nkululeko 0.48.0__py3-none-any.whl → 0.49.0__py3-none-any.whl

nkululeko/augment.py

@@ -38,7 +38,13 @@ def main(src_dir):
     util.debug(f'train shape : {expr.df_train.shape}, test shape:{expr.df_test.shape}')
 
     # augment
-    expr.augment()
+    augmenting = util.config_val('DATA', 'augment', False)
+    if augmenting:
+        expr.augment()
+    
+    random_splicing = util.config_val('DATA', 'random_splice', False)
+    if random_splicing:
+        expr.random_splice()
 
     print('DONE')
 

nkululeko/augmenter.py

@@ -12,8 +12,8 @@ class Augmenter:
     """
         augmenting the train split
     """
-    def __init__(self, train_df):
-        self.train_df = train_df
+    def __init__(self, df):
+        self.df = df
         self.util = Util()
         # Define a standard transformation that randomly add augmentations to files
         self.audioment = Compose([
@@ -30,15 +30,15 @@ class Augmenter:
  #       audeer.mkdir(newpath)
         return fp.replace(fullpath, np)
 
-    def augment(self):
+    def augment(self, sample_selection):
         """
         augment the training files and return a dataframe with new files index.
         """
-        files = self.train_df.index.get_level_values(0).values
+        files = self.df.index.get_level_values(0).values
         store = self.util.get_path('store')
         filepath = f'{store}augmentations/'
         audeer.mkdir(filepath)
-        self.util.debug(f'augmenting the training set to {filepath}')
+        self.util.debug(f'augmenting {sample_selection} samples to {filepath}')
         newpath = ''
         for i, f in enumerate(files):
             signal, sr = audiofile.read(f)
@@ -50,9 +50,9 @@ class Augmenter:
             audiofile.write(f'{newpath}{filename}', signal=sig_aug, sampling_rate=sr)
             if i%10==0:
                 print(f'augmented {i} of {len(files)}')
-        df_ret = self.train_df.copy()
+        df_ret = self.df.copy()
         df_ret = df_ret.set_index(map_file_path(df_ret.index, lambda x: self.changepath(x, newpath)))
-        aug_db_filename = self.util.config_val('DATA', 'augment', 'augment.csv')
+        aug_db_filename = self.util.config_val('DATA', 'augment_result', 'augment.csv')
         target = self.util.config_val('DATA', 'target', 'emotion')
         df_ret[target] = df_ret['class_label']
         df_ret = df_ret.drop(columns=['class_label'])

nkululeko/constants.py

@@ -1 +1 @@
-VERSION = '0.48.0'
+VERSION = '0.49.0'

nkululeko/dataset.py

@@ -51,7 +51,15 @@ class Dataset:
             train_tables = ast.literal_eval(trains)
             tables += train_tables
         return tables
-
+    
+    def _load_db(self):
+        root = self.util.config_val_data(self.name, '', '')
+        self.util.debug(f'{self.name}: loading from {root}')
+        try:
+            self.db = audformat.Database.load(root)
+        except FileNotFoundError:
+            self.util.error( f'{self.name}: no database found at {root}')
+        return root
 
