add strat and config for testing on PR
This commit is contained in:
Mark Regan
@@ -1,10 +1,13 @@
|
||||
import numpy as np
|
||||
from joblib import Parallel
|
||||
from sklearn.multioutput import MultiOutputRegressor, _fit_estimator
|
||||
from sklearn.base import is_classifier
|
||||
from sklearn.multioutput import MultiOutputClassifier, _fit_estimator
|
||||
from sklearn.utils.fixes import delayed
|
||||
from sklearn.utils.validation import has_fit_parameter
|
||||
from sklearn.utils.multiclass import check_classification_targets
|
||||
from sklearn.utils.validation import check_is_fitted, has_fit_parameter
|
||||
|
||||
|
||||
class FreqaiMultiOutputRegressor(MultiOutputRegressor):
|
||||
class FreqaiMultiOutputClassifier(MultiOutputClassifier):
|
||||
|
||||
def fit(self, X, y, sample_weight=None, fit_params=None):
|
||||
"""Fit the model to data, separately for each output variable.
|
||||
@@ -17,7 +20,7 @@ class FreqaiMultiOutputRegressor(MultiOutputRegressor):
|
||||
estimation.
|
||||
sample_weight : array-like of shape (n_samples,), default=None
|
||||
Sample weights. If `None`, then samples are equally weighted.
|
||||
Only supported if the underlying regressor supports sample
|
||||
Only supported if the underlying classifier supports sample
|
||||
weights.
|
||||
fit_params : A list of dicts for the fit_params
|
||||
Parameters passed to the ``estimator.fit`` method of each step.
|
||||
@@ -35,6 +38,9 @@ class FreqaiMultiOutputRegressor(MultiOutputRegressor):
|
||||
|
||||
y = self._validate_data(X="no_validation", y=y, multi_output=True)
|
||||
|
||||
if is_classifier(self):
|
||||
check_classification_targets(y)
|
||||
|
||||
if y.ndim == 1:
|
||||
raise ValueError(
|
||||
"y must have at least two dimensions for "
|
||||
@@ -56,9 +62,66 @@ class FreqaiMultiOutputRegressor(MultiOutputRegressor):
|
||||
for i in range(y.shape[1])
|
||||
)
|
||||
|
||||
self.classes_ = []
|
||||
for estimator in self.estimators_:
|
||||
self.classes_.extend(estimator.classes_)
|
||||
|
||||
if hasattr(self.estimators_[0], "n_features_in_"):
|
||||
self.n_features_in_ = self.estimators_[0].n_features_in_
|
||||
if hasattr(self.estimators_[0], "feature_names_in_"):
|
||||
self.feature_names_in_ = self.estimators_[0].feature_names_in_
|
||||
|
||||
return
|
||||
return self
|
||||
|
||||
def predict_proba(self, X):
|
||||
"""Return prediction probabilities for each class of each output.
|
||||
|
||||
This method will raise a ``ValueError`` if any of the
|
||||
estimators do not have ``predict_proba``.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
X : array-like of shape (n_samples, n_features)
|
||||
The input data.
|
||||
|
||||
Returns
|
||||
-------
|
||||
p : array of shape (n_samples, n_classes), or a list of n_outputs \
|
||||
such arrays if n_outputs > 1.
|
||||
The class probabilities of the input samples. The order of the
|
||||
classes corresponds to that in the attribute :term:`classes_`.
|
||||
|
||||
.. versionchanged:: 0.19
|
||||
This function now returns a list of arrays where the length of
|
||||
the list is ``n_outputs``, and each array is (``n_samples``,
|
||||
``n_classes``) for that particular output.
|
||||
"""
|
||||
check_is_fitted(self)
|
||||
results = np.hstack([estimator.predict_proba(X) for estimator in self.estimators_])
|
||||
return np.squeeze(results)
|
||||
|
||||
def predict(self, X):
|
||||
"""Predict multi-output variable using model for each target variable.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
X : {array-like, sparse matrix} of shape (n_samples, n_features)
|
||||
The input data.
|
||||
|
||||
Returns
|
||||
-------
|
||||
y : {array-like, sparse matrix} of shape (n_samples, n_outputs)
|
||||
Multi-output targets predicted across multiple predictors.
|
||||
Note: Separate models are generated for each predictor.
