nkululeko 0.86.7__py3-none-any.whl → 0.86.8__py3-none-any.whl

nkululeko/constants.py

@@ -1,2 +1,2 @@
-VERSION="0.86.7"
+VERSION="0.86.8"
 SAMPLING_RATE = 16000

nkululeko/experiment.py

@@ -5,13 +5,13 @@ import pickle
 import random
 import time
 
+import audeer
+import audformat
 import numpy as np
 import pandas as pd
 from sklearn.preprocessing import LabelEncoder
 
-import audeer
-import audformat
-
+import nkululeko.glob_conf as glob_conf
 from nkululeko.data.dataset import Dataset
 from nkululeko.data.dataset_csv import Dataset_CSV
 from nkululeko.demo_predictor import Demo_predictor
@@ -19,8 +19,6 @@ from nkululeko.feat_extract.feats_analyser import FeatureAnalyser
 from nkululeko.feature_extractor import FeatureExtractor
 from nkululeko.file_checker import FileChecker
 from nkululeko.filter_data import DataFilter
-from nkululeko.filter_data import filter_min_dur
-import nkululeko.glob_conf as glob_conf
 from nkululeko.plots import Plots
 from nkululeko.reporting.report import Report
 from nkululeko.runmanager import Runmanager
@@ -109,7 +107,8 @@ class Experiment:
         # print keys/column
         dbs = ",".join(list(self.datasets.keys()))
         labels = self.util.config_val("DATA", "labels", False)
-        auto_labels = list(next(iter(self.datasets.values())).df[self.target].unique())
+        auto_labels = list(
+            next(iter(self.datasets.values())).df[self.target].unique())
         if labels:
             self.labels = ast.literal_eval(labels)
             self.util.debug(f"Using target labels (from config): {labels}")
@@ -159,7 +158,8 @@ class Experiment:
                 data.split()
                 data.prepare_labels()
                 self.df_test = pd.concat(
-                    [self.df_test, self.util.make_segmented_index(data.df_test)]
+                    [self.df_test, self.util.make_segmented_index(
+                        data.df_test)]
                 )
                 self.df_test.is_labeled = data.is_labeled
             self.df_test.got_gender = self.got_gender
@@ -260,7 +260,8 @@ class Experiment:
                     test_cats = self.df_test[self.target].unique()
                 else:
                     # if there is no target, copy a dummy label
-                    self.df_test = self._add_random_target(self.df_test).astype("str")
+                    self.df_test = self._add_random_target(
+                        self.df_test).astype("str")
                 train_cats = self.df_train[self.target].unique()
                 # print(f"df_train: {pd.DataFrame(self.df_train[self.target])}")
                 # print(f"train_cats with target {self.target}: {train_cats}")
@@ -268,7 +269,8 @@ class Experiment:
                 if type(test_cats) == np.ndarray:
                     self.util.debug(f"Categories test (nd.array): {test_cats}")
                 else:
-                    self.util.debug(f"Categories test (list): {list(test_cats)}")
+                    self.util.debug(
+                        f"Categories test (list): {list(test_cats)}")
             if type(train_cats) == np.ndarray:
                 self.util.debug(f"Categories train (nd.array): {train_cats}")
             else:
@@ -291,7 +293,8 @@ class Experiment:
 
         target_factor = self.util.config_val("DATA", "target_divide_by", False)
         if target_factor:
-            self.df_test[self.target] = self.df_test[self.target] / float(target_factor)
+            self.df_test[self.target] = self.df_test[self.target] / \
+                float(target_factor)
             self.df_train[self.target] = self.df_train[self.target] / float(
                 target_factor
             )
@@ -314,14 +317,16 @@ class Experiment:
     def plot_distribution(self, df_labels):
         """Plot the distribution of samples and speaker per target class and biological sex"""
         plot = Plots()
-        sample_selection = self.util.config_val("EXPL", "sample_selection", "all")
+        sample_selection = self.util.config_val(
+            "EXPL", "sample_selection", "all")
         plot.plot_distributions(df_labels)
         if self.got_speaker:
             plot.plot_distributions_speaker(df_labels)
 
