nkululeko 0.89.1__py3-none-any.whl → 0.90.0__py3-none-any.whl

nkululeko/augment.py

@@ -37,8 +37,8 @@ def doit(config_file):
 
     filename = util.config_val("AUGMENT", "result", "augmented.csv")
     filename = f"{expr.data_dir}/{filename}"
-
-    if os.path.exists(filename):
+    no_reuse = eval(util.config_val("DATA", "no_reuse", "False"))
+    if os.path.exists(filename) and not no_reuse:
         util.debug("files already augmented")
     else:
         # load the data

nkululeko/augmenting/randomsplicer.py

@@ -41,14 +41,17 @@ class Randomsplicer:
             * top_db: top db level for silence to be recognized (default: 12)
         """
 
-        p_reverse = 0.3
-        top_db = 12
+        p_reverse = float(self.util.config_val("AUGMENT", "p_reverse", "0.3"))
+        top_db = float(self.util.config_val("AUGMENT", "top_db", "12"))
 
         files = self.df.index.get_level_values(0).values
         store = self.util.get_path("store")
         filepath = f"{store}randomspliced/"
         audeer.mkdir(filepath)
-        self.util.debug(f"random splicing {sample_selection} samples to {filepath}")
+        self.util.debug(
+            f"random splicing {sample_selection} samples to {filepath}, "
+            + f"p_reverse = {p_reverse}, top_db = {top_db}",
+        )
         newpath = ""
         index_map = {}
         for i, f in enumerate(tqdm(files)):

nkululeko/constants.py

@@ -1,2 +1,2 @@
-VERSION="0.89.1"
+VERSION="0.90.0"
 SAMPLING_RATE = 16000

nkululeko/data/dataset.py

@@ -30,8 +30,8 @@ class Dataset:
     def __init__(self, name):
         """Constructor setting up name and configuration"""
         self.name = name
-        self.target = glob_conf.config["DATA"]["target"]
         self.util = Util("dataset")
+        self.target = self.util.config_val("DATA", "target", "none")
         self.plot = Plots()
         self.limit = int(self.util.config_val_data(self.name, "limit", 0))
         self.start_fresh = eval(self.util.config_val("DATA", "no_reuse", "False"))
@@ -127,6 +127,9 @@ class Dataset:
             self.got_gender,
             self.got_age,
         ) = self._get_df_for_lists(self.db, df_files_tables)
+        if df.shape[0] > 0 and self.target == "none":
+            self.df = df
+            return
         if False in {
             self.is_labeled,
             self.got_speaker,
@@ -553,7 +556,10 @@ class Dataset:
             " samples in train/test"
         )
         # because this generates new train/test sample quantaties, the feature extraction has to be done again
-        glob_conf.config["FEATS"]["needs_feature_extraction"] = "True"
+        try:
+            glob_conf.config["FEATS"]["needs_feature_extraction"] = "True"
+        except KeyError:
+            pass
 
     def random_split(self):
         """One way to split train and eval sets: Specify percentage of random samples"""

nkululeko/ensemble.py

@@ -18,6 +18,7 @@ Raises:
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
 
+
 from typing import List
 import configparser
 import time
@@ -26,10 +27,15 @@ from pathlib import Path
 
 import numpy as np
 import pandas as pd
+import matplotlib.pyplot as plt
+
 from sklearn.metrics import(
+    RocCurveDisplay,
     balanced_accuracy_score, 
     classification_report,
-    f1_score
+    auc,
+    roc_auc_score,
+    roc_curve
 )
 
 from nkululeko.constants import VERSION
@@ -289,9 +295,7 @@ def ensemble_predictions(
     uar = balanced_accuracy_score(truth, predicted)
     acc = (truth == predicted).mean()
     # print classification report
-    Util("ensemble").debug(f"\n {classification_report(truth, predicted)}")
-    # f1 = f1_score(truth, predicted, pos_label='p')
-    # Util("ensemble").debug(f"F1: {f1:.3f}")
+    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/experiment.py

