nkululeko 0.89.0__py3-none-any.whl → 0.89.2__py3-none-any.whl

nkululeko/constants.py

@@ -1,2 +1,2 @@
-VERSION="0.89.0"
+VERSION="0.89.2"
 SAMPLING_RATE = 16000

nkululeko/ensemble.py

@@ -18,6 +18,7 @@ Raises:
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
 
+
 from typing import List
 import configparser
 import time
@@ -26,7 +27,16 @@ from pathlib import Path
 
 import numpy as np
 import pandas as pd
-from sklearn.metrics import balanced_accuracy_score
+import matplotlib.pyplot as plt
+
+from sklearn.metrics import(
+    RocCurveDisplay,
+    balanced_accuracy_score, 
+    classification_report,
+    auc,
+    roc_auc_score,
+    roc_curve
+)
 
 from nkululeko.constants import VERSION
 from nkululeko.experiment import Experiment
@@ -284,6 +294,8 @@ def ensemble_predictions(
     predicted = ensemble_preds["predicted"]
     uar = balanced_accuracy_score(truth, predicted)
     acc = (truth == predicted).mean()
+    # print classification report
+    Util("ensemble").debug(f"\n {classification_report(truth, predicted, digits=4)}")
     Util("ensemble").debug(f"{method}: UAR: {uar:.3f}, ACC: {acc:.3f}")
 
     return ensemble_preds

nkululeko/explore.py

@@ -91,7 +91,9 @@ def main(src_dir):
             # these investigations need features to explore
             expr.extract_feats()
             needs_feats = True
-        # explore
+            # explore
+            expr.init_runmanager()
+            expr.runmgr.do_runs()
     expr.analyse_features(needs_feats)
     expr.store_report()
     print("DONE")

nkululeko/feat_extract/feats_analyser.py

@@ -50,19 +50,32 @@ class FeatureAnalyser:
 
         name = "my_shap_values"
         if not self.util.exist_pickle(name):
-
+            # get model name
+            model_name = self.util.get_model_type()
+            if hasattr(model, "predict_shap"):
+                model_func = model.predict_shap
+            elif hasattr(model, "clf"):
+                model_func = model.clf.predict
+            else:
+                raise Exception("Model not supported for SHAP analysis")
+            
+            self.util.debug(f"using SHAP explainer for {model_name} model")
+            
             explainer = shap.Explainer(
-                model.predict_shap,
+                model_func,
                 self.features,
                 output_names=glob_conf.labels,
                 algorithm="permutation",
                 npermutations=5,
             )
+ 
             self.util.debug("computing SHAP values...")
             shap_values = explainer(self.features)
             self.util.to_pickle(shap_values, name)
         else:
             shap_values = self.util.from_pickle(name)
+        # plt.figure()
+        plt.close('all')
         plt.tight_layout()
         shap.plots.bar(shap_values)
         fig_dir = self.util.get_path("fig_dir") + "../"  # one up because of the runs
@@ -71,7 +84,8 @@ class FeatureAnalyser:
         filename = f"_SHAP_{model.name}"
         filename = f"{fig_dir}{exp_name}{filename}.{format}"
         plt.savefig(filename)
-        self.util.debug(f"plotted SHAP feature importance tp {filename}")
+        plt.close()
+        self.util.debug(f"plotted SHAP feature importance to {filename}")
 
     def analyse(self):
         models = ast.literal_eval(self.util.config_val("EXPL", "model", "['log_reg']"))
@@ -139,7 +153,7 @@ class FeatureAnalyser:
                 elif model_s == "svm":
                     from sklearn.svm import SVC
 
-                    c = float(self.util.config_val("MODEL", "C_val", "0.001"))
+                    c = float(self.util.config_val("MODEL", "C_val", "1.0"))
                     model = SVC(kernel="linear", C=c, gamma="scale")
                     result_importances[model_s] = self._get_importance(
                         model, permutation
@@ -205,7 +219,7 @@ class FeatureAnalyser:
                         model, permutation
                     )
                 elif model_s == "xgr":
-                    from xgboost import XGBClassifier
+                    from xgboost import XGBRegressor
 
                     model = XGBRegressor()
                     result_importances[model_s] = self._get_importance(
@@ -270,12 +284,14 @@ class FeatureAnalyser:
             )
         )
 
