nkululeko 0.88.9__py3-none-any.whl → 0.88.11__py3-none-any.whl

nkululeko/constants.py

@@ -1,2 +1,2 @@
-VERSION="0.88.9"
+VERSION="0.88.11"
 SAMPLING_RATE = 16000

nkululeko/explore.py

@@ -1,3 +1,24 @@
+"""
+Explore the feature sets of a machine learning experiment.
+
+This script is the entry point for the 'explore' module of the nkululeko framework.
+It handles loading the experiment configuration, setting up the experiment, and
+running various feature exploration techniques based on the configuration.
+
+The script supports the following configuration options:
+- `no_warnings`: If set to `True`, it will ignore all warnings during the exploration.
+- `feature_distributions`: If set to `True`, it will generate plots of the feature distributions.
+- `tsne`: If set to `True`, it will generate a t-SNE plot of the feature space.
+- `scatter`: If set to `True`, it will generate a scatter plot of the feature space.
+- `spotlight`: If set to `True`, it will generate a 'spotlight' plot of the feature space.
+- `shap`: If set to `True`, it will generate SHAP feature importance plots.
+- `model`: The type of model to use for the feature exploration (e.g. 'SVM').
+- `plot_tree`: If set to `True`, it will generate a decision tree plot.
+
+The script can be run from the command line with the `--config` argument to specify
+the configuration file to use. If no configuration file is provided, it will look
+for an `exp.ini` file in the same directory as the script.
+"""
 # explore.py
 # explore the feature sets
 

nkululeko/feat_extract/feats_agender_agender.py

@@ -7,18 +7,19 @@ import nkululeko.glob_conf as glob_conf
 import audonnx
 import numpy as np
 import audinterface
+import torch
 
-
-class AgenderAgenderSet(Featureset):
+class Agender_agenderSet(Featureset):
     """
     Age and gender predictions from the wav2vec2. based model finetuned on agender, described in the paper
     "Speech-based Age and Gender Prediction with Transformers"
     https://arxiv.org/abs/2306.16962
     """
 
-    def __init__(self, name, data_df):
-        super().__init__(name, data_df)
+    def __init__(self, name, data_df, feats_type):
+        super().__init__(name, data_df, feats_type)
         self.model_loaded = False
+        self.feats_type = feats_type
 
     def _load_model(self):
         model_url = "https://zenodo.org/record/7761387/files/w2v2-L-robust-6-age-gender.25c844af-1.1.1.zip"

nkululeko/feat_extract/feats_spkrec.py

@@ -12,7 +12,7 @@ import pandas as pd
 import torch
 import torchaudio
 from nkululeko.feat_extract.featureset import Featureset
-from speechbrain.pretrained import EncoderClassifier
+from speechbrain.inference import EncoderClassifier
 from tqdm import tqdm
 
 # from transformers import HubertModel, Wav2Vec2FeatureExtractor

nkululeko/feat_extract/feinberg_praat.py

@@ -380,11 +380,11 @@ def compute_features(file_index):
     )
 
     # add pca data
-    pcaData = run_pca(df)  # Run jitter and shimmer PCA
-    df = pd.concat([df, pcaData], axis=1)  # Add PCA data
+    pca_data = run_pca(df)  # Run jitter and shimmer PCA
+    df = pd.concat([df, pca_data], axis=1)  # Add PCA data
     # reload the data so it's all numbers
-    df.to_csv("processed_results.csv", index=False)
-    df = pd.read_csv("processed_results.csv", header=0)
+    # df.to_csv("processed_results.csv", index=False)
+    # df = pd.read_csv("processed_results.csv", header=0)
     #    df.sort_values('voiceID').head(20)
     # ## Next we calculate the vocal-tract length estimates
 

nkululeko/models/model_gmm.py

@@ -2,7 +2,7 @@
 
 from sklearn import mixture
 from nkululeko.models.model import Model
-
+import pandas as pd
 