     def extract_test_feats(self):
         self.feats_test = pd.DataFrame()
-        feats_name = "_".join(ast.literal_eval(glob_conf.config["DATA"]["tests"]))
+        feats_name = "_".join(ast.literal_eval(
+            glob_conf.config["DATA"]["tests"]))
         feats_types = self.util.config_val_list("FEATS", "type", ["os"])
         self.feature_extractor = FeatureExtractor(
             self.df_test, feats_types, feats_name, "test"
@@ -338,9 +343,17 @@ class Experiment:
 
         """
         df_train, df_test = self.df_train, self.df_test
-        feats_name = "_".join(ast.literal_eval(glob_conf.config["DATA"]["databases"]))
+        feats_name = "_".join(ast.literal_eval(
+            glob_conf.config["DATA"]["databases"]))
         self.feats_test, self.feats_train = pd.DataFrame(), pd.DataFrame()
-        feats_types = self.util.config_val_list("FEATS", "type", [])
+        feats_types = self.util.config_val("FEATS", "type", "os")
+        # Ensure feats_types is always a list of strings
+        if isinstance(feats_types, str):
+            if feats_types.startswith("[") and feats_types.endswith("]"):
+                feats_types = ast.literal_eval(feats_types)
+            else:
+                feats_types = [feats_types]
+        # print(f"feats_types: {feats_types}")
         # for some models no features are needed
         if len(feats_types) == 0:
             self.util.debug("no feature extractor specified.")
@@ -372,7 +385,8 @@ class Experiment:
                 f"test feats ({self.feats_test.shape[0]}) != test labels"
                 f" ({self.df_test.shape[0]})"
             )
-            self.df_test = self.df_test[self.df_test.index.isin(self.feats_test.index)]
+            self.df_test = self.df_test[self.df_test.index.isin(
+                self.feats_test.index)]
             self.util.warn(f"new test labels shape: {self.df_test.shape[0]}")
 
         self._check_scale()
@@ -387,7 +401,8 @@ class Experiment:
         """Augment the selected samples."""
         from nkululeko.augmenting.augmenter import Augmenter
 
-        sample_selection = self.util.config_val("AUGMENT", "sample_selection", "all")
+        sample_selection = self.util.config_val(
+            "AUGMENT", "sample_selection", "all")
         if sample_selection == "all":
             df = pd.concat([self.df_train, self.df_test])
         elif sample_selection == "train":
@@ -482,7 +497,8 @@ class Experiment:
         """
         from nkululeko.augmenting.randomsplicer import Randomsplicer
 
-        sample_selection = self.util.config_val("AUGMENT", "sample_selection", "all")
+        sample_selection = self.util.config_val(
+            "AUGMENT", "sample_selection", "all")
         if sample_selection == "all":
             df = pd.concat([self.df_train, self.df_test])
         elif sample_selection == "train":
@@ -503,7 +519,8 @@ class Experiment:
         plot_feats = eval(
             self.util.config_val("EXPL", "feature_distributions", "False")
         )
-        sample_selection = self.util.config_val("EXPL", "sample_selection", "all")
+        sample_selection = self.util.config_val(
+            "EXPL", "sample_selection", "all")
         # get the data labels
         if sample_selection == "all":
             df_labels = pd.concat([self.df_train, self.df_test])
@@ -566,7 +583,8 @@ class Experiment:
             for scat_target in scat_targets:
                 if self.util.is_categorical(df_labels[scat_target]):
                     for scatter in scatters:
-                        plots.scatter_plot(df_feats, df_labels, scat_target, scatter)
+                        plots.scatter_plot(
+                            df_feats, df_labels, scat_target, scatter)
                 else:
                     self.util.debug(
                         f"{self.name}: binning continuous variable to categories"
@@ -657,7 +675,8 @@ class Experiment:
         preds = best.preds
         speakers = self.df_test.speaker.values
         print(f"{len(truths)} {len(preds)} {len(speakers) }")
-        df = pd.DataFrame(data={"truth": truths, "pred": preds, "speaker": speakers})
+        df = pd.DataFrame(
+            data={"truth": truths, "pred": preds, "speaker": speakers})
         plot_name = "result_combined_per_speaker"
         self.util.debug(
             f"plotting speaker combination ({function}) confusion matrix to"
@@ -733,7 +752,6 @@ class Experiment:
         if model.is_ann():
             print("converting to onnx from torch")
         else:
-            from skl2onnx import to_onnx
 
