nkululeko 0.95.5__py3-none-any.whl → 0.95.7__py3-none-any.whl

nkululeko/constants.py

@@ -1,2 +1,2 @@
-VERSION="0.95.5"
+VERSION="0.95.7"
 SAMPLING_RATE = 16000

nkululeko/data/dataset.py

@@ -294,12 +294,21 @@ class Dataset:
                 # try to get the gender values
                 if "gender" in source_df:
                     df_local["gender"] = source_df["gender"]
-                    got_gender = True
+                else:
+                    # try to get the gender via the speaker description
+                    gender_map = db['speaker'].get().to_dict()['gender']
+                    df_local['gender'] = df_local['speaker'].map(gender_map).astype(str)
+                got_gender = True
             except (KeyError, ValueError, audformat.errors.BadKeyError):
                 pass
             try:
                 # try to get the age values
-                df_local["age"] = source_df["age"].astype(int)
+                if "age" in source_df:
+                    df_local["age"] = source_df["age"].astype(int)
+                else:
+                    # try to get the age via the speaker description
+                    age_map = db['speaker'].get().to_dict()['age']
+                    df_local['age'] = df_local['speaker'].map(age_map).astype(int)
                 got_age = True
             except (KeyError, ValueError, audformat.errors.BadKeyError):
                 pass

nkululeko/explore.py

@@ -65,6 +65,7 @@ def main():
     try:
         # load the experiment
         expr.load(f"{util.get_save_name()}")
+        expr.util.set_config(config)
         needs_feats = True
         experiment_loaded = True
     except FileNotFoundError:

nkululeko/plots.py

@@ -9,6 +9,7 @@ from scipy import stats
 import seaborn as sns
 from sklearn.manifold import TSNE
 
+import audeer
 from audmetric import concordance_cc as ccc
 
 import nkululeko.glob_conf as glob_conf
@@ -218,7 +219,7 @@ class Plots:
 
     def save_plot(self, ax, caption, header, filename, type_s):
         # one up because of the runs
-        fig_dir = os.path.dirname(self.util.get_path("fig_dir"))
+        fig_dir = audeer.path(self.util.get_path("fig_dir"), "..")
         fig_plots = ax.figure
         # avoid warning
         # plt.tight_layout()

nkululeko/reporting/reporter.py

@@ -12,13 +12,9 @@ from scipy.special import softmax
 from scipy.stats import entropy
 from scipy.stats import pearsonr
 from sklearn.metrics import ConfusionMatrixDisplay
-from sklearn.metrics import RocCurveDisplay
-from sklearn.metrics import auc
 from sklearn.metrics import classification_report
 from sklearn.metrics import confusion_matrix
 from sklearn.metrics import r2_score
-from sklearn.metrics import roc_auc_score
-from sklearn.metrics import roc_curve
 
 # from torch import is_tensor
 from audmetric import accuracy
@@ -186,6 +182,7 @@ class Reporter:
                     if not file_name.endswith(".csv"):
                         file_name = file_name + ".csv"
             self.probas = probas
+            self.plot_proba_conf()
             probas.to_csv(file_name)
             self.util.debug(f"Saved probabilities to {file_name}")
             plots = Plots()
@@ -196,10 +193,27 @@ class Reporter:
                 ax,
                 caption,
                 "Uncertainty",
-                "uncertainty_samples",
+                "uncertainty",
                 "samples",
             )
 
+    def plot_proba_conf(self):
+        uncertainty_threshold = self.util.config_val("PLOT", "uncertainty_threshold", False)
+        if uncertainty_threshold:
+            uncertainty_threshold = float(uncertainty_threshold)
+            old_size = self.probas.shape[0]
+            df = self.probas[self.probas["uncertainty"] < uncertainty_threshold]
+            new_size = df.shape[0]
+            difference = old_size - new_size
+            self.util.debug(
+                f"Filtered probabilities: {old_size} -> {new_size} ({difference}) samples with uncertainty < {uncertainty_threshold}"
+            )
+            truths = df["truth"].values
+            preds = df["predicted"].values
+            self._plot_confmat(truths, preds, f"uncertainty_less_than_{uncertainty_threshold}_cnf",
+                            epoch=None, test_result=None)
+
+
     def set_id(self, run, epoch):
         """Make the report identifiable with run and epoch index."""
         self.run = run

{nkululeko-0.95.5.dist-info → nkululeko-0.95.7.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: nkululeko
-Version: 0.95.5
+Version: 0.95.7
 Summary: Machine learning audio prediction experiments based on templates
 Home-page: https://github.com/felixbur/nkululeko
 Author: Felix Burkhardt