     def load(self):
         """Load the dataframe with files, speakers and task labels"""
@@ -59,6 +67,7 @@ class Dataset:
         store = self.util.get_path('store')
         store_file = f'{store}{self.name}.pkl'
         self.util.debug(f'{self.name}: loading ...')
+        root = self._load_db()
 #        self.got_speaker, self.got_gender = False, False 
         if not self.start_fresh and os.path.isfile(store_file):
             self.util.debug(f'{self.name}: reusing previously stored file {store_file}')
@@ -71,29 +80,23 @@ class Dataset:
                 f'samples: got targets: {self.is_labeled}, got speakers: {self.got_speaker}, '\
                 f'got sexes: {self.got_gender}')        
             return
-        root = self.util.config_val_data(self.name, '', '')
-        self.util.debug(f'{self.name}: loading from {root}')
-        try:
-            db = audformat.Database.load(root)
-        except FileNotFoundError:
-            self.util.error( f'{self.name}: no database found at {root}')
         tables = self._get_tables()
         self.util.debug(f'{self.name}: loading tables: {tables}')
         #db = audb.load(root, )
         # map the audio file paths 
-        db.map_files(lambda x: os.path.join(root, x))
+        self.db.map_files(lambda x: os.path.join(root, x))
         # the dataframes (potentially more than one) with at least the file names
         df_files = self.util.config_val_data(self.name, 'files_tables', '[\'files\']')
         df_files_tables =  ast.literal_eval(df_files)
         # The label for the target column 
         self.col_label = self.util.config_val_data(self.name, 'label', self.target)
-        df, self.is_labeled, self.got_speaker, self.got_gender, self.got_age = self._get_df_for_lists(db, df_files_tables)
+        df, self.is_labeled, self.got_speaker, self.got_gender, self.got_age = self._get_df_for_lists(self.db, df_files_tables)
         if False in {self.is_labeled, self.got_speaker, self.got_gender, self.got_age}:
             try :
             # There might be a separate table with the targets, e.g. emotion or age    
                 df_targets = self.util.config_val_data(self.name, 'target_tables', f'[\'{self.target}\']')
                 df_target_tables =  ast.literal_eval(df_targets)
-                df_target, got_target2, got_speaker2, got_gender2, got_age2 = self._get_df_for_lists(db, df_target_tables)
+                df_target, got_target2, got_speaker2, got_gender2, got_age2 = self._get_df_for_lists(self.db, df_target_tables)
                 self.is_labeled = got_target2 or self.is_labeled
                 self.got_speaker = got_speaker2 or self.got_speaker
                 self.got_gender = got_gender2 or self.got_gender
@@ -117,7 +120,6 @@ class Dataset:
         df.got_age = self.got_age
         df.got_speaker = self.got_speaker
         self.df = df
-        self.db = db
         self.df.is_labeled = self.is_labeled
         self.util.debug(f'Loaded database {self.name} with {df.shape[0]} '\
             f'samples: got targets: {self.is_labeled}, got speakers: {self.got_speaker}, '\

nkululeko/experiment.py

@@ -292,18 +292,38 @@ class Experiment:
 
     def augment(self):
         """
-        Augment the training set
+        Augment the selected samples
         """
         from nkululeko.augmenter import Augmenter
-        augmenter = Augmenter(self.df_train)
-        augmenter.augment()
-
-    # def augment_train(self):
-    #     """Augment the train dataframe"""
-    #     from nkululeko.augmenter import Augmenter
-    #     augment_train = Augmenter(self.df_train)
-    #     df_train_aug = augment_train.augment()
-    #     self.df_train = self.df_train.append(df_train_aug)
+        sample_selection = self.util.config_val(' DATA', 'augment', 'train')
+        if sample_selection=='all':
+            df = pd.concat([self.df_train, self.df_test])
+        elif sample_selection=='train':
+            df = self.df_train
+        elif sample_selection=='test':
+            df = self.df_test
+        else:
+            self.util.error(f'unknown augmentation selection specifier {sample_selection}, should be [all | train | test]')
+
+        augmenter = Augmenter(df)
+        augmenter.augment(sample_selection)
+
+    def random_splice(self):
+        """
+        Random-splice the selected samples
+        """
+        from nkululeko.randomsplicer import Randomsplicer
+        sample_selection = self.util.config_val(' DATA', 'random_splice', 'train')
+        if sample_selection=='all':
+            df = pd.concat([self.df_train, self.df_test])
+        elif sample_selection=='train':
+            df = self.df_train
+        elif sample_selection=='test':
+            df = self.df_test
+        else:
+            self.util.error(f'unknown augmentation selection specifier {sample_selection}, should be [all | train | test]')
+        randomsplicer = Randomsplicer(df)
+        randomsplicer.run(sample_selection)
 
 
     def analyse_features(self, needs_feats):

nkululeko/feinberg_praat.py

@@ -119,7 +119,6 @@ def runPCA(df):
     # PCA
     pca = PCA(n_components=2)
     principalComponents = pca.fit_transform(x)
-    print(type(principalComponents))
     if np.any(np.isnan(principalComponents)):
         print ('pc is nan')
         print(f'count: {np.count_nonzero(np.isnan(principalComponents))}')

