add noise feature, improve docstrings

freqtrade/freqai/data_kitchen.py

@@ -655,6 +655,114 @@ class FreqaiDataKitchen:
 
         return
 
+    def compute_inlier_metric(self, set_='train') -> None:
+        """
+
+        Compute inlier metric from backwards distance distributions.
+        This metric defines how well features from a timepoint fit
+        into previous timepoints.
+        """
+
+        import scipy.stats as ss
+
+        no_prev_pts = self.freqai_config["feature_parameters"]["inlier_metric_window"]
+        weib_pct = self.freqai_config["feature_parameters"]["inlier_metric_weibull_cutoff"]
+
+        if set_ == 'train':
+            compute_df = copy.deepcopy(self.data_dictionary['train_features'])
+        elif set_ == 'test':
+            compute_df = copy.deepcopy(self.data_dictionary['test_features'])
+        else:
+            compute_df = copy.deepcopy(self.data_dictionary['prediction_features'])
+
+        compute_df_reindexed = compute_df.reindex(
+            index=np.flip(compute_df.index)
+        )
+
+        pairwise = pd.DataFrame(
+            np.triu(
+                pairwise_distances(compute_df_reindexed, n_jobs=self.thread_count)
+            ),
+            columns=compute_df_reindexed.index,
+            index=compute_df_reindexed.index
+        )
+        pairwise = pairwise.round(5)
+
+        column_labels = [
+            '{}{}'.format('d', i) for i in range(1, no_prev_pts + 1)
+        ]
+        distances = pd.DataFrame(
+            columns=column_labels, index=compute_df.index
+        )
+
+        for index in compute_df.index[no_prev_pts:]:
+            current_row = pairwise.loc[[index]]
+            current_row_no_zeros = current_row.loc[
+                :, (current_row != 0).any(axis=0)
+            ]
+            distances.loc[[index]] = current_row_no_zeros.iloc[
+                :, :no_prev_pts
+            ]
+        distances = distances.replace([np.inf, -np.inf], np.nan)
+        drop_index = pd.isnull(distances).any(1)
+        distances = distances[drop_index == 0]
+
+        inliers = pd.DataFrame(index=distances.index)
+        for key in distances.keys():
+            current_distances = distances[key].dropna()
+            fit_params = ss.weibull_min.fit(current_distances)
+            cutoff = ss.weibull_min.ppf(weib_pct, *fit_params)
+            is_inlier = np.where(
+                current_distances <= cutoff, 1, 0
+            )
+            df_inlier = pd.DataFrame(
+                {key + '_IsInlier': is_inlier}, index=distances.index
+            )
+            inliers = pd.concat(
+                [inliers, df_inlier], axis=1
+            )
+
+        inlier_metric = pd.DataFrame(
+            data=inliers.sum(axis=1) / no_prev_pts,
+            columns=['inlier_metric'],
+            index=compute_df.index
+        )
+
+        inlier_metric = 2 * (inlier_metric - inlier_metric.min()) / \
+            (inlier_metric.max() - inlier_metric.min()) - 1
+
+        if set_ in ('train', 'test'):
+            inlier_metric = inlier_metric.iloc[no_prev_pts:]
+            compute_df = compute_df.iloc[no_prev_pts:]
+            self.remove_beginning_points_from_data_dict(set_, no_prev_pts)
+            self.data_dictionary[f'{set_}_features'] = pd.concat(
+                [compute_df, inlier_metric], axis=1)
+        else:
+            self.data_dictionary['prediction_features'] = pd.concat(
+                [compute_df, inlier_metric], axis=1)
+            self.data_dictionary['prediction_features'].fillna(0, inplace=True)
+
+        return None
+
+    def remove_beginning_points_from_data_dict(self, set_='train', no_prev_pts: int = 10):
+        features = self.data_dictionary[f'{set_}_features']
+        weights = self.data_dictionary[f'{set_}_weights']
+        labels = self.data_dictionary[f'{set_}_labels']
+        self.data_dictionary[f'{set_}_weights'] = weights[no_prev_pts:]
+        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

