nkululeko 0.93.9__tar.gz → 0.93.11__tar.gz

{nkululeko-0.93.9 → nkululeko-0.93.11}/CHANGELOG.md

@@ -1,6 +1,15 @@
 Changelog
 =========
 
+Version 0.93.11
+--------------
+* bugfix: silero segmenter assigned file duration values
+
+Version 0.93.10
+--------------
+* added nan check for imported features
+* added LOGO result output
+
 Version 0.93.9
 --------------
 * added manual seed to torch models

{nkululeko-0.93.9/nkululeko.egg-info → nkululeko-0.93.11}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: nkululeko
-Version: 0.93.9
+Version: 0.93.11
 Summary: Machine learning audio prediction experiments based on templates
 Home-page: https://github.com/felixbur/nkululeko
 Author: Felix Burkhardt
@@ -353,6 +353,15 @@ If you use it, please mention the Nkululeko paper:
 Changelog
 =========
 
+Version 0.93.11
+--------------
+* bugfix: silero segmenter assigned file duration values
+
+Version 0.93.10
+--------------
+* added nan check for imported features
+* added LOGO result output
+
 Version 0.93.9
 --------------
 * added manual seed to torch models

{nkululeko-0.93.9 → nkululeko-0.93.11}/nkululeko/constants.py

@@ -1,2 +1,2 @@
-VERSION="0.93.9"
+VERSION="0.93.11"
 SAMPLING_RATE = 16000

{nkululeko-0.93.9 → nkululeko-0.93.11}/nkululeko/feat_extract/feats_import.py

@@ -30,7 +30,7 @@ class ImportSet(Featureset):
                 "feature type == import needs import_file = ['file1', 'filex']"
             )
         except SyntaxError:
-            if type(feat_import_files) == str:
+            if type(feat_import_files) is str:
                 feat_import_files = [feat_import_files]
             else:
                 self.util.error(f"import_file is wrong: {feat_import_files}")
@@ -40,6 +40,11 @@ class ImportSet(Featureset):
             if not os.path.isfile(feat_import_file):
                 self.util.error(f"no import file: {feat_import_file}")
             df = audformat.utils.read_csv(feat_import_file)
+            if df.isnull().values.any():
+                self.util.warn(
+                    f"imported features contain {df.isna().sum()} NAN, filling with zero."
+                )
+                df = df.fillna(0)
             df = self.util.make_segmented_index(df)
             df = df[df.index.isin(self.data_df.index)]
             if import_files_append:

{nkululeko-0.93.9 → nkululeko-0.93.11}/nkululeko/models/model.py

@@ -171,6 +171,7 @@ class Model:
             f"LOGO: {self.logo} folds: mean {results.mean():.3f}, std:"
             f" {results.std():.3f}"
         )
+        report.print_logo(results)
 
     def train(self):
         """Train the model."""

{nkululeko-0.93.9 → nkululeko-0.93.11}/nkululeko/plots.py

@@ -628,8 +628,7 @@ class Plots:
         # one up because of the runs
         fig_dir = self.util.get_path("fig_dir") + "../"
         exp_name = self.util.get_exp_name(only_data=True)
-        format = self.util.config_val("PLOT", "format", "png")
-        filename = f"{fig_dir}{exp_name}EXPL_tree-plot.{format}"
+        filename = f"{fig_dir}{exp_name}EXPL_tree-plot.{self.format}"
         fig = ax.figure
         fig.savefig(filename)
         fig.clear()

{nkululeko-0.93.9 → nkululeko-0.93.11}/nkululeko/reporting/reporter.py

@@ -380,6 +380,18 @@ class Reporter:
     def set_filename_add(self, my_string):
         self.filenameadd = f"_{my_string}"
 
+    def print_logo(self, results):
+        res_dir = self.util.get_path("res_dir")
+        result_str = f"LOGO results: [{','.join(results.astype(str))}]"
+        file_name = f"{res_dir}/logo_results.txt"
+        with open(file_name, "w") as text_file:
+            text_file.write(
+                f"LOGO: mean {results.mean():.3f},  std: " + f"{results.std():.3f}"
+            )
+            text_file.write("\n")
+            text_file.write(result_str)
+        self.util.debug(result_str)
+
     def print_results(self, epoch=None):
         if epoch is None:
             epoch = self.epoch

{nkululeko-0.93.9 → nkululeko-0.93.11}/nkululeko/segment.py

@@ -62,6 +62,11 @@ def main():
     expr.fill_train_and_tests()
     util.debug(f"train shape : {expr.df_train.shape}, test shape:{expr.df_test.shape}")
 
+    def calc_dur(x):
+        starts = x[1]
+        ends = x[2]
+        return (ends - starts).total_seconds()
+
     # segment
     segmented_file = util.config_val("SEGMENT", "result", "segmented.csv")
 
@@ -104,16 +109,11 @@ def main():
             df_seg = df_seg.drop(columns=[target])
             df_seg = df_seg.rename(columns={"class_label": target})
         # save file
+        df_seg["duration"] = df_seg.index.to_series().map(lambda x: calc_dur(x))
         df_seg.to_csv(f"{expr.data_dir}/{segmented_file}")
 
-    def calc_dur(x):
-        starts = x[1]
-        ends = x[2]
-        return (ends - starts).total_seconds()
-
     if "duration" not in df.columns:
         df["duration"] = df.index.to_series().map(lambda x: calc_dur(x))
-    df_seg["duration"] = df_seg.index.to_series().map(lambda x: calc_dur(x))
     num_before = df.shape[0]
     num_after = df_seg.shape[0]
     util.debug(

{nkululeko-0.93.9 → nkululeko-0.93.11/nkululeko.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: nkululeko
-Version: 0.93.9
+Version: 0.93.11
 Summary: Machine learning audio prediction experiments based on templates
 Home-page: https://github.com/felixbur/nkululeko
 Author: Felix Burkhardt
@@ -353,6 +353,15 @@ If you use it, please mention the Nkululeko paper:
 Changelog
 =========
 
+Version 0.93.11
+--------------
+* bugfix: silero segmenter assigned file duration values
+
+Version 0.93.10
+--------------
+* added nan check for imported features
+* added LOGO result output
+
 Version 0.93.9
 --------------
 * added manual seed to torch models