@@ -101,12 +101,15 @@ class Experiment:
             if data.got_speaker:
                 self.got_speaker = True
             self.datasets.update({d: data})
-        self.target = self.util.config_val("DATA", "target", "emotion")
+        self.target = self.util.config_val("DATA", "target", "none")
         glob_conf.set_target(self.target)
         # print target via debug
         self.util.debug(f"target: {self.target}")
         # print keys/column
         dbs = ",".join(list(self.datasets.keys()))
+        if self.target == "none":
+            self.util.debug(f"loaded databases {dbs}")
+            return
         labels = self.util.config_val("DATA", "labels", False)
         auto_labels = list(next(iter(self.datasets.values())).df[self.target].unique())
         if labels:
@@ -191,7 +194,8 @@ class Experiment:
             self.df_train, self.df_test = pd.DataFrame(), pd.DataFrame()
             for d in self.datasets.values():
                 d.split()
-                d.prepare_labels()
+                if self.target != "none":
+                    d.prepare_labels()
                 if d.df_train.shape[0] == 0:
                     self.util.debug(f"warn: {d.name} train empty")
                 self.df_train = pd.concat([self.df_train, d.df_train])
@@ -207,6 +211,8 @@ class Experiment:
             self.df_test.to_csv(storage_test)
             self.df_train.to_csv(storage_train)
 
+        if self.target == "none":
+            return
         self.util.copy_flags(self, self.df_test)
         self.util.copy_flags(self, self.df_train)
         # Try data checks

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']"))

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/plots.py

@@ -263,7 +263,7 @@ class Plots:
 
     def plotcatcont(self, df, cat_col, cont_col, xlab, ylab):
         """Plot relation of categorical distribution with continuous."""
-        dist_type = self.util.config_val("EXPL", "dist_type", "hist")
+        dist_type = self.util.config_val("EXPL", "dist_type", "kde")
         cats, cat_str, es = su.get_effect_size(df, cat_col, cont_col)
         model_type = self.util.get_model_type()
         if dist_type == "hist" and model_type != "tree":

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-0.89.1.dist-info → nkululeko-0.90.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: nkululeko
-Version: 0.89.1
+Version: 0.90.0
 Summary: Machine learning audio prediction experiments based on templates
 Home-page: https://github.com/felixbur/nkululeko
 Author: Felix Burkhardt
@@ -356,6 +356,16 @@ F. Burkhardt, Johannes Wagner, Hagen Wierstorf, Florian Eyben and Björn Schulle
 Changelog
 =========
 
+Version 0.90.0
+--------------
+* augmentation can now be done without target
+* random splicing params configurable
+* made kde default for plot continous/categorical plots
+
+Version 0.89.2
+--------------
+* fix shap value calculation
+  
 Version 0.89.1
 --------------
 * print and save result of feature importance