nkululeko/randomsplicer.py

@@ -0,0 +1,76 @@
+# randomsplicer.py
+
+"""
+Code originally by Oliver Pauly
+
+Based on an idea by Klaus Scherer
+
+K. R. Scherer, “Randomized splicing: A note on a simple technique for masking speech content” 
+Journal of Experimental Research in Personality, vol. 5, pp. 155–159, 1971.
+
+Evaluated in:
+F. Burkhardt, Anna Derington, Matthias Kahlau, Klaus Scherer, Florian Eyben and Björn Schuller: Masking Speech Contents by Random Splicing: is Emotional Expression Preserved?, Proc. ICASSP, 2023
+
+"""
+
+import pandas as pd
+from nkululeko.util import Util 
+import nkululeko.randomsplicing as rsp
+import numpy as np
+import audiofile as af
+import os
+from audformat.utils import map_file_path
+import audeer
+
+class Randomsplicer:
+    """
+        augmenting the train split
+    """
+    def __init__(self, df):
+        self.df = df
+        self.util = Util()
+
+    def changepath(self, fp, np):
+        fullpath = os.path.dirname(fp)
+        return fp.replace(fullpath, np)
+
+    def run(self, sample_selection):
+        """
+        random splice the selected samples and return a dataframe with new files index.
+            adjustable parameters:
+            * p_reverse: probability of some samples to be in reverse order (default: 0.3)
+            * top_db: top db level for silence to be recognized (default: 12)   
+        """
+
+        p_reverse=0.3
+        top_db=12
+
+        files = self.df.index.get_level_values(0).values
+        store = self.util.get_path('store')
+        filepath = f'{store}randomspliced/'
+        audeer.mkdir(filepath)
+        self.util.debug(f'random splicing {sample_selection} samples to {filepath}')
+        newpath = ''
+        for i, f in enumerate(files):
+            signal, sr = af.read(f)
+            filename = os.path.basename(f)
+            parent = os.path.dirname(f).split('/')[-1]
+            sig_new = rsp.random_splicing(
+                signal, sr,
+                p_reverse=p_reverse,
+                top_db=top_db,
+                )
+
+            newpath = f'{filepath}/{parent}/'
+            audeer.mkdir(newpath)
+            af.write(f'{newpath}{filename}', signal=sig_new, sampling_rate=sr)
+            if i%10==0:
+                print(f'random spliced {i} of {len(files)}')
+        df_ret = self.df.copy()
+        df_ret = df_ret.set_index(map_file_path(df_ret.index, lambda x: self.changepath(x, newpath)))
+        db_filename = self.util.config_val('DATA', 'random_splice_result', 'random_spliced.csv')
+        target = self.util.config_val('DATA', 'target', 'emotion')
+        df_ret[target] = df_ret['class_label']
+        df_ret = df_ret.drop(columns=['class_label'])
+        df_ret.to_csv(db_filename)
+        return df_ret

nkululeko/randomsplicing.py

@@ -0,0 +1,74 @@
+"""
+Code originally by Oliver Pauly
+
+Based on an idea by Klaus Scherer
+
+K. R. Scherer, “Randomized splicing: A note on a simple technique for masking speech content” 
+Journal of Experimental Research in Personality, vol. 5, pp. 155–159, 1971.
+
+Evaluated in:
+F. Burkhardt, Anna Derington, Matthias Kahlau, Klaus Scherer, Florian Eyben and Björn Schuller: Masking Speech Contents by Random Splicing: is Emotional Expression Preserved?, Proc. ICASSP, 2023
+
+"""
+import numpy as np
+import librosa
+import audiofile as af
+
+def random_splicing(
+    signal, sr,
+    p_reverse=0.0,
+    top_db=12,
+    ):
+    """
+    randomly splice the signal and re-arrange.    
+    
+    p_reverse: probability of some samples to be in reverse order
+    top_db:  top db level for silence to be recognized
+    
+    """
+    signal /= np.max(abs(signal))
+
+    indices = split_wav_naive(signal, top_db=top_db)
+
+    np.random.shuffle(indices) 
+
+    wav_spliced = remix_random_reverse(signal, indices, p_reverse=p_reverse)
+        
+    return wav_spliced
+
+
+def split_wav_naive(wav, top_db=12):
+      
+    indices = librosa.effects.split(wav, top_db=top_db)
+    
+    indices = np.array(indices)
+    # (re)add the silence-segments
+    indices = indices.repeat(2)[1:-1].reshape((-1, 2))
+    # add first segment
+    indices = np.vstack(((0, indices[0][0]), indices))
+    # add last segment
+    indices = np.vstack((indices, [indices[-1][-1], wav.shape[0]]))
+
+    return indices
+
+
+def remix_random_reverse(wav, indices, p_reverse=0):
+    
+    import random
+
+    wav_remix = []
+    
+    for seg in indices:
+        
+        start = seg[0]
+        end = seg[1]
+        wav_seg = wav[start:end]
+            
+        if np.random.rand(1)[0] <= p_reverse:
+            wav_seg = wav_seg[::-1]
+    
+        wav_remix.append(wav_seg)
+        
+    wav_remix = np.hstack(wav_remix)
+    
+    return wav_remix

