nkululeko 0.93.10__py3-none-any.whl → 0.93.12__py3-none-any.whl

nkululeko/constants.py

@@ -1,2 +1,2 @@
-VERSION="0.93.10"
+VERSION="0.93.12"
 SAMPLING_RATE = 16000

nkululeko/data/dataset.py

@@ -34,9 +34,11 @@ class Dataset:
         self.plot = Plots()
         self.limit = int(self.util.config_val_data(self.name, "limit", 0))
         self.target_tables_append = eval(
-            self.util.config_val_data(self.name, "target_tables_append", "False")
+            self.util.config_val_data(
+                self.name, "target_tables_append", "False")
         )
-        self.start_fresh = eval(self.util.config_val("DATA", "no_reuse", "False"))
+        self.start_fresh = eval(
+            self.util.config_val("DATA", "no_reuse", "False"))
         self.is_labeled, self.got_speaker, self.got_gender, self.got_age = (
             False,
             False,
@@ -70,7 +72,8 @@ class Dataset:
         try:
             self.db = audformat.Database.load(root)
         except FileNotFoundError:
-            self.util.error(f"{self.name}: no audformat database found at {root}")
+            self.util.error(
+                f"{self.name}: no audformat database found at {root}")
         return root
 
     def _check_cols(self, df):
@@ -92,7 +95,8 @@ class Dataset:
         )
         self.util.debug(r_string)
         if glob_conf.report.initial:
-            glob_conf.report.add_item(ReportItem("Data", "Load report", r_string))
+            glob_conf.report.add_item(ReportItem(
+                "Data", "Load report", r_string))
             glob_conf.report.initial = False
 
     def load(self):
@@ -103,7 +107,8 @@ class Dataset:
         store_file = f"{store}{self.name}.{store_format}"
         self.root = self._load_db()
         if not self.start_fresh and os.path.isfile(store_file):
-            self.util.debug(f"{self.name}: reusing previously stored file {store_file}")
+            self.util.debug(
+                f"{self.name}: reusing previously stored file {store_file}")
             self.df = self.util.get_store(store_file, store_format)
             self.is_labeled = self.target in self.df
             self.got_gender = "gender" in self.df
@@ -118,10 +123,12 @@ class Dataset:
         # map the audio file paths
         self.db.map_files(lambda x: os.path.join(self.root, x))
         # the dataframes (potentially more than one) with at least the file names
-        df_files = self.util.config_val_data(self.name, "files_tables", "['files']")
+        df_files = self.util.config_val_data(
+            self.name, "files_tables", "['files']")
         df_files_tables = ast.literal_eval(df_files)
         # The label for the target column
-        self.col_label = self.util.config_val_data(self.name, "label", self.target)
+        self.col_label = self.util.config_val_data(
+            self.name, "label", self.target)
         (
             df,
             self.is_labeled,
@@ -157,7 +164,8 @@ class Dataset:
                 self.got_age = got_age2 or self.got_age
                 if audformat.is_filewise_index(df_target.index):
                     try:
-                        df_target = df_target.loc[df.index.get_level_values("file")]
+                        df_target = df_target.loc[df.index.get_level_values(
+                            "file")]
                         df_target = df_target.set_index(df.index)
                     except KeyError:
                         # just a try...
@@ -206,7 +214,8 @@ class Dataset:
             end = self.df.index.get_level_values(2)
             self.df["duration"] = (end - start).total_seconds()
         elif self.df.duration.dtype == "timedelta64[ns]":
-            self.df["duration"] = self.df["duration"].map(lambda x: x.total_seconds())
+            self.df["duration"] = self.df["duration"].map(
+                lambda x: x.total_seconds())
         # Perform some filtering if desired
         required = self.util.config_val_data(self.name, "required", False)
         if required:
@@ -236,15 +245,18 @@ class Dataset:
                 res.append(abs(n - max))
             return res
 
