add noise feature, improve docstrings

freqtrade/freqai/data_kitchen.py

@@ -821,6 +821,17 @@ class FreqaiDataKitchen:
         self.data_dictionary[f'{set_}_features'] = features.iloc[no_prev_pts:]
         self.data_dictionary[f'{set_}_labels'] = labels.iloc[no_prev_pts:]
 
+    def add_noise_to_training_features(self) -> None:
+        """
+        Add noise to train features to reduce the risk of overfitting.
+        """
+        mu = 0  # no shift
+        sigma = self.freqai_config["feature_parameters"]["noise_standard_deviation"]
+        compute_df = self.data_dictionary['train_features']
+        noise = np.random.normal(mu, sigma, [compute_df.shape[0], compute_df.shape[1]])
+        self.data_dictionary['train_features'] += noise
+        return
+
     def find_features(self, dataframe: DataFrame) -> None:
         """
         Find features in the strategy provided dataframe

freqtrade/freqai/freqai_interface.py

@@ -399,10 +399,9 @@ class IFreqaiModel(ABC):
 
     def data_cleaning_train(self, dk: FreqaiDataKitchen) -> None:
         """
-        Base data cleaning method for train
+        Base data cleaning method for train.
-        Any function inside this method should drop training data points from the filtered_dataframe
+        Functions here improve/modify the input data by identifying outliers,
-        based on user decided logic. See FreqaiDataKitchen::use_SVM_to_remove_outliers() for an
+        computing additional metrics, adding noise, reducing dimensionality etc.
-        example of how outlier data points are dropped from the dataframe used for training.
         """
 
         ft_params = self.freqai_info["feature_parameters"]
@@ -431,16 +430,13 @@ class IFreqaiModel(ABC):
             if self.freqai_info["data_split_parameters"]["test_size"] > 0:
                 dk.compute_inlier_metric(set_='test')
 
+        if self.freqai_info["feature_parameters"].get('noise_standard_deviation', 0):
+            dk.add_noise_to_training_features()
+
     def data_cleaning_predict(self, dk: FreqaiDataKitchen, dataframe: DataFrame) -> None:
         """
         Base data cleaning method for predict.
-        These functions each modify dk.do_predict, which is a dataframe with equal length
+        Functions here are complementary to the functions of data_cleaning_train.
-        to the number of candles coming from and returning to the strategy. Inside do_predict,
-         1 allows prediction and < 0 signals to the strategy that the model is not confident in
-         the prediction.
-         See FreqaiDataKitchen::remove_outliers() for an example
-        of how the do_predict vector is modified. do_predict is ultimately passed back to strategy
-        for buy signals.
         """
         ft_params = self.freqai_info["feature_parameters"]