nkululeko 0.91.1__py3-none-any.whl → 0.91.3__py3-none-any.whl

nkululeko/autopredict/ap_sid.py

@@ -0,0 +1,43 @@
+""""
+A predictor for sid - Speaker ID.
+"""
+
+from pyannote.audio import Pipeline
+
+
+import numpy as np
+
+import nkululeko.glob_conf as glob_conf
+from nkululeko.feature_extractor import FeatureExtractor
+from nkululeko.utils.util import Util
+
+
+class SIDPredictor:
+    """SIDPredictor.
+
+    predicting speaker id.
+    """
+
+    def __init__(self, df):
+        self.df = df
+        self.util = Util("sidPredictor")
+        self.pipeline = Pipeline.from_pretrained(
+            "pyannote/speaker-diarization-3.1",
+            use_auth_token="HUGGINGFACE_ACCESS_TOKEN_GOES_HERE",
+        )
+
+    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"]))
+        self.feature_extractor = FeatureExtractor(
+            self.df, ["squim"], feats_name, split_selection
+        )
+        result_df = self.feature_extractor.extract()
+        # replace missing values by 0
+        result_df = result_df.fillna(0)
+        result_df = result_df.replace(np.nan, 0)
+        result_df.replace([np.inf, -np.inf], 0, inplace=True)
+        pred_vals = result_df.pesq * 100
+        return_df["pesq_pred"] = pred_vals.astype("int") / 100
+        return return_df

nkululeko/constants.py

@@ -1,2 +1,2 @@
-VERSION="0.91.1"
+VERSION="0.91.3"
 SAMPLING_RATE = 16000

nkululeko/data/dataset_csv.py

@@ -39,6 +39,8 @@ class Dataset_CSV(Dataset):
             df = audformat.utils.read_csv(data_file)
         if isinstance(df, pd.Series):
             df = df.to_frame()
+        elif isinstance(df, pd.Index):
+            df = pd.DataFrame(index=df)
         rename_cols = self.util.config_val_data(self.name, "colnames", False)
         if rename_cols:
             col_dict = ast.literal_eval(rename_cols)
@@ -78,7 +80,11 @@ class Dataset_CSV(Dataset):
 
         self.df = df
         self.db = None
-        self.got_target = True
+        target = self.util.config_val("DATA", "target", None)
+        if target is not None:
+            self.got_target = True
+        else:
+            self.got_target = False
         self.is_labeled = self.got_target
         self.start_fresh = eval(self.util.config_val("DATA", "no_reuse", "False"))
         is_index = False

nkululeko/experiment.py

@@ -125,7 +125,15 @@ class Experiment:
         # df = pd.read_csv(storage, header=0, index_col=[0,1,2])
         # df.index.set_levels(pd.to_timedelta(df.index.levels[1]), level=1)
         # df.index.set_levels(pd.to_timedelta(df.index.levels[2]), level=2)
-        df = audformat.utils.read_csv(storage)
+        try:
+            df = audformat.utils.read_csv(storage)
+        except ValueError:
+            # split might be empty
+            return pd.DataFrame()
+        if isinstance(df, pd.Series):
+            df = df.to_frame()
+        elif isinstance(df, pd.Index):
+            df = pd.DataFrame(index=df)
         df.is_labeled = True if self.target in df else False
         # print(df.head())
         return df

nkululeko/plots.py

@@ -305,6 +305,9 @@ class Plots:
         except AttributeError as ae:
             self.util.warn(ae)
             ax = sns.histplot(df, x="duration", kde=True)
+        except ValueError as error:
+            self.util.warn(error)
+            ax = sns.histplot(df, x="duration", kde=True)
         min = self.util.to_3_digits(df.duration.min())
         max = self.util.to_3_digits(df.duration.max())
         title = f"Duration distr. for {sample_selection} {df.shape[0]}. min={min}, max={max}"

nkululeko/segment.py

@@ -110,7 +110,7 @@ def main():
     )
     print("")
     # remove encoded labels
-    target = util.config_val("DATA", "target", "emotion")
+    target = util.config_val("DATA", "target", None)
     if "class_label" in df_seg.columns:
         df_seg = df_seg.drop(columns=[target])
         df_seg = df_seg.rename(columns={"class_label": target})

nkululeko/test_pretrain.py

@@ -216,7 +216,6 @@ def doit(config_file):
     )
 
     class Trainer(transformers.Trainer):
-
         def compute_loss(
             self,
             model,