 class GMM_model(Model):
     """An GMM model"""
@@ -12,9 +12,26 @@ class GMM_model(Model):
     def __init__(self, df_train, df_test, feats_train, feats_test):
         super().__init__(df_train, df_test, feats_train, feats_test)
         self.name = "gmm"
-        n_components = int(self.util.config_val("MODEL", "GMM_components", "4"))
+        self.n_components = int(self.util.config_val("MODEL", "GMM_components", "4"))
         covariance_type = self.util.config_val("MODEL", "GMM_covariance_type", "full")
         self.clf = mixture.GaussianMixture(
-            n_components=n_components, covariance_type=covariance_type
+            n_components=self.n_components, 
+            covariance_type=covariance_type,
+            random_state = 42,
         )
         # set up the classifier
+
+    def get_predictions(self):
+        """Use the predict_proba method of the GaussianMixture model to get 
+        probabilities. Create a DataFrame with these probabilities and return 
+        it along with the predictions."""
+        probs = self.clf.predict_proba(self.feats_test)
+        preds = self.clf.predict(self.feats_test)
+        
+        # Convert predictions to a list
+        preds = preds.tolist()
+        
+        # Create a DataFrame for probabilities
+        proba_df = pd.DataFrame(probs, index=self.feats_test.index, columns=range(self.n_components))
+        
+        return preds, proba_df

nkululeko/multidb.py

@@ -1,3 +1,10 @@
+"""
+Demonstrates the usage of the ML-experiment framework for the nkululeko MULTIDB project.
+
+The `main` function is the entry point of the script, which parses command-line arguments, reads a configuration file, and runs the nkululeko or aug_train functions based on the configuration.
+
+The `plot_heatmap` function generates a heatmap plot of the results and saves it to a file, along with some summary statistics.
+"""
 # main.py
 # Demonstration code to use the ML-experiment framework
 

nkululeko/plots.py

@@ -4,14 +4,14 @@ import ast
 import matplotlib.pyplot as plt
 import numpy as np
 import pandas as pd
-from scipy import stats
 import seaborn as sns
+from scipy import stats
 from sklearn.manifold import TSNE
 
 import nkululeko.glob_conf as glob_conf
+import nkululeko.utils.stats as su
 from nkululeko.reporting.defines import Header
 from nkululeko.reporting.report_item import ReportItem
-import nkululeko.utils.stats as su
 from nkululeko.utils.util import Util
 
 
@@ -32,9 +32,9 @@ class Plots:
         # plot the distribution of samples per speaker
         # one up because of the runs
         fig_dir = self.util.get_path("fig_dir") + "../"
-        self.util.debug(f"plotting samples per speaker")
+        self.util.debug("plotting samples per speaker")
         if "gender" in df_speakers:
-            filename = f"samples_value_counts"
+            filename = "samples_value_counts"
             ax = (
                 df_speakers.groupby("samplenum")["gender"]
                 .value_counts()
@@ -46,7 +46,7 @@ class Plots:
                     rot=0,
                 )
             )
-            ax.set_ylabel(f"number of speakers")
+            ax.set_ylabel("number of speakers")
             ax.set_xlabel("number of samples")
             self.save_plot(
                 ax,
@@ -58,7 +58,7 @@ class Plots:
 
             # fig.clear()
         else:
-            filename = f"samples_value_counts"
+            filename = "samples_value_counts"
             ax = (
                 df_speakers["samplenum"]
                 .value_counts()
@@ -265,7 +265,8 @@ class Plots:
         """Plot relation of categorical distribution with continuous."""
         dist_type = self.util.config_val("EXPL", "dist_type", "hist")
         cats, cat_str, es = su.get_effect_size(df, cat_col, cont_col)
-        if dist_type == "hist":
+        model_type = self.util.get_model_type()
+        if dist_type == "hist" and model_type != "tree":
             ax = sns.histplot(df, x=cont_col, hue=cat_col, kde=True)
             caption = f"{ylab} {df.shape[0]}. {cat_str} ({cats}):" f" {es}"
             ax.set_title(caption)
@@ -489,7 +490,7 @@ class Plots:
         glob_conf.report.add_item(
             ReportItem(
                 Header.HEADER_EXPLORE,
-                f"Scatter plot",
+                "Scatter plot",
                 f"using {dimred_type}",
                 filename,
             )
@@ -561,8 +562,8 @@ class Plots:
         glob_conf.report.add_item(
             ReportItem(
                 Header.HEADER_EXPLORE,
-                f"Tree plot",
-                f"for feature importance",
+                "Tree plot",
+                "for feature importance",
                 filename,
             )
         )

