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

Merge branch 'develop' into dev-merge-rl

Browse Source
This commit is contained in:
robcaulk
2022-09-14 22:49:11 +02:00
parent 69b3fcfd32 075748b21a
commit 81417cb795
59 changed files with 1259 additions and 679 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_dataframe: DataFrame, pair: str, dk: FreqaiDataKitchen
) -> 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_dataframe: 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_dataframe,
dk.training_features_list,
dk.label_list,
training_filter=True,
)
start_date = unfiltered_dataframe["date"].iloc[0].strftime("%Y-%m-%d")
end_date = unfiltered_dataframe["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)}'
f' features and {len(data_dictionary["train_features"])} data points'
)
model = self.fit(data_dictionary)
logger.info(f"--------------------done training {pair}--------------------")
return model
def predict(
self, unfiltered_dataframe: DataFrame, dk: FreqaiDataKitchen, first: bool = False
) -> Tuple[DataFrame, npt.NDArray[np.int_]]:
"""
Filter the prediction features data and predict with it.
:param: unfiltered_dataframe: 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_dataframe)
filtered_dataframe, _ = dk.filter_features(
unfiltered_dataframe, dk.training_features_list, training_filter=False
)
filtered_dataframe = dk.normalize_data_from_metadata(filtered_dataframe)
dk.data_dictionary["prediction_features"] = filtered_dataframe
self.data_cleaning_predict(dk, filtered_dataframe)
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_dataframe: DataFrame, pair: str, dk: FreqaiDataKitchen
) -> 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_dataframe: 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_dataframe,
dk.training_features_list,
dk.label_list,
training_filter=True,
)
start_date = unfiltered_dataframe["date"].iloc[0].strftime("%Y-%m-%d")
end_date = unfiltered_dataframe["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)}'
f' features and {len(data_dictionary["train_features"])} data points'
)
model = self.fit(data_dictionary)
logger.info(f"--------------------done training {pair}--------------------")
return model
def predict(
self, unfiltered_dataframe: DataFrame, dk: FreqaiDataKitchen, first: bool = False
) -> Tuple[DataFrame, npt.NDArray[np.int_]]:
"""
Filter the prediction features data and predict with it.
:param: unfiltered_dataframe: 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_dataframe)
filtered_dataframe, _ = dk.filter_features(
unfiltered_dataframe, dk.training_features_list, training_filter=False
)
filtered_dataframe = dk.normalize_data_from_metadata(filtered_dataframe)
dk.data_dictionary["prediction_features"] = filtered_dataframe
# optional additional data cleaning/analysis
self.data_cleaning_predict(dk, filtered_dataframe)
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_dataframe: DataFrame, pair: str, dk: FreqaiDataKitchen
) -> 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_dataframe: 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_dataframe,
dk.training_features_list,
dk.label_list,
training_filter=True,
)
start_date = unfiltered_dataframe["date"].iloc[0].strftime("%Y-%m-%d")
end_date = unfiltered_dataframe["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)}'
f' features and {len(data_dictionary["train_features"])} data points'
)
model = self.fit(data_dictionary)
logger.info(f"--------------------done training {pair}--------------------")
return model

9
freqtrade/freqai/prediction_models/CatboostClassifier.py
View File

@@ -3,7 +3,8 @@ from typing import Any, Dict
from catboost import CatBoostClassifier, Pool
from freqtrade.freqai.prediction_models.BaseClassifierModel import BaseClassifierModel
from freqtrade.freqai.base_models.BaseClassifierModel import BaseClassifierModel
from freqtrade.freqai.data_kitchen import FreqaiDataKitchen
logger = logging.getLogger(__name__)
@@ -16,7 +17,7 @@ class CatboostClassifier(BaseClassifierModel):
has its own DataHandler where data is held, saved, loaded, and managed.
"""
def fit(self, data_dictionary: Dict[str, Any], pair: str = '') -> Any:
def fit(self, data_dictionary: Dict, dk: FreqaiDataKitchen, **kwargs) -> Any:
"""
User sets up the training and test data to fit their desired model here
:params:
@@ -36,6 +37,8 @@ class CatboostClassifier(BaseClassifierModel):
**self.model_training_parameters,
)
cbr.fit(train_data)
init_model = self.get_init_model(dk.pair)
cbr.fit(train_data, init_model=init_model)
return cbr