{nkululeko-0.91.1.dist-info → nkululeko-0.91.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: nkululeko
-Version: 0.91.1
+Version: 0.91.3
 Summary: Machine learning audio prediction experiments based on templates
 Home-page: https://github.com/felixbur/nkululeko
 Author: Felix Burkhardt
@@ -200,7 +200,7 @@ 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
+  * *--config*: which experiments (INI files) to combine
   * *--method* (optional): majority_voting, mean (default), max, sum, uncertainty, uncertainty_weighted, confidence_weighted, performance_weighted  
   * *--threshold*: uncertainty threshold (1.0 means no threshold)
   * *--weights*: weights for performance_weighted method (could be from previous UAR, ACC)
@@ -261,7 +261,7 @@ There's my [blog](http://blog.syntheticspeech.de/?s=nkululeko) with tutorials:
 * [Predict new labels for your data from public models and check bias](http://blog.syntheticspeech.de/2023/08/16/nkululeko-how-to-predict-labels-for-your-data-from-existing-models-and-check-them/)
 * [Resample](http://blog.syntheticspeech.de/2023/08/31/how-to-fix-different-sampling-rates-in-a-dataset-with-nkululeko/)
 * [Get some statistics on correlation and effect-size](http://blog.syntheticspeech.de/2023/09/05/nkululeko-get-some-statistics-on-correlation-and-effect-size/)
-* [Automatic generation  of a latex / pdf report](http://blog.syntheticspeech.de/2023/09/26/nkululeko-generate-a-latex-pdf-report/) 
+* [Automatic generation of a latex / pdf report](http://blog.syntheticspeech.de/2023/09/26/nkululeko-generate-a-latex-pdf-report/) 
 * [Inspect your data with Spotlight](http://blog.syntheticspeech.de/2023/10/31/nkululeko-inspect-your-data-with-spotlight/)
 * [Automatically stratify your split sets](http://blog.syntheticspeech.de/2023/11/07/nkululeko-automatically-stratify-your-split-sets/)
 * [re-name data column names](http://blog.syntheticspeech.de/2023/11/16/nkululeko-re-name-data-column-names/)
@@ -355,6 +355,15 @@ F. Burkhardt, Johannes Wagner, Hagen Wierstorf, Florian Eyben and Björn Schulle
 Changelog
 =========
 
+Version 0.91.3
+--------------
+* some additions for robustness
+
+Version 0.91.2
+--------------
+* making lint work by excluding constants from check
+
+Version 0.91.1
 --------------
 * minor refactoring in ensemble module
 

