adelorenzo/stable
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

enable continual learning and evaluation sets on multioutput models.

Browse Source
This commit is contained in:
robcaulk
2022-09-10 16:54:13 +02:00
parent 170bec0438
commit 10b6aebc5f
12 changed files with 170 additions and 38 deletions
Download Patch File Download Diff File Expand all files Collapse all files

99
freqtrade/freqai/prediction_models/BaseClassifierModel.py
View File

@@ -1,99 +0,0 @@
import logging
from typing import Any, Tuple
import numpy as np
import numpy.typing as npt
import pandas as pd
from pandas import DataFrame
from freqtrade.freqai.data_kitchen import FreqaiDataKitchen
from freqtrade.freqai.freqai_interface import IFreqaiModel
logger = logging.getLogger(__name__)
class BaseClassifierModel(IFreqaiModel):
"""
Base class for regression type models (e.g. Catboost, LightGBM, XGboost etc.).
User *must* inherit from this class and set fit() and predict(). See example scripts
such as prediction_models/CatboostPredictionModel.py for guidance.
"""
def train(
self, unfiltered_df: DataFrame, pair: str, dk: FreqaiDataKitchen, **kwargs
) -> Any:
"""
Filter the training data and train a model to it. Train makes heavy use of the datakitchen
for storing, saving, loading, and analyzing the data.
:param unfiltered_df: Full dataframe for the current training period
:param metadata: pair metadata from strategy.
:return:
:model: Trained model which can be used to inference (self.predict)
"""
logger.info("-------------------- Starting training " f"{pair} --------------------")
# filter the features requested by user in the configuration file and elegantly handle NaNs
features_filtered, labels_filtered = dk.filter_features(
unfiltered_df,
dk.training_features_list,
dk.label_list,
training_filter=True,
)
start_date = unfiltered_df["date"].iloc[0].strftime("%Y-%m-%d")
end_date = unfiltered_df["date"].iloc[-1].strftime("%Y-%m-%d")
logger.info(f"-------------------- Training on data from {start_date} to "
f"{end_date}--------------------")
# split data into train/test data.
data_dictionary = dk.make_train_test_datasets(features_filtered, labels_filtered)
if not self.freqai_info.get('fit_live_predictions', 0) or not self.live:
dk.fit_labels()
# normalize all data based on train_dataset only
data_dictionary = dk.normalize_data(data_dictionary)
# optional additional data cleaning/analysis
self.data_cleaning_train(dk)
logger.info(
f'Training model on {len(dk.data_dictionary["train_features"].columns)}' " features"
)
logger.info(f'Training model on {len(data_dictionary["train_features"])} data points')
model = self.fit(data_dictionary, dk)
logger.info(f"--------------------done training {pair}--------------------")
return model
def predict(
self, unfiltered_df: DataFrame, dk: FreqaiDataKitchen, **kwargs
) -> Tuple[DataFrame, npt.NDArray[np.int_]]:
"""
Filter the prediction features data and predict with it.
:param: unfiltered_df: Full dataframe for the current backtest period.
:return:
:pred_df: dataframe containing the predictions
:do_predict: np.array of 1s and 0s to indicate places where freqai needed to remove
data (NaNs) or felt uncertain about data (PCA and DI index)
"""
dk.find_features(unfiltered_df)
filtered_df, _ = dk.filter_features(
unfiltered_df, dk.training_features_list, training_filter=False
)
filtered_df = dk.normalize_data_from_metadata(filtered_df)
dk.data_dictionary["prediction_features"] = filtered_df
self.data_cleaning_predict(dk, filtered_df)
predictions = self.model.predict(dk.data_dictionary["prediction_features"])
pred_df = DataFrame(predictions, columns=dk.label_list)
predictions_prob = self.model.predict_proba(dk.data_dictionary["prediction_features"])
pred_df_prob = DataFrame(predictions_prob, columns=self.model.classes_)
pred_df = pd.concat([pred_df, pred_df_prob], axis=1)
return (pred_df, dk.do_predict)

