nkululeko 0.90.1__tar.gz → 0.90.3__tar.gz

{nkululeko-0.90.1 → nkululeko-0.90.3}/CHANGELOG.md

@@ -1,6 +1,15 @@
 Changelog
 =========
 
+Version 0.90.3
+--------------
+* refactorings and documentations
+
+Version 0.90.2
+--------------
+* added probability output to finetuning classification models
+* switched path to prob. output from "store" to "results"
+
 Version 0.90.1
 --------------
 * Add balancing for finetune and update data README

{nkululeko-0.90.1/nkululeko.egg-info → nkululeko-0.90.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: nkululeko
-Version: 0.90.1
+Version: 0.90.3
 Summary: Machine learning audio prediction experiments based on templates
 Home-page: https://github.com/felixbur/nkululeko
 Author: Felix Burkhardt
@@ -68,7 +68,7 @@ A project to detect speaker characteristics by machine learning experiments with
 
 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 nkululek: [Ensemble learning](http://blog.syntheticspeech.de/2024/06/25/nkululeko-ensemble-classifiers-with-late-fusion/)
+* 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/)
 * The latest features can be seen in [the ini-file](./ini_file.md) options that are used to control Nkululeko
 * Below is a [Hello World example](#helloworld) that should set you up fastly, also on [Google Colab](https://colab.research.google.com/drive/1GYNBd5cdZQ1QC3Jm58qoeMaJg3UuPhjw?usp=sharing#scrollTo=4G_SjuF9xeQf), and [with Kaggle](https://www.kaggle.com/felixburk/nkululeko-hello-world-example)
@@ -356,6 +356,15 @@ F. Burkhardt, Johannes Wagner, Hagen Wierstorf, Florian Eyben and Björn Schulle
 Changelog
 =========
 
+Version 0.90.3
+--------------
+* refactorings and documentations
+
+Version 0.90.2
+--------------
+* added probability output to finetuning classification models
+* switched path to prob. output from "store" to "results"
+
 Version 0.90.1
 --------------
 * Add balancing for finetune and update data README

{nkululeko-0.90.1 → nkululeko-0.90.3}/README.md

@@ -24,7 +24,7 @@ A project to detect speaker characteristics by machine learning experiments with
 
 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 nkululek: [Ensemble learning](http://blog.syntheticspeech.de/2024/06/25/nkululeko-ensemble-classifiers-with-late-fusion/)
+* 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/)
 * The latest features can be seen in [the ini-file](./ini_file.md) options that are used to control Nkululeko
 * Below is a [Hello World example](#helloworld) that should set you up fastly, also on [Google Colab](https://colab.research.google.com/drive/1GYNBd5cdZQ1QC3Jm58qoeMaJg3UuPhjw?usp=sharing#scrollTo=4G_SjuF9xeQf), and [with Kaggle](https://www.kaggle.com/felixburk/nkululeko-hello-world-example)

{nkululeko-0.90.1 → nkululeko-0.90.3}/nkululeko/augment.py

@@ -83,17 +83,13 @@ def doit(config_file):
         print("DONE")
 
 
-def main(src_dir):
+def main():
     parser = argparse.ArgumentParser(description="Call the nkululeko framework.")
     parser.add_argument("--config", default="exp.ini", help="The base configuration")
     args = parser.parse_args()
-    if args.config is not None:
-        config_file = args.config
-    else:
-        config_file = f"{src_dir}/exp.ini"
+    config_file = args.config if args.config is not None else "exp.ini"
     doit(config_file)
 
 
 if __name__ == "__main__":
-    cwd = os.path.dirname(os.path.abspath(__file__))
-    main(cwd)  # use this if you want to state the config file path on command line
+    main()

{nkululeko-0.90.1 → nkululeko-0.90.3}/nkululeko/constants.py

@@ -1,2 +1,2 @@
-VERSION = "0.90.1"
+VERSION="0.90.3"
 SAMPLING_RATE = 16000

{nkululeko-0.90.1 → nkululeko-0.90.3}/nkululeko/demo.py

@@ -30,7 +30,7 @@ from nkululeko.experiment import Experiment
 from nkululeko.utils.util import Util
 
