CTYPTO/freqtrade
1
0
Fork 0
mirror of https://github.com/freqtrade/freqtrade.git synced 2025-12-19 06:11:15 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: ensure test_size=0 is still accommodated

Browse Source
This commit is contained in:
robcaulk
2023-06-17 15:39:33 +02:00
parent 447feb16b4
commit b0ab400ff3
5 changed files with 34 additions and 28 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
freqtrade/freqai/RL/BaseReinforcementLearningModel.py
View File

@@ -126,11 +126,12 @@ class BaseReinforcementLearningModel(IFreqaiModel):
dd["train_labels"],
dd["train_weights"])
(dd["test_features"],
dd["test_labels"],
dd["test_weights"]) = dk.feature_pipeline.transform(dd["test_features"],
dd["test_labels"],
dd["test_weights"])
if self.freqai_info.get('data_split_parameters', {}).get('test_size', 0.1) != 0:
(dd["test_features"],
dd["test_labels"],
dd["test_weights"]) = dk.feature_pipeline.transform(dd["test_features"],
dd["test_labels"],
dd["test_weights"])
logger.info(
f'Training model on {len(dk.data_dictionary["train_features"].columns)}'

11
freqtrade/freqai/base_models/BaseClassifierModel.py
View File

@@ -61,11 +61,12 @@ class BaseClassifierModel(IFreqaiModel):
dd["train_labels"],
dd["train_weights"])
(dd["test_features"],
dd["test_labels"],
dd["test_weights"]) = dk.feature_pipeline.transform(dd["test_features"],
dd["test_labels"],
dd["test_weights"])
if self.freqai_info.get('data_split_parameters', {}).get('test_size', 0.1) != 0:
(dd["test_features"],
dd["test_labels"],
dd["test_weights"]) = dk.feature_pipeline.transform(dd["test_features"],
dd["test_labels"],
dd["test_weights"])
logger.info(
f"Training model on {len(dk.data_dictionary['train_features'].columns)} features"

11
freqtrade/freqai/base_models/BasePyTorchClassifier.py
View File

@@ -197,11 +197,12 @@ class BasePyTorchClassifier(BasePyTorchModel):
dd["train_labels"],
dd["train_weights"])
(dd["test_features"],
dd["test_labels"],
dd["test_weights"]) = dk.feature_pipeline.transform(dd["test_features"],
dd["test_labels"],
dd["test_weights"])
if self.freqai_info.get('data_split_parameters', {}).get('test_size', 0.1) != 0:
(dd["test_features"],
dd["test_labels"],
dd["test_weights"]) = dk.feature_pipeline.transform(dd["test_features"],
dd["test_labels"],
dd["test_weights"])
logger.info(
f"Training model on {len(dk.data_dictionary['train_features'].columns)} features"

13
freqtrade/freqai/base_models/BasePyTorchRegressor.py
View File

@@ -96,12 +96,15 @@ class BasePyTorchRegressor(BasePyTorchModel):
dd["train_weights"]) = dk.feature_pipeline.fit_transform(dd["train_features"],
dd["train_labels"],
dd["train_weights"])
dd["train_labels"], _, _ = dk.label_pipeline.fit_transform(dd["train_labels"])
(dd["test_features"],
dd["test_labels"],
dd["test_weights"]) = dk.feature_pipeline.transform(dd["test_features"],
dd["test_labels"],
dd["test_weights"])
if self.freqai_info.get('data_split_parameters', {}).get('test_size', 0.1) != 0:
(dd["test_features"],
dd["test_labels"],
dd["test_weights"]) = dk.feature_pipeline.transform(dd["test_features"],
dd["test_labels"],
dd["test_weights"])
dd["test_labels"], _, _ = dk.label_pipeline.transform(dd["test_labels"])
logger.info(
f"Training model on {len(dk.data_dictionary['train_features'].columns)} features"

16
freqtrade/freqai/base_models/BaseRegressionModel.py
View File

@@ -60,15 +60,15 @@ class BaseRegressionModel(IFreqaiModel):
dd["train_weights"]) = dk.feature_pipeline.fit_transform(dd["train_features"],
dd["train_labels"],
dd["train_weights"])
(dd["test_features"],
dd["test_labels"],
dd["test_weights"]) = dk.feature_pipeline.transform(dd["test_features"],
dd["test_labels"],
dd["test_weights"])
dd["train_labels"], _, _ = dk.label_pipeline.fit_transform(dd["train_labels"])
dd["test_labels"], _, _ = dk.label_pipeline.transform(dd["test_labels"])
if self.freqai_info.get('data_split_parameters', {}).get('test_size', 0.1) != 0:
(dd["test_features"],
dd["test_labels"],
dd["test_weights"]) = dk.feature_pipeline.transform(dd["test_features"],
dd["test_labels"],
dd["test_weights"])
dd["test_labels"], _, _ = dk.label_pipeline.transform(dd["test_labels"])
logger.info(
f"Training model on {len(dk.data_dictionary['train_features'].columns)} features"