nkululeko 0.89.0__tar.gz → 0.89.2__tar.gz

{nkululeko-0.89.0 → nkululeko-0.89.2}/CHANGELOG.md

@@ -1,6 +1,14 @@
 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/nkululeko.egg-info → nkululeko-0.89.2}/PKG-INFO

@@ -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 → nkululeko-0.89.2}/nkululeko/constants.py

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

{nkululeko-0.89.0 → nkululeko-0.89.2}/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-0.89.0 → nkululeko-0.89.2}/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-0.89.0 → nkululeko-0.89.2}/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-0.89.0 → nkululeko-0.89.2}/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-0.89.0 → nkululeko-0.89.2}/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 → nkululeko-0.89.2/nkululeko.egg-info}/PKG-INFO

@@ -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