nkululeko 0.45.0__tar.gz → 0.45.2__tar.gz

{nkululeko-0.45.0 → nkululeko-0.45.2}/CHANGELOG.md

@@ -6,6 +6,13 @@ Version 0.44.1
 * bugfixing: feature importance: https://github.com/felixbur/nkululeko/issues/23
 * bugfixing: loading csv database with filewise index https://github.com/felixbur/nkululeko/issues/24 
 
+Version 0.45.2
+--------------
+* added sample_selection for sample distribution plots
+
+Version 0.45.1
+--------------
+* fixed dataframe.append bug
 
 Version 0.45.0
 --------------

{nkululeko-0.45.0/nkululeko.egg-info → nkululeko-0.45.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: nkululeko
-Version: 0.45.0
+Version: 0.45.2
 Summary: Machine learning audio prediction experiments based on templates
 Home-page: https://github.com/felixbur/nkululeko
 Author: Felix Burkhardt
@@ -123,7 +123,6 @@ There's my [blog](http://blog.syntheticspeech.de/?s=nkululeko) with tutorials:
 * [Combine feature sets](http://blog.syntheticspeech.de/2022/06/30/how-to-combine-feature-sets-with-nkululeko/)
 * [Classifying continuous variables](http://blog.syntheticspeech.de/2022/01/26/nkululeko-classifying-continuous-variables/) 
 * [Try out / demo a trained model](http://blog.syntheticspeech.de/2022/01/24/nkululeko-try-out-demo-a-trained-model/) 
-* [Plot distributions of feature values](http://blog.syntheticspeech.de/2023/02/16/nkululeko-how-to-plot-distributions-of-feature-values/)
 * [Perform cross database experiments](http://blog.syntheticspeech.de/2021/10/05/nkululeko-perform-cross-database-experiments/)
 * [Meta parameter optimization](http://blog.syntheticspeech.de/2021/09/03/perform-optimization-with-nkululeko/)
 * [How to set up wav2vec embedding](http://blog.syntheticspeech.de/2021/12/03/how-to-set-up-wav2vec-embedding-for-nkululeko/)
@@ -217,6 +216,13 @@ Version 0.44.1
 * bugfixing: feature importance: https://github.com/felixbur/nkululeko/issues/23
 * bugfixing: loading csv database with filewise index https://github.com/felixbur/nkululeko/issues/24 
 
+Version 0.45.2
+--------------
+* added sample_selection for sample distribution plots
+
+Version 0.45.1
+--------------
+* fixed dataframe.append bug
 
 Version 0.45.0
 --------------

{nkululeko-0.45.0 → nkululeko-0.45.2}/README.md

@@ -107,7 +107,6 @@ There's my [blog](http://blog.syntheticspeech.de/?s=nkululeko) with tutorials:
 * [Combine feature sets](http://blog.syntheticspeech.de/2022/06/30/how-to-combine-feature-sets-with-nkululeko/)
 * [Classifying continuous variables](http://blog.syntheticspeech.de/2022/01/26/nkululeko-classifying-continuous-variables/) 
 * [Try out / demo a trained model](http://blog.syntheticspeech.de/2022/01/24/nkululeko-try-out-demo-a-trained-model/) 
-* [Plot distributions of feature values](http://blog.syntheticspeech.de/2023/02/16/nkululeko-how-to-plot-distributions-of-feature-values/)
 * [Perform cross database experiments](http://blog.syntheticspeech.de/2021/10/05/nkululeko-perform-cross-database-experiments/)
 * [Meta parameter optimization](http://blog.syntheticspeech.de/2021/09/03/perform-optimization-with-nkululeko/)
 * [How to set up wav2vec embedding](http://blog.syntheticspeech.de/2021/12/03/how-to-set-up-wav2vec-embedding-for-nkululeko/)

nkululeko-0.45.2/nkululeko/constants.py

@@ -0,0 +1 @@
+VERSION = '0.45.2'

{nkululeko-0.45.0 → nkululeko-0.45.2}/nkululeko/experiment.py

@@ -247,17 +247,20 @@ class Experiment:
     def plot_distribution(self):
         """Plot the distribution of samples and speaker per target class and biological sex"""
         plot = Plots()
-        if self.util.exp_is_classification():
-            # self.df_train['labels'] = self.label_encoder.inverse_transform(self.df_train[self.target])
-            # if self.df_test.is_labeled:
-            #     self.df_test['labels'] = self.label_encoder.inverse_transform(self.df_test[self.target])
-            if self.df_test.shape[0] > 0:
-                plot.describe_df('dev_set', self.df_test, self.target, f'test_distplot')
-            plot.describe_df('train_set', self.df_train, self.target, f'train_distplot')
+        sample_selection = self.util.config_val('EXPL', 'sample_selection', 'all')
+        if sample_selection=='all':
+            df_labels = pd.concat([self.df_train, self.df_test])
+            self.util.copy_flags(self.df_train, df_labels)
+        elif sample_selection=='train':
+            df_labels = self.df_train
+            self.util.copy_flags(self.df_train, df_labels)
+        elif sample_selection=='test':
+            df_labels = self.df_test
+            self.util.copy_flags(self.df_test, df_labels)
         else:
-            if self.df_test.shape[0] > 0:
-                plot.describe_df('dev_set', self.df_test, self.target, f'test_distplot')
-            plot.describe_df('train_set', self.df_train, self.target, f'train_distplot')
+            self.util.error(f'unkown sample selection specifier {sample_selection}, should be [all | train | test]')
+
+        plot.describe_df(f'{sample_selection}_set', df_labels, self.target, f'{sample_selection}_distplot')
 
     def extract_test_feats(self):
         self.feats_test = pd.DataFrame()
@@ -303,7 +306,7 @@ class Experiment:
     #     self.df_train = self.df_train.append(df_train_aug)
 