{nkululeko-0.89.1.dist-info → nkululeko-0.90.0.dist-info}/RECORD

@@ -1,24 +1,24 @@
 nkululeko/__init__.py,sha256=62f8HiEzJ8rG2QlTFJXUCMpvuH3fKI33DoJSj33mscc,63
 nkululeko/aug_train.py,sha256=YhuZnS_WVWnun9G-M6g5n6rbRxoVREz6Zh7k6qprFNQ,3194
-nkululeko/augment.py,sha256=4MG0apTAG5RgkuJrYEjGgDdbodZWi_HweSPNI1JJ5QA,3051
+nkululeko/augment.py,sha256=xNeOR22sXHD5mxv0SEe6kvgEXX0RtiUL4BK-m-BDfcM,3133
 nkululeko/cacheddataset.py,sha256=lIJ6hUo5LoxSrzXtWV8mzwO7wRtUETWnOQ4ws2XfL1E,969
-nkululeko/constants.py,sha256=nRA0bWrvi-5tXm8QWv4dzDE-3sujMiz26U4QgSVuck0,39
+nkululeko/constants.py,sha256=t11gtE4sZM7oZrRSZhmVhIKwQAI83AN0cEZRPXkw5cs,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=egtOFxEp7gjuM5cKBfETnhTn1-7_4zWBPEah65K1C3U,12927
-nkululeko/experiment.py,sha256=L4PzoScPLG2xTyniVy9evcBy_8CIe3RTeTEUVTqiuvQ,31186
-nkululeko/explore.py,sha256=_GOgcRaPvh2xBbKPAkSJjYzgHhD_xb3ZCB6M1MPA6ao,3867
+nkululeko/ensemble.py,sha256=MayHpngGH_FTvSxUsH3NdxJd6WBAosGRFQeQ7cMjIco,12922
+nkululeko/experiment.py,sha256=BXUmJrJn17W-umYh4O0Jt6ZZzr2u_VDL7Lq7fPEEVMQ,31390
+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
-nkululeko/plots.py,sha256=gfNy9Eu2PhSaykMazBPThcYS5o5KwuQwY2jshAUK5Rk,22965
+nkululeko/plots.py,sha256=p9YyN-xAtdGBKjcA305V0KOagAzG8VG6D_Ceoa9rae4,22964
 nkululeko/predict.py,sha256=sF091sSSLnEWcISx9ZcULLie3tY5XeFsQJd6b3vrxFg,2409
 nkululeko/resample.py,sha256=2d9eao_0sLrGZ_KSl8OVKsPor3BkFrlmMhrpB9WelIs,4267
 nkululeko/runmanager.py,sha256=xvxL5a9d3jtGFqx0Z3nyyxowA368uNyP0ZitO8kxIIE,7581
@@ -30,7 +30,7 @@ nkululeko/test_predictor.py,sha256=DEHE_D3A6m6KJTrpDKceA1n655t_UZV3WQd57K4a3Ho,2
 nkululeko/test_pretrain.py,sha256=ZWl-bR6nmeSmXkGAIE6zyfQEjN8Zg0rIxfaS-O6Zbas,8465
 nkululeko/augmenting/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nkululeko/augmenting/augmenter.py,sha256=XAt0dpmlnKxqyysqCgV3rcz-pRIvOz7rU7dmGDCVAzs,2905
-nkululeko/augmenting/randomsplicer.py,sha256=Z5rxdKKUpuncLWuTS6xVfVKUeVbeiYU_dLRHQ5fcg4Y,2669
+nkululeko/augmenting/randomsplicer.py,sha256=jmn4uZc2O_-A_O-GXz7lh0rHR6-2sD9eNG0vwgtRd2w,2861
 nkululeko/augmenting/randomsplicing.py,sha256=ldym9vZNsZIU5BAAaJVaOmAgmVHNs4a5i5K3bW-WAQU,1791
 nkululeko/augmenting/resampler.py,sha256=nOBsiQpX6p4jXsP7x6wak78F3B5YYYRmC_iHX8iuOXs,3542
 nkululeko/autopredict/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -46,12 +46,12 @@ nkululeko/autopredict/ap_stoi.py,sha256=It0Lk-ki-gohA2AzD8nkLAN2WahYvD9rPDGTQuvd
 nkululeko/autopredict/ap_valence.py,sha256=n-hctRKySzhmJtowuMOTUu0T_ld3uK5pnfOzWeWW4VM,1024
 nkululeko/autopredict/estimate_snr.py,sha256=S-bpS0xFkwWc4Ch75UrjbS8y538lQ0U3g_iLRFXureY,5048
 nkululeko/data/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-nkululeko/data/dataset.py,sha256=xaawk5QthuVStWjHWTFBtorcIe71lbPQgC6mHzSXGeI,29286
+nkululeko/data/dataset.py,sha256=QqU1YoBQk41g3MV8bc0iW1YN_gMHDizuG-cjmSq0d_o,29455
 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=tMK3_qs8adylNNSR0CS1RjU9RxmpumLqmuyzmc2ZYjA,3184
 nkululeko/feat_extract/feats_agender_agender.py,sha256=19NoRT0KJ8WoZ3EabTYexXymD7bDy58-H20jYmdqjD0,3498
-nkululeko/feat_extract/feats_analyser.py,sha256=eW0v7Boybfj2gXi77MPjaLyHUQ1C42mx9hgoQeDwNac,12999
+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-0.89.1.dist-info/LICENSE,sha256=0zGP5B_W35yAcGfHPS18Q2B8UhvLRY3dQq1MhpsJU_U,1076
-nkululeko-0.89.1.dist-info/METADATA,sha256=AuVssWNRMXlseH5xSzcls--AAYLFSeEbFtHbAFT2o_o,40667
-nkululeko-0.89.1.dist-info/WHEEL,sha256=UvcQYKBHoFqaQd6LKyqHw9fxEolWLQnlzP0h_LgJAfI,91
-nkululeko-0.89.1.dist-info/top_level.txt,sha256=DPFNNSHPjUeVKj44dVANAjuVGRCC3MusJ08lc2a8xFA,10
-nkululeko-0.89.1.dist-info/RECORD,,
+nkululeko-0.90.0.dist-info/LICENSE,sha256=0zGP5B_W35yAcGfHPS18Q2B8UhvLRY3dQq1MhpsJU_U,1076
+nkululeko-0.90.0.dist-info/METADATA,sha256=BiguFg1WzW9crNTqgr2qbtmaOL_PgeLP3M1Azn4Lehk,40900
+nkululeko-0.90.0.dist-info/WHEEL,sha256=cVxcB9AmuTcXqmwrtPhNK88dr7IR_b6qagTj0UvIEbY,91
+nkululeko-0.90.0.dist-info/top_level.txt,sha256=DPFNNSHPjUeVKj44dVANAjuVGRCC3MusJ08lc2a8xFA,10
+nkululeko-0.90.0.dist-info/RECORD,,

{nkululeko-0.89.1.dist-info → nkululeko-0.90.0.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