+        # print feature importance values to file and debug and save to result
+        self.util.debug(f"Importance features from {model_name}: features = \n{df_imp['feats'].values.tolist()}")
         # result file
         res_dir = self.util.get_path("res_dir")
         filename = f"_EXPL_{model_name}"
         if permutation:
             filename += "_perm"
-        filename = f"{res_dir}{self.util.get_exp_name(only_data=True)}{filename}_{model_name}.txt"
+        filename = f"{res_dir}{self.util.get_exp_name(only_data=True)}{filename}_{max_feat_num}_fi.txt"
         with open(filename, "w") as text_file:
             text_file.write(
                 "features in order of decreasing importance according to model"
@@ -283,7 +299,8 @@ class FeatureAnalyser:
             )
 
         df_imp.to_csv(filename, mode="a")
-
+        self.util.debug(f"Saved feature importance values to {filename}")
+        
         # check if feature distributions should be plotted
         plot_feats = self.util.config_val("EXPL", "feature_distributions", False)
         if plot_feats:

nkululeko/modelrunner.py

@@ -53,8 +53,8 @@ class Modelrunner:
             # epochs are handled by Huggingface API
             self.model.train()
             report = self.model.predict()
-            # todo: findout the best epoch, no need
-            # since oad_best_model_at_end is given in training args
+            # todo: findout the best epoch -> no need
+            # since load_best_model_at_end is given in training args
             epoch = epoch_num
             report.set_id(self.run, epoch)
             plot_name = self.util.get_plot_name() + f"_{self.run}_{epoch:03d}_cnf"

nkululeko/reporting/reporter.py

@@ -402,7 +402,7 @@ class Reporter:
                 )
                 # print classifcation report in console
                 self.util.debug(
-                    f"\n {classification_report(self.truths, self.preds, target_names=labels)}"
+                    f"\n {classification_report(self.truths, self.preds, target_names=labels, digits=4)}"
                 )
             except ValueError as e:
                 self.util.debug(
@@ -422,16 +422,17 @@ class Reporter:
                 if len(np.unique(self.truths)) == 2:
                     fpr, tpr, _ = roc_curve(self.truths, self.preds)
                     auc_score = auc(fpr, tpr)
+                    plot_path = f"{fig_dir}{self.util.get_exp_name()}_{epoch}{self.filenameadd}_roc.{self.format}"
+                    plt.figure()
                     display = RocCurveDisplay(
                         fpr=fpr,
                         tpr=tpr,
                         roc_auc=auc_score,
                         estimator_name=f"{self.model_type} estimator",
                     )
-                    # save plot
-                    plot_path = f"{fig_dir}{self.util.get_exp_name()}_{epoch}{self.filenameadd}_roc.{self.format}"
                     display.plot(ax=None)
                     plt.savefig(plot_path)
+                    plt.close()
                     self.util.debug(f"Saved ROC curve to {plot_path}")
                     pauc_score = roc_auc_score(self.truths, self.preds, max_fpr=0.1)
                     auc_pauc = f"auc: {auc_score:.3f}, pauc: {pauc_score:.3f} from epoch: {epoch}"

{nkululeko-0.89.0.dist-info → nkululeko-0.89.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: nkululeko
-Version: 0.89.0
+Version: 0.89.2
 Summary: Machine learning audio prediction experiments based on templates
 Home-page: https://github.com/felixbur/nkululeko
 Author: Felix Burkhardt
@@ -356,6 +356,14 @@ F. Burkhardt, Johannes Wagner, Hagen Wierstorf, Florian Eyben and Björn Schulle
 Changelog
 =========
 
+Version 0.89.2
+--------------
+* fix shap value calculation
+  
+Version 0.89.1
+--------------
+* print and save result of feature importance
+
 Version 0.89.0
 --------------
 * added Roc plots and classification report on Debug