{nkululeko-0.48.0.dist-info → nkululeko-0.49.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: nkululeko
-Version: 0.48.0
+Version: 0.49.0
 Summary: Machine learning audio prediction experiments based on templates
 Home-page: https://github.com/felixbur/nkululeko
 Author: Felix Burkhardt
@@ -239,6 +239,14 @@ Nkululeko can be used under the [MIT license](https://choosealicense.com/license
 Changelog
 =========
 
+Version 0.49.0
+--------------
+* added random-splicing
+
+Version 0.48.1
+--------------
+* bugfix: database object was not loaded when dataframe was reused
+
 Version 0.48.0
 --------------
 * enabled specific feature selection for praat and opensmile features

{nkululeko-0.48.0.dist-info → nkululeko-0.49.0.dist-info}/RECORD

@@ -1,15 +1,15 @@
 nkululeko/__init__.py,sha256=62f8HiEzJ8rG2QlTFJXUCMpvuH3fKI33DoJSj33mscc,63
-nkululeko/augment.py,sha256=J-HxHKU7u1xZdIiVw_abYVYWOUmZI84HMQNQpcoYk9s,1385
-nkululeko/augmenter.py,sha256=whDW3mnda33Wl9TUk2yG_My6507PFCqCzBgy0027Q2c,2399
+nkululeko/augment.py,sha256=rl7oCNWSyg6CGTy0t5BAYayQebhRRSDX5etLwpNyFjo,1595
+nkululeko/augmenter.py,sha256=Ut7bIHspL7OovmB3Zo81UarKZtYTUg2B68aMUEcmnjQ,2404
 nkululeko/balancer.py,sha256=64ftZN68sMDfkvuovCDHpAHmSJgCO6Kdk9bwmpSisec,12
 nkululeko/cacheddataset.py,sha256=bSJ_SDg7TxL89YL_pJXp-sFvdUXJtHuBTd5KSTE4AkQ,955
-nkululeko/constants.py,sha256=AnpegoMFbAq1OJWivUVuj3UsmEPMR5bGnwjnYbtvP8Q,18
-nkululeko/dataset.py,sha256=bsuW00zcLHU5xHpcFSwNT8FHM_2-8e34qsRjM6Jg-L8,21627
+nkululeko/constants.py,sha256=1-g8LlrznB2-gkAcuxyB5d6ESYqVCNUpbjMnueTmqEE,18
+nkululeko/dataset.py,sha256=ISnU4EuGC3Af2Z5F57d47e94_ZnI7aWqfwcYD7VlcVo,21705
 nkululeko/dataset_csv.py,sha256=2VTZizY5cXPFAUkRRkQSAz-RjoHtwM1OroJA9ZvhfUA,2042
 nkululeko/dataset_ravdess.py,sha256=pTt98sr4_egdUCv2fWepkZTlkQ6x3A2YshO_n302DNg,537
 nkululeko/demo.py,sha256=OwmliItSdzCvsjN2maC4_mFc-ZKzzjwwAiobKTWRizA,1815
 nkululeko/demo_predictor.py,sha256=hYuvvKyW-DxbORAq1Y63owqhRgq-Bl8qPOymVISvO7M,2286
-nkululeko/experiment.py,sha256=waTSajWp7yKSfWfJjMu__EHnL-uf-_JRCn-KukiXUCY,20319
+nkululeko/experiment.py,sha256=Oj3xkKGUG0QIWwhophzwWmpJvNTWDs9ljf0n8MIy2RQ,21185
 nkululeko/explore.py,sha256=HfHrCPl5LbjgfbG7Z_SNRQKv36_m81QuTb8TWrrOXJ8,1960
 nkululeko/feats_analyser.py,sha256=RWR9-YK1bJ4f2OrA1aGu33nRxg4qLZ_xNqh7lC_zHh4,3821
 nkululeko/feats_audmodel.py,sha256=w-cV9Fgk_9wAV5u4ELzxvB9KM06IptPFneDenXXEmV0,2748
@@ -24,7 +24,7 @@ nkululeko/feats_trill.py,sha256=m_052ZPPjhrvt6LeXytJEpfCtDlxI5GywA2NfkIR-to,2975
