0.77.14

CHANGELOG.md

@@ -1,6 +1,10 @@
 Changelog
 =========
 
+Version 0.77.14
+--------------
+* fixed bug preventing bin scaling to work
+
 Version 0.77.13
 --------------
 * added bins scaler

nkululeko/constants.py

@@ -1,2 +1,2 @@
-VERSION="0.77.13"
+VERSION="0.77.14"
 SAMPLING_RATE = 16000

nkululeko/experiment.py

@@ -577,6 +577,9 @@ def _check_scale(self):
                 scale_feats,
             )
             self.feats_train, self.feats_test = self.scaler_feats.scale()
+            # store versions
+            self.util.save_to_store(self.feats_train, "feats_train_scaled")
+            self.util.save_to_store(self.feats_test, "feats_test_scaled")
 
     def init_runmanager(self):
         """Initialize the manager object for the runs."""

nkululeko/scaler.py

@@ -95,10 +95,12 @@ def bin_to_three(self):
             b2 = np.quantile(self.feats_train[c], 0.66)
             feats_bin_train[c] = self._bin(self.feats_train[c].values, b1, b2).values
             feats_bin_test[c] = self._bin(self.feats_test[c].values, b1, b2).values
+        self.feats_train = feats_bin_train
+        self.feats_test = feats_bin_test
 
     def _bin(self, series, b1, b2):
         bins = [-1000000, b1, b2, 1000000]
-        labels = ["low", "middle", "high"]
+        labels = [0, 0.5, 1]
         result = np.digitize(series, bins) - 1
         result = pd.Series(result)
         for i, l in enumerate(labels):

nkululeko/utils/util.py

@@ -307,7 +307,13 @@ def get_store(self, name, format):
         elif format == "csv":
             return audformat.utils.read_csv(name)
         else:
-            self.error(f"unkown store format: {format}")
+            self.error(f"unknown store format: {format}")
+
+    def save_to_store(self, df, name):
+        store = self.get_path("store")
+        store_format = self.config_val("FEATS", "store_format", "pkl")
+        storage = f"{store}{name}.{store_format}"
+        self.write_store(df, storage, store_format)
 
     def copy_flags(self, df_source, df_target):
         if hasattr(df_source, "is_labeled"):