@@ -66,7 +66,6 @@ class IFreqaiModel(ABC):
             "data_split_parameters", {})
         self.model_training_parameters: Dict[str, Any] = config.get("freqai", {}).get(
             "model_training_parameters", {})
-        self.feature_parameters = config.get("freqai", {}).get("feature_parameters")
         self.retrain = False
         self.first = True
         self.set_full_path()
@@ -74,11 +73,14 @@ class IFreqaiModel(ABC):
         self.dd = FreqaiDataDrawer(Path(self.full_path), self.config, self.follow_mode)
         self.identifier: str = self.freqai_info.get("identifier", "no_id_provided")
         self.scanning = False
+        self.ft_params = self.freqai_info["feature_parameters"]
         self.keras: bool = self.freqai_info.get("keras", False)
-        if self.keras and self.freqai_info.get("feature_parameters", {}).get("DI_threshold", 0):
-            self.freqai_info["feature_parameters"]["DI_threshold"] = 0
+        if self.keras and self.ft_params.get("DI_threshold", 0):
+            self.ft_params["DI_threshold"] = 0
             logger.warning("DI threshold is not configured for Keras models yet. Deactivating.")
         self.CONV_WIDTH = self.freqai_info.get("conv_width", 2)
+        if self.ft_params.get("inlier_metric_window", 0):
+            self.CONV_WIDTH = self.ft_params.get("inlier_metric_window", 0) * 2
         self.pair_it = 0
         self.total_pairs = len(self.config.get("exchange", {}).get("pair_whitelist"))
         self.last_trade_database_summary: DataFrame = {}
@@ -383,24 +385,25 @@ class IFreqaiModel(ABC):
 
     def data_cleaning_train(self, dk: FreqaiDataKitchen) -> None:
         """
-        Base data cleaning method for train
-        Any function inside this method should drop training data points from the filtered_dataframe
-        based on user decided logic. See FreqaiDataKitchen::use_SVM_to_remove_outliers() for an
-        example of how outlier data points are dropped from the dataframe used for training.
+        Base data cleaning method for train.
+        Functions here improve/modify the input data by identifying outliers,
+        computing additional metrics, adding noise, reducing dimensionality etc.
         """
 
-        if self.freqai_info["feature_parameters"].get(
+        ft_params = self.freqai_info["feature_parameters"]
+
+        if ft_params.get(
             "principal_component_analysis", False
         ):
             dk.principal_component_analysis()
 
-        if self.freqai_info["feature_parameters"].get("use_SVM_to_remove_outliers", False):
+        if ft_params.get("use_SVM_to_remove_outliers", False):
             dk.use_SVM_to_remove_outliers(predict=False)
 
-        if self.freqai_info["feature_parameters"].get("DI_threshold", 0):
+        if ft_params.get("DI_threshold", 0):
             dk.data["avg_mean_dist"] = dk.compute_distances()
 
-        if self.freqai_info["feature_parameters"].get("use_DBSCAN_to_remove_outliers", False):
+        if ft_params.get("use_DBSCAN_to_remove_outliers", False):
             if dk.pair in self.dd.old_DBSCAN_eps:
                 eps = self.dd.old_DBSCAN_eps[dk.pair]
             else:
@@ -408,29 +411,36 @@ class IFreqaiModel(ABC):
             dk.use_DBSCAN_to_remove_outliers(predict=False, eps=eps)
             self.dd.old_DBSCAN_eps[dk.pair] = dk.data['DBSCAN_eps']
 
+        if ft_params.get('inlier_metric_window', 0):
+            dk.compute_inlier_metric(set_='train')
+            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
-        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.
+        Functions here are complementary to the functions of data_cleaning_train.
         """
-        if self.freqai_info["feature_parameters"].get(
+        ft_params = self.freqai_info["feature_parameters"]
+
+        if ft_params.get('inlier_metric_window', 0):
+            dk.compute_inlier_metric(set_='predict')
+
+        if ft_params.get(
             "principal_component_analysis", False
         ):
             dk.pca_transform(dataframe)
 
-        if self.freqai_info["feature_parameters"].get("use_SVM_to_remove_outliers", False):
+        if ft_params.get("use_SVM_to_remove_outliers", False):
             dk.use_SVM_to_remove_outliers(predict=True)
 
-        if self.freqai_info["feature_parameters"].get("DI_threshold", 0):
+        if ft_params.get("DI_threshold", 0):
             dk.check_if_pred_in_training_spaces()
 
-        if self.freqai_info["feature_parameters"].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)
 
     def model_exists(