{nkululeko-0.88.9.dist-info → nkululeko-0.88.11.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: nkululeko
-Version: 0.88.9
+Version: 0.88.11
 Summary: Machine learning audio prediction experiments based on templates
 Home-page: https://github.com/felixbur/nkululeko
 Author: Felix Burkhardt
@@ -192,8 +192,6 @@ type = svm
 [EXPL]
 model = tree
 plot_tree = True
-[PLOT]
-combine_per_speaker = mode
 ```
 Read the [Hello World example](#hello-world-example) for initial usage with Emo-DB dataset.
 
@@ -204,9 +202,10 @@ 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): majority_voting, mean, max, sum, max_class, uncertainty_threshold, uncertainty_weighted, confidence_weighted
+  * *--method* (optional): majority_voting, mean (default), max, sum, uncertainty, uncertainty_weighted, confidence_weighted, performance_weighted  
   * *--threshold*: uncertainty threshold (1.0 means no threshold)
-  * *--outfile* (optional): name of CSV file for output
+  * *--weightes*: weights for performance_weighted method (could be from previous UAR, ACC)
+  * *--outfile* (optional): name of CSV file for output (default: ensemble_result.csv)
   * *--no_labels* (optional): indicate that no ground truth is given 
 * **nkululeko.multidb**: do [multiple experiments](http://blog.syntheticspeech.de/2024/01/02/nkululeko-compare-several-databases/), comparing several databases cross and in itself
 * **nkululeko.demo**: [demo the current best model](http://blog.syntheticspeech.de/2022/01/24/nkululeko-try-out-demo-a-trained-model/) on the command line
@@ -360,6 +359,15 @@ F. Burkhardt, Johannes Wagner, Hagen Wierstorf, Florian Eyben and Björn Schulle
 Changelog
 =========
 
+Version 0.88.11
+--------------
+* removed hack in Praat script 
+
+Version 0.88.10
+--------------
+* SVM C val defaults to 1
+* fixed agender_agender naming bug
+
 Version 0.88.9
 --------------
 * added performance_weighted ensemble

{nkululeko-0.88.9.dist-info → nkululeko-0.88.11.dist-info}/RECORD

@@ -2,23 +2,23 @@ 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=tK1QIQ72lahwT47cOoEvhMfH2sH4BRnP3p6P7kdC_QQ,39
+nkululeko/constants.py,sha256=vAMfrlfXY0Xl1htJgzd9fGZGvioFWzmphB4SRJLDRfQ,40
 nkululeko/demo.py,sha256=bLuHkeEl5rOfm7ecGHCcWATiPK7-njNbtrGljxzNzFs,5088
 nkululeko/demo_feats.py,sha256=sAeGFojhEj9WEDFtG3SzPBmyYJWLF2rkbpp65m8Ujo4,2025
 nkululeko/demo_predictor.py,sha256=zs1bjhpnKuNCPLJeiyDm19ME1NEDOQT3QNeyVKJq9Yc,4882
 nkululeko/ensemble.py,sha256=cVz8hWd2m7poyS0lTIfrsha0K8U-hd6eiBWMqDOAlt8,12669
