.
subscribe_fields: list subscribe_fields: list

35
qlib/contrib/strategy/strategy.py
View File

@@ -26,7 +26,9 @@ class BaseStrategy:
def generate_order_list(self, score_series, current, trade_exchange, pred_date, trade_date): def generate_order_list(self, score_series, current, trade_exchange, pred_date, trade_date):
""" """
Parameters: DO NOT directly change the state of current
Parameters
----------- -----------
score_series : pd.Seires score_series : pd.Seires
stock_id , score stock_id , score
@@ -39,14 +41,13 @@ class BaseStrategy:
predict date predict date
trade_date : pd.Timestamp trade_date : pd.Timestamp
trade date trade date
DO NOT directly change the state of current
""" """
pass pass
def update(self, score_series, pred_date, trade_date): def update(self, score_series, pred_date, trade_date):
"""User can use this method to update strategy state each trade date. """User can use this method to update strategy state each trade date.
Parameters:
Parameters
----------- -----------
score_series : pd.Series score_series : pd.Series
stock_id , score stock_id , score
@@ -98,8 +99,9 @@ class AdjustTimer:
"""AdjustTimer """AdjustTimer
Responsible for timing of position adjusting Responsible for timing of position adjusting
This is designed as multiple inheritance mechanism due to 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
""" """
@@ -140,21 +142,24 @@ class WeightStrategyBase(BaseStrategy, AdjustTimer):
def generate_target_weight_position(self, score, current, trade_date): def generate_target_weight_position(self, score, current, trade_date):
""" """
Parameters: Generate target position from score for this date and the current position.The cash is not considered in the position
Parameters
----------- -----------
score : pred score for this trade date, pd.Series, index is stock_id, contain 'score' column score : pd.Series
current : current position, use Position() class pred score for this trade date, index is stock_id, contain 'score' column
current : Position()
current position
trade_exchange : Exchange() trade_exchange : Exchange()
trade_date : trade date trade_date : pd.Timestamp
generate target position from score for this date and the current position trade date
The cash is not considered in the position
""" """
raise NotImplementedError() raise NotImplementedError()
def generate_order_list(self, score_series, current, trade_exchange, pred_date, trade_date): def generate_order_list(self, score_series, current, trade_exchange, pred_date, trade_date):
""" """
Parameters: Parameters
---------- -----------
score_series : pd.Seires score_series : pd.Seires
stock_id , score stock_id , score
current : Position() current : Position()
@@ -188,7 +193,7 @@ class WeightStrategyBase(BaseStrategy, AdjustTimer):
class TopkDropoutStrategy(BaseStrategy, ListAdjustTimer): class TopkDropoutStrategy(BaseStrategy, ListAdjustTimer):
def __init__(self, topk, n_drop, method="bottom", risk_degree=0.95, thresh=1, hold_thresh=1, **kwargs): def __init__(self, topk, n_drop, method="bottom", risk_degree=0.95, thresh=1, hold_thresh=1, **kwargs):
""" """
Parameters: Parameters
----------- -----------
topk : int topk : int
The number of stocks in the portfolio The number of stocks in the portfolio
@@ -229,7 +234,7 @@ class TopkDropoutStrategy(BaseStrategy, ListAdjustTimer):
""" """
Gnererate order list according to score_series at trade_date, will not change current. Gnererate order list according to score_series at trade_date, will not change current.
Parameters: Parameters
----------- -----------
score_series : pd.Series score_series : pd.Series
stock_id , score stock_id , score

65
qlib/data/dataset/__init__.py
View File

@@ -14,9 +14,11 @@ class Dataset(Serializable):
def __init__(self, *args, **kwargs): def __init__(self, *args, **kwargs):
""" """
init is designed to finish following steps init is designed to finish following steps:
- setup data - setup data
- The data related attributes' names should start with '_' so that it will not be saved on disk when serializing - The data related attributes' names should start with '_' so that it will not be saved on disk when serializing
- initialize the state of the dataset(info to prepare the data) - initialize the state of the dataset(info to prepare the data)
- The name of essential state for preparing data should not start with '_' so that it could be serialized on disk when serializing. - The name of essential state for preparing data should not start with '_' so that it could be serialized on disk when serializing.
@@ -29,11 +31,15 @@ class Dataset(Serializable):
""" """
setup the data setup the data
We split the setup_data function for following situation We split the setup_data function for following situation:
- 1) User have a Dataset object with learned status on disk
- 2) User load the Dataset object from the disk(Note the init function is skiped) - User have a Dataset object with learned status on disk
- 3) User call `setup_data` to load new data
- 4) User prepare data for model based on previous status - User load the Dataset object from the disk(Note the init function is skiped)
- User call `setup_data` to load new data
- User prepare data for model based on previous status
""" """
pass pass
@@ -41,8 +47,9 @@ class Dataset(Serializable):
""" """
The type of dataset depends on the model. (It could be pd.DataFrame, pytorch.DataLoader, etc.) The type of dataset depends on the model. (It could be pd.DataFrame, pytorch.DataLoader, etc.)
The parameters should specify the scope for the prepared data The parameters should specify the scope for the prepared data
The method sould The method should:
- process the data - process the data
- return the processed data - return the processed data
Returns Returns
@@ -55,11 +62,12 @@ class Dataset(Serializable):
class DatasetH(Dataset): class DatasetH(Dataset):
""" """
Dataset with Data(H)anler Dataset with Data(H)andler
User should try to put the data preprocessing functions into handler. User should try to put the data preprocessing functions into handler.
Only following data processing functions should be placed in Dataset Only following data processing functions should be placed in Dataset:
- The processing is related to specific model. - The processing is related to specific model.
- The processing is related to data split - The processing is related to data split
""" """
@@ -81,21 +89,26 @@ class DatasetH(Dataset):
Parameters Parameters
---------- ----------
handler : Union[dict, DataHandler] handler : Union[dict, DataHandler]
handler could be handler could be:
1) insntance of `DataHandler`
2) config of `DataHandler`. Please refer to `DataHandler` - insntance of `DataHandler`
- config of `DataHandler`. Please refer to `DataHandler`
segments : list segments : list
Describe the options to segment the data. Describe the options to segment the data.
Here are some examples Here are some examples:
1) 'segments': {
'train': ("2008-01-01", "2014-12-31"), .. code-block::
'valid': ("2017-01-01", "2020-08-01",),
'test': ("2015-01-01", "2016-12-31",), 1) 'segments': {
} 'train': ("2008-01-01", "2014-12-31"),
2) 'segments': { 'valid': ("2017-01-01", "2020-08-01",),
'insample': ("2008-01-01", "2014-12-31"), 'test': ("2015-01-01", "2016-12-31",),
'outsample': ("2017-01-01", "2020-08-01",), }
} 2) 'segments': {
'insample': ("2008-01-01", "2014-12-31"),
'outsample': ("2017-01-01", "2020-08-01",),
}
""" """
self._handler = init_instance_by_config(handler, accept_types=DataHandler) self._handler = init_instance_by_config(handler, accept_types=DataHandler)
self._segments = segments.copy() self._segments = segments.copy()
@@ -114,9 +127,11 @@ class DatasetH(Dataset):
---------- ----------
segments : Union[List[str], Tuple[str], str, slice] segments : Union[List[str], Tuple[str], str, slice]
Describe the scope of the data to be prepared Describe the scope of the data to be prepared
Here are some examples Here are some examples:
1) 'train'
2) ['train', 'valid'] - 'train'
- ['train', 'valid']
col_set : str col_set : str
The col_set will be passed to self._handler when fetching data The col_set will be passed to self._handler when fetching data
data_key: str data_key: str