15
freqtrade/freqai/prediction_models/CatboostRegressor.py
View File

@@ -1,10 +1,10 @@
import gc
import logging
from typing import Any, Dict
from catboost import CatBoostRegressor, Pool
from freqtrade.freqai.prediction_models.BaseRegressionModel import BaseRegressionModel
from freqtrade.freqai.base_models.BaseRegressionModel import BaseRegressionModel
from freqtrade.freqai.data_kitchen import FreqaiDataKitchen
logger = logging.getLogger(__name__)
@@ -17,7 +17,7 @@ class CatboostRegressor(BaseRegressionModel):
has its own DataHandler where data is held, saved, loaded, and managed.
"""
def fit(self, data_dictionary: Dict[str, Any], pair: str = '') -> Any:
def fit(self, data_dictionary: Dict, dk: FreqaiDataKitchen, **kwargs) -> Any:
"""
User sets up the training and test data to fit their desired model here
:param data_dictionary: the dictionary constructed by DataHandler to hold
@@ -38,16 +38,13 @@ class CatboostRegressor(BaseRegressionModel):
weight=data_dictionary["test_weights"],
)
init_model = self.get_init_model(dk.pair)
model = CatBoostRegressor(
allow_writing_files=False,
**self.model_training_parameters,
)
model.fit(X=train_data, eval_set=test_data)
# some evidence that catboost pools have memory leaks:
# https://github.com/catboost/catboost/issues/1835
del train_data, test_data
gc.collect()
model.fit(X=train_data, eval_set=test_data, init_model=init_model)
return model

44
freqtrade/freqai/prediction_models/CatboostRegressorMultiTarget.py
View File

@@ -1,10 +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.prediction_models.BaseRegressionModel import BaseRegressionModel
from freqtrade.freqai.base_models.BaseRegressionModel import BaseRegressionModel
from freqtrade.freqai.base_models.FreqaiMultiOutputRegressor import FreqaiMultiOutputRegressor
from freqtrade.freqai.data_kitchen import FreqaiDataKitchen
logger = logging.getLogger(__name__)
@@ -17,7 +18,7 @@ class CatboostRegressorMultiTarget(BaseRegressionModel):
has its own DataHandler where data is held, saved, loaded, and managed.
"""
def fit(self, data_dictionary: Dict) -> Any:
def fit(self, data_dictionary: Dict, dk: FreqaiDataKitchen, **kwargs) -> Any:
"""
User sets up the training and test data to fit their desired model here
:param data_dictionary: the dictionary constructed by DataHandler to hold
@@ -31,14 +32,37 @@ 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"]
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)
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

9
freqtrade/freqai/prediction_models/LightGBMClassifier.py
View File

@@ -3,7 +3,8 @@ from typing import Any, Dict
from lightgbm import LGBMClassifier
from freqtrade.freqai.prediction_models.BaseClassifierModel import BaseClassifierModel
from freqtrade.freqai.base_models.BaseClassifierModel import BaseClassifierModel
from freqtrade.freqai.data_kitchen import FreqaiDataKitchen
logger = logging.getLogger(__name__)
@@ -16,7 +17,7 @@ class LightGBMClassifier(BaseClassifierModel):
has its own DataHandler where data is held, saved, loaded, and managed.
"""
def fit(self, data_dictionary: Dict) -> Any:
def fit(self, data_dictionary: Dict, dk: FreqaiDataKitchen, **kwargs) -> Any:
"""
User sets up the training and test data to fit their desired model here
:params:
@@ -35,9 +36,11 @@ class LightGBMClassifier(BaseClassifierModel):
y = data_dictionary["train_labels"].to_numpy()[:, 0]
train_weights = data_dictionary["train_weights"]
init_model = self.get_init_model(dk.pair)
model = LGBMClassifier(**self.model_training_parameters)
model.fit(X=X, y=y, eval_set=eval_set, sample_weight=train_weights,
eval_sample_weight=[test_weights])
eval_sample_weight=[test_weights], init_model=init_model)
return model

