nkululeko 0.88.4__py3-none-any.whl → 0.88.6__py3-none-any.whl

nkululeko/constants.py

@@ -1,2 +1,2 @@
-VERSION="0.88.4"
+VERSION="0.88.6"
 SAMPLING_RATE = 16000

nkululeko/data/dataset.py

@@ -423,6 +423,9 @@ class Dataset:
             self.util.debug(f"{self.name}: trying to reuse data splits")
             self.df_test = pd.read_pickle(storage_test)
             self.df_train = pd.read_pickle(storage_train)
+        elif isinstance(ast.literal_eval(split_strategy), list):
+            # treat this as a list of test speakers
+            self.assign_speakers(ast.literal_eval(split_strategy))
         else:
             self.util.error(f"unknown split strategy: {split_strategy}")
 
@@ -515,6 +518,19 @@ class Dataset:
         # because this generates new train/test sample quantaties, the feature extraction has to be done again
         glob_conf.config["FEATS"]["needs_feature_extraction"] = "True"
 
+    def assign_speakers(self, speakers):
+        """One way to split train and eval sets: Specify test speaker names."""
+        self.df_test = self.df[self.df.speaker.isin(speakers)]
+        if len(self.df_test) == 0:
+            self.util.error(f"no speakers found in {speakers}")
+        self.df_train = self.df[~self.df.index.isin(self.df_test.index)]
+        self.util.debug(
+            f"{self.name} (speakers assigned): [{self.df_train.shape[0]}/{self.df_test.shape[0]}]"
+            " samples in train/test"
+        )
+        # because this generates new train/test sample quantaties, the feature extraction has to be done again
+        glob_conf.config["FEATS"]["needs_feature_extraction"] = "True"
+
     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))

nkululeko/feat_extract/feats_agender.py

@@ -1,13 +1,14 @@
 # feats_agender.py
+
 from nkululeko.feat_extract.featureset import Featureset
 import os
-import pandas as pd
+# import pandas as pd
 import audeer
 import nkululeko.glob_conf as glob_conf
 import audonnx
 import numpy as np
 import audinterface
-
+import torch
 
 class AgenderSet(Featureset):
     """
@@ -32,7 +33,8 @@ class AgenderSet(Featureset):
             archive_path = audeer.download_url(
                 model_url, cache_root, verbose=True)
             audeer.extract_archive(archive_path, model_root)
-        device = self.util.config_val("MODEL", "device", "cpu")
+        cuda = "cuda" if torch.cuda.is_available() else "cpu"
+        device = self.util.config_val("MODEL", "device", cuda)
         self.model = audonnx.load(model_root, device=device)
         self.util.debug(f"initialized agender model")
         self.model_loaded = True

nkululeko/feat_extract/feats_spkrec.py

@@ -24,7 +24,7 @@ class Spkrec(Featureset):
     def __init__(self, name, data_df, feat_type):
         """Constructor. is_train is needed to distinguish from test/dev sets,
         because they use the codebook from the training"""
-        super().__init__(name, data_df)
+        super().__init__(name, data_df, feat_type)
         # check if device is not set, use cuda if available
         cuda = "cuda" if torch.cuda.is_available() else "cpu"
         self.device = self.util.config_val("MODEL", "device", cuda)

nkululeko/reporting/reporter.py

@@ -2,28 +2,32 @@ import ast
 import glob
 import json
 import math
-import os
 
-from confidence_intervals import evaluate_with_conf_int
 import matplotlib.pyplot as plt
 import numpy as np
+
+# from torch import is_tensor
+from audmetric import (
+    accuracy,
+    concordance_cc,
+    mean_absolute_error,
+    mean_squared_error,
+    unweighted_average_recall,
+)
+
+# import os
+from confidence_intervals import evaluate_with_conf_int
 from scipy.special import softmax
-from scipy.stats import entropy
-from scipy.stats import pearsonr
-from sklearn.metrics import ConfusionMatrixDisplay
-from sklearn.metrics import auc
-from sklearn.metrics import classification_report
-from sklearn.metrics import confusion_matrix
-from sklearn.metrics import r2_score
-from sklearn.metrics import roc_auc_score
-from sklearn.metrics import roc_curve
-from torch import is_tensor
-
-from audmetric import accuracy
-from audmetric import concordance_cc
-from audmetric import mean_absolute_error
-from audmetric import mean_squared_error
-from audmetric import unweighted_average_recall
+from scipy.stats import entropy, pearsonr
+from sklearn.metrics import (
+    ConfusionMatrixDisplay,
+    auc,
+    classification_report,
+    confusion_matrix,
+    r2_score,
+    roc_auc_score,
+    roc_curve,
+)
 