 
-    def analyse_features(self):
+    def analyse_features(self, needs_feats):
         """
         Do a feature exploration
         
@@ -311,7 +314,8 @@ class Experiment:
 
         if self.util.config_val('EXPL', 'value_counts', False):
             self.plot_distribution()
-
+        if not needs_feats:
+            return
         sample_selection = self.util.config_val('EXPL', 'sample_selection', 'False')
         if sample_selection=='all':
             df_feats = pd.concat([self.feats_train, self.feats_test])
@@ -325,7 +329,7 @@ class Experiment:
         elif sample_selection=='False':
             pass
         else:
-            self.util.error(f'unkown feature_distribution specifier {sample_selection}, should be [all | train | test]')
+            self.util.error(f'unkown sample selection specifier {sample_selection}, should be [all | train | test]')
         if sample_selection in ('all', 'train', 'test'):
             feat_analyser = FeatureAnalyser(sample_selection, df_labels, df_feats)        
             feat_analyser.analyse()
@@ -336,8 +340,8 @@ class Experiment:
             scatters = ast.literal_eval(glob_conf.config['EXPL']['scatter'])
             if self.util.exp_is_classification():
                 plots = Plots()
-                all_feats =self.feats_train.append(self.feats_test)
-                all_labels = self.df_train['class_label'].append(self.df_test['class_label'])
+                all_feats = pd.concat([self.feats_train, self.feats_test])
+                all_labels = pd.concat([self.df_train['class_label'], self.df_test['class_label']])
                 for scatter in scatters:
                     plots.scatter_plot(all_feats, all_labels, scatter)
             else:

{nkululeko-0.45.0 → nkululeko-0.45.2}/nkululeko/explore.py

@@ -42,12 +42,13 @@ def main(src_dir):
     scatter = eval(util.config_val('EXPL', 'scatter', 'False'))
     model_type = util.config_val('EXPL', 'model', False)
     plot_tree = eval(util.config_val('EXPL', 'plot_tree', 'False'))
+    needs_feats = False
     if plot_feats or tsne or scatter or model_type or plot_tree: 
         # these investigations need features to explore
         expr.extract_feats()
-
+        needs_feats = True
     # explore
-    expr.analyse_features()
+    expr.analyse_features(needs_feats)
 
     print('DONE')
 

{nkululeko-0.45.0 → nkululeko-0.45.2}/nkululeko/util.py

@@ -226,4 +226,9 @@ class Util:
         elif format == 'csv':
             return audformat.utils.read_csv(name)
         else:
-            self.error(f'unkown store format: {format}')
+            self.error(f'unkown store format: {format}')
+
+    def copy_flags(self, df_source, df_target):
+        df_target.is_labeled = df_source.is_labeled
+        df_target.got_gender = df_source.got_gender
+        df_target.got_speaker = df_source.got_speaker

{nkululeko-0.45.0 → nkululeko-0.45.2/nkululeko.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: nkululeko
-Version: 0.45.0
+Version: 0.45.2
 Summary: Machine learning audio prediction experiments based on templates
 Home-page: https://github.com/felixbur/nkululeko
 Author: Felix Burkhardt
@@ -123,7 +123,6 @@ There's my [blog](http://blog.syntheticspeech.de/?s=nkululeko) with tutorials:
 * [Combine feature sets](http://blog.syntheticspeech.de/2022/06/30/how-to-combine-feature-sets-with-nkululeko/)
 * [Classifying continuous variables](http://blog.syntheticspeech.de/2022/01/26/nkululeko-classifying-continuous-variables/) 
 * [Try out / demo a trained model](http://blog.syntheticspeech.de/2022/01/24/nkululeko-try-out-demo-a-trained-model/) 
-* [Plot distributions of feature values](http://blog.syntheticspeech.de/2023/02/16/nkululeko-how-to-plot-distributions-of-feature-values/)
 * [Perform cross database experiments](http://blog.syntheticspeech.de/2021/10/05/nkululeko-perform-cross-database-experiments/)
 * [Meta parameter optimization](http://blog.syntheticspeech.de/2021/09/03/perform-optimization-with-nkululeko/)
 * [How to set up wav2vec embedding](http://blog.syntheticspeech.de/2021/12/03/how-to-set-up-wav2vec-embedding-for-nkululeko/)
@@ -217,6 +216,13 @@ Version 0.44.1
 * bugfixing: feature importance: https://github.com/felixbur/nkululeko/issues/23
 * bugfixing: loading csv database with filewise index https://github.com/felixbur/nkululeko/issues/24 
 
+Version 0.45.2
+--------------
+* added sample_selection for sample distribution plots
+
+Version 0.45.1
+--------------
+* fixed dataframe.append bug
 
 Version 0.45.0
 --------------

{nkululeko-0.45.0 → nkululeko-0.45.2}/setup.cfg

@@ -1,6 +1,6 @@
 [metadata]
 name = nkululeko
-version = 0.45.0
+version = 0.45.2
 author = Felix Burkhardt
 author_email = fxburk@gmail.com
 description = Machine learning audio prediction experiments based on templates

nkululeko-0.45.0/nkululeko/constants.py

@@ -1 +0,0 @@
-VERSION = '0.45.0'