Merge pull request #7508 from aemr3/fix-pca-errors
Fix feature list match for PCA
This commit is contained in:
parent
19b3669d97
commit
03256fc776
@ -92,7 +92,7 @@ class BaseClassifierModel(IFreqaiModel):
|
|||||||
filtered_df = dk.normalize_data_from_metadata(filtered_df)
|
filtered_df = dk.normalize_data_from_metadata(filtered_df)
|
||||||
dk.data_dictionary["prediction_features"] = filtered_df
|
dk.data_dictionary["prediction_features"] = filtered_df
|
||||||
|
|
||||||
self.data_cleaning_predict(dk, filtered_df)
|
self.data_cleaning_predict(dk)
|
||||||
|
|
||||||
predictions = self.model.predict(dk.data_dictionary["prediction_features"])
|
predictions = self.model.predict(dk.data_dictionary["prediction_features"])
|
||||||
pred_df = DataFrame(predictions, columns=dk.label_list)
|
pred_df = DataFrame(predictions, columns=dk.label_list)
|
||||||
|
@ -92,7 +92,7 @@ class BaseRegressionModel(IFreqaiModel):
|
|||||||
dk.data_dictionary["prediction_features"] = filtered_df
|
dk.data_dictionary["prediction_features"] = filtered_df
|
||||||
|
|
||||||
# optional additional data cleaning/analysis
|
# optional additional data cleaning/analysis
|
||||||
self.data_cleaning_predict(dk, filtered_df)
|
self.data_cleaning_predict(dk)
|
||||||
|
|
||||||
predictions = self.model.predict(dk.data_dictionary["prediction_features"])
|
predictions = self.model.predict(dk.data_dictionary["prediction_features"])
|
||||||
pred_df = DataFrame(predictions, columns=dk.label_list)
|
pred_df = DataFrame(predictions, columns=dk.label_list)
|
||||||
|
@ -423,7 +423,7 @@ class FreqaiDataDrawer:
|
|||||||
|
|
||||||
dk.data["data_path"] = str(dk.data_path)
|
dk.data["data_path"] = str(dk.data_path)
|
||||||
dk.data["model_filename"] = str(dk.model_filename)
|
dk.data["model_filename"] = str(dk.model_filename)
|
||||||
dk.data["training_features_list"] = list(dk.data_dictionary["train_features"].columns)
|
dk.data["training_features_list"] = dk.training_features_list
|
||||||
dk.data["label_list"] = dk.label_list
|
dk.data["label_list"] = dk.label_list
|
||||||
# store the metadata
|
# store the metadata
|
||||||
with open(save_path / f"{dk.model_filename}_metadata.json", "w") as fp:
|
with open(save_path / f"{dk.model_filename}_metadata.json", "w") as fp:
|
||||||
|
@ -881,6 +881,7 @@ class FreqaiDataKitchen:
|
|||||||
"""
|
"""
|
||||||
column_names = dataframe.columns
|
column_names = dataframe.columns
|
||||||
features = [c for c in column_names if "%" in c]
|
features = [c for c in column_names if "%" in c]
|
||||||
|
|
||||||
if not features:
|
if not features:
|
||||||
raise OperationalException("Could not find any features!")
|
raise OperationalException("Could not find any features!")