{nkululeko-0.95.5.dist-info → nkululeko-0.95.7.dist-info}/RECORD

@@ -4,14 +4,14 @@ nkululeko/aug_train.py,sha256=wpiHCJ7zsW38kumg3ypwXZe2HQrhUblAnv7P2QeJnAc,3525
 nkululeko/augment.py,sha256=3RzaxB3gRxovgJVjHXi0glprW01J7RaHhUkqotW2T3U,2955
 nkululeko/balance.py,sha256=r7opXbrqAipm2euPPaOmLlA5J10p2bHQgO5kWk2x9ro,8702
 nkululeko/cacheddataset.py,sha256=XFpWZmbJRg0pvhnIgYf0TkclxllD-Fctu-Ol0PF_00c,969
-nkululeko/constants.py,sha256=uY1Jr5zRXhQbcZ07E355HAsT4h-soeECnBVXSukC-wY,39
+nkululeko/constants.py,sha256=6jfPRCrnqqRsGqz83bT34_5gPBbTiIAsnhzVWUrKXl4,39
 nkululeko/demo-ft.py,sha256=iD9Pzp9QjyAv31q1cDZ75vPez7Ve8A4Cfukv5yfZdrQ,770
 nkululeko/demo.py,sha256=tu7Al2l5MCLVegkDC-NE2wcuc_YE7NRbgOlPW3yhGEs,4940
 nkululeko/demo_feats.py,sha256=BvZjeNFTlERIRlq34OHM4Z96jdDQAhB01BGQAUcX9dM,2026
 nkululeko/demo_predictor.py,sha256=lDF-xOxRdEAclOmbepAYg-BQXQdGkHfq2n74PTIoop8,4872
 nkululeko/ensemble.py,sha256=71V-rre61H3J4sh7lu-OTo4I2_g7mm_rQxwW1ARDHgY,12782
 nkululeko/experiment.py,sha256=BAc220lktt_tvifl-m-ZIPO7Nwi-HzDBNyTfjPDbQkE,38397
-nkululeko/explore.py,sha256=aDVHwuo-lkih7VZrbb_zFKg5fowSrAIcx0V9wf0SRGo,4175
+nkululeko/explore.py,sha256=PjNcLuPdvWqCqYXUvGhd0hBijIhzdyi3ED1RF6o5Gjk,4212
 nkululeko/export.py,sha256=U-V4acxtuL6qKt6oAsVcM5TTeWogYUJ3GU-lA6rq6d4,4336
 nkululeko/feature_extractor.py,sha256=CsKmBoxwNClRGu20ox_eCxMG4u_1OH8Y83FYw7GfUwA,4230
 nkululeko/file_checker.py,sha256=xJY0Q6w47pnmgJVK5rcAKPYBrCpV7eBT4_3YBzTx-H8,3454
@@ -24,7 +24,7 @@ nkululeko/nkuluflag.py,sha256=_83LqLr2bSHjnVJuPeSAHCIyuiIbRxgpFKW6CwanWFM,3728
 nkululeko/nkululeko.py,sha256=6ALPMMIz6l0O3IRaP0q4b59ZUxpfzNqLQUqZMf5t3Zo,1976
 nkululeko/optim.py,sha256=Pn_02irXYJJmNG1yWA9GImHirpbXXywV61MalZb2wVA,1658
 nkululeko/optimizationrunner.py,sha256=UfWU_gOPaHUVjvYaw3AoF9HoDGYxIjbCyTGmi1PVu3s,44283
-nkululeko/plots.py,sha256=lUxgyoriYTwdpHZvBBQ4e41v77deQrt0PcRDLJWijys,27503
+nkululeko/plots.py,sha256=rVkOGWB7yLkZ1dGg_MXeKhPOtiquiYIyCam4KYOdJQY,27519
 nkululeko/predict.py,sha256=PWv1Pc39lrxqqIWrYszVk5SL37dDL93CHgcruItNID8,2211
 nkululeko/resample.py,sha256=rn3-M1A-iwVGibfQNGyeYNa7briD24lIN9Szq_1uTJo,5194
 nkululeko/runmanager.py,sha256=YtGQP0UyyQTKkilncB1XYM-T8oatzGcZEOcj5SorjJw,8902
@@ -58,7 +58,7 @@ nkululeko/autopredict/whisper_transcriber.py,sha256=DWDvpRaV5KmUF18ojPEvxnVXm_h_
 nkululeko/autopredict/tests/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nkululeko/autopredict/tests/test_whisper_transcriber.py,sha256=ilas6j3OUvq_xnQCRZgytQCtyrpNU6tvG5a8kPvVKBQ,5085
 nkululeko/data/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-nkululeko/data/dataset.py,sha256=2-I7d91M9f296SANYiL4eTZmcXKs-nj1vqsUEXpp-cA,42461