 
-def main(src_dir):
+def main():
     parser = argparse.ArgumentParser(description="Call the nkululeko DEMO framework.")
     parser.add_argument("--config", default="exp.ini", help="The base configuration")
     parser.add_argument(
@@ -142,5 +142,4 @@ def main(src_dir):
 
 
 if __name__ == "__main__":
-    cwd = os.path.dirname(os.path.abspath(__file__))
-    main(cwd)  # use this if you want to state the config file path on command line
+    main()

{nkululeko-0.90.1 → nkululeko-0.90.3}/nkululeko/explore.py

@@ -25,33 +25,27 @@ for an `exp.ini` file in the same directory as the script.
 
 import argparse
 import configparser
-import os
+from pathlib import Path
 
 from nkululeko.constants import VERSION
 from nkululeko.experiment import Experiment
 from nkululeko.utils.util import Util
 
 
-def main(src_dir):
+def main():
     parser = argparse.ArgumentParser(
         description="Call the nkululeko EXPLORE framework."
     )
     parser.add_argument("--config", default="exp.ini", help="The base configuration")
     args = parser.parse_args()
-    if args.config is not None:
-        config_file = args.config
-    else:
-        config_file = f"{src_dir}/exp.ini"
+    config_file = args.config if args.config is not None else "exp.ini"
 
-    # test if the configuration file exists
-    if not os.path.isfile(config_file):
+    if not Path(config_file).is_file():
         print(f"ERROR: no such file: {config_file}")
         exit()
 
-    # load one configuration per experiment
     config = configparser.ConfigParser()
     config.read(config_file)
-    # create a new experiment
     expr = Experiment(config)
     module = "explore"
     expr.set_module(module)
@@ -101,5 +95,4 @@ def main(src_dir):
 
 
 if __name__ == "__main__":
-    cwd = os.path.dirname(os.path.abspath(__file__))
-    main(cwd)  # use this if you want to state the config file path on command line
+    main()

{nkululeko-0.90.1 → nkululeko-0.90.3}/nkululeko/export.py

@@ -15,24 +15,18 @@ from nkululeko.experiment import Experiment
 from nkululeko.utils.util import Util
 
 
-def main(src_dir):
+def main():
     parser = argparse.ArgumentParser(description="Call the nkululeko framework.")
     parser.add_argument("--config", default="exp.ini", help="The base configuration")
     args = parser.parse_args()
-    if args.config is not None:
-        config_file = args.config
-    else:
-        config_file = f"{src_dir}/exp.ini"
+    config_file = args.config if args.config is not None else "exp.ini"
 
-    # test if the configuration file exists
     if not os.path.isfile(config_file):
         print(f"ERROR: no such file: {config_file}")
         exit()
 
-    # load one configuration per experiment
     config = configparser.ConfigParser()
     config.read(config_file)
-    # create a new experiment
     expr = Experiment(config)
     util = Util("export")
     util.debug(
@@ -122,5 +116,4 @@ def main(src_dir):
 
 
 if __name__ == "__main__":
-    cwd = os.path.dirname(os.path.abspath(__file__))
-    main(cwd)  # use this if you want to state the config file path on command line
+    main()

{nkululeko-0.90.1 → nkululeko-0.90.3}/nkululeko/models/model_tuned.py

@@ -30,10 +30,16 @@ class TunedModel(BaseModel):
         """Constructor taking the configuration and all dataframes."""
         super().__init__(df_train, df_test, feats_train, feats_test)
         super().set_model_type("finetuned")
+        self.df_test, self.df_train, self.feats_test, self.feats_train = (
+            df_test,
+            df_train,
+            feats_test,
+            feats_train,
+        )
         self.name = "finetuned_wav2vec2"
         self.target = glob_conf.config["DATA"]["target"]
-        labels = glob_conf.labels
-        self.class_num = len(labels)
+        self.labels = glob_conf.labels
+        self.class_num = len(self.labels)
         device = self.util.config_val("MODEL", "device", False)
         if not device:
             self.device = "cuda" if torch.cuda.is_available() else "cpu"
@@ -304,7 +310,7 @@ class TunedModel(BaseModel):
             else:
                 self.util.error(f"criterion {criterion} not supported for classifier")
         else:
-            self.criterion = self.util.config_val("MODEL", "loss", "ccc")
+            criterion = self.util.config_val("MODEL", "loss", "1-ccc")
             if criterion == "1-ccc":
                 criterion = ConcordanceCorCoeff()
             elif criterion == "mse":
@@ -402,7 +408,7 @@ class TunedModel(BaseModel):
         self.load(self.run, self.epoch)
 