{nkululeko-0.91.1.dist-info → nkululeko-0.91.3.dist-info}/RECORD

@@ -2,13 +2,13 @@ nkululeko/__init__.py,sha256=62f8HiEzJ8rG2QlTFJXUCMpvuH3fKI33DoJSj33mscc,63
 nkululeko/aug_train.py,sha256=FoMbBrfyOZd4QAw7oIHl3X6-UpsqAKWVDIolCA7qOWs,3196
 nkululeko/augment.py,sha256=3RzaxB3gRxovgJVjHXi0glprW01J7RaHhUkqotW2T3U,2955
 nkululeko/cacheddataset.py,sha256=XFpWZmbJRg0pvhnIgYf0TkclxllD-Fctu-Ol0PF_00c,969
-nkululeko/constants.py,sha256=iYlIApfoK9ylYhWWe4mizk150FEYR7mV6iaGEZJ9NNU,39
+nkululeko/constants.py,sha256=tT5Su7q7ufkiVtsEMOV5FgJVkE2U8idmrVxrNi4gFmc,39
 nkululeko/demo-ft.py,sha256=iD9Pzp9QjyAv31q1cDZ75vPez7Ve8A4Cfukv5yfZdrQ,770
 nkululeko/demo.py,sha256=4Yzhg6pCPBYPGJrP7JX2TysVosl_R1llpVDKc2P_gUA,4955
 nkululeko/demo_feats.py,sha256=BvZjeNFTlERIRlq34OHM4Z96jdDQAhB01BGQAUcX9dM,2026
 nkululeko/demo_predictor.py,sha256=lDF-xOxRdEAclOmbepAYg-BQXQdGkHfq2n74PTIoop8,4872
 nkululeko/ensemble.py,sha256=71V-rre61H3J4sh7lu-OTo4I2_g7mm_rQxwW1ARDHgY,12782
-nkululeko/experiment.py,sha256=octx5S4Y8-gAD0dXCRb6DFZwsXTYgzk06RBA3LX2SN0,31388
+nkululeko/experiment.py,sha256=kRz3diGyupXneXFBLmmUm6BV-sGSqQJv44Zojn0Bhcs,31649
 nkululeko/explore.py,sha256=Y5lPPychnI-7fyP8zvwVb9P09fvprbUPOofOppuABYQ,3658
 nkululeko/export.py,sha256=U-V4acxtuL6qKt6oAsVcM5TTeWogYUJ3GU-lA6rq6d4,4336
 nkululeko/feature_extractor.py,sha256=UnspIWz3XrNhKnBBhWZkH2bHvD-sROtrQVqB1JvkUyw,4088
@@ -20,16 +20,16 @@ nkululeko/modelrunner.py,sha256=lJy-xM4QfDDWeL0dLTE_VIb4sYrnd_Z_yJRK3wwohQA,1119
 nkululeko/multidb.py,sha256=sO6OwJn8sn1-C-ig3thsIL8QMWHdV9SnJhDodKjeKrI,6876
 nkululeko/nkuluflag.py,sha256=PGWSmZz-PiiHLgcZJAoGOI_Y-sZDVI1ksB8p5r7riWM,3725
 nkululeko/nkululeko.py,sha256=M7baIq2nAoi6dEoBL4ATEuqAs5U1fvl_hyqAl5DybAQ,2040
-nkululeko/plots.py,sha256=p9YyN-xAtdGBKjcA305V0KOagAzG8VG6D_Ceoa9rae4,22964
+nkululeko/plots.py,sha256=sR061gOsyvuh8UBYS52FINSal4CYNQgvq3B4WOSimDw,23092
 nkululeko/predict.py,sha256=b35YOqovGb5PLDz0nDuhJGykEAPq2Y45R9lzxJZMuMU,2083
 nkululeko/resample.py,sha256=akSAjJ3qn-O5NAyLJHVHdsK7MUZPGaZUvM2TwMSmj2M,5194
 nkululeko/runmanager.py,sha256=AswmORVUkCIH0gTx6zEyufvFATQBS8C5TXo2erSNdVg,7611
 nkululeko/scaler.py,sha256=7VOZ4sREMoQtahfETt9RyuR29Fb7PCwxlYVjBbdCVFc,4101
-nkululeko/segment.py,sha256=S8TZt728CADXBEVw7GTWQq42vdXkRxmL738C8V_iy3k,4324
+nkululeko/segment.py,sha256=PAc5sVLoqKzOVENd9A5ybaKrJOvD9WEPwDdJGTv6OIM,4319
 nkululeko/syllable_nuclei.py,sha256=5w_naKxNxz66a_qLkraemi2fggM-gWesiiBPS47iFcE,9931
 nkululeko/test.py,sha256=1w624vo5KTzmFC8BUStGlLDmIEAFuJUz7J0W-gp7AxI,1677
 nkululeko/test_predictor.py,sha256=DEHE_D3A6m6KJTrpDKceA1n655t_UZV3WQd57K4a3Ho,2863
-nkululeko/test_pretrain.py,sha256=jZxwnKrUKo04j2I92RiaCpbf7su-bbqGhMFS_2M7n-s,8464
+nkululeko/test_pretrain.py,sha256=6FZeETlWzg9Cq_sn3BFKhfH91jW26nAIDm1bJkInNNA,8463
 nkululeko/augmenting/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nkululeko/augmenting/augmenter.py,sha256=TUUznEz0pe9DSMC9r7LoBckuvsJTprvypeV5-8zLn20,2846
 nkululeko/augmenting/randomsplicer.py,sha256=TKPqp8np5dvyJIAjOTvtlanatFQ9OwKxZ02QoCwZ2Jw,2802