 nkululeko/experiment.py,sha256=L4PzoScPLG2xTyniVy9evcBy_8CIe3RTeTEUVTqiuvQ,31186
-nkululeko/explore.py,sha256=lDzRoW_Taa5u4BBABZLD89BcQWnYlrftJR4jgt1yyj0,2609
+nkululeko/explore.py,sha256=_GOgcRaPvh2xBbKPAkSJjYzgHhD_xb3ZCB6M1MPA6ao,3867
 nkululeko/export.py,sha256=mHeEAAmtZuxdyebLlbSzPrHSi9OMgJHbk35d3DTxRBc,4632
 nkululeko/feature_extractor.py,sha256=UnspIWz3XrNhKnBBhWZkH2bHvD-sROtrQVqB1JvkUyw,4088
 nkululeko/file_checker.py,sha256=LoLnL8aHpW-axMQ46qbqrManTs5otG9ShpEZuz9iRSk,3474
 nkululeko/filter_data.py,sha256=w-X2mhKdYr5DxDIz50E5yzO6Jmzk4jjDBoXsgOOVtcA,7222
 nkululeko/glob_conf.py,sha256=KL9YJQTHvTztxo1vr25qRRgaPnx4NTg0XrdbovKGMmw,525
 nkululeko/modelrunner.py,sha256=cKYD9a7MRoBxfqUy3X8kf6rGTYho-33In8I9YkzMOo8,11196
-nkululeko/multidb.py,sha256=1X2vZwDHf6HuYKCoIGDP34FECMZ2mcGNZ6-cFYZFnIQ,6332
+nkululeko/multidb.py,sha256=CCjmVsZyvydgOztFlaeBvOJH8nsvU-sPQdFAw8-q0U4,6752
 nkululeko/nkuluflag.py,sha256=PGWSmZz-PiiHLgcZJAoGOI_Y-sZDVI1ksB8p5r7riWM,3725
 nkululeko/nkululeko.py,sha256=Kn3s2E3yyH8cJ7z6lkMxrnqtCxTu7-qfe9Zr_ONTD5g,1968
-nkululeko/plots.py,sha256=WsI_dtPKfrYPsKymHRmIhqj33aZzTcE8fF_EwLkm_5A,22899
+nkululeko/plots.py,sha256=gfNy9Eu2PhSaykMazBPThcYS5o5KwuQwY2jshAUK5Rk,22965
 nkululeko/predict.py,sha256=sF091sSSLnEWcISx9ZcULLie3tY5XeFsQJd6b3vrxFg,2409
 nkululeko/resample.py,sha256=2d9eao_0sLrGZ_KSl8OVKsPor3BkFrlmMhrpB9WelIs,4267
 nkululeko/runmanager.py,sha256=xvxL5a9d3jtGFqx0Z3nyyxowA368uNyP0ZitO8kxIIE,7581
@@ -50,7 +50,7 @@ nkululeko/data/dataset.py,sha256=xaawk5QthuVStWjHWTFBtorcIe71lbPQgC6mHzSXGeI,292
 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=sHyvxxlWXv1QGYXHGHIYEQK7X39eifSVie0tu-zBG3M,3189
-nkululeko/feat_extract/feats_agender_agender.py,sha256=tgH2BnwcxpvuLmOkrMbVdBSX0Onfz2MG12FsddalRKI,3424
+nkululeko/feat_extract/feats_agender_agender.py,sha256=19NoRT0KJ8WoZ3EabTYexXymD7bDy58-H20jYmdqjD0,3498
 nkululeko/feat_extract/feats_analyser.py,sha256=Y9hMpZ9WsQOrxTP3B1diHnzMeOgwbVpVFWVlIyhHMJs,12722
 nkululeko/feat_extract/feats_ast.py,sha256=ycJn5eSVOxcEpmeHVk0FPB8q5XiTC8VSKz61L9n0Wa4,4638
 nkululeko/feat_extract/feats_auddim.py,sha256=VlzKKXTXa5kjLgQBWyEFy-daIyU1SkOwCCOIhKsWCvE,3162
@@ -65,14 +65,14 @@ 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=FugR-X2lDFKLLRRhKnhUYJhz-VIktIj8iVEDLbwNwtw,4814
+nkululeko/feat_extract/feats_spkrec.py,sha256=j_-h2NfLa3qes6vOFrNiIfPc5HmAxDpMpMlw5QqSBAM,4813
 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
 nkululeko/feat_extract/feats_wavlm.py,sha256=O9cfc39VF5aPJRRATKb37pHT4W11i2cu5O1mY9LOjIA,4755