96
freqtrade/freqai/prediction_models/BaseRegressionModel.py
View File

@@ -1,96 +0,0 @@
import logging
from typing import Any, Tuple
import numpy as np
import numpy.typing as npt
from pandas import DataFrame
from freqtrade.freqai.data_kitchen import FreqaiDataKitchen
from freqtrade.freqai.freqai_interface import IFreqaiModel
logger = logging.getLogger(__name__)
class BaseRegressionModel(IFreqaiModel):
"""
Base class for regression type models (e.g. Catboost, LightGBM, XGboost etc.).
User *must* inherit from this class and set fit() and predict(). See example scripts
such as prediction_models/CatboostPredictionModel.py for guidance.
"""
def train(
self, unfiltered_df: DataFrame, pair: str, dk: FreqaiDataKitchen, **kwargs
) -> Any:
"""
Filter the training data and train a model to it. Train makes heavy use of the datakitchen
for storing, saving, loading, and analyzing the data.
:param unfiltered_df: Full dataframe for the current training period
:param metadata: pair metadata from strategy.
:return:
:model: Trained model which can be used to inference (self.predict)
"""
logger.info("-------------------- Starting training " f"{pair} --------------------")
# filter the features requested by user in the configuration file and elegantly handle NaNs
features_filtered, labels_filtered = dk.filter_features(
unfiltered_df,
dk.training_features_list,
dk.label_list,
training_filter=True,
)
start_date = unfiltered_df["date"].iloc[0].strftime("%Y-%m-%d")
end_date = unfiltered_df["date"].iloc[-1].strftime("%Y-%m-%d")
logger.info(f"-------------------- Training on data from {start_date} to "
f"{end_date}--------------------")
# split data into train/test data.
data_dictionary = dk.make_train_test_datasets(features_filtered, labels_filtered)
if not self.freqai_info.get('fit_live_predictions', 0) or not self.live:
dk.fit_labels()
# normalize all data based on train_dataset only
data_dictionary = dk.normalize_data(data_dictionary)
# optional additional data cleaning/analysis
self.data_cleaning_train(dk)
logger.info(
f'Training model on {len(dk.data_dictionary["train_features"].columns)}' " features"
)
logger.info(f'Training model on {len(data_dictionary["train_features"])} data points')
model = self.fit(data_dictionary, dk)
logger.info(f"--------------------done training {pair}--------------------")
return model
def predict(
self, unfiltered_df: DataFrame, dk: FreqaiDataKitchen, **kwargs
) -> Tuple[DataFrame, npt.NDArray[np.int_]]:
"""
Filter the prediction features data and predict with it.
:param: unfiltered_df: Full dataframe for the current backtest period.
:return:
:pred_df: dataframe containing the predictions
:do_predict: np.array of 1s and 0s to indicate places where freqai needed to remove
data (NaNs) or felt uncertain about data (PCA and DI index)
"""
dk.find_features(unfiltered_df)
filtered_df, _ = dk.filter_features(
unfiltered_df, dk.training_features_list, training_filter=False
)
filtered_df = dk.normalize_data_from_metadata(filtered_df)
dk.data_dictionary["prediction_features"] = filtered_df
# optional additional data cleaning/analysis
self.data_cleaning_predict(dk, filtered_df)
predictions = self.model.predict(dk.data_dictionary["prediction_features"])
pred_df = DataFrame(predictions, columns=dk.label_list)
pred_df = dk.denormalize_labels_from_metadata(pred_df)
return (pred_df, dk.do_predict)