@@ -43,13 +43,14 @@ nkululeko/autopredict/ap_gender.py,sha256=b6oTqHKVwOnYh4YlKbuMflssS4HJqs_c1ayusa
 nkululeko/autopredict/ap_mos.py,sha256=e4hmgb0Yf1_AbC5P0CqXJIvufjhbTrqmI5goARxrY0Y,1107
 nkululeko/autopredict/ap_pesq.py,sha256=mRt3Loucaoy4vJxwfuxUt0fP88bMGvkmrLCEpKEXWp0,1140
 nkululeko/autopredict/ap_sdr.py,sha256=VQ2UkxOO3ipqYNNjFwKgEaGCk8IzLI5lX_2tZFLIvTY,1188
+nkululeko/autopredict/ap_sid.py,sha256=1TYJg-Bg_LJGPzIWF-oYtXmD5Otvi0fW_f8uzEVZY5g,1309
 nkululeko/autopredict/ap_snr.py,sha256=AiTU8-7CMEeowmYkMO19lw1HCb1yTXC6KeulNf8gOqw,1110
 nkululeko/autopredict/ap_stoi.py,sha256=UEQg1ZV0meAsxgdWB8ieRs9GPXHqArmsaOyCGRwpcnA,1187
 nkululeko/autopredict/ap_valence.py,sha256=WrW4Ltqi_odW49_4QEVKkfnrcztLIVZ4cXIEHu4dBN8,1026
 nkululeko/autopredict/estimate_snr.py,sha256=1k9-XadABudnsNOeFZD_Fg0E64-GUQVS7JEp82MLQS4,4995
 nkululeko/data/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nkululeko/data/dataset.py,sha256=Hz2IOsdcESG-P3aP7r4d1xj_gIP6fyGCYOwukoQ7SM8,29321
-nkululeko/data/dataset_csv.py,sha256=rPiOIy9Da0wne05kdpGHMpKMAgHy4a1dnB6At9jJuAM,4590
+nkululeko/data/dataset_csv.py,sha256=mb7FpHOmJHxpt1QYVBKveyqJN3MUt30TRfwwJw0TT5c,4816
 nkululeko/feat_extract/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nkululeko/feat_extract/feats_agender.py,sha256=onfAQ6-xx_mFMJXEF1IX8cHBmGtGeX6weJmxbkfh1_o,3184
 nkululeko/feat_extract/feats_agender_agender.py,sha256=_YQv1qw--3uQfnyTQDCwlmPRnrhdMhgXbYK2yQtseW0,3464
@@ -110,9 +111,9 @@ nkululeko/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nkululeko/utils/files.py,sha256=UiGAtZRWYjHSvlmPaTMtzyNNGE6qaLaxQkybctS7iRM,4021
 nkululeko/utils/stats.py,sha256=vCRzhCR0Gx5SiJyAGbj1TIto8ocGz58CM5Pr3LltagA,2948
 nkululeko/utils/util.py,sha256=XFZdhCc_LM4EmoZ5tKKaBCQLXclcNmvHwhfT_CXB98c,16723
-nkululeko-0.91.1.dist-info/LICENSE,sha256=0zGP5B_W35yAcGfHPS18Q2B8UhvLRY3dQq1MhpsJU_U,1076
-nkululeko-0.91.1.dist-info/METADATA,sha256=F-icPu_THEFHxMm-uAV5MALbVMLrXcO3ZuoPeo6bPwk,41417
-nkululeko-0.91.1.dist-info/WHEEL,sha256=OVMc5UfuAQiSplgO0_WdW7vXVGAt9Hdd6qtN4HotdyA,91
-nkululeko-0.91.1.dist-info/entry_points.txt,sha256=lNTkFEdh6Kjo5o95ZAWf_0Lq-4ztGoAoMVSDuPtuyS0,442
-nkululeko-0.91.1.dist-info/top_level.txt,sha256=DPFNNSHPjUeVKj44dVANAjuVGRCC3MusJ08lc2a8xFA,10
-nkululeko-0.91.1.dist-info/RECORD,,
+nkululeko-0.91.3.dist-info/LICENSE,sha256=0zGP5B_W35yAcGfHPS18Q2B8UhvLRY3dQq1MhpsJU_U,1076
+nkululeko-0.91.3.dist-info/METADATA,sha256=FI1hcOEFJbfAHNQi1SCFhPv7sC06vdWa75lIw2Ix4YA,41584
+nkululeko-0.91.3.dist-info/WHEEL,sha256=P9jw-gEje8ByB7_hXoICnHtVCrEwMQh-630tKvQWehc,91
+nkululeko-0.91.3.dist-info/entry_points.txt,sha256=lNTkFEdh6Kjo5o95ZAWf_0Lq-4ztGoAoMVSDuPtuyS0,442
+nkululeko-0.91.3.dist-info/top_level.txt,sha256=DPFNNSHPjUeVKj44dVANAjuVGRCC3MusJ08lc2a8xFA,10
+nkululeko-0.91.3.dist-info/RECORD,,

{nkululeko-0.91.1.dist-info → nkululeko-0.91.3.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (75.2.0)
+Generator: setuptools (75.3.0)
 Root-Is-Purelib: true
 Tag: py3-none-any