     def get_predictions(self):
-        results = []
+        results = [[]].pop(0)
         for (file, start, end), _ in audeer.progress_bar(
             self.df_test.iterrows(),
             total=len(self.df_test),
@@ -415,18 +421,37 @@ class TunedModel(BaseModel):
                     file, duration=end - start, offset=start, always_2d=True
                 )
             assert sr == self.sampling_rate
-            predictions = self.model.predict(signal)
-            results.append(predictions.argmax())
-        return results
+            prediction = self.model.predict(signal)
+            results.append(prediction)
+            # results.append(predictions.argmax())
+        predictions = np.asarray(results)
+        if self.util.exp_is_classification():
+            # make a dataframe for the class probabilities
+            proba_d = {}
+            for c in range(self.class_num):
+                proba_d[c] = []
+            # get the class probabilities
+            # predictions = self.clf.predict_proba(self.feats_test.to_numpy())
+            # pred = self.clf.predict(features)
+            for i in range(self.class_num):
+                proba_d[i] = list(predictions.T[i])
+            probas = pd.DataFrame(proba_d)
+            probas = probas.set_index(self.df_test.index)
+            predictions = probas.idxmax(axis=1).values
+        else:
+            predictions = predictions.flatten()
+            probas = None
+        return predictions, probas
 
     def predict(self):
         """Predict the whole eval feature set"""
-        predictions = self.get_predictions()
+        predictions, probas = self.get_predictions()
         report = Reporter(
             self.df_test[self.target].to_numpy().astype(float),
             predictions,
             self.run,
             self.epoch_num,
+            probas=probas,
         )
         self._plot_epoch_progression(report)
         return report
@@ -438,6 +463,7 @@ class TunedModel(BaseModel):
         )
         with open(log_file, "r") as file:
             data = file.read()
+        data = data.strip().replace("nan", "0")
         list = ast.literal_eval(data)
         epochs, vals, loss = [], [], []
         for index, tp in enumerate(list):

{nkululeko-0.90.1 → nkululeko-0.90.3}/nkululeko/nkululeko.py

@@ -2,7 +2,7 @@
 # Entry script to do a Nkululeko experiment
 import argparse
 import configparser
-import os.path
+from pathlib import Path
 
 import numpy as np
 
@@ -13,7 +13,7 @@ from nkululeko.utils.util import Util
 
 def doit(config_file):
     # test if the configuration file exists
-    if not os.path.isfile(config_file):
+    if not Path(config_file).is_file():
         print(f"ERROR: no such file: {config_file}")
         exit()
 
@@ -57,17 +57,18 @@ def doit(config_file):
     return result, int(np.asarray(last_epochs).min())
 
 
-def main(src_dir):
+def main():
+    cwd = Path(__file__).parent.absolute()
     parser = argparse.ArgumentParser(description="Call the nkululeko framework.")
+    parser.add_argument("--version", action="version", version=f"Nkululeko {VERSION}")
     parser.add_argument("--config", default="exp.ini", help="The base configuration")
     args = parser.parse_args()
     if args.config is not None:
         config_file = args.config
     else:
-        config_file = f"{src_dir}/exp.ini"
+        config_file = cwd / "exp.ini"
     doit(config_file)
 
 
 if __name__ == "__main__":
-    cwd = os.path.dirname(os.path.abspath(__file__))
-    main(cwd)  # use this if you want to state the config file path on command line
+    main()  # use this if you want to state the config file path on command line

{nkululeko-0.90.1 → nkululeko-0.90.3}/nkululeko/predict.py

@@ -24,26 +24,20 @@ from nkululeko.experiment import Experiment
 from nkululeko.utils.util import Util
 
 
-def main(src_dir):
+def main():
     parser = argparse.ArgumentParser(
         description="Call the nkululeko PREDICT framework."
     )
     parser.add_argument("--config", default="exp.ini", help="The base configuration")
     args = parser.parse_args()
-    if args.config is not None:
-        config_file = args.config
-    else:
-        config_file = f"{src_dir}/exp.ini"
+    config_file = args.config if args.config is not None else "exp.ini"
 