+nkululeko/data/dataset.py,sha256=uj4rtcAoiEUpoZv8dlgrdzBuUdFrXtU7Pai6wSHY2xU,42997
 nkululeko/data/dataset_csv.py,sha256=AIbtB6pGk5BSQGIgfokZ7tEGFjmuOq5w2XumRSimVWs,4833
 nkululeko/feat_extract/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nkululeko/feat_extract/feats_agender.py,sha256=onfAQ6-xx_mFMJXEF1IX8cHBmGtGeX6weJmxbkfh1_o,3184
@@ -120,7 +120,7 @@ nkululeko/reporting/defines.py,sha256=0vh-Tlx4fAPpk1o6mP_4x3EkIoqzYMr38IZnj-JM5z
 nkululeko/reporting/latex_writer.py,sha256=NGwSIfd4nfslDkNUOSZSdqY_VDLA8634thyhe-vj1bY,1824
 nkululeko/reporting/report.py,sha256=B5eoIKMz46VKDBsi7M9u_iegzAD-E3eGCmolzSFjZ3c,1118
 nkululeko/reporting/report_item.py,sha256=drkknsyFhGviaPJNmPQtCXJmRhTSSfjNcJt0Bls6JAA,533
-nkululeko/reporting/reporter.py,sha256=awBaewERa8xSQtZ0c1KVAQhV77L-BvXSDyU959hQ6qU,21150
+nkululeko/reporting/reporter.py,sha256=ITxM5O9Hoe_1z_59g-GF4b9vciR4shokZxeFzCrDaag,21869
 nkululeko/reporting/result.py,sha256=G63a2tHCwHhM6NBJgYzsWKWJm4Yu3r4hsCHA2Km7eHU,1073
 nkululeko/segmenting/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nkululeko/segmenting/seg_inaspeechsegmenter.py,sha256=b3t0zdpJYofKWMyKRMtMMX91xeR-k8d5pbnNaQHcsOE,1902
@@ -134,9 +134,9 @@ nkululeko/utils/files.py,sha256=SrrYaU7AB80MZHiV1jcB0h_zigvYLYgSVNTXV4ao38g,4593
 nkululeko/utils/stats.py,sha256=3Fyx8q8BSKYmiufT6OkRug9RATWmGrr9BaX_y8jziWo,3074
 nkululeko/utils/unzip.py,sha256=G68f5120TjwACZC3bQcneMniddnwubPbBdMc2L5KBOo,1206
 nkululeko/utils/util.py,sha256=yHgzfj-8ncgCvyrrrH_NDWCh6VmhAqVYY6Vlgyg-c6E,18585
-nkululeko-0.95.5.dist-info/licenses/LICENSE,sha256=0zGP5B_W35yAcGfHPS18Q2B8UhvLRY3dQq1MhpsJU_U,1076
-nkululeko-0.95.5.dist-info/METADATA,sha256=jt5I1QkdFV2jSe6vVu4SgJ5Ptlc9GMvKSpxRCpc9Awk,21998
-nkululeko-0.95.5.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-nkululeko-0.95.5.dist-info/entry_points.txt,sha256=lNTkFEdh6Kjo5o95ZAWf_0Lq-4ztGoAoMVSDuPtuyS0,442
-nkululeko-0.95.5.dist-info/top_level.txt,sha256=bf1k1YKkqcXemNX_cUgoyKqQ3_GVErPqAY-53J36jkM,19
-nkululeko-0.95.5.dist-info/RECORD,,
+nkululeko-0.95.7.dist-info/licenses/LICENSE,sha256=0zGP5B_W35yAcGfHPS18Q2B8UhvLRY3dQq1MhpsJU_U,1076
+nkululeko-0.95.7.dist-info/METADATA,sha256=s_XLh9XUEm_NRApCwnUc8QKkRHWqlva7yxY8Jce0vSI,21998
+nkululeko-0.95.7.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+nkululeko-0.95.7.dist-info/entry_points.txt,sha256=lNTkFEdh6Kjo5o95ZAWf_0Lq-4ztGoAoMVSDuPtuyS0,442
+nkululeko-0.95.7.dist-info/top_level.txt,sha256=bf1k1YKkqcXemNX_cUgoyKqQ3_GVErPqAY-53J36jkM,19
+nkululeko-0.95.7.dist-info/RECORD,,