|
||||
"""
|
||||
check_is_fitted(self)
|
||||
if not hasattr(self.estimators_[0], "predict"):
|
||||
raise ValueError("The base estimator should implement a predict method")
|
||||
|
||||
y = Parallel(n_jobs=self.n_jobs)(
|
||||
delayed(e.predict)(X) for e in self.estimators_
|
||||
)
|
||||
|
||||
results = np.asarray(y).T
|
||||
|
||||
return np.squeeze(results)
|
||||
|
||||
@@ -6,13 +6,14 @@ from typing import Any, Dict
|
||||
from catboost import CatBoostClassifier, Pool
|
||||
|
||||
from freqtrade.freqai.base_models.BaseClassifierModel import BaseClassifierModel
|
||||
from freqtrade.freqai.base_models.FreqaiMultiOutputClassifier import FreqaiMultiOutputClassifier
|
||||
from freqtrade.freqai.data_kitchen import FreqaiDataKitchen
|
||||
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class CatboostClassifier(BaseClassifierModel):
|
||||
class CatboostClassifierMultiTarget(BaseClassifierModel):
|
||||
"""
|
||||
User created prediction model. The class needs to override three necessary
|
||||
functions, predict(), train(), fit(). The class inherits ModelHandler which
|
||||
@@ -26,30 +27,48 @@ class CatboostClassifier(BaseClassifierModel):
|
||||
all the training and test data/labels.
|
||||
"""
|
||||
|
||||
train_data = Pool(
|
||||
data=data_dictionary["train_features"],
|
||||
label=data_dictionary["train_labels"],
|
||||
weight=data_dictionary["train_weights"],
|
||||
)
|
||||
if self.freqai_info.get("data_split_parameters", {}).get("test_size", 0.1) == 0:
|
||||
test_data = None
|
||||
else:
|
||||
test_data = Pool(
|
||||
data=data_dictionary["test_features"],
|
||||
label=data_dictionary["test_labels"],
|
||||
weight=data_dictionary["test_weights"],
|
||||
)
|
||||
|
||||
cbr = CatBoostClassifier(
|
||||
cbc = CatBoostClassifier(
|
||||
allow_writing_files=True,
|
||||
loss_function='MultiClass',
|
||||
train_dir=Path(dk.data_path),
|
||||
**self.model_training_parameters,
|
||||
)
|
||||
|
||||
X = data_dictionary["train_features"]
|
||||
y = data_dictionary["train_labels"]
|
||||
|
||||
sample_weight = data_dictionary["train_weights"]
|
||||
|
||||
eval_sets = [None] * y.shape[1]
|
||||
|
||||
if self.freqai_info.get('data_split_parameters', {}).get('test_size', 0.1) != 0:
|
||||
eval_sets = [None] * data_dictionary['test_labels'].shape[1]
|
||||
|
||||
for i in range(data_dictionary['test_labels'].shape[1]):
|
||||
eval_sets[i] = Pool(
|
||||
data=data_dictionary["test_features"],
|
||||
label=data_dictionary["test_labels"].iloc[:, i],
|
||||
weight=data_dictionary["test_weights"],
|
||||
)
|
||||
|
||||
init_model = self.get_init_model(dk.pair)
|
||||
|
||||
cbr.fit(X=train_data, eval_set=test_data, init_model=init_model,
|
||||
log_cout=sys.stdout, log_cerr=sys.stderr)
|
||||
if init_model:
|
||||
init_models = init_model.estimators_
|
||||
else:
|
||||
init_models = [None] * y.shape[1]
|
||||
|
||||
return cbr
|
||||
fit_params = []
|
||||
for i in range(len(eval_sets)):
|
||||
fit_params.append({
|
||||
'eval_set': eval_sets[i], 'init_model': init_models[i],
|
||||
'log_cout': sys.stdout, 'log_cerr': sys.stderr,
|
||||
})
|
||||
|
||||
model = FreqaiMultiOutputClassifier(estimator=cbc)
|
||||
thread_training = self.freqai_info.get('multitarget_parallel_training', False)
|
||||
if thread_training:
|
||||
model.n_jobs = y.shape[1]
|
||||
model.fit(X=X, y=y, sample_weight=sample_weight, fit_params=fit_params)
|
||||
|
||||
return model
|
||||
|
||||
Reference in New Issue
Block a user