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

allow user to pass test_size = 0 and avoid using eval sets in prediction models

Browse Source
This commit is contained in:
robcaulk 2022-07-25 19:40:13 +02:00
parent 55cf378ec2
commit 56b17e6f3c
4 changed files with 67 additions and 44 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
freqtrade/freqai/data_kitchen.py
View File

@ -243,6 +243,7 @@ class FreqaiDataKitchen:
else:
stratification = None
if self.freqai_config.get('data_split_parameters', {}).get('test_size', 0.1) != 0:
(
train_features,
test_features,
@ -257,6 +258,13 @@ class FreqaiDataKitchen:
stratify=stratification,
**self.config["freqai"]["data_split_parameters"],
)
else:
test_labels = np.zeros(2)
test_features = pd.DataFrame()
test_weights = np.zeros(2)
train_features = filtered_dataframe
train_labels = labels
train_weights = weights
return self.build_data_dictionary(
train_features, test_features, train_labels, test_labels, train_weights, test_weights
@ -392,6 +400,7 @@ class FreqaiDataKitchen:
/ (train_labels_max - train_labels_min)
- 1
)
if self.freqai_config.get('data_split_parameters', {}).get('test_size', 0.1) != 0:
data_dictionary["test_labels"][item] = (
2
* (data_dictionary["test_labels"][item] - train_labels_min)
@ -555,6 +564,7 @@ class FreqaiDataKitchen:
self.data["training_features_list_raw"] = copy.deepcopy(self.training_features_list)
self.training_features_list = self.data_dictionary["train_features"].columns
if self.freqai_config.get('data_split_parameters', {}).get('test_size', 0.1) != 0:
self.data_dictionary["test_features"] = pd.DataFrame(
data=test_components,
columns=["PC" + str(i) for i in range(0, n_keep_components)],
@ -652,12 +662,14 @@ class FreqaiDataKitchen:
)
# same for test data
if self.freqai_config.get('data_split_parameters', {}).get('test_size', 0.1) != 0:
y_pred = self.svm_model.predict(self.data_dictionary["test_features"])
dropped_points = np.where(y_pred == -1, 0, y_pred)
self.data_dictionary["test_features"] = self.data_dictionary["test_features"][
(y_pred == 1)
]
self.data_dictionary["test_labels"] = self.data_dictionary["test_labels"][(y_pred == 1)]
self.data_dictionary["test_labels"] = self.data_dictionary["test_labels"][(
y_pred == 1)]
self.data_dictionary["test_weights"] = self.data_dictionary["test_weights"][
(y_pred == 1)
]

7
freqtrade/freqai/prediction_models/CatboostPredictionModel.py
View File

@ -28,7 +28,9 @@ class CatboostPredictionModel(BaseRegressionModel):
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"],
@ -39,6 +41,9 @@ class CatboostPredictionModel(BaseRegressionModel):
allow_writing_files=False,
**self.model_training_parameters,
)
if self.freqai_info.get('data_split_parameters', {}).get('test_size', 0.1) == 0:
test_data = None
model.fit(X=train_data, eval_set=test_data)
return model

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

@ -36,6 +36,8 @@ class CatboostPredictionMultiModel(BaseRegressionModel):
model = MultiOutputRegressor(estimator=cbr)
model.fit(X=X, y=y, sample_weight=sample_weight) # , eval_set=eval_set)
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}")

4
freqtrade/freqai/prediction_models/LightGBMPredictionModel.py
View File

@ -25,11 +25,15 @@ class LightGBMPredictionModel(BaseRegressionModel):
all the training and test data/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"])
X = data_dictionary["train_features"]
y = data_dictionary["train_labels"]
model = LGBMRegressor(**self.model_training_parameters)
model.fit(X=X, y=y, eval_set=eval_set)
return model