nkululeko 0.88.5__tar.gz → 0.88.6__tar.gz

{nkululeko-0.88.5 → nkululeko-0.88.6}/CHANGELOG.md

@@ -1,6 +1,10 @@
 Changelog
 =========
 
+Version 0.88.6
+--------------
+* added test speaker assign
+
 Version 0.88.5
 --------------
 * add a unique name to the uncertainty plot

{nkululeko-0.88.5/nkululeko.egg-info → nkululeko-0.88.6}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: nkululeko
-Version: 0.88.5
+Version: 0.88.6
 Summary: Machine learning audio prediction experiments based on templates
 Home-page: https://github.com/felixbur/nkululeko
 Author: Felix Burkhardt
@@ -360,6 +360,10 @@ F. Burkhardt, Johannes Wagner, Hagen Wierstorf, Florian Eyben and Björn Schulle
 Changelog
 =========
 
+Version 0.88.6
+--------------
+* added test speaker assign
+
 Version 0.88.5
 --------------
 * add a unique name to the uncertainty plot

{nkululeko-0.88.5 → nkululeko-0.88.6}/nkululeko/constants.py

@@ -1,2 +1,2 @@
-VERSION="0.88.5"
+VERSION="0.88.6"
 SAMPLING_RATE = 16000

{nkululeko-0.88.5 → nkululeko-0.88.6}/nkululeko/data/dataset.py

@@ -423,6 +423,9 @@ class Dataset:
             self.util.debug(f"{self.name}: trying to reuse data splits")
             self.df_test = pd.read_pickle(storage_test)
             self.df_train = pd.read_pickle(storage_train)
+        elif isinstance(ast.literal_eval(split_strategy), list):
+            # treat this as a list of test speakers
+            self.assign_speakers(ast.literal_eval(split_strategy))
         else:
             self.util.error(f"unknown split strategy: {split_strategy}")
 
@@ -515,6 +518,19 @@ class Dataset:
         # because this generates new train/test sample quantaties, the feature extraction has to be done again
         glob_conf.config["FEATS"]["needs_feature_extraction"] = "True"
 
+    def assign_speakers(self, speakers):
+        """One way to split train and eval sets: Specify test speaker names."""
+        self.df_test = self.df[self.df.speaker.isin(speakers)]
+        if len(self.df_test) == 0:
+            self.util.error(f"no speakers found in {speakers}")
+        self.df_train = self.df[~self.df.index.isin(self.df_test.index)]
+        self.util.debug(
+            f"{self.name} (speakers assigned): [{self.df_train.shape[0]}/{self.df_test.shape[0]}]"
+            " samples in train/test"
+        )
+        # because this generates new train/test sample quantaties, the feature extraction has to be done again
+        glob_conf.config["FEATS"]["needs_feature_extraction"] = "True"
+
     def split_speakers(self):
         """One way to split train and eval sets: Specify percentage of evaluation speakers"""
         test_percent = int(self.util.config_val_data(self.name, "test_size", 20))

{nkululeko-0.88.5 → nkululeko-0.88.6/nkululeko.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: nkululeko
-Version: 0.88.5
+Version: 0.88.6
 Summary: Machine learning audio prediction experiments based on templates
 Home-page: https://github.com/felixbur/nkululeko
 Author: Felix Burkhardt
@@ -360,6 +360,10 @@ F. Burkhardt, Johannes Wagner, Hagen Wierstorf, Florian Eyben and Björn Schulle
 Changelog
 =========
 
+Version 0.88.6
+--------------
+* added test speaker assign
+
 Version 0.88.5
 --------------
 * add a unique name to the uncertainty plot