Skip to content

Feature implementation from commits 8480407..bc06f03#3

Open
yashuatla wants to merge 15 commits intofeature-base-3from
feature-head-3
Open

Feature implementation from commits 8480407..bc06f03#3
yashuatla wants to merge 15 commits intofeature-base-3from
feature-head-3

Conversation

@yashuatla
Copy link
Owner

This PR contains changes from a range of commits from the original repository.

Commit Range: 8480407..bc06f03
Files Changed: 48 (46 programming files)
Programming Ratio: 95.8%

Commits included:

ChengzhenDu and others added 15 commits August 22, 2022 17:45
* Use dict-like configuration

* Rename from_neutrader to integration

* SAOE strategy

* Optimize file structure

* Optimize code

* Format code

* create_state_maintainer_recursive

* Remove explicit time_per_step

* CI test passed

* Resolve PR comments

* Pass all CI

* Minor test issue

* Refine SAOE adapter logic

* Minor bugfix

* Cherry pick updates

* Resolve PR comments

* CI issues

* Refine adapter & saoe_data logic

* Resolve PR comments

* Resolve PR comments

* Rename ONE_SEC to EPS_T; complete backtest loop

* CI issue

* Resolve Yuge's PR comments
* Fix CI pylint bug

* Update log.py
* My own implementation of ChangeInstrument Op. There is a newer, simpler
implemenation from remote.
On branch main
Your branch is behind 'origin/main' by 127 commits, and can be fast-forwarded.
  (use "git pull" to update your local branch)

Changes to be committed:
       modified:   qlib/data/ops.py

Changes not staged for commit:
       modified:   qlib/contrib/evaluate.py
       modified:   qlib/contrib/strategy/signal_strategy.py
       modified:   qlib/utils/__init__.py
       modified:   qlib/workflow/cli.py
       modified:   qlib/workflow/expm.py

Untracked files:
       .idea/

------------------------ >8 ------------------------
Do not modify or remove the line above.
Everything below it will be ignored.
diff --git a/qlib/data/ops.py b/qlib/data/ops.py
index bdc032c..23db25c 100644
--- a/qlib/data/ops.py
+++ b/qlib/data/ops.py
@@ -32,6 +32,90 @@ except ValueError as e:

 np.seterr(invalid="ignore")

+#################### Change instrument ########################
+# In some case, one may want to change to another instrument when calculating, for example
+# calculate beta of a stock with respect to a market index
+# this would require change the calculation of features from the stock (original instrument) to
+# the index (reference instrument)
+# #############################
+
+
+class ChangeInstrument(ExpressionOps):
+    """Change Instrument Operator
+    In some case, one may want to change to another instrument when calculating, for example, to
+    calculate beta of a stock with respect to a market index.
+    This would require changing the calculation of features from the stock (original instrument) to
+    the index (reference instrument)
+    Parameters
+    ----------
+    instrument: new instrument for which the downstream operations should be performed upon.
+                i.e., SH000300 (CSI300 index), or ^GPSC (SP500 index).
+
+    feature: the feature to be calculated for the new instrument.
+    Returns
+    ----------
+    Expression
+        feature operation output
+    """
+
+    def __init__(self, instrument, feature):
+        self.instrument = instrument
+        self.feature = feature
+
+    def __str__(self):
+        return "{}({},{})".format(type(self).__name__, self.instrument, self.feature)
+
+    def load(self, instrument, start_index, end_index, freq):
+        """load  feature
+
+        Parameters
+        ----------
+        instrument : str
+            instrument code, however, the actual instrument loaded is self.instrument through initialization
+        start_index : str
+            feature start index [in calendar].
+        end_index : str
+            feature end  index  [in calendar].
+        freq : str
+            feature frequency.
+
+        Returns
+        ----------
+        pd.Series
+            feature series: The index of the series is the calendar index
+        """
+        from .cache import H  # pylint: disable=C0415
+
+        # cache
+        args = str(self), self.instrument, start_index, end_index, freq
+        if args in H["f"]:
+            return H["f"][args]
+        if start_index is not None and end_index is not None and start_index > end_index:
+            raise ValueError("Invalid index range: {} {}".format(start_index, end_index))
+        try:
+            series = self._load_internal(self.instrument, start_index, end_index, freq)
+        except Exception as e:
+            get_module_logger("data").debug(
+                f"Loading data error: instrument={instrument}, expression={str(self)}, "
+                f"start_index={start_index}, end_index={end_index}, freq={freq}. "
+                f"error info: {str(e)}"
+            )
+            raise
+        series.name = str(self)
+        H["f"][args] = series
+        return series
+
+    def _load_internal(self, instrument, start_index, end_index, freq):
+        series = self.feature.load(self.instrument, start_index, end_index, freq)
+        return series
+
+    def get_longest_back_rolling(self):
+        return self.feature.get_longest_back_rolling()
+
+    def get_extended_window_size(self):
+        return self.feature.get_extended_window_size()
+
+
 #################### Element-Wise Operator ####################

@@ -1541,6 +1625,7 @@ class TResample(ElemOperator):

 TOpsList = [TResample]
 OpsList = [
+    ChangeInstrument,
     Rolling,
     Ref,
     Max,

* update expm.py

* removed duplicate implementation for ChangeInstrument
* Fix bug

* A weird Mypy issue
* Update features_sample.py

* Update features_sample.py
* Backtest migration

* Minor bug fix in test

* Reorganize file to avoid loop import

* Fix test SAOE bug

* Remove unnecessary names

* Resolve PR comments; remove private classes;

* Fix CI error

* Resolve PR comments

* Refactor data interfaces

* Remove convert_instance_config and change config

* Pylint issue

* Pylint issue

* Fix tempfile warning

* Resolve PR comments

* Add more comments
doc for search_records
* feat(data): ✨ add a general highfreq data handler for open source

Add HighFreqOpenHandler and HighFreqOpenBacktestHandler for data pipeline without paused_num
information.

* fix: position of parameter init

* style(data): 💄 rename open to general

* style(data): 💄 lint

* style: 💄 delete useless comment & fix inheritance relation

* style: 💄 lint

* style: 💄 remove duplicated function

Co-authored-by: mingzhehan <v-zhaoxing@Microsoft.com>
* RL backtest with simulator

* Minor modification in init_qlib

* Cherry pick PR 1302

* Resolve PR comments

* Fix missing data processing

* Minor bugfix

* Add TODOs and docs

* Add a comment
* Add REG_US and REG_TW into test case: test_utils.py.

* Fix black.

* Trigger checks.

* Add REG_US and REG_TW into test case: test_utils.py.

* Fix black.

* Trigger checks.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

10 participants