nkululeko 0.93.11__tar.gz → 0.93.13__tar.gz

{nkululeko-0.93.11 → nkululeko-0.93.13}/CHANGELOG.md

@@ -1,12 +1,20 @@
 Changelog
 =========
 
+Version 0.93.13 (24-01-27)
+--------------------------
+* plot: replaced "class_label" by target name for continuous distributions
+
+Version 0.93.12
+---------------
+* bugfix: map_continuous_to_cat crashed on empty data
+
 Version 0.93.11
---------------
+---------------
 * bugfix: silero segmenter assigned file duration values
 
 Version 0.93.10
---------------
+---------------
 * added nan check for imported features
 * added LOGO result output
 

nkululeko-0.93.13/PKG-INFO

@@ -0,0 +1,39 @@
+Metadata-Version: 2.2
+Name: nkululeko
+Version: 0.93.13
+Summary: Machine learning audio prediction experiments based on templates
+Home-page: https://github.com/felixbur/nkululeko
+Author: Felix Burkhardt
+Author-email: fxburk@gmail.com
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Development Status :: 3 - Alpha
+Classifier: Topic :: Scientific/Engineering
+Requires-Python: >=3.9
+License-File: LICENSE
+Requires-Dist: audeer
+Requires-Dist: audformat
+Requires-Dist: audinterface
+Requires-Dist: audiofile
+Requires-Dist: audiomentations
+Requires-Dist: audmetric
+Requires-Dist: audonnx
+Requires-Dist: confidence_intervals
+Requires-Dist: datasets
+Requires-Dist: imageio
+Requires-Dist: matplotlib
+Requires-Dist: numpy
+Requires-Dist: opensmile
+Requires-Dist: pandas
+Requires-Dist: praat-parselmouth
+Requires-Dist: scikit_learn
+Requires-Dist: scipy
+Requires-Dist: seaborn
+Requires-Dist: sounddevice
+Requires-Dist: torch
+Requires-Dist: torchvision
+Requires-Dist: transformers
+Requires-Dist: umap-learn
+Requires-Dist: xgboost
+Requires-Dist: pylatex

{nkululeko-0.93.11 → nkululeko-0.93.13}/README.md

@@ -22,7 +22,7 @@
 ## Overview
 A project to detect speaker characteristics by machine learning experiments with a high-level interface.
 
-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.
+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: [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/)

{nkululeko-0.93.11 → nkululeko-0.93.13}/nkululeko/constants.py

@@ -1,2 +1,2 @@
-VERSION="0.93.11"
+VERSION="0.93.13"
 SAMPLING_RATE = 16000

{nkululeko-0.93.11 → nkululeko-0.93.13}/nkululeko/data/dataset.py

@@ -676,6 +676,8 @@ class Dataset:
 
     def map_continuous_classification(self, df):
         """Map labels to bins for continuous data that should be classified"""
+        if df.empty:
+            return
         if self.check_continuous_classification():
             self.util.debug(f"{self.name}: binning continuous variable to categories")
             cat_vals = self.util.continuous_to_categorical(df[self.target])

{nkululeko-0.93.11 → nkululeko-0.93.13}/nkululeko/feat_extract/feats_analyser.py

@@ -4,8 +4,10 @@ import ast
 import matplotlib.pyplot as plt
 import pandas as pd
 from sklearn.inspection import permutation_importance
-from sklearn.linear_model import LinearRegression, LogisticRegression
-from sklearn.tree import DecisionTreeClassifier, DecisionTreeRegressor
+from sklearn.linear_model import LinearRegression
+from sklearn.linear_model import LogisticRegression
+from sklearn.tree import DecisionTreeClassifier
+from sklearn.tree import DecisionTreeRegressor
 
 import nkululeko.glob_conf as glob_conf
 from nkululeko.plots import Plots

{nkululeko-0.93.11 → nkululeko-0.93.13}/nkululeko/feat_extract/feats_wav2vec2.py

@@ -49,6 +49,7 @@ class Wav2vec2(Featureset):
         hidden_layer = int(self.util.config_val("FEATS", "wav2vec2.layer", "0"))
         config.num_hidden_layers = layer_num - hidden_layer
         self.util.debug(f"using hidden layer #{config.num_hidden_layers}")
+
         self.processor = Wav2Vec2FeatureExtractor.from_pretrained(model_path)
         self.model = Wav2Vec2Model.from_pretrained(model_path, config=config).to(
             self.device