|
||||||
|
|
||||||
|
@ -275,7 +275,8 @@ class IFreqaiModel(ABC):
|
|||||||
|
|
||||||
if dk.check_if_backtest_prediction_exists():
|
if dk.check_if_backtest_prediction_exists():
|
||||||
self.dd.load_metadata(dk)
|
self.dd.load_metadata(dk)
|
||||||
self.check_if_feature_list_matches_strategy(dataframe_train, dk)
|
dk.find_features(dataframe_train)
|
||||||
|
self.check_if_feature_list_matches_strategy(dk)
|
||||||
append_df = dk.get_backtesting_prediction()
|
append_df = dk.get_backtesting_prediction()
|
||||||
dk.append_predictions(append_df)
|
dk.append_predictions(append_df)
|
||||||
else:
|
else:
|
||||||
@ -296,7 +297,6 @@ class IFreqaiModel(ABC):
|
|||||||
else:
|
else:
|
||||||
self.model = self.dd.load_data(pair, dk)
|
self.model = self.dd.load_data(pair, dk)
|
||||||
|
|
||||||
# self.check_if_feature_list_matches_strategy(dataframe_train, dk)
|
|
||||||
pred_df, do_preds = self.predict(dataframe_backtest, dk)
|
pred_df, do_preds = self.predict(dataframe_backtest, dk)
|
||||||
append_df = dk.get_predictions_to_append(pred_df, do_preds)
|
append_df = dk.get_predictions_to_append(pred_df, do_preds)
|
||||||
dk.append_predictions(append_df)
|
dk.append_predictions(append_df)
|
||||||
@ -420,7 +420,7 @@ class IFreqaiModel(ABC):
|
|||||||
return
|
return
|
||||||
|
|
||||||
def check_if_feature_list_matches_strategy(
|
def check_if_feature_list_matches_strategy(
|
||||||
self, dataframe: DataFrame, dk: FreqaiDataKitchen
|
self, dk: FreqaiDataKitchen
|
||||||
) -> None:
|
) -> None:
|
||||||
"""
|
"""
|
||||||
Ensure user is passing the proper feature set if they are reusing an `identifier` pointing
|
Ensure user is passing the proper feature set if they are reusing an `identifier` pointing
|
||||||
@ -429,11 +429,12 @@ class IFreqaiModel(ABC):
|
|||||||
:param dk: FreqaiDataKitchen = non-persistent data container/analyzer for
|
:param dk: FreqaiDataKitchen = non-persistent data container/analyzer for
|
||||||
current coin/bot loop
|
current coin/bot loop
|
||||||
"""
|
"""
|
||||||
dk.find_features(dataframe)
|
|
||||||
if "training_features_list_raw" in dk.data:
|
if "training_features_list_raw" in dk.data:
|
||||||
feature_list = dk.data["training_features_list_raw"]
|
feature_list = dk.data["training_features_list_raw"]
|
||||||
else:
|
else:
|
||||||
feature_list = dk.data['training_features_list']
|
feature_list = dk.data['training_features_list']
|
||||||
|
|
||||||
if dk.training_features_list != feature_list:
|
if dk.training_features_list != feature_list:
|
||||||
raise OperationalException(
|
raise OperationalException(
|
||||||
"Trying to access pretrained model with `identifier` "
|
"Trying to access pretrained model with `identifier` "
|
||||||
@ -481,13 +482,16 @@ class IFreqaiModel(ABC):
|
|||||||
if self.freqai_info["feature_parameters"].get('noise_standard_deviation', 0):
|
if self.freqai_info["feature_parameters"].get('noise_standard_deviation', 0):
|
||||||
dk.add_noise_to_training_features()
|
dk.add_noise_to_training_features()
|
||||||
|
|
||||||
def data_cleaning_predict(self, dk: FreqaiDataKitchen, dataframe: DataFrame) -> None:
|
def data_cleaning_predict(self, dk: FreqaiDataKitchen) -> None:
|
||||||
"""
|
"""
|
||||||
Base data cleaning method for predict.
|
Base data cleaning method for predict.
|
||||||
Functions here are complementary to the functions of data_cleaning_train.
|
Functions here are complementary to the functions of data_cleaning_train.
|
||||||
"""
|
"""
|
||||||
ft_params = self.freqai_info["feature_parameters"]
|
ft_params = self.freqai_info["feature_parameters"]
|
||||||
|
|
||||||
|
# ensure user is feeding the correct indicators to the model
|
||||||
|
self.check_if_feature_list_matches_strategy(dk)
|
||||||
|
|
||||||
if ft_params.get('inlier_metric_window', 0):
|
if ft_params.get('inlier_metric_window', 0):
|
||||||
dk.compute_inlier_metric(set_='predict')
|
dk.compute_inlier_metric(set_='predict')
|
||||||
|
|
||||||
@ -505,9 +509,6 @@ class IFreqaiModel(ABC):
|
|||||||
if ft_params.get("use_DBSCAN_to_remove_outliers", False):
|
if ft_params.get("use_DBSCAN_to_remove_outliers", False):
|
||||||
dk.use_DBSCAN_to_remove_outliers(predict=True)
|
dk.use_DBSCAN_to_remove_outliers(predict=True)
|
||||||
|
|
||||||
# ensure user is feeding the correct indicators to the model
|
|
||||||
self.check_if_feature_list_matches_strategy(dk.data_dictionary['prediction_features'], dk)
|
|
||||||
|
|
||||||
def model_exists(self, dk: FreqaiDataKitchen) -> bool:
|
def model_exists(self, dk: FreqaiDataKitchen) -> bool:
|
||||||
"""
|
"""
|
||||||
Given a pair and path, check if a model already exists
|
Given a pair and path, check if a model already exists
|
||||||
|
Loading…
Reference in New Issue
Block a user