-    # test if the configuration file exists
     if not os.path.isfile(config_file):
         print(f"ERROR: no such file: {config_file}")
         exit()
 
-    # load one configuration per experiment
     config = configparser.ConfigParser()
     config.read(config_file)
-    # create a new experiment
     expr = Experiment(config)
     module = "predict"
     expr.set_module(module)
@@ -73,5 +67,4 @@ def main(src_dir):
 
 
 if __name__ == "__main__":
-    cwd = os.path.dirname(os.path.abspath(__file__))
-    main(cwd)  # use this if you want to state the config file path on command line
+    main()

{nkululeko-0.90.1 → nkululeko-0.90.3}/nkululeko/resample.py

@@ -1,3 +1,25 @@
+"""
+Resample audio files or INI files (train, test, all) to change the sampling rate.
+
+This script provides a command-line interface to resample audio files or INI files
+containing train, test, and all data. It supports resampling a single file, a
+directory of files, or all files specified in an INI configuration file.
+
+The script uses the `Resampler` class from the `nkululeko.augmenting.resampler`
+module to perform the resampling operation. It can optionally replace the original
+audio files with the resampled versions.
+
+The script supports the following command-line arguments:
+- `--config`: The base configuration file (INI format) to use for resampling.
+- `--file`: The input audio file to resample.
+- `--folder`: The input directory containing audio files and subdirectories to resample.
+- `--replace`: Whether to replace the original audio files with the resampled versions.
+
+The script also supports loading configuration from an INI file, which can be used
+to specify the sample selection (all, train, or test) and whether to replace the
+original files.
+"""
+
 # resample.py
 # change the sampling rate for audio file or INI file (train, test, all)
 
@@ -15,7 +37,7 @@ from nkululeko.utils.files import find_files
 from nkululeko.utils.util import Util
 
 
-def main(src_dir):
+def main():
     parser = argparse.ArgumentParser(
         description="Call the nkululeko RESAMPLE framework."
     )
@@ -118,5 +140,4 @@ def main(src_dir):
 
 
 if __name__ == "__main__":
-    cwd = os.path.dirname(os.path.abspath(__file__))
-    main(cwd)
+    main()

{nkululeko-0.90.1 → nkululeko-0.90.3}/nkululeko/segment.py

@@ -14,24 +14,18 @@ from nkululeko.reporting.report_item import ReportItem
 from nkululeko.utils.util import Util
 
 
-def main(src_dir):
+def main():
     parser = argparse.ArgumentParser(description="Call the nkululeko framework.")
     parser.add_argument("--config", default="exp.ini", help="The base configuration")
     args = parser.parse_args()
-    if args.config is not None:
-        config_file = args.config
-    else:
-        config_file = f"{src_dir}/exp.ini"
+    config_file = args.config if args.config is not None else "exp.ini"
 
-    # test if the configuration file exists
     if not os.path.isfile(config_file):
         print(f"ERROR: no such file: {config_file}")
         exit()
 
-    # load one configuration per experiment
     config = configparser.ConfigParser()
     config.read(config_file)
-    # create a new experiment
     expr = Experiment(config)
     module = "segment"
     expr.set_module(module)
@@ -153,5 +147,4 @@ def segment_dataframe(df):
 
 
 if __name__ == "__main__":
-    cwd = os.path.dirname(os.path.abspath(__file__))
-    main(cwd)  # use this if you want to state the config file path on command line
+    main()  # use this if you want to state the config file path on command line

{nkululeko-0.90.1 → nkululeko-0.90.3}/nkululeko/utils/util.py

@@ -155,10 +155,10 @@ class Util:
         return f"{store}/{self.get_exp_name()}.pkl"
 
     def get_pred_name(self):
-        store = self.get_path("store")
+        results_dir = self.get_path("res_dir")
         target = self.get_target_name()
         pred_name = self.get_model_description()
-        return f"{store}/pred_{target}_{pred_name}.csv"
+        return f"{results_dir}/pred_{target}_{pred_name}.csv"
 
     def is_categorical(self, pd_series):
         """Check if a dataframe column is categorical."""

{nkululeko-0.90.1 → nkululeko-0.90.3/nkululeko.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: nkululeko
-Version: 0.90.1
+Version: 0.90.3
 Summary: Machine learning audio prediction experiments based on templates
 Home-page: https://github.com/felixbur/nkululeko
 Author: Felix Burkhardt
@@ -68,7 +68,7 @@ A project to detect speaker characteristics by machine learning experiments with
 
 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 nkululek: [Ensemble learning](http://blog.syntheticspeech.de/2024/06/25/nkululeko-ensemble-classifiers-with-late-fusion/)
+* 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/)
 * The latest features can be seen in [the ini-file](./ini_file.md) options that are used to control Nkululeko
 * Below is a [Hello World example](#helloworld) that should set you up fastly, also on [Google Colab](https://colab.research.google.com/drive/1GYNBd5cdZQ1QC3Jm58qoeMaJg3UuPhjw?usp=sharing#scrollTo=4G_SjuF9xeQf), and [with Kaggle](https://www.kaggle.com/felixburk/nkululeko-hello-world-example)
@@ -356,6 +356,15 @@ F. Burkhardt, Johannes Wagner, Hagen Wierstorf, Florian Eyben and Björn Schulle
 Changelog
 =========
 
+Version 0.90.3
+--------------
+* refactorings and documentations
+
+Version 0.90.2
+--------------
+* added probability output to finetuning classification models
+* switched path to prob. output from "store" to "results"
+
 Version 0.90.1
 --------------
 * Add balancing for finetune and update data README

{nkululeko-0.90.1 → nkululeko-0.90.3}/nkululeko.egg-info/SOURCES.txt

@@ -60,7 +60,6 @@ nkululeko/demo_feats.py
 nkululeko/demo_predictor.py
 nkululeko/ensemble.py
 nkululeko/experiment.py
-nkululeko/experiment_felix.py
 nkululeko/explore.py
 nkululeko/export.py
 nkululeko/feature_extractor.py
@@ -75,7 +74,6 @@ nkululeko/nkululeko.py
 nkululeko/plots.py
 nkululeko/predict.py
 nkululeko/resample.py
-nkululeko/resample_cli.py
 nkululeko/runmanager.py
 nkululeko/scaler.py
 nkululeko/segment.py
@@ -86,6 +84,7 @@ nkululeko/test_pretrain.py
 nkululeko.egg-info/PKG-INFO
 nkululeko.egg-info/SOURCES.txt
 nkululeko.egg-info/dependency_links.txt
+nkululeko.egg-info/entry_points.txt
 nkululeko.egg-info/requires.txt
 nkululeko.egg-info/top_level.txt
 nkululeko/augmenting/__init__.py

nkululeko-0.90.3/nkululeko.egg-info/entry_points.txt

@@ -0,0 +1,10 @@
+[console_scripts]
+nkululeko.augment = nkululeko.augment:main
+nkululeko.demo = nkululeko.demo:main
+nkululeko.explore = nkululeko.explore:main
+nkululeko.export = nkululeko.export:main
+nkululeko.nkululeko = nkululeko.nkululeko:main
+nkululeko.predict = nkululeko.predict:main
+nkululeko.resample = nkululeko.resample:main
+nkululeko.segment = nkululeko.segment:main
+nkululeko.test = nkululeko.test:main

nkululeko-0.90.3/setup.py

@@ -0,0 +1,21 @@
+# from nkululeko.constants import VERSION
+from setuptools import setup
+
+setup(
+    use_scm_version=True,
+    # version=VERSION,
+    entry_points={
+        "console_scripts": [
+            # 'nkululeko=nkululeko.nkululeko:main',
+            "nkululeko.explore=nkululeko.explore:main",
+            "nkululeko.nkululeko=nkululeko.nkululeko:main",
+            "nkululeko.augment=nkululeko.augment:main",
+            "nkululeko.demo=nkululeko.demo:main",
+            "nkululeko.export=nkululeko.export:main",
+            "nkululeko.predict=nkululeko.predict:main",
+            "nkululeko.resample=nkululeko.resample:main",
+            "nkululeko.segment=nkululeko.segment:main",
+            "nkululeko.test=nkululeko.test:main",
+        ],
+    },
+)