-        reverse = eval(self.util.config_val_data(self.name, "reverse", "False"))
+        reverse = eval(self.util.config_val_data(
+            self.name, "reverse", "False"))
         if reverse:
-            max = eval(self.util.config_val_data(self.name, "reverse.max", "False"))
+            max = eval(self.util.config_val_data(
+                self.name, "reverse.max", "False"))
             if max:
                 max = float(max)
             else:
                 max = self.df[self.target].values.max()
             self.util.debug(f"reversing target numbers with max values: {max}")
-            self.df[self.target] = reverse_array(self.df[self.target].values, max)
+            self.df[self.target] = reverse_array(
+                self.df[self.target].values, max)
 
         # check if the target variable should be scaled (z-transformed)
         scale = self.util.config_val_data(self.name, "scale", False)
@@ -317,13 +329,15 @@ class Dataset:
                 pass
             try:
                 # also it might be possible that the age is part of the speaker description
-                df_local["age"] = db[table]["speaker"].get(map="age").astype(int)
+                df_local["age"] = db[table]["speaker"].get(
+                    map="age").astype(int)
                 got_age = True
             except (ValueError, audformat.errors.BadKeyError):
                 pass
             try:
                 # same for the target, e.g. "age"
-                df_local[self.target] = db[table]["speaker"].get(map=self.target)
+                df_local[self.target] = db[table]["speaker"].get(
+                    map=self.target)
                 is_labeled = True
             except (ValueError, audformat.core.errors.BadKeyError):
                 pass
@@ -384,8 +398,10 @@ class Dataset:
             testdf = self.db.tables[self.target + ".test"].df
             traindf = self.db.tables[self.target + ".train"].df
             # use only the train and test samples that were not perhaps filtered out by an earlier processing step
-            self.df_test = self.df.loc[self.df.index.intersection(testdf.index)]
-            self.df_train = self.df.loc[self.df.index.intersection(traindf.index)]
+            self.df_test = self.df.loc[self.df.index.intersection(
+                testdf.index)]
+            self.df_train = self.df.loc[self.df.index.intersection(
+                traindf.index)]
         elif split_strategy == "train":
             self.df_train = self.df
             self.df_test = pd.DataFrame()
@@ -408,18 +424,23 @@ class Dataset:
             if entry_train_tables:
                 train_tables = ast.literal_eval(entry_train_tables)
                 for train_table in train_tables:
-                    traindf = pd.concat([traindf, self.db.tables[train_table].df])
+                    traindf = pd.concat(
+                        [traindf, self.db.tables[train_table].df])
             # use only the train and test samples that were not perhaps filtered out by an earlier processing step
             # testdf.index.map(lambda x: os.path.join(self.root, x))
             #            testdf.index = testdf.index.to_series().apply(lambda x: self.root+x)
             testdf = testdf.set_index(
-                audformat.utils.to_segmented_index(testdf.index, allow_nat=False)
+                audformat.utils.to_segmented_index(
+                    testdf.index, allow_nat=False)
             )
             traindf = traindf.set_index(
-                audformat.utils.to_segmented_index(traindf.index, allow_nat=False)
+                audformat.utils.to_segmented_index(
+                    traindf.index, allow_nat=False)
             )
-            self.df_test = self.df.loc[self.df.index.intersection(testdf.index)]
-            self.df_train = self.df.loc[self.df.index.intersection(traindf.index)]
+            self.df_test = self.df.loc[self.df.index.intersection(
+                testdf.index)]
+            self.df_train = self.df.loc[self.df.index.intersection(
+                traindf.index)]
             # it might be necessary to copy the target values
             try:
                 self.df_test[self.target] = testdf[self.target]
@@ -446,10 +467,12 @@ class Dataset:
             self.util.error(f"unknown split strategy: {split_strategy}")
 
         # check if train or test set should be ignored
-        as_test = eval(self.util.config_val_data(self.name, "as_test", "False"))
+        as_test = eval(self.util.config_val_data(
+            self.name, "as_test", "False"))
         if as_test:
             self.df_train = pd.DataFrame()
-        as_train = eval(self.util.config_val_data(self.name, "as_train", "False"))
+        as_train = eval(self.util.config_val_data(
+            self.name, "as_train", "False"))
         if as_train:
             self.df_test = pd.DataFrame()
 