 import nkululeko.glob_conf as glob_conf
 from nkululeko.plots import Plots
@@ -167,7 +171,7 @@ class Reporter:
             probas["uncertainty"] = uncertainty
             probas["correct"] = probas.predicted == probas.truth
             sp = self.util.get_pred_name()
-            
+
             self.probas = probas
             probas.to_csv(sp)
             self.util.debug(f"Saved probabilities to {sp}")
@@ -175,7 +179,13 @@ class Reporter:
             ax, caption = plots.plotcatcont(
                 probas, "correct", "uncertainty", "uncertainty", "correct"
             )
-            plots.save_plot(ax, caption, "Uncertainty", "uncertainty", "samples")
+            plots.save_plot(
+                ax,
+                caption,
+                "Uncertainty",
+                "uncertainty_samples",
+                self.util.get_exp_name(),
+            )
 
     def set_id(self, run, epoch):
         """Make the report identifiable with run and epoch index."""

nkululeko/utils/util.py

@@ -157,8 +157,9 @@ class Util:
 
     def get_pred_name(self):
         store = self.get_path("store")
+        target = self.get_target_name()
         pred_name = self.get_model_description()
-        return f"{store}/pred_{pred_name}.csv"
+        return f"{store}/pred_{target}_{pred_name}.csv"
 
     def is_categorical(self, pd_series):
         """Check if a dataframe column is categorical"""
@@ -217,9 +218,14 @@ class Util:
         return_string = f"{ds}"
         if not only_data:
             mt = self.get_model_description()
-            return_string = return_string + "_" + mt
+            target = self.get_target_name()
+            return_string = return_string + "_" + target + "_" + mt
         return return_string.replace("__", "_")
 
+    def get_target_name(self):
+        """Get a string as name from all target sets that are used."""
+        return self.config["DATA"]["target"]
+
     def get_model_type(self):
         return self.config["MODEL"]["type"]
 

{nkululeko-0.88.4.dist-info → nkululeko-0.88.6.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: nkululeko
-Version: 0.88.4
+Version: 0.88.6
 Summary: Machine learning audio prediction experiments based on templates
 Home-page: https://github.com/felixbur/nkululeko
 Author: Felix Burkhardt
@@ -68,7 +68,8 @@ 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 nkululeko: [Finetune transformer-models](http://blog.syntheticspeech.de/2024/05/29/nkululeko-how-to-finetune-a-transformer-model/)
+* NEW with nkululek: [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)
 * [Here's a blog post on how to set up nkululeko on your computer.](http://blog.syntheticspeech.de/2021/08/30/how-to-set-up-your-first-nkululeko-project/)
@@ -203,7 +204,7 @@ All of them take *--config <my_config.ini>* as an argument.
 * **nkululeko.nkululeko**: do machine learning experiments combining features and learners
 * **nkululeko.ensemble**: [combine several nkululeko experiments](http://blog.syntheticspeech.de/2024/06/25/nkululeko-ensemble-classifiers-with-late-fusion/) and report on late fusion results
   * *configurations*: which experiments to combine
-  * *--method* (optional): mean, max, sum, max_class, uncertainty_threshold, uncertainty_weighted, confidence_weighted
+  * *--method* (optional): majority_voting, mean, max, sum, max_class, uncertainty_threshold, uncertainty_weighted, confidence_weighted
   * *--threshold*: uncertainty threshold (1.0 means no threshold)
   * *--outfile* (optional): name of CSV file for output
   * *--no_labels* (optional): indicate that no ground truth is given 
@@ -359,6 +360,16 @@ F. Burkhardt, Johannes Wagner, Hagen Wierstorf, Florian Eyben and Björn Schulle
 Changelog
 =========
 