 nkululeko/feats_wav2vec2.py,sha256=S63QmTiGlyEalO4HjacAh9KxOAVO80vZntG-Alk91WU,4005
 nkululeko/feature_extractor.py,sha256=_NZt0Cy407FFSx9H_oPzrMf_tdBogRafb9koOHmsizk,3456
 nkululeko/featureset.py,sha256=MoKrd7nx6IN6F3joi88BoQBx0vSiTjtWBT0JcGOn8IY,1319
-nkululeko/feinberg_praat.py,sha256=T3Wcd3cE2Ge5ytj2DyWFC100qPA82pT_x0AIkz33Y8U,19509
+nkululeko/feinberg_praat.py,sha256=fUrdVo1aJNitdG1L0sZRfIvGMJJdQwG3BXoAV5xjh5o,19472
 nkululeko/filter_data.py,sha256=vzUT7b1sW-_d4kurFcd9_PYkpwdE7KUggDnO_jtEnxM,1821
 nkululeko/glob_conf.py,sha256=2Tl0NZQeVeydDO8T2tuJC2lCv99wvaTVRX9Dy1Mq_L4,237
 nkululeko/loss_ccc.py,sha256=BM2I6j_rjKlpua5gKbo81EAS3hhZK-ClBTqJHot9Ils,939
@@ -46,6 +46,8 @@ nkululeko/model_xgr.py,sha256=rOJ3QZjTLIpxHh6GqyCo-ewG9IUL35Fd-0jRDNuM_bk,242
 nkululeko/modelrunner.py,sha256=5Ix7lD5OqfRAzDutLZFKqv6v3WXe_u3KCODr7w2KhrU,5367
 nkululeko/nkululeko.py,sha256=XblSDCn2tzXydhOAavYYEnIR2cC1Z9ceOREGAoLmPYQ,1540
 nkululeko/plots.py,sha256=bRrBIUvX3On0VrcXkzvazjri736HNzDz_Ap9YpDz5io,6554
+nkululeko/randomsplicer.py,sha256=GXp-H4OETrNdRRthmn_1KkkEsrM1alNB_6tEgpmyeTM,2659
+nkululeko/randomsplicing.py,sha256=MOLwxFTM0omsVBmKAN82PmGkD4zNnxwDYoWS4WQnuVU,1867
 nkululeko/reporter.py,sha256=aI6bVgTkvHTrJGHMSzcQvFjDftI-VeOCXhqRS6qh-40,10167
 nkululeko/result.py,sha256=Ey5FPsAyfnQVtzO_J6_4hkOAZ191YWmF_vXxlgNjCdc,406
 nkululeko/runmanager.py,sha256=No6l8422bAI-GmPchA41KnTIFMFe4J3kdcBlj2tuaiU,6753
@@ -54,8 +56,8 @@ nkululeko/syllable_nuclei.py,sha256=vK9dj5deqRnyEmlZmhFtKPzqKVGNCgTnWaG8UDITKNg,
 nkululeko/test.py,sha256=yv-9Qh30CDsud3NwRJ8jS9RzGyKNKqM_UOvYSw_aPuQ,1366
 nkululeko/test_predictor.py,sha256=4XGFa9AsHNtOkGdY0X23RxPpESyAlICqoXqR-YidHXA,2315
 nkululeko/util.py,sha256=83YKkdDPyyK8L2WGyA64YcRXMweXmeuLSsbcVymfaMY,8967
-nkululeko-0.48.0.dist-info/LICENSE,sha256=0zGP5B_W35yAcGfHPS18Q2B8UhvLRY3dQq1MhpsJU_U,1076
-nkululeko-0.48.0.dist-info/METADATA,sha256=yryB8TKPki6H_zmKXxxXyIgUL6qJ2T0tbpKeyQE9MUQ,18769
-nkululeko-0.48.0.dist-info/WHEEL,sha256=pkctZYzUS4AYVn6dJ-7367OJZivF2e8RA9b_ZBjif18,92
-nkululeko-0.48.0.dist-info/top_level.txt,sha256=DPFNNSHPjUeVKj44dVANAjuVGRCC3MusJ08lc2a8xFA,10
-nkululeko-0.48.0.dist-info/RECORD,,
+nkululeko-0.49.0.dist-info/LICENSE,sha256=0zGP5B_W35yAcGfHPS18Q2B8UhvLRY3dQq1MhpsJU_U,1076
+nkululeko-0.49.0.dist-info/METADATA,sha256=M9iRkSojEyaOL8Ej2DueKrZaREDUBkTZR0We_Oeq0ew,18922
+nkululeko-0.49.0.dist-info/WHEEL,sha256=pkctZYzUS4AYVn6dJ-7367OJZivF2e8RA9b_ZBjif18,92
+nkululeko-0.49.0.dist-info/top_level.txt,sha256=DPFNNSHPjUeVKj44dVANAjuVGRCC3MusJ08lc2a8xFA,10
+nkululeko-0.49.0.dist-info/RECORD,,