64
freqtrade/freqai/prediction_models/BaseTensorFlowModel.py
View File

@@ -1,64 +0,0 @@
import logging
from typing import Any
from pandas import DataFrame
from freqtrade.freqai.data_kitchen import FreqaiDataKitchen
from freqtrade.freqai.freqai_interface import IFreqaiModel
logger = logging.getLogger(__name__)
class BaseTensorFlowModel(IFreqaiModel):
"""
Base class for TensorFlow type models.
User *must* inherit from this class and set fit() and predict().
"""
def train(
self, unfiltered_df: DataFrame, pair: str, dk: FreqaiDataKitchen, **kwargs
) -> Any:
"""
Filter the training data and train a model to it. Train makes heavy use of the datakitchen
for storing, saving, loading, and analyzing the data.
:param unfiltered_df: Full dataframe for the current training period
:param metadata: pair metadata from strategy.
:return:
:model: Trained model which can be used to inference (self.predict)
"""
logger.info("-------------------- Starting training " f"{pair} --------------------")
# filter the features requested by user in the configuration file and elegantly handle NaNs
features_filtered, labels_filtered = dk.filter_features(
unfiltered_df,
dk.training_features_list,
dk.label_list,
training_filter=True,
)
start_date = unfiltered_df["date"].iloc[0].strftime("%Y-%m-%d")
end_date = unfiltered_df["date"].iloc[-1].strftime("%Y-%m-%d")
logger.info(f"-------------------- Training on data from {start_date} to "
f"{end_date}--------------------")
# split data into train/test data.
data_dictionary = dk.make_train_test_datasets(features_filtered, labels_filtered)
if not self.freqai_info.get('fit_live_predictions', 0) or not self.live:
dk.fit_labels()
# normalize all data based on train_dataset only
data_dictionary = dk.normalize_data(data_dictionary)
# optional additional data cleaning/analysis
self.data_cleaning_train(dk)
logger.info(
f'Training model on {len(dk.data_dictionary["train_features"].columns)}' " features"
)
logger.info(f'Training model on {len(data_dictionary["train_features"])} data points')
model = self.fit(data_dictionary, dk)
logger.info(f"--------------------done training {pair}--------------------")
return model

2
freqtrade/freqai/prediction_models/CatboostClassifier.py
View File

@@ -3,8 +3,8 @@ from typing import Any, Dict
from catboost import CatBoostClassifier, Pool
from freqtrade.freqai.base_models.BaseClassifierModel import BaseClassifierModel
from freqtrade.freqai.data_kitchen import FreqaiDataKitchen
from freqtrade.freqai.prediction_models.BaseClassifierModel import BaseClassifierModel
logger = logging.getLogger(__name__)

2
freqtrade/freqai/prediction_models/CatboostRegressor.py
View File

@@ -3,8 +3,8 @@ from typing import Any, Dict
from catboost import CatBoostRegressor, Pool
from freqtrade.freqai.base_models.BaseRegressionModel import BaseRegressionModel
from freqtrade.freqai.data_kitchen import FreqaiDataKitchen
from freqtrade.freqai.prediction_models.BaseRegressionModel import BaseRegressionModel
logger = logging.getLogger(__name__)

41
freqtrade/freqai/prediction_models/CatboostRegressorMultiTarget.py
View File

@@ -1,11 +1,11 @@
import logging
from typing import Any, Dict
from catboost import CatBoostRegressor # , Pool
from sklearn.multioutput import MultiOutputRegressor
from catboost import CatBoostRegressor, Pool
from freqtrade.freqai.base_models.BaseRegressionModel import BaseRegressionModel
from freqtrade.freqai.base_models.FreqaiMultiOutputRegressor import FreqaiMultiOutputRegressor
from freqtrade.freqai.data_kitchen import FreqaiDataKitchen
from freqtrade.freqai.prediction_models.BaseRegressionModel import BaseRegressionModel
logger = logging.getLogger(__name__)
@@ -32,17 +32,34 @@ class CatboostRegressorMultiTarget(BaseRegressionModel):
X = data_dictionary["train_features"]
y = data_dictionary["train_labels"]
eval_set = (data_dictionary["test_features"], data_dictionary["test_labels"])
sample_weight = data_dictionary["train_weights"]
if self.continual_learning:
logger.warning('Continual learning not supported for MultiTarget models')
model = MultiOutputRegressor(estimator=cbr)
model.fit(X=X, y=y, sample_weight=sample_weight) # , eval_set=eval_set)
eval_sets = [None] * y.shape[1]
if self.freqai_info.get('data_split_parameters', {}).get('test_size', 0.1) != 0:
train_score = model.score(X, y)
test_score = model.score(*eval_set)
logger.info(f"Train score {train_score}, Test score {test_score}")
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)
if init_model:
init_models = init_model.estimators_
else:
init_models = [None] * y.shape[1]
fit_params = []
for i in range(len(eval_sets)):
fit_params.append(
{'eval_set': eval_sets[i], 'init_model': init_models[i]})
model = FreqaiMultiOutputRegressor(estimator=cbr)
model.fit(X=X, y=y, sample_weight=sample_weight, fit_params=fit_params)
return model

