liuyu/qlib
1
0
Fork 0
mirror of https://github.com/microsoft/qlib.git synced 2026-07-15 16:56:54 +08:00
Code Activity

Resolve https://github.com/microsoft/qlib/pull/280\#discussion_r589165409

Browse Source
This commit is contained in:
Charles Young
2021-03-08 17:49:59 +08:00
parent 81b86f8022
commit 351d598c9f
3 changed files with 34 additions and 83 deletions
Download Patch File Download Diff File Expand all files Collapse all files

28
qlib/model/riskmodel/base.py
View File

@@ -1,6 +1,7 @@
# Copyright (c) Microsoft Corporation. # Copyright (c) Microsoft Corporation.
# Licensed under the MIT License. # Licensed under the MIT License.
import inspect
import numpy as np import numpy as np
import pandas as pd import pandas as pd
from typing import Union from typing import Union
@@ -37,18 +38,24 @@ class RiskModel(BaseModel):
self.scale_return = scale_return self.scale_return = scale_return
def predict( def predict(
self, X: Union[pd.Series, pd.DataFrame, np.ndarray], return_corr: bool = False, is_price: bool = True self, X: Union[pd.Series, pd.DataFrame, np.ndarray], return_corr: bool = False, is_price: bool = True,
) -> Union[pd.DataFrame, np.ndarray]: return_decomposed_components=False,
) -> Union[pd.DataFrame, np.ndarray, tuple]:
""" """
Args: Args:
X (pd.Series, pd.DataFrame or np.ndarray): data from which to estimate the covariance, X (pd.Series, pd.DataFrame or np.ndarray): data from which to estimate the covariance,
with variables as columns and observations as rows. with variables as columns and observations as rows.
return_corr (bool): whether return the correlation matrix. return_corr (bool): whether return the correlation matrix.
is_price (bool): whether `X` contains price (if not assume stock returns). is_price (bool): whether `X` contains price (if not assume stock returns).
return_decomposed_components (bool): whether return decomposed components of the covariance matrix.
Returns: Returns:
pd.DataFrame or np.ndarray: estimated covariance (or correlation). pd.DataFrame or np.ndarray: estimated covariance (or correlation).
""" """
assert (
not return_corr or not return_decomposed_components
), "Can only return either correlation matrix or decomposed components."
# transform input into 2D array # transform input into 2D array
if not isinstance(X, (pd.Series, pd.DataFrame)): if not isinstance(X, (pd.Series, pd.DataFrame)):
columns = None columns = None
@@ -75,6 +82,14 @@ class RiskModel(BaseModel):
# handle nan and centered # handle nan and centered
X = self._preprocess(X) X = self._preprocess(X)
# return decomposed components if needed
if return_decomposed_components:
assert 'return_decomposed_components' in inspect.getfullargspec(self._predict).args, \
'This risk model does not support return decomposed components of the covariance matrix '
F, cov_b, var_u = self._predict(X, return_decomposed_components=True)
return F, cov_b, var_u
# estimate covariance # estimate covariance
S = self._predict(X) S = self._predict(X)
@@ -126,12 +141,3 @@ class RiskModel(BaseModel):
if not self.assume_centered: if not self.assume_centered:
X = X - np.nanmean(X, axis=0) X = X - np.nanmean(X, axis=0)
return X return X