             print("converting to onnx from sklearn")
         # save the rest

nkululeko/feature_extractor.py

@@ -39,16 +39,20 @@ class FeatureExtractor:
         self.feats = pd.DataFrame()
         for feats_type in self.feats_types:
             store_name = f"{self.data_name}_{feats_type}"
-            self.feat_extractor = self._get_feat_extractor(store_name, feats_type)
+            self.feat_extractor = self._get_feat_extractor(
+                store_name, feats_type)
             self.feat_extractor.extract()
             self.feat_extractor.filter()
-            self.feats = pd.concat([self.feats, self.feat_extractor.df], axis=1)
+            self.feats = pd.concat(
+                [self.feats, self.feat_extractor.df], axis=1)
         return self.feats
 
     def extract_sample(self, signal, sr):
         return self.feat_extractor.extract_sample(signal, sr)
 
     def _get_feat_extractor(self, store_name, feats_type):
+        if isinstance(feats_type, list) and len(feats_type) == 1:
+            feats_type = feats_type[0]
         feat_extractor_class = self._get_feat_extractor_class(feats_type)
         if feat_extractor_class is None:
             self.util.error(f"unknown feats_type: {feats_type}")
@@ -103,13 +107,15 @@ class FeatureExtractor:
         prefix, _, ext = feats_type.partition("-")
         from importlib import import_module
 
-        module = import_module(f"nkululeko.feat_extract.feats_{prefix.lower()}")
+        module = import_module(
+            f"nkululeko.feat_extract.feats_{prefix.lower()}")
         class_name = f"{prefix.capitalize()}"
         return getattr(module, class_name)
 
     def _get_feat_extractor_by_name(self, feats_type):
         from importlib import import_module
 
-        module = import_module(f"nkululeko.feat_extract.feats_{feats_type.lower()}")
+        module = import_module(
+            f"nkululeko.feat_extract.feats_{feats_type.lower()}")
         class_name = f"{feats_type.capitalize()}Set"
         return getattr(module, class_name)

nkululeko/utils/util.py

@@ -5,15 +5,15 @@ import os.path
 import pickle
 import sys
 
-import numpy as np
-import pandas as pd
-
 import audeer
 import audformat
+import numpy as np
+import pandas as pd
 
 
 class Util:
-    # a list of words that need not to be warned upon if default values are used
+    # a list of words that need not to be warned upon if default values are
+    # used
     stopvals = [
         "all",
         False,
@@ -40,7 +40,8 @@ class Util:
                 self.got_data_roots = self.config_val(
                     "DATA", "root_folders", False)
                 if self.got_data_roots:
-                    # if there is a global data rootfolder file, read from there
+                    # if there is a global data rootfolder file, read from
+                    # there
                     if not os.path.isfile(self.got_data_roots):
                         self.error(f"no such file: {self.got_data_roots}")
                     self.data_roots = configparser.ConfigParser()
@@ -107,16 +108,17 @@ class Util:
             if self.got_data_roots:
                 try:
                     if len(key) > 0:
-                        return self.data_roots["DATA"][dataset + "." + key].strip("'\"")
+                        return self.data_roots["DATA"][dataset +
+                                                       "." + key].strip("'\"")
                     else:
                         return self.data_roots["DATA"][dataset].strip("'\"")
                 except KeyError:
-                    if not default in self.stopvals:
+                    if default not in self.stopvals:
                         self.debug(
-                            f"value for {key} not found, using default:" f" {default}"
-                        )
+                            f"value for {key} not found, using default:"
+                            f" {default}")
                     return default
-            if not default in self.stopvals:
+            if default not in self.stopvals:
                 self.debug(
                     f"value for {key} not found, using default: {default}")
             return default
@@ -182,7 +184,7 @@ class Util:
 