 nkululeko/feat_extract/feats_whisper.py,sha256=0N7Vj65OVi2PNoB_NrDjWT5lP6xZNKxFOZZIoxkJvcA,4533
 nkululeko/feat_extract/featureset.py,sha256=ll7tyKAdr--TDShyOYJg0FB4I9NqBq0Ni1k_kUJ-2Vw,1541
-nkululeko/feat_extract/feinberg_praat.py,sha256=EP9pMALjlKdiYInLQdrZ7MmE499Mq-ISRCgqbqL3Rxc,21304
+nkululeko/feat_extract/feinberg_praat.py,sha256=_8MwVikn0vjcyv1ygjScfjIJijOr_IN-o2ZQW1VVZtg,21310
 nkululeko/losses/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nkululeko/losses/loss_ccc.py,sha256=NOK0y0fxKUnU161B5geap6Fmn8QzoPl2MqtPiV8IuJE,976
 nkululeko/losses/loss_softf1loss.py,sha256=5gW-PuiqeAZcRgfwjueIOQtMokOjZWgQnVIv59HKTCo,1309
@@ -80,7 +80,7 @@ nkululeko/models/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,
 nkululeko/models/model.py,sha256=JXrd0fbU0JhTxUDrs0kOEHF9rtPJBxBeO6zcrHAzk8k,12475
 nkululeko/models/model_bayes.py,sha256=WJFZ8wFKwWATz6MhmjeZIi1Pal1viU549WL_PjXDSy8,406
 nkululeko/models/model_cnn.py,sha256=NreR2LrKMyBYHyIJEL6wm3UQ4mA5HleZfpUyA5wNYpA,10629
-nkululeko/models/model_gmm.py,sha256=hZ9UO36KNf48qa3J-xkWIicIj9-TApmt21zNES2vEOs,649
+nkululeko/models/model_gmm.py,sha256=m1ONBql-T0La8Cv0awB7lPUG-kgbygoWmbuqzDzmj-Y,1337
 nkululeko/models/model_knn.py,sha256=KlnrJfwiVnmXZrAaYGFrKA2f5sznvTzSJQ8-5etOP0k,599
 nkululeko/models/model_knn_reg.py,sha256=j7YFfVm6xOR2d9yBYdQiwwqYfqkX0JynX_qLCvkr1fk,610
 nkululeko/models/model_lin_reg.py,sha256=0D7mSnSwK82lNWDMwHYRyq3FmGa6y-DHDGg4qUe85q4,422
@@ -107,8 +107,8 @@ 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=KMxPzb0HN3XuNzAd7Kn3M3Nq91-0sDrAAEBgDKryCdo,16688
-nkululeko-0.88.9.dist-info/LICENSE,sha256=0zGP5B_W35yAcGfHPS18Q2B8UhvLRY3dQq1MhpsJU_U,1076
-nkululeko-0.88.9.dist-info/METADATA,sha256=2NTuv6JzIYo9FbjMFT2zP_SuxZcBuagowGZ9YneOcOA,40134
-nkululeko-0.88.9.dist-info/WHEEL,sha256=Wyh-_nZ0DJYolHNn1_hMa4lM7uDedD_RGVwbmTjyItk,91
-nkululeko-0.88.9.dist-info/top_level.txt,sha256=DPFNNSHPjUeVKj44dVANAjuVGRCC3MusJ08lc2a8xFA,10
-nkululeko-0.88.9.dist-info/RECORD,,
+nkululeko-0.88.11.dist-info/LICENSE,sha256=0zGP5B_W35yAcGfHPS18Q2B8UhvLRY3dQq1MhpsJU_U,1076
+nkululeko-0.88.11.dist-info/METADATA,sha256=siesWp8FeTPWYYvZRnoiwVvN4js0m_Rj3WLCryoyMko,40394
+nkululeko-0.88.11.dist-info/WHEEL,sha256=R0nc6qTxuoLk7ShA2_Y-UWkN8ZdfDBG2B6Eqpz2WXbs,91
+nkululeko-0.88.11.dist-info/top_level.txt,sha256=DPFNNSHPjUeVKj44dVANAjuVGRCC3MusJ08lc2a8xFA,10
+nkululeko-0.88.11.dist-info/RECORD,,

{nkululeko-0.88.9.dist-info → nkululeko-0.88.11.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (71.1.0)
+Generator: setuptools (72.1.0)
 Root-Is-Purelib: true
 Tag: py3-none-any