nkululeko 0.85.1__py3-none-any.whl → 0.85.2__py3-none-any.whl

nkululeko/constants.py

@@ -1,2 +1,2 @@
-VERSION="0.85.1"
+VERSION="0.85.2"
 SAMPLING_RATE = 16000

nkululeko/data/dataset_csv.py

@@ -21,7 +21,7 @@ class Dataset_CSV(Dataset):
         #     exp_root = self.util.config_val("EXP", "root", "")
         #     data_file = os.path.join(exp_root, data_file)
         root = os.path.dirname(data_file)
-        audio_path = self.util.config_val_data(self.name, "audio_path", "")
+        audio_path = self.util.config_val_data(self.name, "audio_path", "./")
         df = pd.read_csv(data_file)
         # special treatment for segmented dataframes with only one column:
         if "start" in df.columns and len(df.columns) == 4:
@@ -49,7 +49,8 @@ class Dataset_CSV(Dataset):
                     .map(lambda x: root + "/" + audio_path + "/" + x)
                     .values
                 )
-                df = df.set_index(df.index.set_levels(file_index, level="file"))
+                df = df.set_index(df.index.set_levels(
+                    file_index, level="file"))
             else:
                 if not isinstance(df, pd.DataFrame):
                     df = pd.DataFrame(df)
@@ -63,7 +64,8 @@ class Dataset_CSV(Dataset):
         self.db = None
         self.got_target = True
         self.is_labeled = self.got_target
-        self.start_fresh = eval(self.util.config_val("DATA", "no_reuse", "False"))
+        self.start_fresh = eval(
+            self.util.config_val("DATA", "no_reuse", "False"))
         is_index = False
         try:
             if self.is_labeled and not "class_label" in self.df.columns:
@@ -90,7 +92,8 @@ class Dataset_CSV(Dataset):
                 f" {self.got_gender}, got age: {self.got_age}"
             )
         self.util.debug(r_string)
-        glob_conf.report.add_item(ReportItem("Data", "Loaded report", r_string))
+        glob_conf.report.add_item(ReportItem(
+            "Data", "Loaded report", r_string))
 
     def prepare(self):
         super().prepare()

nkululeko/experiment.py

@@ -109,14 +109,15 @@ class Experiment:
         # print keys/column
         dbs = ",".join(list(self.datasets.keys()))
         labels = self.util.config_val("DATA", "labels", False)
+        auto_labels = list(
+            next(iter(self.datasets.values())).df[self.target].unique()
+        )
         if labels:
             self.labels = ast.literal_eval(labels)
             self.util.debug(f"Target labels (from config): {labels}")
         else:
-            self.labels = list(
-                next(iter(self.datasets.values())).df[self.target].unique()
-            )
-            self.util.debug(f"Target labels (from database): {labels}")
+            self.labels = auto_labels
+        self.util.debug(f"Target labels (from database): {auto_labels}")
         glob_conf.set_labels(self.labels)
         self.util.debug(f"loaded databases {dbs}")
 
@@ -159,7 +160,8 @@ class Experiment:
                 data.split()
                 data.prepare_labels()
                 self.df_test = pd.concat(
-                    [self.df_test, self.util.make_segmented_index(data.df_test)]
+                    [self.df_test, self.util.make_segmented_index(
+                        data.df_test)]
                 )
                 self.df_test.is_labeled = data.is_labeled
             self.df_test.got_gender = self.got_gender
@@ -260,7 +262,8 @@ class Experiment:
                     test_cats = self.df_test[self.target].unique()
                 else:
                     # if there is no target, copy a dummy label
-                    self.df_test = self._add_random_target(self.df_test).astype("str")
+                    self.df_test = self._add_random_target(
+                        self.df_test).astype("str")
                 train_cats = self.df_train[self.target].unique()
                 # print(f"df_train: {pd.DataFrame(self.df_train[self.target])}")
                 # print(f"train_cats with target {self.target}: {train_cats}")
@@ -268,7 +271,8 @@ class Experiment:
                 if type(test_cats) == np.ndarray:
                     self.util.debug(f"Categories test (nd.array): {test_cats}")
                 else:
-                    self.util.debug(f"Categories test (list): {list(test_cats)}")
+                    self.util.debug(
+                        f"Categories test (list): {list(test_cats)}")
             if type(train_cats) == np.ndarray:
                 self.util.debug(f"Categories train (nd.array): {train_cats}")
             else:
@@ -291,7 +295,8 @@ class Experiment:
 
         target_factor = self.util.config_val("DATA", "target_divide_by", False)
         if target_factor:
-            self.df_test[self.target] = self.df_test[self.target] / float(target_factor)
+            self.df_test[self.target] = self.df_test[self.target] / \
+                float(target_factor)
             self.df_train[self.target] = self.df_train[self.target] / float(
                 target_factor
             )
@@ -314,14 +319,16 @@ class Experiment:
     def plot_distribution(self, df_labels):
         """Plot the distribution of samples and speaker per target class and biological sex"""
         plot = Plots()
-        sample_selection = self.util.config_val("EXPL", "sample_selection", "all")
+        sample_selection = self.util.config_val(
+            "EXPL", "sample_selection", "all")
         plot.plot_distributions(df_labels)
         if self.got_speaker:
             plot.plot_distributions_speaker(df_labels)
 
     def extract_test_feats(self):
         self.feats_test = pd.DataFrame()
-        feats_name = "_".join(ast.literal_eval(glob_conf.config["DATA"]["tests"]))
+        feats_name = "_".join(ast.literal_eval(
+            glob_conf.config["DATA"]["tests"]))
         feats_types = self.util.config_val_list("FEATS", "type", ["os"])
         self.feature_extractor = FeatureExtractor(
             self.df_test, feats_types, feats_name, "test"
@@ -338,7 +345,8 @@ class Experiment:
 
         """
         df_train, df_test = self.df_train, self.df_test
-        feats_name = "_".join(ast.literal_eval(glob_conf.config["DATA"]["databases"]))
+        feats_name = "_".join(ast.literal_eval(
+            glob_conf.config["DATA"]["databases"]))
         self.feats_test, self.feats_train = pd.DataFrame(), pd.DataFrame()
         feats_types = self.util.config_val_list("FEATS", "type", [])
         # for some models no features are needed
@@ -372,7 +380,8 @@ class Experiment:
                 f"test feats ({self.feats_test.shape[0]}) != test labels"
                 f" ({self.df_test.shape[0]})"
             )
-            self.df_test = self.df_test[self.df_test.index.isin(self.feats_test.index)]
+            self.df_test = self.df_test[self.df_test.index.isin(
+                self.feats_test.index)]
             self.util.warn(f"mew test labels shape: {self.df_test.shape[0]}")
 
         self._check_scale()
@@ -383,7 +392,8 @@ class Experiment:
         """
         from nkululeko.augmenting.augmenter import Augmenter
 
-        sample_selection = self.util.config_val("AUGMENT", "sample_selection", "all")
+        sample_selection = self.util.config_val(
+            "AUGMENT", "sample_selection", "all")
         if sample_selection == "all":
             df = pd.concat([self.df_train, self.df_test])
         elif sample_selection == "train":
@@ -478,7 +488,8 @@ class Experiment:
         """
         from nkululeko.augmenting.randomsplicer import Randomsplicer
 
-        sample_selection = self.util.config_val("AUGMENT", "sample_selection", "all")
+        sample_selection = self.util.config_val(
+            "AUGMENT", "sample_selection", "all")
         if sample_selection == "all":
             df = pd.concat([self.df_train, self.df_test])
         elif sample_selection == "train":
@@ -499,7 +510,8 @@ class Experiment:
         plot_feats = eval(
             self.util.config_val("EXPL", "feature_distributions", "False")
         )
-        sample_selection = self.util.config_val("EXPL", "sample_selection", "all")
+        sample_selection = self.util.config_val(
+            "EXPL", "sample_selection", "all")
         # get the data labels
         if sample_selection == "all":
             df_labels = pd.concat([self.df_train, self.df_test])
@@ -562,7 +574,8 @@ class Experiment:
             for scat_target in scat_targets:
                 if self.util.is_categorical(df_labels[scat_target]):
                     for scatter in scatters:
-                        plots.scatter_plot(df_feats, df_labels, scat_target, scatter)
+                        plots.scatter_plot(
+                            df_feats, df_labels, scat_target, scatter)
                 else:
                     self.util.debug(
                         f"{self.name}: binning continuous variable to categories"
@@ -651,7 +664,8 @@ class Experiment:
         preds = best.preds
         speakers = self.df_test.speaker.values
         print(f"{len(truths)} {len(preds)} {len(speakers) }")
-        df = pd.DataFrame(data={"truth": truths, "pred": preds, "speaker": speakers})
+        df = pd.DataFrame(
+            data={"truth": truths, "pred": preds, "speaker": speakers})
         plot_name = "result_combined_per_speaker"
         self.util.debug(
             f"plotting speaker combination ({function}) confusion matrix to"

{nkululeko-0.85.1.dist-info → nkululeko-0.85.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: nkululeko
-Version: 0.85.1
+Version: 0.85.2
 Summary: Machine learning audio prediction experiments based on templates
 Home-page: https://github.com/felixbur/nkululeko
 Author: Felix Burkhardt
@@ -333,6 +333,10 @@ F. Burkhardt, Johannes Wagner, Hagen Wierstorf, Florian Eyben and Björn Schulle
 Changelog
 =========
 
+Version 0.85.2
+--------------
+* added data, and automatic task label detection
+
 Version 0.85.1
 --------------
 * fixed bug in model_finetuned that label_num was constant 2

{nkululeko-0.85.1.dist-info → nkululeko-0.85.2.dist-info}/RECORD

@@ -2,11 +2,11 @@ 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=WnTSXQjJmWE-IrXcNSEa5FFV_83-z0EOGXa9trq00uE,39
+nkululeko/constants.py,sha256=l15EMSj8vmejkCKCzQ6jMrgj5PuNrcHIREXt9kbSw7U,39
 nkululeko/demo.py,sha256=8bl15Kitoesnz8oa8yrs52T6YCSOhWbbq9PnZ8Hj6D0,3232
 nkululeko/demo_feats.py,sha256=sAeGFojhEj9WEDFtG3SzPBmyYJWLF2rkbpp65m8Ujo4,2025
 nkululeko/demo_predictor.py,sha256=es56xbT8ifkS_vnrlb5NTZT54gNmeUtNlA4zVA_gnN8,4757
-nkululeko/experiment.py,sha256=9Nw23b7sVOciH8IaOuAAKbY7otXYSsPrj_rQCA_U9cc,30465
+nkululeko/experiment.py,sha256=ZsSWdasWUyIBF_4vxb4FxvHs42pytG7ErUOABA-WWTo,30722
 nkululeko/explore.py,sha256=lDzRoW_Taa5u4BBABZLD89BcQWnYlrftJR4jgt1yyj0,2609
 nkululeko/export.py,sha256=mHeEAAmtZuxdyebLlbSzPrHSi9OMgJHbk35d3DTxRBc,4632
 nkululeko/feature_extractor.py,sha256=8mssYKmo4LclVI-hiLmJEDZ0ZPyDavFG2YwtXcrGzwM,3976
@@ -46,7 +46,7 @@ nkululeko/autopredict/ap_valence.py,sha256=n-hctRKySzhmJtowuMOTUu0T_ld3uK5pnfOzW
 nkululeko/autopredict/estimate_snr.py,sha256=S-bpS0xFkwWc4Ch75UrjbS8y538lQ0U3g_iLRFXureY,5048
 nkululeko/data/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nkululeko/data/dataset.py,sha256=JGzMD6HIvkFkYBekmbmslIKc5ADaCj06T-8gpqH_kFo,27650
-nkululeko/data/dataset_csv.py,sha256=uLa7jW4w2ft299NkpXZMD361kPHF8oSYoIZ_ucxhuOM,3884
+nkululeko/data/dataset_csv.py,sha256=vTnjIc2UdSJT7foL-ltE9MWrZTCg0nplwKdEtMPxt2o,3933
 nkululeko/feat_extract/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nkululeko/feat_extract/feats_agender.py,sha256=Qm69G4kqAyTVVk7wwRgrXlNwGaDMGRYyKGpuf0vOEgM,3113
 nkululeko/feat_extract/feats_agender_agender.py,sha256=tgH2BnwcxpvuLmOkrMbVdBSX0Onfz2MG12FsddalRKI,3424
@@ -106,8 +106,8 @@ nkululeko/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nkululeko/utils/files.py,sha256=UiGAtZRWYjHSvlmPaTMtzyNNGE6qaLaxQkybctS7iRM,4021
 nkululeko/utils/stats.py,sha256=1yUq0FTOyqkU8TwUocJRYdJaqMU5SlOBBRUun9STo2M,2829
 nkululeko/utils/util.py,sha256=b1IHFucRNuF9Iyv5IJeK4AEg0Rga0xKG80UM5GWWdHA,13816
-nkululeko-0.85.1.dist-info/LICENSE,sha256=0zGP5B_W35yAcGfHPS18Q2B8UhvLRY3dQq1MhpsJU_U,1076
-nkululeko-0.85.1.dist-info/METADATA,sha256=RonY9PdKyHjwYsZ3T9TgEs1JNnY1qbMdDr-Sp6kcCW8,36591
-nkululeko-0.85.1.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
-nkululeko-0.85.1.dist-info/top_level.txt,sha256=DPFNNSHPjUeVKj44dVANAjuVGRCC3MusJ08lc2a8xFA,10
-nkululeko-0.85.1.dist-info/RECORD,,
+nkululeko-0.85.2.dist-info/LICENSE,sha256=0zGP5B_W35yAcGfHPS18Q2B8UhvLRY3dQq1MhpsJU_U,1076
+nkululeko-0.85.2.dist-info/METADATA,sha256=RVGREhA1jakUtQ707C0ecklnUZwx4skVHV0UbPwEsn0,36671
+nkululeko-0.85.2.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
+nkululeko-0.85.2.dist-info/top_level.txt,sha256=DPFNNSHPjUeVKj44dVANAjuVGRCC3MusJ08lc2a8xFA,10
+nkululeko-0.85.2.dist-info/RECORD,,