     def get_feattype_name(self):
         """
-        Get a string as name from all feature sets that are useed
+        Get a string as name from all feature sets that are used
         """
         return "_".join(ast.literal_eval(self.config["FEATS"]["type"]))
 
@@ -205,7 +207,12 @@ class Util:
     def get_model_description(self):
         mt = ""
         mt = f'{self.config["MODEL"]["type"]}'
-        ft = "_".join(ast.literal_eval(self.config["FEATS"]["type"]))
+        # ft = "_".join(ast.literal_eval(self.config["FEATS"]["type"]))
+        ft_value = self.config["FEATS"]["type"]
+        if isinstance(ft_value, str) and ft_value.startswith("[") and ft_value.endswith("]"):
+            ft = "_".join(ast.literal_eval(ft_value))
+        else:
+            ft = ft_value
         ft += "_"
         layer_string = ""
         layer_s = self.config_val("MODEL", "layers", False)
@@ -230,9 +237,8 @@ class Util:
             ["FEATS", "wav2vec2.layer"],
         ]
         for option in options:
-            return_string += self._get_value_descript(option[0], option[1]).replace(
-                ".", "-"
-            )
+            return_string += self._get_value_descript(
+                option[0], option[1]).replace(".", "-")
         return return_string
 
     def get_plot_name(self):
@@ -286,7 +292,7 @@ class Util:
         try:
             return ast.literal_eval(self.config[section][key])
         except KeyError:
-            if not default in self.stopvals:
+            if default not in self.stopvals:
                 self.debug(
                     f"value for {key} not found, using default: {default}")
             return default

{nkululeko-0.86.7.dist-info → nkululeko-0.86.8.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: nkululeko
-Version: 0.86.7
+Version: 0.86.8
 Summary: Machine learning audio prediction experiments based on templates
 Home-page: https://github.com/felixbur/nkululeko
 Author: Felix Burkhardt
@@ -343,6 +343,10 @@ F. Burkhardt, Johannes Wagner, Hagen Wierstorf, Florian Eyben and Björn Schulle
 Changelog
 =========
 
+Version 0.86.8
+--------------
+* handle single feature sets as strings in the config
+
 Version 0.86.7
 --------------
 * handles now audformat tables where the target is in a file index

