fix outlier protection

This commit is contained in:
robcaulk 2022-08-28 12:11:29 +02:00
parent 22b42e91f3
commit 1e41c773a0
2 changed files with 15 additions and 15 deletions

View File

@ -113,7 +113,7 @@ Mandatory parameters are marked as **Required**, which means that they are requi
| `use_SVM_to_remove_outliers` | Train a support vector machine to detect and remove outliers from the training data set, as well as from incoming data points. See details about how it works [here](#removing-outliers-using-a-support-vector-machine-svm). <br> **Datatype:** Boolean. | `use_SVM_to_remove_outliers` | Train a support vector machine to detect and remove outliers from the training data set, as well as from incoming data points. See details about how it works [here](#removing-outliers-using-a-support-vector-machine-svm). <br> **Datatype:** Boolean.
| `svm_params` | All parameters available in Sklearn's `SGDOneClassSVM()`. See details about some select parameters [here](#removing-outliers-using-a-support-vector-machine-svm). <br> **Datatype:** Dictionary. | `svm_params` | All parameters available in Sklearn's `SGDOneClassSVM()`. See details about some select parameters [here](#removing-outliers-using-a-support-vector-machine-svm). <br> **Datatype:** Dictionary.
| `use_DBSCAN_to_remove_outliers` | Cluster data using DBSCAN to identify and remove outliers from training and prediction data. See details about how it works [here](#removing-outliers-with-dbscan). <br> **Datatype:** Boolean. | `use_DBSCAN_to_remove_outliers` | Cluster data using DBSCAN to identify and remove outliers from training and prediction data. See details about how it works [here](#removing-outliers-with-dbscan). <br> **Datatype:** Boolean.
| `outlier_protection_percentage` | If more than `outlier_protection_percentage` fraction of points are removed as outliers, FreqAI will log a warning message and ignore outlier detection while keeping the original dataset intact. <br> **Datatype:** float. Default: `0.3` | `outlier_protection_percentage` | If more than `outlier_protection_percentage` fraction of points are removed as outliers, FreqAI will log a warning message and ignore outlier detection while keeping the original dataset intact. <br> **Datatype:** float. Default: `30`
| | **Data split parameters** | | **Data split parameters**
| `data_split_parameters` | Include any additional parameters available from Scikit-learn `test_train_split()`, which are shown [here](https://scikit-learn.org/stable/modules/generated/sklearn.model_selection.train_test_split.html) (external website). <br> **Datatype:** Dictionary. | `data_split_parameters` | Include any additional parameters available from Scikit-learn `test_train_split()`, which are shown [here](https://scikit-learn.org/stable/modules/generated/sklearn.model_selection.train_test_split.html) (external website). <br> **Datatype:** Dictionary.
| `test_size` | Fraction of data that should be used for testing instead of training. <br> **Datatype:** Positive float < 1. | `test_size` | Fraction of data that should be used for testing instead of training. <br> **Datatype:** Positive float < 1.

View File

@ -519,7 +519,7 @@ class FreqaiDataKitchen:
""" """
outlier_protection_pct = self.freqai_config["feature_parameters"].get( outlier_protection_pct = self.freqai_config["feature_parameters"].get(
"outlier_protection_percentage", 30) "outlier_protection_percentage", 30)
outlier_pct = dropped_pts.sum() / len(dropped_pts) outlier_pct = (dropped_pts.sum() / len(dropped_pts)) * 100
if outlier_pct >= outlier_protection_pct: if outlier_pct >= outlier_protection_pct:
self.svm_model = None self.svm_model = None
return outlier_pct return outlier_pct
@ -563,12 +563,12 @@ class FreqaiDataKitchen:
self.data_dictionary["train_features"] self.data_dictionary["train_features"]
) )
y_pred = self.svm_model.predict(self.data_dictionary["train_features"]) y_pred = self.svm_model.predict(self.data_dictionary["train_features"])
dropped_points = np.where(y_pred == -1, 0, y_pred) kept_points = np.where(y_pred == -1, 0, y_pred)
# keep_index = np.where(y_pred == 1) # keep_index = np.where(y_pred == 1)
outlier_ptc = self.get_outlier_percentage(dropped_points) outlier_pct = self.get_outlier_percentage(1 - kept_points)
if outlier_ptc: if outlier_pct:
logger.warning( logger.warning(
f"SVM detected > {outlier_ptc}% of the points as outliers." f"SVM detected {outlier_pct:.2f}% of the points as outliers. "
f"Keeping original dataset." f"Keeping original dataset."
) )
return return
@ -584,7 +584,7 @@ class FreqaiDataKitchen:
] ]
logger.info( logger.info(
f"SVM tossed {len(y_pred) - dropped_points.sum()}" f"SVM tossed {len(y_pred) - kept_points.sum()}"
f" train points from {len(y_pred)} total points." f" train points from {len(y_pred)} total points."
) )
@ -593,7 +593,7 @@ class FreqaiDataKitchen:
# to reduce code duplication # to reduce code duplication
if self.freqai_config['data_split_parameters'].get('test_size', 0.1) != 0: if self.freqai_config['data_split_parameters'].get('test_size', 0.1) != 0:
y_pred = self.svm_model.predict(self.data_dictionary["test_features"]) y_pred = self.svm_model.predict(self.data_dictionary["test_features"])
dropped_points = np.where(y_pred == -1, 0, y_pred) kept_points = np.where(y_pred == -1, 0, y_pred)
self.data_dictionary["test_features"] = self.data_dictionary["test_features"][ self.data_dictionary["test_features"] = self.data_dictionary["test_features"][
(y_pred == 1) (y_pred == 1)
] ]
@ -604,7 +604,7 @@ class FreqaiDataKitchen:
] ]
logger.info( logger.info(
f"SVM tossed {len(y_pred) - dropped_points.sum()}" f"SVM tossed {len(y_pred) - kept_points.sum()}"
f" test points from {len(y_pred)} total points." f" test points from {len(y_pred)} total points."
) )
@ -688,10 +688,10 @@ class FreqaiDataKitchen:
self.data['DBSCAN_min_samples'] = MinPts self.data['DBSCAN_min_samples'] = MinPts
dropped_points = np.where(clustering.labels_ == -1, 1, 0) dropped_points = np.where(clustering.labels_ == -1, 1, 0)
outlier_ptc = self.get_outlier_percentage(dropped_points) outlier_pct = self.get_outlier_percentage(dropped_points)
if outlier_ptc: if outlier_pct:
logger.warning( logger.warning(
f"DBSCAN detected > {outlier_ptc}% of the points as outliers." f"DBSCAN detected {outlier_pct:.2f}% of the points as outliers. "
f"Keeping original dataset." f"Keeping original dataset."
) )
return return
@ -751,10 +751,10 @@ class FreqaiDataKitchen:
0, 0,
) )
outlier_ptc = self.get_outlier_percentage(1 - do_predict) outlier_pct = self.get_outlier_percentage(1 - do_predict)
if outlier_ptc: if outlier_pct:
logger.warning( logger.warning(
f"DI detected > {outlier_ptc}% of the points as outliers." f"DI detected {outlier_pct:.2f}% of the points as outliers. "
f"Keeping original dataset." f"Keeping original dataset."
) )
return return