liuyu/qlib
1
0
Fork 0
mirror of https://github.com/microsoft/qlib.git synced 2026-07-09 14:00:55 +08:00
Code Activity

Merge branch 'main' into dnn_drop

Browse Source
This commit is contained in:
bxdd
2020-11-26 23:04:34 -06:00
committed by GitHub
parent a144a9c3c6 c8355f9f18
commit c31bf61278
105 changed files with 6034 additions and 2725 deletions
Download Patch File Download Diff File Expand all files Collapse all files

35
qlib/data/dataset/__init__.py
View File

@@ -17,8 +17,8 @@ class Dataset(Serializable):
init is designed to finish following steps:
- 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)
- The name of essential state for preparing data should not start with '_' so that it could be serialized on disk when serializing.
@@ -29,17 +29,17 @@ class Dataset(Serializable):
def setup_data(self, *args, **kwargs):
"""
setup the data
Setup the data.
We split the setup_data function for following situation:
- User have a Dataset object with learned status on disk
- User have a Dataset object with learned status on disk.
- User load the Dataset object from the disk(Note the init function is skiped)
- User load the Dataset object from the disk(Note the init function is skiped).
- User call `setup_data` to load new data
- User call `setup_data` to load new data.
- User prepare data for model based on previous status
- User prepare data for model based on previous status.
"""
pass
@@ -66,9 +66,10 @@ class DatasetH(Dataset):
User should try to put the data preprocessing functions into handler.
Only following data processing functions should be placed in Dataset:
- The processing is related to specific model.
- The processing is related to data split
- The processing is related to data split.
"""
def __init__(self, handler: Union[dict, DataHandler], segments: list):
@@ -76,15 +77,15 @@ class DatasetH(Dataset):
Parameters
----------
handler : Union[dict, DataHandler]
handler will be passed into setup_data
handler will be passed into setup_data.
segments : list
handler will be passed into setup_data
handler will be passed into setup_data.
"""
super().__init__(handler, segments)
def setup_data(self, handler: Union[dict, DataHandler], segments: list):
"""
setup the underlying data
Setup the underlying data.
Parameters
----------
@@ -94,12 +95,13 @@ class DatasetH(Dataset):
- insntance of `DataHandler`
- config of `DataHandler`. Please refer to `DataHandler`
segments : list
Describe the options to segment the data.
Here are some examples:
.. code-block::
1) 'segments': {
'train': ("2008-01-01", "2014-12-31"),
'valid': ("2017-01-01", "2020-08-01",),
@@ -121,7 +123,7 @@ class DatasetH(Dataset):
**kwargs,
) -> Union[List[pd.DataFrame], pd.DataFrame]:
"""
prepare the data for learning and inference
Prepare the data for learning and inference.
Parameters
----------
@@ -132,11 +134,12 @@ class DatasetH(Dataset):
- 'train'
- ['train', 'valid']
col_set : str
The col_set will be passed to self._handler when fetching data
data_key: str
The col_set will be passed to self._handler when fetching data.
data_key : str
The data to fetch: DK_*
Default is DK_I, which indicate fetching data for **inference**
Default is DK_I, which indicate fetching data for **inference**.
Returns
-------