@@ -480,7 +503,8 @@ class Dataset:
 
         seed = 42
         k = 30
-        test_size = int(self.util.config_val_data(self.name, "test_size", 20)) / 100.0
+        test_size = int(self.util.config_val_data(
+            self.name, "test_size", 20)) / 100.0
         df = self.df
         # split target
         targets = df[self.target].to_numpy()
@@ -496,7 +520,8 @@ class Dataset:
         stratif_vars = self.util.config_val("DATA", "balance", False)
         stratif_vars_array = {}
         if not stratif_vars:
-            self.util.error("balanced split needs stratif_vars to stratify the splits")
+            self.util.error(
+                "balanced split needs stratif_vars to stratify the splits")
         else:
             stratif_vars = ast.literal_eval(stratif_vars)
             for stratif_var in stratif_vars.keys():
@@ -505,7 +530,8 @@ class Dataset:
                     continue
                 else:
                     data = df[stratif_var].to_numpy()
-                    bins = self.util.config_val("DATA", f"{stratif_var}_bins", False)
+                    bins = self.util.config_val(
+                        "DATA", f"{stratif_var}_bins", False)
                     if bins:
                         data = binning(data, nbins=int(bins))
                     stratif_vars_array[stratif_var] = data
@@ -556,7 +582,8 @@ class Dataset:
 
     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))
+        test_percent = int(self.util.config_val_data(
+            self.name, "test_size", 20))
         df = self.df
         s_num = df.speaker.nunique()
         test_num = int(s_num * (test_percent / 100))
@@ -575,7 +602,8 @@ class Dataset:
 
     def random_split(self):
         """One way to split train and eval sets: Specify percentage of random samples"""
-        test_percent = int(self.util.config_val_data(self.name, "test_size", 20))
+        test_percent = int(self.util.config_val_data(
+            self.name, "test_size", 20))
         df = self.df
         s_num = len(df)
         test_num = int(s_num * (test_percent / 100))
@@ -676,8 +704,11 @@ class Dataset:
 
     def map_continuous_classification(self, df):
         """Map labels to bins for continuous data that should be classified"""
+        if df.empty:
+            return
         if self.check_continuous_classification():
-            self.util.debug(f"{self.name}: binning continuous variable to categories")
+            self.util.debug(
+                f"{self.name}: binning continuous variable to categories")
             cat_vals = self.util.continuous_to_categorical(df[self.target])
             df[self.target] = cat_vals.values
             labels = ast.literal_eval(glob_conf.config["DATA"]["labels"])

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/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-0.93.10.dist-info → nkululeko-0.93.12.dist-info}/METADATA

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.2
 Name: nkululeko
-Version: 0.93.10
+Version: 0.93.12
 Summary: Machine learning audio prediction experiments based on templates
 Home-page: https://github.com/felixbur/nkululeko
 Author: Felix Burkhardt
@@ -63,7 +63,7 @@ Requires-Dist: pylatex
 ## Overview
 A project to detect speaker characteristics by machine learning experiments with a high-level interface.
 
-The idea is to have a framework (based on e.g. sklearn and torch) that can be used to rapidly and automatically analyse audio data and explore machine learning models based on that data.
+The idea is to have a framework (based on e.g. sklearn and torch) that can be used to rapidly and automatically analyse audio data and explore machine learning models based on that data. 
 