11
qlib/data/dataset/handler.py
View File

@@ -41,7 +41,7 @@ class DataHandler(Serializable):
Example of the data: Example of the data:
The multi-index of the columns is optional. The multi-index of the columns is optional.
.. code-block:: .. code-block:: python
feature label feature label
$close $volume Ref($close, 1) Mean($close, 3) $high-$low LABEL0 $close $volume Ref($close, 1) Mean($close, 3) $high-$low LABEL0
@@ -109,7 +109,8 @@ class DataHandler(Serializable):
Parameters Parameters
---------- ----------
enable_cache : bool enable_cache : bool
default value is false default value is false:
- if `enable_cache` == True: - if `enable_cache` == True:
the processed data will be saved on disk, and handler will load the cached data from the disk directly the processed data will be saved on disk, and handler will load the cached data from the disk directly
@@ -378,8 +379,10 @@ class DataHandlerLP(DataHandler):
init_type : str init_type : str
The type `IT_*` listed above The type `IT_*` listed above
enable_cache : bool enable_cache : bool
default value is false default value is false:
if `enable_cache` == True:
- if `enable_cache` == True:
the processed data will be saved on disk, and handler will load the cached data from the disk directly the processed data will be saved on disk, and handler will load the cached data from the disk directly
when we call `init` next time when we call `init` next time
""" """

36
qlib/data/dataset/loader.py
View File

@@ -39,14 +39,16 @@ class DataLoader(abc.ABC):
pd.DataFrame: pd.DataFrame:
data load from the under layer source data load from the under layer source
Example of the data: Example of the data (The multi-index of the columns is optional.):
(The multi-index of the columns is optional.)
feature label .. code-block::
$close $volume Ref($close, 1) Mean($close, 3) $high-$low LABEL0
datetime instrument feature label
2010-01-04 SH600000 81.807068 17145150.0 83.737389 83.016739 2.741058 0.0032 $close $volume Ref($close, 1) Mean($close, 3) $high-$low LABEL0
SH600004 13.313329 11800983.0 13.313329 13.317701 0.183632 0.0042 datetime instrument
SH600005 37.796539 12231662.0 38.258602 37.919757 0.970325 0.0289 2010-01-04 SH600000 81.807068 17145150.0 83.737389 83.016739 2.741058 0.0032
SH600004 13.313329 11800983.0 13.313329 13.317701 0.183632 0.0042
SH600005 37.796539 12231662.0 38.258602 37.919757 0.970325 0.0289
""" """
pass pass
@@ -55,7 +57,7 @@ class DLWParser(DataLoader):
""" """
(D)ata(L)oader (W)ith (P)arser for features and names (D)ata(L)oader (W)ith (P)arser for features and names
Extracting this class so that QlibDataLoader and other dataloaders(such as QdbDataLoader) can share the fields Extracting this class so that QlibDataLoader and other dataloaders(such as QdbDataLoader) can share the fields.
""" """
def __init__(self, config: Tuple[list, tuple, dict]): def __init__(self, config: Tuple[list, tuple, dict]):
@@ -65,14 +67,16 @@ class DLWParser(DataLoader):
config : Tuple[list, tuple, dict] config : Tuple[list, tuple, dict]
Config will be used to describe the fields and column names Config will be used to describe the fields and column names
<config> := { .. code-block:: YAML
"group_name1": <fields_info1>
"group_name2": <fields_info2>
}
or
<config> := <fields_info>
<fields_info> := ["expr", ...] | (["expr", ...], ["col_name", ...]) <config> := {
"group_name1": <fields_info1>
"group_name2": <fields_info2>
}
or
<config> := <fields_info>
<fields_info> := ["expr", ...] | (["expr", ...], ["col_name", ...])
""" """
self.is_group = isinstance(config, dict) self.is_group = isinstance(config, dict)