9
freqtrade/freqai/prediction_models/LightGBMRegressor.py
View File

@@ -3,7 +3,8 @@ from typing import Any, Dict
from lightgbm import LGBMRegressor
from freqtrade.freqai.prediction_models.BaseRegressionModel import BaseRegressionModel
from freqtrade.freqai.base_models.BaseRegressionModel import BaseRegressionModel
from freqtrade.freqai.data_kitchen import FreqaiDataKitchen
logger = logging.getLogger(__name__)
@@ -16,7 +17,7 @@ class LightGBMRegressor(BaseRegressionModel):
has its own DataHandler where data is held, saved, loaded, and managed.
"""
def fit(self, data_dictionary: Dict) -> Any:
def fit(self, data_dictionary: Dict, dk: FreqaiDataKitchen, **kwargs) -> Any:
"""
Most regressors use the same function names and arguments e.g. user
can drop in LGBMRegressor in place of CatBoostRegressor and all data
@@ -35,9 +36,11 @@ class LightGBMRegressor(BaseRegressionModel):
y = data_dictionary["train_labels"]
train_weights = data_dictionary["train_weights"]
init_model = self.get_init_model(dk.pair)
model = LGBMRegressor(**self.model_training_parameters)
model.fit(X=X, y=y, eval_set=eval_set, sample_weight=train_weights,
eval_sample_weight=[eval_weights])
eval_sample_weight=[eval_weights], init_model=init_model)
return model

43
freqtrade/freqai/prediction_models/LightGBMRegressorMultiTarget.py
View File

@@ -2,9 +2,10 @@ import logging
from typing import Any, Dict
from lightgbm import LGBMRegressor
from sklearn.multioutput import MultiOutputRegressor
from freqtrade.freqai.prediction_models.BaseRegressionModel import BaseRegressionModel
from freqtrade.freqai.base_models.BaseRegressionModel import BaseRegressionModel
from freqtrade.freqai.base_models.FreqaiMultiOutputRegressor import FreqaiMultiOutputRegressor
from freqtrade.freqai.data_kitchen import FreqaiDataKitchen
logger = logging.getLogger(__name__)
@@ -17,7 +18,7 @@ class LightGBMRegressorMultiTarget(BaseRegressionModel):
has its own DataHandler where data is held, saved, loaded, and managed.
"""
def fit(self, data_dictionary: Dict) -> Any:
def fit(self, data_dictionary: Dict, dk: FreqaiDataKitchen, **kwargs) -> Any:
"""
User sets up the training and test data to fit their desired model here
:param data_dictionary: the dictionary constructed by DataHandler to hold
@@ -28,12 +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"]
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}")
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"]]
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)
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

45
freqtrade/freqai/prediction_models/XGBoostRegressor.py Normal file
View File

@@ -0,0 +1,45 @@
import logging
from typing import Any, Dict
from xgboost import XGBRegressor
from freqtrade.freqai.base_models.BaseRegressionModel import BaseRegressionModel
from freqtrade.freqai.data_kitchen import FreqaiDataKitchen
logger = logging.getLogger(__name__)
class XGBoostRegressor(BaseRegressionModel):
"""
User created prediction model. The class needs to override three necessary
functions, predict(), train(), fit(). The class inherits ModelHandler which
has its own DataHandler where data is held, saved, loaded, and managed.
"""
def fit(self, data_dictionary: Dict, dk: FreqaiDataKitchen, **kwargs) -> Any:
"""
User sets up the training and test data to fit their desired model here
:param data_dictionary: the dictionary constructed by DataHandler to hold
all the training and test data/labels.
"""
X = data_dictionary["train_features"]
y = data_dictionary["train_labels"]
if self.freqai_info.get("data_split_parameters", {}).get("test_size", 0.1) == 0:
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"]
xgb_model = self.get_init_model(dk.pair)
model = XGBRegressor(**self.model_training_parameters)
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

63
freqtrade/freqai/prediction_models/XGBoostRegressorMultiTarget.py Normal file
View File

@@ -0,0 +1,63 @@
import logging
from typing import Any, Dict
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
logger = logging.getLogger(__name__)
class XGBoostRegressorMultiTarget(BaseRegressionModel):
"""
User created prediction model. The class needs to override three necessary
functions, predict(), train(), fit(). The class inherits ModelHandler which
has its own DataHandler where data is held, saved, loaded, and managed.
"""
def fit(self, data_dictionary: Dict, dk: FreqaiDataKitchen, **kwargs) -> Any:
"""
User sets up the training and test data to fit their desired model here
:param data_dictionary: the dictionary constructed by DataHandler to hold
all the training and test data/labels.
"""
xgb = XGBRegressor(**self.model_training_parameters)
X = data_dictionary["train_features"]
y = data_dictionary["train_labels"]
sample_weight = data_dictionary["train_weights"]
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)
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