 * NEW with nkululeko: [Ensemble learning](http://blog.syntheticspeech.de/2024/06/25/nkululeko-ensemble-classifiers-with-late-fusion/)
 * NEW: [Finetune transformer-models](http://blog.syntheticspeech.de/2024/05/29/nkululeko-how-to-finetune-a-transformer-model/)
@@ -353,8 +353,16 @@ If you use it, please mention the Nkululeko paper:
 Changelog
 =========
 
+Version 0.93.12
+---------------
+* bugfix: map_continuous_to_cat crashed on empty data
+
+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
 

{nkululeko-0.93.10.dist-info → nkululeko-0.93.12.dist-info}/RECORD

@@ -2,7 +2,7 @@ nkululeko/__init__.py,sha256=62f8HiEzJ8rG2QlTFJXUCMpvuH3fKI33DoJSj33mscc,63
 nkululeko/aug_train.py,sha256=FoMbBrfyOZd4QAw7oIHl3X6-UpsqAKWVDIolCA7qOWs,3196
 nkululeko/augment.py,sha256=3RzaxB3gRxovgJVjHXi0glprW01J7RaHhUkqotW2T3U,2955
 nkululeko/cacheddataset.py,sha256=XFpWZmbJRg0pvhnIgYf0TkclxllD-Fctu-Ol0PF_00c,969
-nkululeko/constants.py,sha256=0grSx0I2K13N--2KpgQU90VQf94GJLPJXHFLbHVPDjI,40
+nkululeko/constants.py,sha256=T9YZzqdg_ltKpuIf2XZdrqFmmlZQmhak97DpM5GQQhI,40
 nkululeko/demo-ft.py,sha256=iD9Pzp9QjyAv31q1cDZ75vPez7Ve8A4Cfukv5yfZdrQ,770
 nkululeko/demo.py,sha256=4Yzhg6pCPBYPGJrP7JX2TysVosl_R1llpVDKc2P_gUA,4955
 nkululeko/demo_feats.py,sha256=BvZjeNFTlERIRlq34OHM4Z96jdDQAhB01BGQAUcX9dM,2026
@@ -20,12 +20,12 @@ nkululeko/modelrunner.py,sha256=lJy-xM4QfDDWeL0dLTE_VIb4sYrnd_Z_yJRK3wwohQA,1119
 nkululeko/multidb.py,sha256=sO6OwJn8sn1-C-ig3thsIL8QMWHdV9SnJhDodKjeKrI,6876
 nkululeko/nkuluflag.py,sha256=PGWSmZz-PiiHLgcZJAoGOI_Y-sZDVI1ksB8p5r7riWM,3725
 nkululeko/nkululeko.py,sha256=M7baIq2nAoi6dEoBL4ATEuqAs5U1fvl_hyqAl5DybAQ,2040
-nkululeko/plots.py,sha256=zHWZ8Ns_0SLOEdbDVulObpRPoXRw_qqPXJv2dM08EeE,26049
+nkululeko/plots.py,sha256=Mm30pDLBb55iE9SYaSg76KFBKnebZTlypFQIBo26wuY,25991
 nkululeko/predict.py,sha256=MLnHEyFmSiHLLs-HDczag8Vu3zKF5T1rXLKdZZJ6py8,2083
 nkululeko/resample.py,sha256=rn3-M1A-iwVGibfQNGyeYNa7briD24lIN9Szq_1uTJo,5194
 nkululeko/runmanager.py,sha256=AswmORVUkCIH0gTx6zEyufvFATQBS8C5TXo2erSNdVg,7611
 nkululeko/scaler.py,sha256=7VOZ4sREMoQtahfETt9RyuR29Fb7PCwxlYVjBbdCVFc,4101
-nkululeko/segment.py,sha256=DRjC6b7SeInYgwBcDPXpTXPvXPS-J8kFQO7H095bK80,4945
+nkululeko/segment.py,sha256=7UrJEwdLmh9wDL5iBwpdJyJm9dwSxidHrHt-_D2qtxw,4949
 nkululeko/syllable_nuclei.py,sha256=5w_naKxNxz66a_qLkraemi2fggM-gWesiiBPS47iFcE,9931
 nkululeko/test.py,sha256=1w624vo5KTzmFC8BUStGlLDmIEAFuJUz7J0W-gp7AxI,1677
