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

Update docs

Browse Source
This commit is contained in:
Jactus
2020-11-30 18:54:31 +08:00
committed by you-n-g
parent 1877ad8c39
commit 29f12e857f
22 changed files with 180 additions and 159 deletions
Download Patch File Download Diff File Expand all files Collapse all files

25
qlib/model/base.py
View File

@@ -27,13 +27,32 @@ class Model(BaseModel):
.. note::
The the attribute names of learned model should `not` start with '_'. So that the model could be
The attribute names of learned model should `not` start with '_'. So that the model could be
dumped to disk.
Parameters
----------
dataset : Dataset
dataset will generate the processed data from model training.
The following code example shows how to retrieve `x_train`, `y_train` and `w_train` from the `dataset`:
.. code-block:: Python
# get features and labels
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"]
# get weights
try:
wdf_train, wdf_valid = dataset.prepare(["train", "valid"], col_set=["weight"], data_key=DataHandlerLP.DK_L)
w_train, w_valid = wdf_train["weight"], wdf_valid["weight"]
except KeyError as e:
w_train = pd.DataFrame(np.ones_like(y_train.values), index=y_train.index)
w_valid = pd.DataFrame(np.ones_like(y_valid.values), index=y_valid.index)
"""
raise NotImplementedError()
@@ -45,6 +64,10 @@ class Model(BaseModel):
----------
dataset : Dataset
dataset will generate the processed dataset from model training.
Returns
-------
Prediction results with certain type such as `pandas.Series`.
"""
raise NotImplementedError()

14
qlib/model/trainer.py
View File

@@ -6,29 +6,29 @@ from qlib.workflow import R
from qlib.workflow.record_temp import SignalRecord
def task_train(config: dict, experiment_name):
def task_train(task_config: dict, experiment_name):
"""
task based training
Parameters
----------
config : dict
A dict describing the training process
task_config : dict
A dict describes a task setting.
"""
# model initiaiton
model = init_instance_by_config(config.get("task")["model"])
dataset = init_instance_by_config(config.get("task")["dataset"])
model = init_instance_by_config(task_config["model"])
dataset = init_instance_by_config(task_config["dataset"])
# start exp
with R.start(experiment_name=experiment_name):
# train model
R.log_params(**flatten_dict(config.get("task")))
R.log_params(**flatten_dict(task_config))
model.fit(dataset)
recorder = R.get_recorder()
# generate records: prediction, backtest, and analysis
for record in config.get("task")["record"]:
for record in task_config.get["record"]:
if record["class"] == SignalRecord.__name__:
srconf = {"model": model, "dataset": dataset, "recorder": recorder}
record["kwargs"].update(srconf)

43
qlib/workflow/__init__.py
View File

@@ -90,7 +90,11 @@ class QlibRecorder:
def search_records(self, experiment_ids, **kwargs):
"""
Get a pandas DataFrame of records that fit the search criteria. Here is the example code of the method:
Get a pandas DataFrame of records that fit the search criteria.
The arguments of this function are not set to be rigid, and they will be different with different implementation of
``ExpManager`` in ``Qlib``. ``Qlib`` now provides an implementation of ``ExpManager`` with mlflow, and here is the
example code of the this method with the ``MLflowExpManager``:
.. code-block:: Python
@@ -139,7 +143,8 @@ class QlibRecorder:
If user doesn't provide the id or name of the experiment, this method will try to retrieve the default experiment and
list all the recorders of the default experiment. If the default experiment doesn't exist, the method will first
create the default experiment, and then create a new recorder under it.
create the default experiment, and then create a new recorder under it. (More information about the default experiment
can be found `here <../component/recorder.html#qlib.workflow.exp.Experiment>`_).
Here is the example code:
@@ -168,27 +173,27 @@ class QlibRecorder:
- If '`create`' is True:
- If ``R``'s running:
- If `active experiment` exists:
- no id or name specified, return the active experiment.
- if id or name is specified, return the specified experiment. If no such exp found, create a new experiment with given id or name, and the experiment is set to be running.
- if id or name is specified, return the specified experiment. If no such exp found, create a new experiment with given id or name, and the experiment is set to be active.
- If ``R``'s not running:
- If `active experiment` not exists:
- no id or name specified, create a default experiment, and the experiment is set to be running.
- no id or name specified, create a default experiment, and the experiment is set to be active.
- if id or name is specified, return the specified experiment. If no such exp found, create a new experiment with given name or the default experiment, and the experiment is set to be running.
- if id or name is specified, return the specified experiment. If no such exp found, create a new experiment with given name or the default experiment, and the experiment is set to be active.
- Else If '`create`' is False:
- If ``R``'s running:
- If ``active experiment` exists:
- no id or name specified, return the active experiment.
- if id or name is specified, return the specified experiment. If no such exp found, raise Error.
- If ``R``'s not running:
- If `active experiment` not exists:
- no id or name specified. If the default experiment exists, return it, otherwise, raise Error.
@@ -272,13 +277,13 @@ class QlibRecorder:
"""
Method for retrieving a recorder.
- If ``R``'s running:
- If `active recorder` exists:
- no id or name specified, return the active recorder.
- if id or name is specified, return the specified recorder.
- If ``R``'s not running:
- If `active recorder` not exists:
- no id or name specified, raise Error.
@@ -351,8 +356,8 @@ class QlibRecorder:
from a local file/directory, or directly saving objects. User can use valid python's keywords arguments
to specify the object to be saved as well as its name (name: value).
- If R's running: it will save the objects through the running recorder.
- If R's not running: the system will create a default experiment, and a new recorder and save objects under it.
- If `active recorder` exists: it will save the objects through the active recorder.
- If `active recorder` not exists: the system will create a default experiment, and a new recorder and save objects under it.
.. note::
@@ -384,8 +389,8 @@ class QlibRecorder:
"""
Method for logging parameters during an experiment. In addition to using ``R``, one can also log to a specific recorder after getting it with `get_recorder` API.
- If R's running: it will log parameters through the running recorder.
- If R's not running: the system will create a default experiment as well as a new recorder, and log parameters under it.
- If `active recorder` exists: it will log parameters through the active recorder.
- If `active recorder` not exists: the system will create a default experiment as well as a new recorder, and log parameters under it.
Here are some use cases:
@@ -409,8 +414,8 @@ class QlibRecorder:
"""
Method for logging metrics during an experiment. In addition to using ``R``, one can also log to a specific recorder after getting it with `get_recorder` API.
- If R's running: it will log metrics through the running recorder.
- If R's not running: the system will create a default experiment as well as a new recorder, and log metrics under it.
- If `active recorder` exists: it will log metrics through the active recorder.
- If `active recorder` not exists: the system will create a default experiment as well as a new recorder, and log metrics under it.
Here are some use cases:
@@ -434,8 +439,8 @@ class QlibRecorder:
"""
Method for setting tags for a recorder. In addition to using ``R``, one can also set the tag to a specific recorder after getting it with `get_recorder` API.
- If R's running: it will set tags through the running recorder.
- If R's not running: the system will create a default experiment as well as a new recorder, and set the tags under it.
- If `active recorder` exists: it will set tags through the active recorder.
- If `active recorder` not exists: the system will create a default experiment as well as a new recorder, and set the tags under it.
Here are some use cases:

6
qlib/workflow/cli.py
View File

@@ -49,13 +49,11 @@ def workflow(config_path, experiment_name="workflow", uri_folder="mlruns"):
# config the `sys` section
sys_config(config, config_path)
provider_uri = config.get("provider_uri")
region = config.get("region")
exp_manager = C["exp_manager"]
exp_manager["kwargs"]["uri"] = "file:" + str(Path(os.getcwd()).resolve() / uri_folder)
qlib.init(provider_uri=provider_uri, region=region, exp_manager=exp_manager)
qlib.init(**config.get("qlib_init"), exp_manager=exp_manager)
task_train(config, experiment_name=experiment_name)
task_train(config.get("task"), experiment_name=experiment_name)
# function to run worklflow by config

12
qlib/workflow/exp.py
View File

@@ -114,24 +114,24 @@ class Experiment:
* If `create` is True:
* If R's running:
* If `active recorder` exists:
* no id or name specified, return the active recorder.
* if id or name is specified, return the specified recorder. If no such exp found, create a new recorder with given id or name, and the recorder shoud be running.
* if id or name is specified, return the specified recorder. If no such exp found, create a new recorder with given id or name, and the recorder shoud be active.
* If R's not running:
* If `active recorder` not exists:
* no id or name specified, create a new recorder.
* if id or name is specified, return the specified experiment. If no such exp found, create a new recorder with given id or name, and the recorder shoud be running.
* if id or name is specified, return the specified experiment. If no such exp found, create a new recorder with given id or name, and the recorder shoud be active.
* Else If `create` is False:
* If R's running:
* If `active recorder` exists:
* no id or name specified, return the active recorder.
* if id or name is specified, return the specified recorder. If no such exp found, raise Error.
* If R's not running:
* If `active recorder` not exists:
* no id or name specified, raise Error.
* if id or name is specified, return the specified recorder. If no such exp found, raise Error.

20
qlib/workflow/expm.py
View File

@@ -23,12 +23,12 @@ class ExpManager:
def __init__(self, uri, default_exp_name):
self.uri = uri
self.default_exp_name = default_exp_name
self.active_experiment = None # only one experiment can running each time
self.active_experiment = None # only one experiment can active each time
def start_exp(self, experiment_name=None, recorder_name=None, uri=None, **kwargs):
"""
Start an experiment. This method includes first get_or_create an experiment, and then
set it to be running.
set it to be active.
Parameters
----------
@@ -47,7 +47,7 @@ class ExpManager:
def end_exp(self, recorder_status: str = Recorder.STATUS_S, **kwargs):
"""
End an running experiment.
End an active experiment.
Parameters
----------
@@ -90,7 +90,7 @@ class ExpManager:
def get_exp(self, experiment_id=None, experiment_name=None, create: bool = True):
"""
Retrieve an experiment. This method includes getting an active experiment, and get_or_create a specific experiment.
The returned experiment will be running.
The returned experiment will be active.
When user specify experiment id and name, the method will try to return the specific experiment.
When user does not provide recorder id or name, the method will try to return the current active experiment.
@@ -99,24 +99,24 @@ class ExpManager:
* If `create` is True:
* If R's running:
* If `active experiment` exists:
* no id or name specified, return the active experiment.
* if id or name is specified, return the specified experiment. If no such exp found, create a new experiment with given id or name, and the experiment is set to be running.
* if id or name is specified, return the specified experiment. If no such exp found, create a new experiment with given id or name, and the experiment is set to be active.
* If R's not running:
* If `active experiment` not exists:
* no id or name specified, create a default experiment.
* if id or name is specified, return the specified experiment. If no such exp found, create a new experiment with given id or name, and the experiment is set to be running.
* if id or name is specified, return the specified experiment. If no such exp found, create a new experiment with given id or name, and the experiment is set to be active.
* Else If `create` is False:
* If R's running:
* If `active experiment` exists:
* no id or name specified, return the active experiment.
* if id or name is specified, return the specified experiment. If no such exp found, raise Error.
* If R's not running:
* If `active experiment` not exists:
* no id or name specified. If the default experiment exists, return it, otherwise, raise Error.
* if id or name is specified, return the specified experiment. If no such exp found, raise Error.