{nkululeko-0.93.11 → nkululeko-0.93.13}/nkululeko/plots.py

@@ -297,6 +297,9 @@ class Plots:
         if cat_col == "class_label":
             plot_df = plot_df.rename(columns={cat_col: self.target})
             cat_col = self.target
+        elif cont_col == "class_label":
+            plot_df = plot_df.rename(columns={cont_col: self.target})
+            cont_col = self.target
         dist_type = self.util.config_val("EXPL", "dist_type", "kde")
         cats, cat_str, es = su.get_effect_size(plot_df, cat_col, cont_col)
         model_type = self.util.get_model_type()
@@ -327,7 +330,7 @@ class Plots:
         if col2 == "class_label":
             plot_df = plot_df.rename(columns={col2: self.target})
             col2 = self.target
-        if col1 == "class_label":
+        elif col1 == "class_label":
             plot_df = plot_df.rename(columns={col1: self.target})
             col1 = self.target
         crosstab = pd.crosstab(index=plot_df[col1], columns=plot_df[col2])

nkululeko-0.93.13/nkululeko.egg-info/PKG-INFO

@@ -0,0 +1,39 @@
+Metadata-Version: 2.2
+Name: nkululeko
+Version: 0.93.13
+Summary: Machine learning audio prediction experiments based on templates
+Home-page: https://github.com/felixbur/nkululeko
+Author: Felix Burkhardt
+Author-email: fxburk@gmail.com
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Development Status :: 3 - Alpha
+Classifier: Topic :: Scientific/Engineering
+Requires-Python: >=3.9
+License-File: LICENSE
+Requires-Dist: audeer
+Requires-Dist: audformat
+Requires-Dist: audinterface
+Requires-Dist: audiofile
+Requires-Dist: audiomentations
+Requires-Dist: audmetric
+Requires-Dist: audonnx
+Requires-Dist: confidence_intervals
+Requires-Dist: datasets
+Requires-Dist: imageio
+Requires-Dist: matplotlib
+Requires-Dist: numpy
+Requires-Dist: opensmile
+Requires-Dist: pandas
+Requires-Dist: praat-parselmouth
+Requires-Dist: scikit_learn
+Requires-Dist: scipy
+Requires-Dist: seaborn
+Requires-Dist: sounddevice
+Requires-Dist: torch
+Requires-Dist: torchvision
+Requires-Dist: transformers
+Requires-Dist: umap-learn
+Requires-Dist: xgboost
+Requires-Dist: pylatex

{nkululeko-0.93.11 → nkululeko-0.93.13}/nkululeko.egg-info/SOURCES.txt

@@ -5,7 +5,6 @@ pyproject.toml
 setup.cfg
 setup.py
 data/aesdd/process_database.py
-data/androids/process_database.py
 data/ased/process_database.py
 data/asvp-esd/process_database.py
 data/baved/process_database.py
@@ -168,5 +167,4 @@ nkululeko/segmenting/seg_silero.py
 nkululeko/utils/__init__.py
 nkululeko/utils/files.py
 nkululeko/utils/stats.py
-nkululeko/utils/util.py
-venv/bin/activate_this.py
+nkululeko/utils/util.py

{nkululeko-0.93.11 → nkululeko-0.93.13}/setup.cfg

@@ -4,8 +4,6 @@ author = Felix Burkhardt
 author_email = fxburk@gmail.com
 description = Machine learning audio prediction experiments based on templates
 version = attr: nkululeko.__version__
-long_description = file: README.md, CHANGELOG.md
-long_description_content_type = text/markdown
 url = https://github.com/felixbur/nkululeko
 classifiers = 
 	Programming Language :: Python :: 3