2
freqtrade/freqai/prediction_models/LightGBMClassifier.py
View File

@@ -3,8 +3,8 @@ from typing import Any, Dict
from lightgbm import LGBMClassifier
from freqtrade.freqai.base_models.BaseClassifierModel import BaseClassifierModel
from freqtrade.freqai.data_kitchen import FreqaiDataKitchen
from freqtrade.freqai.prediction_models.BaseClassifierModel import BaseClassifierModel
logger = logging.getLogger(__name__)

2
freqtrade/freqai/prediction_models/LightGBMRegressor.py
View File

@@ -3,8 +3,8 @@ from typing import Any, Dict
from lightgbm import LGBMRegressor
from freqtrade.freqai.base_models.BaseRegressionModel import BaseRegressionModel
from freqtrade.freqai.data_kitchen import FreqaiDataKitchen
from freqtrade.freqai.prediction_models.BaseRegressionModel import BaseRegressionModel
logger = logging.getLogger(__name__)

41
freqtrade/freqai/prediction_models/LightGBMRegressorMultiTarget.py
View File

@@ -2,10 +2,10 @@ import logging
from typing import Any, Dict
from lightgbm import LGBMRegressor
from sklearn.multioutput import MultiOutputRegressor
from freqtrade.freqai.base_models.BaseRegressionModel import BaseRegressionModel
from freqtrade.freqai.base_models.FreqaiMultiOutputRegressor import FreqaiMultiOutputRegressor
from freqtrade.freqai.data_kitchen import FreqaiDataKitchen
from freqtrade.freqai.prediction_models.BaseRegressionModel import BaseRegressionModel
logger = logging.getLogger(__name__)
@@ -29,15 +29,36 @@ class LightGBMRegressorMultiTarget(BaseRegressionModel):
X = data_dictionary["train_features"]
y = data_dictionary["train_labels"]
eval_set = (data_dictionary["test_features"], data_dictionary["test_labels"])
sample_weight = data_dictionary["train_weights"]
if self.continual_learning:
logger.warning('Continual learning not supported for MultiTarget models')
eval_weights = None
eval_sets = [None] * y.shape[1]
model = MultiOutputRegressor(estimator=lgb)
model.fit(X=X, y=y, sample_weight=sample_weight) # , eval_set=eval_set)
train_score = model.score(X, y)
test_score = model.score(*eval_set)
logger.info(f"Train score {train_score}, Test score {test_score}")
if self.freqai_info.get('data_split_parameters', {}).get('test_size', 0.1) != 0:
eval_weights = [data_dictionary["test_weights"]]
eval_sets = [(None, None)] * data_dictionary['test_labels'].shape[1] # type: ignore
for i in range(data_dictionary['test_labels'].shape[1]):
eval_sets[i] = ( # type: ignore
data_dictionary["test_features"],
data_dictionary["test_labels"].iloc[:, i]
)
init_model = self.get_init_model(dk.pair)
if init_model:
init_models = init_model.estimators_
else:
init_models = [None] * y.shape[1]
fit_params = []
for i in range(len(eval_sets)):
fit_params.append(
{'eval_set': eval_sets[i], 'eval_sample_weight': eval_weights,
'init_model': init_models[i]})
model = FreqaiMultiOutputRegressor(estimator=lgb)
model.fit(X=X, y=y, sample_weight=sample_weight, fit_params=fit_params)
# model = FreqaiMultiOutputRegressor(estimator=lgb)
# model.fit(X=X, y=y, sample_weight=sample_weight, init_models=init_models,
# eval_sets=eval_sets, eval_sample_weight=eval_weights)
return model