74
qlib/model/riskmodel/structured.py
View File

@@ -60,81 +60,13 @@ class StructuredCovEstimator(RiskModel):
self.num_factors = num_factors self.num_factors = num_factors
def predict( def _predict(self, X: np.ndarray, return_decomposed_components=False) -> Union[np.ndarray, tuple]:
self,
X: Union[pd.Series, pd.DataFrame, np.ndarray],
return_corr: bool = False,
is_price: bool = True,
return_decomposed_components=False,
) -> Union[pd.DataFrame, np.ndarray, tuple]:
"""
Args:
X (pd.Series, pd.DataFrame or np.ndarray): data from which to estimate the covariance,
with variables as columns and observations as rows.
return_corr (bool): whether return the correlation matrix.
is_price (bool): whether `X` contains price (if not assume stock returns).
return_decomposed_components (bool): whether return decomposed components of the covariance matrix.
Returns:
tuple or pd.DataFrame or np.ndarray: decomposed covariance matrix or estimated covariance or correlation.
"""
assert (
not return_corr or not return_decomposed_components
), "Can only return either correlation matrix or decomposed components."
# transform input into 2D array
if not isinstance(X, (pd.Series, pd.DataFrame)):
columns = None
else:
if isinstance(X.index, pd.MultiIndex):
if isinstance(X, pd.DataFrame):
X = X.iloc[:, 0].unstack(level="instrument") # always use the first column
else:
X = X.unstack(level="instrument")
else:
# X is 2D DataFrame
pass
columns = X.columns # will be used to restore dataframe
X = X.values
# calculate pct_change
if is_price:
X = X[1:] / X[:-1] - 1 # NOTE: resulting `n - 1` rows
# scale return
if self.scale_return:
X *= 100
# handle nan and centered
X = self._preprocess(X)
if return_decomposed_components:
F, cov_b, var_u = self._predict(X, return_structured=True)
return F, cov_b, var_u
else:
# estimate covariance
S = self._predict(X)
# return correlation if needed
if return_corr:
vola = np.sqrt(np.diag(S))
corr = S / np.outer(vola, vola)
if columns is None:
return corr
return pd.DataFrame(corr, index=columns, columns=columns)
# return covariance
if columns is None:
return S
return pd.DataFrame(S, index=columns, columns=columns)
def _predict(self, X: np.ndarray, return_structured=False) -> Union[np.ndarray, tuple]:
""" """
covariance estimation implementation covariance estimation implementation
Args: Args:
X (np.ndarray): data matrix containing multiple variables (columns) and observations (rows). X (np.ndarray): data matrix containing multiple variables (columns) and observations (rows).
return_structured (bool): whether return decomposed components of the covariance matrix. return_decomposed_components (bool): whether return decomposed components of the covariance matrix.
Returns: Returns:
tuple or np.ndarray: decomposed covariance matrix or covariance matrix. tuple or np.ndarray: decomposed covariance matrix or covariance matrix.
@@ -148,7 +80,7 @@ class StructuredCovEstimator(RiskModel):
cov_b = np.cov(B.T) # num_factors x num_factors cov_b = np.cov(B.T) # num_factors x num_factors
var_u = np.var(U, axis=0) # diagonal var_u = np.var(U, axis=0) # diagonal
if return_structured: if return_decomposed_components:
return F, cov_b, var_u return F, cov_b, var_u
cov_x = F @ cov_b @ F.T + np.diag(var_u) cov_x = F @ cov_b @ F.T + np.diag(var_u)

15
tests/test_structured_cov_estimator.py
View File

@@ -28,7 +28,7 @@ class TestStructuredCovEstimator(unittest.TestCase):
self.assertTrue(if_identical) self.assertTrue(if_identical)
def test_nan_option_covariance(self): def test_nan_option_covariance(self):
# Try to estimate the covariance from a randomly generated matrix. # Test if nan_option is correctly passed.
NUM_VARIABLE = 10 NUM_VARIABLE = 10
NUM_OBSERVATION = 200 NUM_OBSERVATION = 200
EPS = 1e-6 EPS = 1e-6
@@ -45,6 +45,19 @@ class TestStructuredCovEstimator(unittest.TestCase):
self.assertTrue(if_identical) self.assertTrue(if_identical)
def test_decompose_covariance(self):
# Test if return_decomposed_components is correctly passed.
NUM_VARIABLE = 10
NUM_OBSERVATION = 200
estimator = StructuredCovEstimator(scale_return=False, assume_centered=True, nan_option='fill')
X = np.random.rand(NUM_OBSERVATION, NUM_VARIABLE)
F, cov_b, var_u = estimator.predict(X, is_price=False, return_decomposed_components=True)
self.assertTrue(F is not None and cov_b is not None and var_u is not None)
def test_constructed_covariance(self): def test_constructed_covariance(self):
# Try to estimate the covariance from a specially crafted matrix. # Try to estimate the covariance from a specially crafted matrix.
# There should be some significant correlation since X is specially crafted. # There should be some significant correlation since X is specially crafted.