+Version 0.88.6
+--------------
+* added test speaker assign
+
+Version 0.88.5
+--------------
+* add a unique name to the uncertainty plot
+* fix error in speaker embedding (still need speechbrain < 1.0)
+* add get_target_name function in util
+
 Version 0.88.4
 --------------
 * added more ensemble methods, e.g. based on uncertainty

{nkululeko-0.88.4.dist-info → nkululeko-0.88.6.dist-info}/RECORD

@@ -2,7 +2,7 @@ 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=iiVolfJ9RJn2fD9QaaoFnxuLzxJos6Q4H3tzHQGLfp4,39
+nkululeko/constants.py,sha256=HFKr4pZomwthK3M6yBJLjNzKCEuB1PvMeUwKrHm2cL8,39
 nkululeko/demo.py,sha256=bLuHkeEl5rOfm7ecGHCcWATiPK7-njNbtrGljxzNzFs,5088
 nkululeko/demo_feats.py,sha256=sAeGFojhEj9WEDFtG3SzPBmyYJWLF2rkbpp65m8Ujo4,2025
 nkululeko/demo_predictor.py,sha256=zs1bjhpnKuNCPLJeiyDm19ME1NEDOQT3QNeyVKJq9Yc,4882
@@ -46,10 +46,10 @@ nkululeko/autopredict/ap_stoi.py,sha256=It0Lk-ki-gohA2AzD8nkLAN2WahYvD9rPDGTQuvd
 nkululeko/autopredict/ap_valence.py,sha256=n-hctRKySzhmJtowuMOTUu0T_ld3uK5pnfOzWeWW4VM,1024
 nkululeko/autopredict/estimate_snr.py,sha256=S-bpS0xFkwWc4Ch75UrjbS8y538lQ0U3g_iLRFXureY,5048
 nkululeko/data/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-nkululeko/data/dataset.py,sha256=hUD0NqWCfRaSHG8JNs1MsPb0zjUZAf8FJkg_c0ebq0Q,28046
+nkululeko/data/dataset.py,sha256=o2xuluErZg0I8qkR0YtMu2UdewdcgSdRUvUhRXDMwuI,28940
 nkululeko/data/dataset_csv.py,sha256=UGEpi__eT2KFS6Fop6N4HkMrzO-u5VP71gt44kwZavo,4588
 nkululeko/feat_extract/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-nkululeko/feat_extract/feats_agender.py,sha256=Qm69G4kqAyTVVk7wwRgrXlNwGaDMGRYyKGpuf0vOEgM,3113
+nkululeko/feat_extract/feats_agender.py,sha256=sHyvxxlWXv1QGYXHGHIYEQK7X39eifSVie0tu-zBG3M,3189
 nkululeko/feat_extract/feats_agender_agender.py,sha256=tgH2BnwcxpvuLmOkrMbVdBSX0Onfz2MG12FsddalRKI,3424
 nkululeko/feat_extract/feats_analyser.py,sha256=Y9hMpZ9WsQOrxTP3B1diHnzMeOgwbVpVFWVlIyhHMJs,12722
 nkululeko/feat_extract/feats_ast.py,sha256=ycJn5eSVOxcEpmeHVk0FPB8q5XiTC8VSKz61L9n0Wa4,4638
@@ -65,7 +65,7 @@ nkululeko/feat_extract/feats_oxbow.py,sha256=CmIG9cbHTJTJVnzgCPdQpYpnlewWExpsr5Z
 nkululeko/feat_extract/feats_praat.py,sha256=kZrS6srzH7WoWEd2prp1Dxw6g9JklFQGTNq5zzPpHzg,3105
 nkululeko/feat_extract/feats_snr.py,sha256=9dqZ-4RpK98iJEssM3ttozNd18LWlZYM_QVXvp5xDcs,2829
 nkululeko/feat_extract/feats_spectra.py,sha256=5Pex8awIQC3cjQRHSu4NQFmg4quamG0RL3V3Yd0pJHs,3670
-nkululeko/feat_extract/feats_spkrec.py,sha256=VK4ma3uWzM0YZStsgRTirfkbzjWIfRWSgsYI038QlRY,4803