{nkululeko-0.86.7.dist-info → nkululeko-0.86.8.dist-info}/RECORD

@@ -2,14 +2,14 @@ nkululeko/__init__.py,sha256=62f8HiEzJ8rG2QlTFJXUCMpvuH3fKI33DoJSj33mscc,63
 nkululeko/aug_train.py,sha256=YhuZnS_WVWnun9G-M6g5n6rbRxoVREz6Zh7k6qprFNQ,3194
 nkululeko/augment.py,sha256=4MG0apTAG5RgkuJrYEjGgDdbodZWi_HweSPNI1JJ5QA,3051
 nkululeko/cacheddataset.py,sha256=lIJ6hUo5LoxSrzXtWV8mzwO7wRtUETWnOQ4ws2XfL1E,969
-nkululeko/constants.py,sha256=CscqJhC7nceHk2wmZd2bBFSeFExtr0HkXt99qpAZU4E,39
+nkululeko/constants.py,sha256=FOK-XF_DHGNFHsO_OMLof3jwgrn2buWnPVfrHy5QBm8,39
 nkululeko/demo.py,sha256=WSKr-W5uJ9DQfemK923g7Hd5V3kgAn03Er0JX1Pa45I,5142
 nkululeko/demo_feats.py,sha256=sAeGFojhEj9WEDFtG3SzPBmyYJWLF2rkbpp65m8Ujo4,2025
 nkululeko/demo_predictor.py,sha256=es56xbT8ifkS_vnrlb5NTZT54gNmeUtNlA4zVA_gnN8,4757
-nkululeko/experiment.py,sha256=5nF-eDf8OCp6KRIU7KnryWL5SLJQUtr2BueHhEdcKw0,31040
+nkululeko/experiment.py,sha256=s9PIjm45dR9yzmHu_69JpBjX9qMVzi5wIgPfMR3F44A,31530
 nkululeko/explore.py,sha256=lDzRoW_Taa5u4BBABZLD89BcQWnYlrftJR4jgt1yyj0,2609
 nkululeko/export.py,sha256=mHeEAAmtZuxdyebLlbSzPrHSi9OMgJHbk35d3DTxRBc,4632
-nkululeko/feature_extractor.py,sha256=8mssYKmo4LclVI-hiLmJEDZ0ZPyDavFG2YwtXcrGzwM,3976
+nkululeko/feature_extractor.py,sha256=rL-TybLmjZz5uxT9LNTORaDat9FKp_1qloxbyMrinyE,4141
 nkululeko/file_checker.py,sha256=LoLnL8aHpW-axMQ46qbqrManTs5otG9ShpEZuz9iRSk,3474
 nkululeko/filter_data.py,sha256=w-X2mhKdYr5DxDIz50E5yzO6Jmzk4jjDBoXsgOOVtcA,7222
 nkululeko/glob_conf.py,sha256=KL9YJQTHvTztxo1vr25qRRgaPnx4NTg0XrdbovKGMmw,525
@@ -104,9 +104,9 @@ nkululeko/segmenting/seg_silero.py,sha256=lLytS38KzARS17omwv8VBw-zz60RVSXGSvZ5Ev
 nkululeko/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nkululeko/utils/files.py,sha256=UiGAtZRWYjHSvlmPaTMtzyNNGE6qaLaxQkybctS7iRM,4021
 nkululeko/utils/stats.py,sha256=1yUq0FTOyqkU8TwUocJRYdJaqMU5SlOBBRUun9STo2M,2829
-nkululeko/utils/util.py,sha256=ILpfNuaeq-hy1bUkRhVrzO2wG9z9Upaozs9EBoIaMG0,14123
-nkululeko-0.86.7.dist-info/LICENSE,sha256=0zGP5B_W35yAcGfHPS18Q2B8UhvLRY3dQq1MhpsJU_U,1076
-nkululeko-0.86.7.dist-info/METADATA,sha256=t5cI43YRp3qmyJj03ACfgCbKoAuLYImDCLS1QkYbMQM,38024
-nkululeko-0.86.7.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
-nkululeko-0.86.7.dist-info/top_level.txt,sha256=DPFNNSHPjUeVKj44dVANAjuVGRCC3MusJ08lc2a8xFA,10
-nkululeko-0.86.7.dist-info/RECORD,,
+nkululeko/utils/util.py,sha256=ZCS02mE2c3_h9_q4hpsSm4XAooCranqRF_5pY-6055E,14432
+nkululeko-0.86.8.dist-info/LICENSE,sha256=0zGP5B_W35yAcGfHPS18Q2B8UhvLRY3dQq1MhpsJU_U,1076
+nkululeko-0.86.8.dist-info/METADATA,sha256=5TQSWqzrN9E7XJGcVn5oPKGl6qy-RliYGEG2Ycl46qk,38109
+nkululeko-0.86.8.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
+nkululeko-0.86.8.dist-info/top_level.txt,sha256=DPFNNSHPjUeVKj44dVANAjuVGRCC3MusJ08lc2a8xFA,10
+nkululeko-0.86.8.dist-info/RECORD,,