 nkululeko/test_predictor.py,sha256=DEHE_D3A6m6KJTrpDKceA1n655t_UZV3WQd57K4a3Ho,2863
@@ -49,7 +49,7 @@ nkululeko/autopredict/ap_stoi.py,sha256=UEQg1ZV0meAsxgdWB8ieRs9GPXHqArmsaOyCGRwp
 nkululeko/autopredict/ap_valence.py,sha256=WrW4Ltqi_odW49_4QEVKkfnrcztLIVZ4cXIEHu4dBN8,1026
 nkululeko/autopredict/estimate_snr.py,sha256=1k9-XadABudnsNOeFZD_Fg0E64-GUQVS7JEp82MLQS4,4995
 nkululeko/data/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-nkululeko/data/dataset.py,sha256=G4jzD2MvzB7d6Oja_pUIdShFr7Qsbs0ogGzuTcyQfLo,30041
+nkululeko/data/dataset.py,sha256=H65rvQ8sPwEwv_T-FqOEa7FeQ3JBn88v3xOzBOjARe4,30582
 nkululeko/data/dataset_csv.py,sha256=p2b4eS5R2Q5zdOIc56NRRU2PTFXSRt0qrdHGafHkWKo,4830
 nkululeko/feat_extract/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nkululeko/feat_extract/feats_agender.py,sha256=onfAQ6-xx_mFMJXEF1IX8cHBmGtGeX6weJmxbkfh1_o,3184
@@ -112,9 +112,9 @@ nkululeko/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nkululeko/utils/files.py,sha256=SrrYaU7AB80MZHiV1jcB0h_zigvYLYgSVNTXV4ao38g,4593
 nkululeko/utils/stats.py,sha256=vCRzhCR0Gx5SiJyAGbj1TIto8ocGz58CM5Pr3LltagA,2948
 nkululeko/utils/util.py,sha256=wFDslqxpCVDwi6LBakIFDDy1kYsxt5G7ykE38CocmtA,16880
-nkululeko-0.93.10.dist-info/LICENSE,sha256=0zGP5B_W35yAcGfHPS18Q2B8UhvLRY3dQq1MhpsJU_U,1076
-nkululeko-0.93.10.dist-info/METADATA,sha256=vO975smqhzWtD-pm5SqiEqJV6RBxPy4UTHxGz4d6Ta4,42644
-nkululeko-0.93.10.dist-info/WHEEL,sha256=PZUExdf71Ui_so67QXpySuHtCi3-J3wvF4ORK6k_S8U,91
-nkululeko-0.93.10.dist-info/entry_points.txt,sha256=lNTkFEdh6Kjo5o95ZAWf_0Lq-4ztGoAoMVSDuPtuyS0,442
-nkululeko-0.93.10.dist-info/top_level.txt,sha256=DPFNNSHPjUeVKj44dVANAjuVGRCC3MusJ08lc2a8xFA,10
-nkululeko-0.93.10.dist-info/RECORD,,
+nkululeko-0.93.12.dist-info/LICENSE,sha256=0zGP5B_W35yAcGfHPS18Q2B8UhvLRY3dQq1MhpsJU_U,1076
+nkululeko-0.93.12.dist-info/METADATA,sha256=jjO-vG0POWF3v_v3QfliA4uT8jzZPikwmEj2O6v6rhg,42823
+nkululeko-0.93.12.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
+nkululeko-0.93.12.dist-info/entry_points.txt,sha256=lNTkFEdh6Kjo5o95ZAWf_0Lq-4ztGoAoMVSDuPtuyS0,442
+nkululeko-0.93.12.dist-info/top_level.txt,sha256=DPFNNSHPjUeVKj44dVANAjuVGRCC3MusJ08lc2a8xFA,10
+nkululeko-0.93.12.dist-info/RECORD,,

{nkululeko-0.93.10.dist-info → nkululeko-0.93.12.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (75.6.0)
+Generator: setuptools (75.8.0)
 Root-Is-Purelib: true
 Tag: py3-none-any