+nkululeko/feat_extract/feats_spkrec.py,sha256=FugR-X2lDFKLLRRhKnhUYJhz-VIktIj8iVEDLbwNwtw,4814
 nkululeko/feat_extract/feats_squim.py,sha256=Y31YmDmscuG0YozvxyBZIutO3id8t7IZJWCfKucw-6M,4617
 nkululeko/feat_extract/feats_trill.py,sha256=K2ahhdpwpjgg3WZS1POg3UMP2U44i8cLZZvn5Rq7fUI,3228
 nkululeko/feat_extract/feats_wav2vec2.py,sha256=XyxD4NcrF4VFWSeHkXCKWdEOdr8VMzgVUz8N4mwhdyo,5248
@@ -98,7 +98,7 @@ nkululeko/reporting/defines.py,sha256=IsY1YgKRMaABpylVKjBJgJ5bNCEbGCVA_E6pivraqS
 nkululeko/reporting/latex_writer.py,sha256=qiCRSmB4KOD_za4oHu5x-PhwjZohzfo8wecMOwlXZwc,1886
 nkululeko/reporting/report.py,sha256=W0rcigDdjBvxZQ3pZja_gvToILYvaZ1BFtnN2qFRfYI,1060
 nkululeko/reporting/report_item.py,sha256=siWeGNgo4bAE46YBMNcsdf3jTMTy76BO9Fi6DTvDig4,533
-nkululeko/reporting/reporter.py,sha256=vV6SAHWSIvybFvXBGapHjPmWWhKxIsIWuVO-uY9RHzQ,19219
+nkululeko/reporting/reporter.py,sha256=Gt8tEiDQ9rbsYAKb-EbKGVaogPWKKoAEkwtVeiFoTSA,19119
 nkululeko/reporting/result.py,sha256=G63a2tHCwHhM6NBJgYzsWKWJm4Yu3r4hsCHA2Km7eHU,1073
 nkululeko/segmenting/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nkululeko/segmenting/seg_inaspeechsegmenter.py,sha256=pmLHuXsaqvcdYxB4PSW9l1mbQWZZBJFhi_CGabqydas,1947
@@ -106,9 +106,9 @@ 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=eC9dMO-by6CDnGLHDBQu-2B4-BudZNJ0nnWGhKYdUMA,2968
-nkululeko/utils/util.py,sha256=nK108-v6UubFj2kjJo38flS2yTTeUZyu3gNBGyhaR1c,16512
-nkululeko-0.88.4.dist-info/LICENSE,sha256=0zGP5B_W35yAcGfHPS18Q2B8UhvLRY3dQq1MhpsJU_U,1076
-nkululeko-0.88.4.dist-info/METADATA,sha256=WHQrQU39sA1MuTnFTF6Fs47wWfVAtcQTQ4Tga_i5gB0,39583
-nkululeko-0.88.4.dist-info/WHEEL,sha256=y4mX-SOX4fYIkonsAGA5N0Oy-8_gI4FXw5HNI1xqvWg,91
-nkululeko-0.88.4.dist-info/top_level.txt,sha256=DPFNNSHPjUeVKj44dVANAjuVGRCC3MusJ08lc2a8xFA,10
-nkululeko-0.88.4.dist-info/RECORD,,
+nkululeko/utils/util.py,sha256=y-pdrjovT8yGtBTJ3ifIpTcF0fPnoz8UKbuLIZ0efpc,16768
+nkululeko-0.88.6.dist-info/LICENSE,sha256=0zGP5B_W35yAcGfHPS18Q2B8UhvLRY3dQq1MhpsJU_U,1076
+nkululeko-0.88.6.dist-info/METADATA,sha256=7UE8yEbdfJo_SU4xeE3gLlaLkfwC2NEg7w1nou8eGLQ,39955
+nkululeko-0.88.6.dist-info/WHEEL,sha256=Wyh-_nZ0DJYolHNn1_hMa4lM7uDedD_RGVwbmTjyItk,91
+nkululeko-0.88.6.dist-info/top_level.txt,sha256=DPFNNSHPjUeVKj44dVANAjuVGRCC3MusJ08lc2a8xFA,10
+nkululeko-0.88.6.dist-info/RECORD,,

{nkululeko-0.88.4.dist-info → nkululeko-0.88.6.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (70.2.0)
+Generator: setuptools (71.1.0)
 Root-Is-Purelib: true
 Tag: py3-none-any