{nkululeko-0.89.0.dist-info → nkululeko-0.89.2.dist-info}/RECORD

@@ -2,19 +2,19 @@ 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=YlaNUy3dWo6v0O02alzu9cMApavzOisvDjFSaYzGepo,39
+nkululeko/constants.py,sha256=WFGVylIst9Be_eHBZ9GiR43Qi4CdRySmNUzyNox6aMM,39
 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/ensemble.py,sha256=MayHpngGH_FTvSxUsH3NdxJd6WBAosGRFQeQ7cMjIco,12922
 nkululeko/experiment.py,sha256=L4PzoScPLG2xTyniVy9evcBy_8CIe3RTeTEUVTqiuvQ,31186
-nkululeko/explore.py,sha256=_GOgcRaPvh2xBbKPAkSJjYzgHhD_xb3ZCB6M1MPA6ao,3867
+nkululeko/explore.py,sha256=AbTVDmuDIaLfALQGvDW1yndcw2ikaEVEZ_fJVuUS070,3940
 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/modelrunner.py,sha256=lJy-xM4QfDDWeL0dLTE_VIb4sYrnd_Z_yJRK3wwohQA,11199
 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
@@ -51,7 +51,7 @@ nkululeko/data/dataset_csv.py,sha256=UGEpi__eT2KFS6Fop6N4HkMrzO-u5VP71gt44kwZavo
 nkululeko/feat_extract/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nkululeko/feat_extract/feats_agender.py,sha256=tMK3_qs8adylNNSR0CS1RjU9RxmpumLqmuyzmc2ZYjA,3184
 nkululeko/feat_extract/feats_agender_agender.py,sha256=19NoRT0KJ8WoZ3EabTYexXymD7bDy58-H20jYmdqjD0,3498
-nkululeko/feat_extract/feats_analyser.py,sha256=Y9hMpZ9WsQOrxTP3B1diHnzMeOgwbVpVFWVlIyhHMJs,12722
+nkululeko/feat_extract/feats_analyser.py,sha256=rSsN6kcDUv64DaTl2DvReXF3_g7CtSwiPKgMzbJPqVI,13516
 nkululeko/feat_extract/feats_ast.py,sha256=ycJn5eSVOxcEpmeHVk0FPB8q5XiTC8VSKz61L9n0Wa4,4638
 nkululeko/feat_extract/feats_auddim.py,sha256=ulP_o4SGeQDFTs8YYCGKgccARAo6-wcjPK6-hhGjmn8,3155
 nkululeko/feat_extract/feats_audmodel.py,sha256=aRGTBDKdYaTT_9xDaFZqpuyPhzxSNN_3b1PJDUHtYW4,3180
@@ -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=xFyGj6gQ8T1WB3w3tJ0awlgQcq1e3IKXEIfl_DvOngg,19996
+nkululeko/reporting/reporter.py,sha256=oodLaNZXqPpfoRqVxTldYcx68oN35OGgy-vvbAuY-yI,20039
 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
@@ -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=363Lgmcg6fPKCGbroX0DDyW_zcYNx-Ayqv67qdpfYcw,16710
-nkululeko-0.89.0.dist-info/LICENSE,sha256=0zGP5B_W35yAcGfHPS18Q2B8UhvLRY3dQq1MhpsJU_U,1076
-nkululeko-0.89.0.dist-info/METADATA,sha256=IoIlF0i109BRy7ki2K9Heq-OWVeyhg7rModVCY2fQp0,40590
-nkululeko-0.89.0.dist-info/WHEEL,sha256=UvcQYKBHoFqaQd6LKyqHw9fxEolWLQnlzP0h_LgJAfI,91
-nkululeko-0.89.0.dist-info/top_level.txt,sha256=DPFNNSHPjUeVKj44dVANAjuVGRCC3MusJ08lc2a8xFA,10
-nkululeko-0.89.0.dist-info/RECORD,,
+nkululeko-0.89.2.dist-info/LICENSE,sha256=0zGP5B_W35yAcGfHPS18Q2B8UhvLRY3dQq1MhpsJU_U,1076
+nkululeko-0.89.2.dist-info/METADATA,sha256=00CLy_4Wm7IktJy7dAkKrXkCMi0f1HUXCoQYMNcp2kw,40729
+nkululeko-0.89.2.dist-info/WHEEL,sha256=cVxcB9AmuTcXqmwrtPhNK88dr7IR_b6qagTj0UvIEbY,91
+nkululeko-0.89.2.dist-info/top_level.txt,sha256=DPFNNSHPjUeVKj44dVANAjuVGRCC3MusJ08lc2a8xFA,10
+nkululeko-0.89.2.dist-info/RECORD,,

{nkululeko-0.89.0.dist-info → nkululeko-0.89.2.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (74.0.0)
+Generator: setuptools (74.1.2)
 Root-Is-Purelib: true
 Tag: py3-none-any