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

@@ -29,7 +29,7 @@ class DataHandler(Serializable):
"""
The steps to using a handler
1. initialized data handler (call by `init`).
2. use the data
2. use the data.
The data handler try to maintain a handler with 2 level.
@@ -65,17 +65,17 @@ class DataHandler(Serializable):
Parameters
----------
instruments :
The stock list to retrive
The stock list to retrive.
start_time :
start_time of the original data
start_time of the original data.
end_time :
end_time of the original data
end_time of the original data.
data_loader : Tuple[dict, str, DataLoader]
data loader to load the data
data loader to load the data.
init_data :
intialize the original data in the constructor
intialize the original data in the constructor.
fetch_orig : bool
Return the original data instead of copy if possible
Return the original data instead of copy if possible.
"""
# Set logger
self.logger = get_module_logger("DataHandler")
@@ -219,9 +219,9 @@ class DataHandler(Serializable):
get a iterator of sliced data with given periods
Args:
periods (int): number of periods
min_periods (int): minimum periods for sliced dataframe
kwargs (dict): will be passed to `self.fetch`
periods (int): number of periods.
min_periods (int): minimum periods for sliced dataframe.
kwargs (dict): will be passed to `self.fetch`.
"""
trading_dates = self._data.index.unique(level="datetime")
if min_periods is None:
@@ -243,10 +243,10 @@ class DataHandlerLP(DataHandler):
# process type
PTYPE_I = "independent"
# - self._infer will processed by infer_processors
# - self._infer will be processed by infer_processors
# - self._learn will be processed by learn_processors
PTYPE_A = "append"
# - self._infer will processed by infer_processors
# - self._infer will be processed by infer_processors
# - self._learn will be processed by infer_processors + learn_processors
# - (e.g. self._infer processed by learn_processors )
@@ -265,30 +265,40 @@ class DataHandlerLP(DataHandler):
Parameters
----------
infer_processors : list
list of <description info> of processors to generate data for inference
example of <description info>:
1) classname & kwargs:
{
"class": "MinMaxNorm",
"kwargs": {
"fit_start_time": "20080101",
"fit_end_time": "20121231"
- list of <description info> of processors to generate data for inference
- example of <description info>:
.. code-block::
1) classname & kwargs:
{
"class": "MinMaxNorm",
"kwargs": {
"fit_start_time": "20080101",
"fit_end_time": "20121231"
}
}
}
2) Only classname:
"DropnaFeature"
3) object instance of Processor
2) Only classname:
"DropnaFeature"
3) object instance of Processor
learn_processors : list
similar to infer_processors, but for generating data for learning models
process_type: str
PTYPE_I = 'independent'
- self._infer will processed by infer_processors
- self._learn will be processed by learn_processors
PTYPE_A = 'append'
- self._infer will processed by infer_processors
- self._learn will be processed by infer_processors + learn_processors
- (e.g. self._infer processed by learn_processors )
"""
@@ -377,7 +387,7 @@ class DataHandlerLP(DataHandler):
Parameters
----------
init_type : str
The type `IT_*` listed above
The type `IT_*` listed above.
enable_cache : bool
default value is false:
@@ -419,13 +429,13 @@ class DataHandlerLP(DataHandler):
Parameters
----------
selector : Union[pd.Timestamp, slice, str]
describe how to select data by index
describe how to select data by index.
level : Union[str, int]
which index level to select the data
which index level to select the data.
col_set : str
select a set of meaningful columns.(e.g. features, columns)
data_key: str
The data to fetch: DK_*
select a set of meaningful columns.(e.g. features, columns).
data_key : str
the data to fetch: DK_*.
Returns
-------
@@ -443,9 +453,9 @@ class DataHandlerLP(DataHandler):
Parameters
----------
col_set : str
select a set of meaningful columns.(e.g. features, columns)
data_key: str
The data to fetch: DK_*
select a set of meaningful columns.(e.g. features, columns).
data_key : str
the data to fetch: DK_*.
Returns
-------