6
freqtrade/freqai/prediction_models/XGBoostRegressor.py
View File

@@ -3,8 +3,8 @@ from typing import Any, Dict
from xgboost import XGBRegressor
from freqtrade.freqai.base_models.BaseRegressionModel import BaseRegressionModel
from freqtrade.freqai.data_kitchen import FreqaiDataKitchen
from freqtrade.freqai.prediction_models.BaseRegressionModel import BaseRegressionModel
logger = logging.getLogger(__name__)
@@ -31,6 +31,7 @@ class XGBoostRegressor(BaseRegressionModel):
eval_set = None
else:
eval_set = [(data_dictionary["test_features"], data_dictionary["test_labels"])]
eval_weights = [data_dictionary['test_weights']]
sample_weight = data_dictionary["train_weights"]
@@ -38,6 +39,7 @@ class XGBoostRegressor(BaseRegressionModel):
model = XGBRegressor(**self.model_training_parameters)
model.fit(X=X, y=y, sample_weight=sample_weight, eval_set=eval_set, xgb_model=xgb_model)
model.fit(X=X, y=y, sample_weight=sample_weight, eval_set=eval_set,
sample_weight_eval_set=eval_weights, xgb_model=xgb_model)
return model

37
freqtrade/freqai/prediction_models/XGBoostRegressorMultiTarget.py
View File

@@ -1,11 +1,11 @@
import logging
from typing import Any, Dict
from sklearn.multioutput import MultiOutputRegressor
from xgboost import XGBRegressor
from freqtrade.freqai.base_models.BaseRegressionModel import BaseRegressionModel
from freqtrade.freqai.base_models.FreqaiMultiOutputRegressor import FreqaiMultiOutputRegressor
from freqtrade.freqai.data_kitchen import FreqaiDataKitchen
from freqtrade.freqai.prediction_models.BaseRegressionModel import BaseRegressionModel
logger = logging.getLogger(__name__)
@@ -29,15 +29,32 @@ class XGBoostRegressorMultiTarget(BaseRegressionModel):
X = data_dictionary["train_features"]
y = data_dictionary["train_labels"]
eval_set = (data_dictionary["test_features"], data_dictionary["test_labels"])
sample_weight = data_dictionary["train_weights"]
if self.continual_learning:
logger.warning('Continual learning not supported for MultiTarget models')
eval_weights = None
eval_sets = [None] * y.shape[1]
if self.freqai_info.get('data_split_parameters', {}).get('test_size', 0.1) != 0:
eval_weights = [data_dictionary["test_weights"]]
for i in range(data_dictionary['test_labels'].shape[1]):
eval_sets[i] = [( # type: ignore
data_dictionary["test_features"],
data_dictionary["test_labels"].iloc[:, i]
)]
init_model = self.get_init_model(dk.pair)
if init_model:
init_models = init_model.estimators_
else:
init_models = [None] * y.shape[1]
fit_params = []
for i in range(len(eval_sets)):
fit_params.append(
{'eval_set': eval_sets[i], 'sample_weight_eval_set': eval_weights,
'xgb_model': init_models[i]})
model = FreqaiMultiOutputRegressor(estimator=xgb)
model.fit(X=X, y=y, sample_weight=sample_weight, fit_params=fit_params)
model = MultiOutputRegressor(estimator=xgb)
model.fit(X=X, y=y, sample_weight=sample_weight) # , eval_set=eval_set)
train_score = model.score(X, y)
test_score = model.score(*eval_set)
logger.info(f"Train score {train_score}, Test score {test_score}")
return model