nkululeko 0.81.3__py3-none-any.whl → 0.81.6__py3-none-any.whl

nkululeko/autopredict/estimate_snr.py

@@ -1,20 +1,30 @@
 # estimate.snr
-import numpy as np
+"""
+Module for estimating SNR (signal to noise ratio) from an audio signal.
+
+This module provides a class `SNREstimator` which calculates the SNR based on
+the log energy and energy thresholds of the audio signal.
+
+"""
+
+import argparse
+
 import audiofile
 import matplotlib.pyplot as plt
+import numpy as np
 from scipy.signal.windows import hamming
-import argparse
 
 
 class SNREstimator:
-    """Estimate SNR from audio signal using log energy and energy thresholds
+    """Estimate SNR from audio signal using log energy and energy thresholds.
+
     Args:
         input_data (ndarray): Input audio signal
         sample_rate (int): Sampling rate of input audio signal
         window_size (int): Window size in samples
         hop_size (int): Hop size in samples
 
-        Returns:
+    Returns:
         object: SNREstimator object
         estimated_snr (float): Estimated SNR in dB, extracted from SNREstimator.estimate_snr()
 
@@ -34,7 +44,7 @@ class SNREstimator:
         num_frames = 1 + (len(signal) - self.frame_length) // self.hop_length
         frames = [
             signal[
-                i * self.hop_length : (i * self.hop_length) + self.frame_length
+                i * self.hop_length: (i * self.hop_length) + self.frame_length
             ]
             for i in range(num_frames)
         ]
@@ -54,7 +64,8 @@ class SNREstimator:
             for frame in frames
         ]
 
-        energy_threshold_low = np.percentile(log_energies, 25)  # First quartile
+        energy_threshold_low = np.percentile(
+            log_energies, 25)  # First quartile
         energy_threshold_high = np.percentile(
             log_energies, 75
         )  # Third quartile

nkululeko/constants.py

@@ -1,2 +1,2 @@
-VERSION="0.81.3"
+VERSION="0.81.6"
 SAMPLING_RATE = 16000

nkululeko/data/dataset.py

@@ -76,6 +76,7 @@ class Dataset:
         if rename_cols:
             col_dict = ast.literal_eval(rename_cols)
             df = df.rename(columns=col_dict)
+            self.util.debug(f"renamed data columns: {col_dict}")
         return df
 
     def _report_load(self):
@@ -96,8 +97,8 @@ class Dataset:
         """Load the dataframe with files, speakers and task labels"""
         # store the dataframe
         store = self.util.get_path("store")
-        store_file = f"{store}{self.name}"
         store_format = self.util.config_val("FEATS", "store_format", "pkl")
+        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}")
@@ -241,7 +242,7 @@ class Dataset:
         # store the dataframe
         store = self.util.get_path("store")
         store_format = self.util.config_val("FEATS", "store_format", "pkl")
-        store_file = f"{store}{self.name}"
+        store_file = f"{store}{self.name}.{store_format}"
         self.util.write_store(self.df, store_file, store_format)
 
     def _get_df_for_lists(self, db, df_files):
@@ -281,13 +282,19 @@ class Dataset:
                 # try to get the age values
                 df_local["age"] = source_df["age"].astype(int)
                 got_age = True
-            except (KeyError, ValueError, audformat.errors.BadKeyError) as e:
+            except (KeyError, ValueError, audformat.errors.BadKeyError):
                 pass
             try:
                 # also it might be possible that the sex is part of the speaker description
                 df_local["gender"] = db[table]["speaker"].get(map="gender")
                 got_gender = True
-            except (ValueError, audformat.errors.BadKeyError) as e:
+            except (ValueError, audformat.errors.BadKeyError):
+                pass
+            try:
+                # also it might be possible that the sex is part of the speaker description
+                df_local["gender"] = db[table]["speaker"].get(map="sex")
+                got_gender = True
+            except (ValueError, audformat.errors.BadKeyError):
                 pass
             try:
                 # also it might be possible that the age is part of the speaker description

nkululeko/demo.py

@@ -2,20 +2,35 @@
 # Demonstration code to use the ML-experiment framework
 # Test the loading of a previously trained model and demo mode
 # needs the project config file to run before
+"""
+This script is used to test the loading of a previously trained model and run it in demo mode.
+It requires the project config file to be run before.
 
-import os
+Usage:  
+python -m nkululeko.demo [--config CONFIG] [--file FILE] [--list LIST] [--folder FOLDER] [--outfile OUTFILE]  
+
+Options:   \n
+--config CONFIG     The base configuration file (default: exp.ini) \n  
+--file FILE         A file that should be processed (16kHz mono wav) \n  
+--list LIST         A file with a list of files, one per line, that should be processed (16kHz mono wav) \n  
+--folder FOLDER     A name of a folder where the files within the list are in   (default: ./) \n   
+--outfile OUTFILE   A filename to store the results in CSV  (default: None)  
+"""
 import argparse
 import configparser
+import os
 
+import nkululeko.glob_conf as glob_conf
+from nkululeko.constants import VERSION
 from nkululeko.experiment import Experiment
 from nkululeko.utils.util import Util
-from nkululeko.constants import VERSION
-import nkululeko.glob_conf as glob_conf
 
 
 def main(src_dir):
-    parser = argparse.ArgumentParser(description="Call the nkululeko framework.")
-    parser.add_argument("--config", default="exp.ini", help="The base configuration")
+    parser = argparse.ArgumentParser(
+        description="Call the nkululeko DEMO framework.")
+    parser.add_argument("--config", default="exp.ini",
+                        help="The base configuration")
     parser.add_argument(
         "--file", help="A file that should be processed (16kHz mono wav)"
     )

nkululeko/demo_predictor.py

@@ -1,8 +1,11 @@
+# demo_predictor.py
 import os
-import pandas as pd
-import numpy as np
-import audiofile
+
 import audformat
+import audiofile
+import numpy as np
+import pandas as pd
+
 import nkululeko.glob_conf as glob_conf
 from nkululeko.utils.util import Util
 

nkululeko/experiment.py

@@ -685,7 +685,7 @@ class Experiment:
         glob_conf.set_labels(self.labels)
 
     def save(self, filename):
-        if self.runmgr.modelrunner.model.is_ANN():
+        if self.runmgr.modelrunner.model.is_ann():
             self.runmgr.modelrunner.model = None
             self.util.warn(
                 f"Save experiment: Can't pickle the learning model so saving without it."
@@ -695,7 +695,7 @@ class Experiment:
             pickle.dump(self.__dict__, f)
             f.close()
         except TypeError:
-            self.feature_extractor.featExtractor.model = None
+            self.feature_extractor.feat_extractor.model = None
             f = open(filename, "wb")
             pickle.dump(self.__dict__, f)
             f.close()
@@ -708,7 +708,7 @@ class Experiment:
     def save_onnx(self, filename):
         # export the model to onnx
         model = self.runmgr.get_best_model()
-        if model.is_ANN():
+        if model.is_ann():
             print("converting to onnx from torch")
         else:
             from skl2onnx import to_onnx

nkululeko/explore.py

@@ -1,17 +1,20 @@
 # explore.py
 # explore the feature sets
 
-from nkululeko.experiment import Experiment
-import configparser
-from nkululeko.utils.util import Util
-from nkululeko.constants import VERSION
 import argparse
+import configparser
 import os
 
+from nkululeko.constants import VERSION
+from nkululeko.experiment import Experiment
+from nkululeko.utils.util import Util
+
 
 def main(src_dir):
-    parser = argparse.ArgumentParser(description="Call the nkululeko framework.")
-    parser.add_argument("--config", default="exp.ini", help="The base configuration")
+    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
@@ -46,9 +49,11 @@ def main(src_dir):
 
     # split into train and test
     expr.fill_train_and_tests()
-    util.debug(f"train shape : {expr.df_train.shape}, test shape:{expr.df_test.shape}")
+    util.debug(
+        f"train shape : {expr.df_train.shape}, test shape:{expr.df_test.shape}")
 
-    plot_feats = eval(util.config_val("EXPL", "feature_distributions", "False"))
+    plot_feats = eval(util.config_val(
+        "EXPL", "feature_distributions", "False"))
     tsne = eval(util.config_val("EXPL", "tsne", "False"))
     scatter = eval(util.config_val("EXPL", "scatter", "False"))
     spotlight = eval(util.config_val("EXPL", "spotlight", "False"))

nkululeko/feat_extract/feats_agender.py

@@ -32,10 +32,7 @@ class AudModelAgenderSet(Featureset):
             audeer.extract_archive(archive_path, model_root)
         device = self.util.config_val("MODEL", "device", "cpu")
         self.model = audonnx.load(model_root, device=device)
-        pytorch_total_params = sum(p.numel() for p in self.model.parameters())
-        self.util.debug(
-            f"initialized agender model with {pytorch_total_params} parameters in total"
-        )
+        self.util.debug(f"initialized agender model")
         self.model_loaded = True
 
     def extract(self):

nkululeko/feat_extract/{feats_audmodel_dim.py → feats_auddim.py}

@@ -1,19 +1,24 @@
 # feats_audmodel_dim.py
-from nkululeko.feat_extract.featureset import Featureset
 import os
+
+import numpy as np
 import pandas as pd
+import torch
+
 import audeer
-import nkululeko.glob_conf as glob_conf
-import audonnx
-import numpy as np
 import audinterface
+import audonnx
+
+from nkululeko.feat_extract.featureset import Featureset
+import nkululeko.glob_conf as glob_conf
 
 
-class AudModelDimSet(Featureset):
-    """
-    Emotional dimensions from the wav2vec2. based model finetuned on MSPPodcast emotions, described in the paper
+class AuddimSet(Featureset):
+    """Emotional dimensions from the wav2vec2 model finetuned on MSPPodcast emotions.
+
+    Described in the paper
     "Dawn of the transformer era in speech emotion recognition: closing the valence gap"
-    https://arxiv.org/abs/2203.07378
+    https://arxiv.org/abs/2203.07378.
     """
 
     def __init__(self, name, data_df):

nkululeko/feat_extract/feats_audmodel.py

@@ -11,11 +11,12 @@ import torch
 from nkululeko.feat_extract.featureset import Featureset
 
 
-class AudModelSet(Featureset):
-    """
-    Embeddings from the wav2vec2. based model finetuned on MSPPodcast emotions, described in the paper
+class AudmodelSet(Featureset):
+    """Embeddings from the wav2vec2 based model finetuned on MSPPodcast emotions.
+
+    Described in the paper:
     "Dawn of the transformer era in speech emotion recognition: closing the valence gap"
-    https://arxiv.org/abs/2203.07378
+    https://arxiv.org/abs/2203.07378.
     """
 
     def __init__(self, name, data_df):

nkululeko/feat_extract/feats_import.py

@@ -8,7 +8,7 @@ from nkululeko.utils.util import Util
 from nkululeko.feat_extract.featureset import Featureset
 
 
-class Importset(Featureset):
+class ImportSet(Featureset):
     """Class to import features that have been compiled elsewhere"""
 
     def __init__(self, name, data_df):

nkululeko/feat_extract/feats_mos.py

@@ -10,6 +10,7 @@ pip uninstall -y torch torchvision torchaudio
 pip install --pre torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/nightly/cpu
 
 """
+
 import os
 import pandas as pd
 from tqdm import tqdm
@@ -23,7 +24,7 @@ from nkululeko.utils.util import Util
 from nkululeko.feat_extract.featureset import Featureset
 
 
-class MOSSet(Featureset):
+class MosSet(Featureset):
     """Class to predict MOS (mean opinion score)"""
 
     def __init__(self, name, data_df):

nkululeko/feat_extract/feats_praat.py

@@ -1,17 +1,19 @@
 # feats_praat.py
-from nkululeko.feat_extract.featureset import Featureset
+import ast
 import os
-import pandas as pd
+
 import numpy as np
-import nkululeko.glob_conf as glob_conf
+import pandas as pd
+
 from nkululeko.feat_extract import feinberg_praat
-import ast
+from nkululeko.feat_extract.featureset import Featureset
+import nkululeko.glob_conf as glob_conf
 
 
-class Praatset(Featureset):
-    """
-    a feature extractor for the Praat software, based on
-    David R. Feinberg's Praat scripts for the parselmouth python interface.
+class PraatSet(Featureset):
+    """A feature extractor for the Praat software.
+
+    Based on David R. Feinberg's Praat scripts for the parselmouth python interface.
     https://osf.io/6dwr3/
 
     """

nkululeko/feat_extract/feats_snr.py

@@ -1,14 +1,17 @@
-""" feats_snr.py
-    Estimate snr (signal to noise ratio as acoustic features)
+""" feats_snr.py is to estimate snr.
+
+SNR (signal to noise ratio) is extracted as acoustic features.
 """
 import os
-from tqdm import tqdm
-import pandas as pd
+
 import audiofile
+import pandas as pd
+from tqdm import tqdm
+
 import nkululeko.glob_conf as glob_conf
-from nkululeko.utils.util import Util
-from nkululeko.feat_extract.featureset import Featureset
 from nkululeko.autopredict.estimate_snr import SNREstimator
+from nkululeko.feat_extract.featureset import Featureset
+from nkululeko.utils.util import Util
 
 
 class SNRSet(Featureset):
@@ -16,14 +19,17 @@ class SNRSet(Featureset):
 
     def __init__(self, name, data_df):
         """Constructor."""
+
         super().__init__(name, data_df)
 
     def extract(self):
         """Estimate the features or load them from disk if present."""
+
         store = self.util.get_path("store")
         store_format = self.util.config_val("FEATS", "store_format", "pkl")
         storage = f"{store}{self.name}.{store_format}"
-        extract = self.util.config_val("FEATS", "needs_feature_extraction", False)
+        extract = self.util.config_val(
+            "FEATS", "needs_feature_extraction", False)
         no_reuse = eval(self.util.config_val("FEATS", "no_reuse", "False"))
         if extract or no_reuse or not os.path.isfile(storage):
             self.util.debug("estimating SNR, this might take a while...")
@@ -40,7 +46,8 @@ class SNRSet(Featureset):
                 snr = self.get_snr(signal[0], sampling_rate)
                 snr_series[idx] = snr
             print("")
-            self.df = pd.DataFrame(snr_series.values.tolist(), index=self.data_df.index)
+            self.df = pd.DataFrame(
+                snr_series.values.tolist(), index=self.data_df.index)
             self.df.columns = ["snr"]
             self.util.write_store(self.df, storage, store_format)
             try:
@@ -53,10 +60,11 @@ class SNRSet(Featureset):
 
     def get_snr(self, signal, sampling_rate):
         r"""Estimate SNR from raw audio signal.
+
         Args:
             signal: audio signal
             sampling_rate: sample rate
-        Returns
+        Returns:
             snr: estimated signal to noise ratio
         """
         snr_estimator = SNREstimator(signal, sampling_rate)

nkululeko/feat_extract/feats_squim.py

@@ -1,36 +1,33 @@
-""" feats_squim.py
-predict SQUIM ( SPEECH QUALITY AND INTELLIGIBILITY
-MEASURES) features
+"""Predict SQUIM ( SPEECH QUALITY AND INTELLIGIBILITY MEASURES) features.
 
-
-    Wideband Perceptual Estimation of Speech Quality (PESQ) [2]
-    Short-Time Objective Intelligibility (STOI) [3]
-    Scale-Invariant Signal-to-Distortion Ratio (SI-SDR) [4]
-
-
-adapted from
+Wideband Perceptual Estimation of Speech Quality (PESQ) [2].
+    Short-Time Objective Intelligibility (STOI) [3].
+    Scale-Invariant Signal-to-Distortion Ratio (SI-SDR) [4].
+Adapted from
 from https://pytorch.org/audio/main/tutorials/squim_tutorial.html#sphx-glr-tutorials-squim-tutorial-py
-paper: https://arxiv.org/pdf/2304.01448.pdf
-
-needs 
+paper: https://arxiv.org/pdf/2304.01448.pdf.
+Needs
 pip uninstall -y torch torchvision torchaudio
 pip install --pre torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/nightly/cpu
 
 """
 
 import os
-from tqdm import tqdm
+
 import pandas as pd
 import torch
 import torchaudio
 from torchaudio.pipelines import SQUIM_OBJECTIVE
+from tqdm import tqdm
+
 import audiofile
+
+from nkululeko.feat_extract.featureset import Featureset
 import nkululeko.glob_conf as glob_conf
 from nkululeko.utils.util import Util
-from nkululeko.feat_extract.featureset import Featureset
 
 
-class SQUIMSet(Featureset):
+class SquimSet(Featureset):
     """Class to predict SQUIM features"""
 
     def __init__(self, name, data_df):