47
qlib/data/dataset/loader.py
View File

@@ -21,27 +21,11 @@ class DataLoader(abc.ABC):
@abc.abstractmethod
def load(self, instruments, start_time=None, end_time=None) -> pd.DataFrame:
"""
load the data as pd.DataFrame
load the data as pd.DataFrame.
Parameters
----------
self : [TODO:type]
[TODO:description]
instruments : [TODO:type]
[TODO:description]
start_time : [TODO:type]
[TODO:description]
end_time : [TODO:type]
[TODO:description]
Example of the data (The multi-index of the columns is optional.):
Returns
-------
pd.DataFrame:
data load from the under layer source
Example of the data (The multi-index of the columns is optional.):
.. code-block::
.. code-block:: python
feature label
$close $volume Ref($close, 1) Mean($close, 3) $high-$low LABEL0
@@ -49,6 +33,21 @@ class DataLoader(abc.ABC):
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
Parameters
----------
instruments : str or dict
it can either be the market name or the config file of instruments generated by InstrumentProvider.
start_time : str
start of the time range.
end_time : str
end of the time range.
Returns
-------
pd.DataFrame:
data load from the under layer source
"""
pass
@@ -67,7 +66,7 @@ class DLWParser(DataLoader):
config : Tuple[list, tuple, dict]
Config will be used to describe the fields and column names
.. code-block:: YAML
.. code-block::
<config> := {
"group_name1": <fields_info1>
@@ -102,16 +101,16 @@ class DLWParser(DataLoader):
Parameters
----------
instruments :
the instruments
the instruments.
exprs : list
The expressions to describe the content of the data
the expressions to describe the content of the data.
names : list
The name of the data
the name of the data.
Returns
-------
pd.DataFrame:
the queried dataframe
the queried dataframe.
"""
pass

46
qlib/data/dataset/processor.py
View File

@@ -21,7 +21,7 @@ def get_group_columns(df: pd.DataFrame, group: str):
Parameters
----------
df : pd.DataFrame
with multi of columns
with multi of columns.
group : str
the name of the feature group, i.e. the first level value of the group index.
"""
@@ -56,7 +56,7 @@ class Processor(Serializable):
Parameters
----------
df : pd.DataFrame
The raw_df of handler or result from previous processor
The raw_df of handler or result from previous processor.
"""
pass
@@ -68,7 +68,7 @@ class Processor(Serializable):
Returns
-------
bool:
if it is usable for infenrece
if it is usable for infenrece.
"""
return True
@@ -176,7 +176,9 @@ class MinMaxNorm(Processor):
return df
class ZscoreNorm(Processor):
class ZScoreNorm(Processor):
"""ZScore Normalization"""
def __init__(self, fit_start_time, fit_end_time, fields_group=None):
self.fit_start_time = fit_start_time
self.fit_end_time = fit_end_time
@@ -203,6 +205,42 @@ class ZscoreNorm(Processor):
return df
class RobustZScoreNorm(Processor):
"""Robust ZScore Normalization
Use robust statistics for Z-Score normalization:
mean(x) = median(x)
std(x) = MAD(x) * 1.4826
Reference:
https://en.wikipedia.org/wiki/Median_absolute_deviation.
"""
def __init__(self, fit_start_time, fit_end_time, fields_group=None, clip_outlier=True):
self.fit_start_time = fit_start_time
self.fit_end_time = fit_end_time
self.fields_group = fields_group
self.clip_outlier = clip_outlier
def fit(self, df):
df = fetch_df_by_index(df, slice(self.fit_start_time, self.fit_end_time), level="datetime")
self.cols = get_group_columns(df, self.fields_group)
X = df[self.cols].values
self.mean_train = np.nanmedian(X, axis=0)
self.std_train = np.nanmedian(np.abs(X - self.mean_train), axis=0)
self.std_train += EPS
self.std_train *= 1.4826
def __call__(self, df):
X = df[self.cols]
X -= self.mean_train
X /= self.std_train
df[self.cols] = X
if self.clip_outlier:
df.clip(-3, 3, inplace=True)
return df
class CSZScoreNorm(Processor):
"""Cross Sectional ZScore Normalization"""

3
qlib/data/dataset/utils.py
View File

@@ -51,6 +51,9 @@ def fetch_df_by_index(
-------
Data of the given index.
"""
# level = None -> use selector directly
if level == None:
return df.loc(axis=0)[selector]
# Try to get the right index
idx_slc = (selector, slice(None, None))
if get_level_index(df, level) == 1: