nkululeko 0.76.0__py3-none-any.whl → 0.77.1__py3-none-any.whl

nkululeko/augment.py

@@ -7,7 +7,7 @@ import os
 import ast
 from nkululeko.experiment import Experiment
 import configparser
-from nkululeko.util import Util
+from nkululeko.utils.util import Util
 from nkululeko.constants import VERSION
 
 

nkululeko/augmenting/augmenter.py

@@ -14,7 +14,7 @@ from audiomentations import (
     Shift,
     TimeStretch,
 )
-from nkululeko.util import Util
+from nkululeko.utils.util import Util
 from tqdm import tqdm
 
 

nkululeko/augmenting/randomsplicer.py

@@ -20,7 +20,7 @@ import numpy as np
 import audiofile as af
 from audformat.utils import map_file_path
 import audeer
-from nkululeko.util import Util
+from nkululeko.utils.util import Util
 import nkululeko.augmenting.randomsplicing as rsp
 
 

nkululeko/augmenting/resampler.py

@@ -8,7 +8,7 @@ import shutil
 import audformat
 import pandas as pd
 import torchaudio
-from nkululeko.util import Util
+from nkululeko.utils.util import Util
 
 
 class Resampler:
@@ -42,9 +42,7 @@ class Resampler:
                 continue
             if org_sr != self.SAMPLING_RATE:
                 self.util.debug(f"resampling {f} (sr = {org_sr})")
-                resampler = torchaudio.transforms.Resample(
-                    org_sr, self.SAMPLING_RATE
-                )
+                resampler = torchaudio.transforms.Resample(org_sr, self.SAMPLING_RATE)
                 signal = resampler(signal)
                 if replace:
                     torchaudio.save(
@@ -61,9 +59,7 @@ class Resampler:
             self.df = self.df.set_index(
                 self.df.index.set_levels(new_files, level="file")
             )
-            target_file = self.util.config_val(
-                "RESAMPLE", "target", "resampled.csv"
-            )
+            target_file = self.util.config_val("RESAMPLE", "target", "resampled.csv")
             # remove encoded labels
             target = self.util.config_val("DATA", "target", "emotion")
             if "class_label" in self.df.columns:
@@ -72,8 +68,7 @@ class Resampler:
             # save file
             self.df.to_csv(target_file)
             self.util.debug(
-                "saved resampled list of files to"
-                f" {os.path.abspath(target_file)}"
+                "saved resampled list of files to" f" {os.path.abspath(target_file)}"
             )
         self.util.debug(f"resampled {succes} files, {error} errors")
 

nkululeko/autopredict/ap_age.py

@@ -2,7 +2,7 @@
 A predictor for age.
 Currently based on audEERING's agender model.
 """
-from nkululeko.util import Util
+from nkululeko.utils.util import Util
 from nkululeko.feature_extractor import FeatureExtractor
 import ast
 import nkululeko.glob_conf as glob_conf
@@ -21,9 +21,7 @@ class AgePredictor:
 
     def predict(self, split_selection):
         self.util.debug(f"predicting age for {split_selection} samples")
-        feats_name = "_".join(
-            ast.literal_eval(glob_conf.config["DATA"]["databases"])
-        )
+        feats_name = "_".join(ast.literal_eval(glob_conf.config["DATA"]["databases"]))
         self.feature_extractor = FeatureExtractor(
             self.df, ["agender_agender"], feats_name, split_selection
         )

nkululeko/autopredict/ap_arousal.py

@@ -2,7 +2,7 @@
 A predictor for emotional arousal.
 Currently based on audEERING's emotional dimension model.
 """
-from nkululeko.util import Util
+from nkululeko.utils.util import Util
 from nkululeko.feature_extractor import FeatureExtractor
 import ast
 import nkululeko.glob_conf as glob_conf
@@ -21,9 +21,7 @@ class ArousalPredictor:
 
     def predict(self, split_selection):
         self.util.debug(f"predicting arousal for {split_selection} samples")
-        feats_name = "_".join(
-            ast.literal_eval(glob_conf.config["DATA"]["databases"])
-        )
+        feats_name = "_".join(ast.literal_eval(glob_conf.config["DATA"]["databases"]))
         self.feature_extractor = FeatureExtractor(
             self.df, ["auddim"], feats_name, split_selection
         )

nkululeko/autopredict/ap_dominance.py

@@ -3,7 +3,7 @@ A predictor for emotional dominance.
 Currently based on audEERING's emotional dimension model.
 """
 
-from nkululeko.util import Util
+from nkululeko.utils.util import Util
 from nkululeko.feature_extractor import FeatureExtractor
 import ast
 import nkululeko.glob_conf as glob_conf
@@ -21,9 +21,7 @@ class DominancePredictor:
 
     def predict(self, split_selection):
         self.util.debug(f"predicting dominance for {split_selection} samples")
-        feats_name = "_".join(
-            ast.literal_eval(glob_conf.config["DATA"]["databases"])
-        )
+        feats_name = "_".join(ast.literal_eval(glob_conf.config["DATA"]["databases"]))
         self.feature_extractor = FeatureExtractor(
             self.df, ["auddim"], feats_name, split_selection
         )

nkululeko/autopredict/ap_gender.py

@@ -2,7 +2,7 @@
 A predictor for biological sex.
 Currently based on audEERING's agender model.
 """
-from nkululeko.util import Util
+from nkululeko.utils.util import Util
 from nkululeko.feature_extractor import FeatureExtractor
 import ast
 import nkululeko.glob_conf as glob_conf
@@ -21,9 +21,7 @@ class GenderPredictor:
 
     def predict(self, split_selection):
         self.util.debug(f"predicting gender for {split_selection} samples")
-        feats_name = "_".join(
-            ast.literal_eval(glob_conf.config["DATA"]["databases"])
-        )
+        feats_name = "_".join(ast.literal_eval(glob_conf.config["DATA"]["databases"]))
         self.feature_extractor = FeatureExtractor(
             self.df, ["agender_agender"], feats_name, split_selection
         )

nkululeko/autopredict/ap_mos.py

@@ -1,7 +1,7 @@
 """"
 A predictor for MOS - mean opinion score.
 """
-from nkululeko.util import Util
+from nkululeko.utils.util import Util
 import ast
 import nkululeko.glob_conf as glob_conf
 from nkululeko.feature_extractor import FeatureExtractor
@@ -22,9 +22,7 @@ class MOSPredictor:
     def predict(self, split_selection):
         self.util.debug(f"estimating MOS for {split_selection} samples")
         return_df = self.df.copy()
-        feats_name = "_".join(
-            ast.literal_eval(glob_conf.config["DATA"]["databases"])
-        )
+        feats_name = "_".join(ast.literal_eval(glob_conf.config["DATA"]["databases"]))
         self.feature_extractor = FeatureExtractor(
             self.df, ["mos"], feats_name, split_selection
         )

nkululeko/autopredict/ap_pesq.py

@@ -1,7 +1,7 @@
 """"
 A predictor for PESQ - Perceptual Evaluation of Speech Quality.
 """
-from nkululeko.util import Util
+from nkululeko.utils.util import Util
 import ast
 import nkululeko.glob_conf as glob_conf
 from nkululeko.feature_extractor import FeatureExtractor
@@ -22,9 +22,7 @@ class PESQPredictor:
     def predict(self, split_selection):
         self.util.debug(f"estimating PESQ for {split_selection} samples")
         return_df = self.df.copy()
-        feats_name = "_".join(
-            ast.literal_eval(glob_conf.config["DATA"]["databases"])
-        )
+        feats_name = "_".join(ast.literal_eval(glob_conf.config["DATA"]["databases"]))
         self.feature_extractor = FeatureExtractor(
             self.df, ["squim"], feats_name, split_selection
         )

nkululeko/autopredict/ap_sdr.py

@@ -2,7 +2,7 @@
 A predictor for SDR - Signal to Distortion Ratio.
 as estimated by Scale-Invariant Signal-to-Distortion Ratio (SI-SDR) 
 """
-from nkululeko.util import Util
+from nkululeko.utils.util import Util
 import ast
 import nkululeko.glob_conf as glob_conf
 from nkululeko.feature_extractor import FeatureExtractor
@@ -23,9 +23,7 @@ class SDRPredictor:
     def predict(self, split_selection):
         self.util.debug(f"estimating SDR for {split_selection} samples")
         return_df = self.df.copy()
-        feats_name = "_".join(
-            ast.literal_eval(glob_conf.config["DATA"]["databases"])
-        )
+        feats_name = "_".join(ast.literal_eval(glob_conf.config["DATA"]["databases"]))
         self.feature_extractor = FeatureExtractor(
             self.df, ["squim"], feats_name, split_selection
         )

nkululeko/autopredict/ap_snr.py

@@ -1,7 +1,7 @@
 """"
 A predictor for SNR - signal-to-noise ratio.
 """
-from nkululeko.util import Util
+from nkululeko.utils.util import Util
 import ast
 import nkululeko.glob_conf as glob_conf
 from nkululeko.feature_extractor import FeatureExtractor
@@ -22,9 +22,7 @@ class SNRPredictor:
     def predict(self, split_selection):
         self.util.debug(f"estimating SNR for {split_selection} samples")
         return_df = self.df.copy()
-        feats_name = "_".join(
-            ast.literal_eval(glob_conf.config["DATA"]["databases"])
-        )
+        feats_name = "_".join(ast.literal_eval(glob_conf.config["DATA"]["databases"]))
         self.feature_extractor = FeatureExtractor(
             self.df, ["snr"], feats_name, split_selection
         )

nkululeko/autopredict/ap_stoi.py

@@ -1,7 +1,7 @@
 """"
 A predictor for STOI - Short-Time Objective Intelligibility (STOI)
 """
-from nkululeko.util import Util
+from nkululeko.utils.util import Util
 import ast
 import nkululeko.glob_conf as glob_conf
 from nkululeko.feature_extractor import FeatureExtractor
@@ -22,9 +22,7 @@ class STOIPredictor:
     def predict(self, split_selection):
         self.util.debug(f"estimating STOI for {split_selection} samples")
         return_df = self.df.copy()
-        feats_name = "_".join(
-            ast.literal_eval(glob_conf.config["DATA"]["databases"])
-        )
+        feats_name = "_".join(ast.literal_eval(glob_conf.config["DATA"]["databases"]))
         self.feature_extractor = FeatureExtractor(
             self.df, ["squim"], feats_name, split_selection
         )

nkululeko/autopredict/ap_valence.py

@@ -2,7 +2,7 @@
 A predictor for emotional valence.
 Currently based on audEERING's emotional dimension model.
 """
-from nkululeko.util import Util
+from nkululeko.utils.util import Util
 from nkululeko.feature_extractor import FeatureExtractor
 import ast
 import nkululeko.glob_conf as glob_conf
@@ -21,9 +21,7 @@ class ValencePredictor:
 
     def predict(self, split_selection):
         self.util.debug(f"predicting valence for {split_selection} samples")
-        feats_name = "_".join(
-            ast.literal_eval(glob_conf.config["DATA"]["databases"])
-        )
+        feats_name = "_".join(ast.literal_eval(glob_conf.config["DATA"]["databases"]))
         self.feature_extractor = FeatureExtractor(
             self.df, ["auddim"], feats_name, split_selection
         )

nkululeko/constants.py

@@ -1,2 +1,2 @@
-VERSION="0.76.0"
+VERSION="0.77.1"
 SAMPLING_RATE = 16000

nkululeko/data/dataset.py

@@ -14,8 +14,7 @@ import nkululeko.glob_conf as glob_conf
 from nkululeko.filter_data import DataFilter
 from nkululeko.plots import Plots
 from nkululeko.reporting.report_item import ReportItem
-from nkululeko.util import Util
-import nkululeko.split.split_utils as split
+from nkululeko.utils.util import Util
 
 
 class Dataset:
@@ -431,6 +430,9 @@ class Dataset:
 
     def balanced_split(self):
         """One way to split train and eval sets: Generate split dataframes for some balancing criterion"""
+        from splitutils import binning
+        from splitutils import optimize_traintest_split
+
         seed = 42
         k = 30
         test_size = int(self.util.config_val_data(self.name, "test_size", 20)) / 100.0
@@ -441,7 +443,7 @@ class Dataset:
         bins = self.util.config_val("DATA", f"bin", False)
         if bins:
             nbins = len(ast.literal_eval(bins))
-            targets = split.binning(targets, nbins=nbins)
+            targets = binning(targets, nbins=nbins)
         # on which variable to split
         speakers = df["speaker"].to_numpy()
 
@@ -460,7 +462,7 @@ class Dataset:
                     data = df[stratif_var].to_numpy()
                     bins = self.util.config_val("DATA", f"{stratif_var}_bins", False)
                     if bins:
-                        data = split.binning(data, nbins=int(bins))
+                        data = binning(data, nbins=int(bins))
                     stratif_vars_array[stratif_var] = data
         # weights for all stratify_on variables and
         # and for test proportion match. Give target
@@ -473,7 +475,8 @@ class Dataset:
             weights[key] = value
         # find optimal test indices TEST_I in DF
         # info: dict with goodness of split information
-        train_i, test_i, info = split.optimize_traintest_split(
+
+        train_i, test_i, info = optimize_traintest_split(
             X=df,
             y=targets,
             split_on=speakers,

nkululeko/demo.py

@@ -5,19 +5,15 @@
 
 from nkululeko.experiment import Experiment
 import configparser
-from nkululeko.util import Util
+from nkululeko.utils.util import Util
 from nkululeko.constants import VERSION
 import argparse
 import os
 
 
 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 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)"
     )
@@ -66,6 +62,4 @@ 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(cwd)  # use this if you want to state the config file path on command line

nkululeko/demo_predictor.py

@@ -1,5 +1,5 @@
 import nkululeko.glob_conf as glob_conf
-from nkululeko.util import Util
+from nkululeko.utils.util import Util
 import numpy as np
 import sounddevice as sd
 import audiofile

nkululeko/experiment.py

@@ -25,7 +25,7 @@ from nkululeko.reporting.report import Report
 from nkululeko.runmanager import Runmanager
 from nkululeko.scaler import Scaler
 from nkululeko.test_predictor import Test_predictor
-from nkululeko.util import Util
+from nkululeko.utils.util import Util
 
 
 class Experiment:
@@ -45,10 +45,15 @@ class Experiment:
         audeer.mkdir(self.data_dir)  # create the experiment directory
         self.util = Util("experiment")
         glob_conf.set_util(self.util)
-        try:
-            with open(os.path.join(self.data_dir, "report.pkl"), "rb") as handle:
-                self.report = pickle.load(handle)
-        except FileNotFoundError:
+        fresh_report = eval(self.util.config_val("REPORT", "fresh", "False"))
+        if not fresh_report:
+            try:
+                with open(os.path.join(self.data_dir, "report.pkl"), "rb") as handle:
+                    self.report = pickle.load(handle)
+            except FileNotFoundError:
+                self.report = Report()
+        else:
+            self.util.debug("starting a fresh report")
             self.report = Report()
         glob_conf.set_report(self.report)
         self.loso = self.util.config_val("MODEL", "loso", False)

nkululeko/explore.py

@@ -3,18 +3,15 @@
 
 from nkululeko.experiment import Experiment
 import configparser
-from nkululeko.util import Util
+from nkululeko.utils.util import Util
 from nkululeko.constants import VERSION
 import argparse
 import os
 
+
 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 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
@@ -47,9 +44,7 @@ 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"))
     tsne = eval(util.config_val("EXPL", "tsne", "False"))
@@ -70,6 +65,4 @@ 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(cwd)  # use this if you want to state the config file path on command line

nkululeko/export.py

@@ -8,18 +8,14 @@ import audeer
 import argparse
 import audiofile
 from nkululeko.experiment import Experiment
-from nkululeko.util import Util
+from nkululeko.utils.util import Util
 from nkululeko.constants import VERSION
 import shutil
 
 
 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 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
@@ -52,9 +48,7 @@ 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}")
 
     # export
     df_train = expr.df_train
@@ -62,9 +56,7 @@ def main(src_dir):
     target_root = util.config_val("EXPORT", "root", "./exported_data/")
     orig_root = util.config_val("EXPORT", "orig_root", None)
     data_name = util.config_val("EXPORT", "data_name", "export")
-    segments_as_files = eval(
-        util.config_val("EXPORT", "segments_as_files", "False")
-    )
+    segments_as_files = eval(util.config_val("EXPORT", "segments_as_files", "False"))
     audeer.mkdir(target_root)
     splits = {"train": df_train, "test": df_test}
     df_all = pd.DataFrame()
@@ -81,12 +73,11 @@ def main(src_dir):
                     always_2d=True,
                 )
                 file_name = (
-                    os.path.splitext(file)[0]
-                    + "_"
-                    + start.total_seconds()
-                    + ".wav"
+                    os.path.splitext(file)[0] + "_" + start.total_seconds() + ".wav"
+                )
+                wav_folder = (
+                    f"{target_root}/{os.path.basename(os.path.normpath(orig_root))}"
                 )
-                wav_folder = f"{target_root}/{os.path.basename(os.path.normpath(orig_root))}"
                 audeer.mkdir(wav_folder)
                 new_rel_path = file_dir[
                     file_dir.index(orig_root) + 1 + len(orig_root) :
@@ -99,7 +90,9 @@ def main(src_dir):
                 files.append(new_file_name)
             else:
                 file_name = os.path.basename(file)
-                wav_folder = f"{target_root}/{os.path.basename(os.path.normpath(orig_root))}"
+                wav_folder = (
+                    f"{target_root}/{os.path.basename(os.path.normpath(orig_root))}"
+                )
                 audeer.mkdir(wav_folder)
                 new_rel_path = file_dir[
                     file_dir.index(orig_root) + 1 + len(orig_root) :
@@ -121,15 +114,11 @@ def main(src_dir):
         df_all = df_all.rename(columns={"class_label": target})
 
     df_all.to_csv(f"{target_root}/{data_name}.csv")
-    util.debug(
-        f"saved {data_name}.csv to {target_root}, {df.shape[0]} samples."
-    )
+    util.debug(f"saved {data_name}.csv to {target_root}, {df.shape[0]} samples.")
 
     print("DONE")
 
 
 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(cwd)  # use this if you want to state the config file path on command line