nkululeko 0.93.12__py3-none-any.whl → 0.93.13__py3-none-any.whl

nkululeko/constants.py

@@ -1,2 +1,2 @@
-VERSION="0.93.12"
+VERSION="0.93.13"
 SAMPLING_RATE = 16000

nkululeko/data/dataset.py

@@ -34,11 +34,9 @@ class Dataset:
         self.plot = Plots()
         self.limit = int(self.util.config_val_data(self.name, "limit", 0))
         self.target_tables_append = eval(
-            self.util.config_val_data(
-                self.name, "target_tables_append", "False")
+            self.util.config_val_data(self.name, "target_tables_append", "False")
         )
-        self.start_fresh = eval(
-            self.util.config_val("DATA", "no_reuse", "False"))
+        self.start_fresh = eval(self.util.config_val("DATA", "no_reuse", "False"))
         self.is_labeled, self.got_speaker, self.got_gender, self.got_age = (
             False,
             False,
@@ -72,8 +70,7 @@ class Dataset:
         try:
             self.db = audformat.Database.load(root)
         except FileNotFoundError:
-            self.util.error(
-                f"{self.name}: no audformat database found at {root}")
+            self.util.error(f"{self.name}: no audformat database found at {root}")
         return root
 
     def _check_cols(self, df):
@@ -95,8 +92,7 @@ class Dataset:
         )
         self.util.debug(r_string)
         if glob_conf.report.initial:
-            glob_conf.report.add_item(ReportItem(
-                "Data", "Load report", r_string))
+            glob_conf.report.add_item(ReportItem("Data", "Load report", r_string))
             glob_conf.report.initial = False
 
     def load(self):
@@ -107,8 +103,7 @@ class Dataset:
         store_file = f"{store}{self.name}.{store_format}"
         self.root = self._load_db()
         if not self.start_fresh and os.path.isfile(store_file):
-            self.util.debug(
-                f"{self.name}: reusing previously stored file {store_file}")
+            self.util.debug(f"{self.name}: reusing previously stored file {store_file}")
             self.df = self.util.get_store(store_file, store_format)
             self.is_labeled = self.target in self.df
             self.got_gender = "gender" in self.df
@@ -123,12 +118,10 @@ class Dataset:
         # map the audio file paths
         self.db.map_files(lambda x: os.path.join(self.root, x))
         # the dataframes (potentially more than one) with at least the file names
-        df_files = self.util.config_val_data(
-            self.name, "files_tables", "['files']")
+        df_files = self.util.config_val_data(self.name, "files_tables", "['files']")
         df_files_tables = ast.literal_eval(df_files)
         # The label for the target column
-        self.col_label = self.util.config_val_data(
-            self.name, "label", self.target)
+        self.col_label = self.util.config_val_data(self.name, "label", self.target)
         (
             df,
             self.is_labeled,
@@ -164,8 +157,7 @@ class Dataset:
                 self.got_age = got_age2 or self.got_age
                 if audformat.is_filewise_index(df_target.index):
                     try:
-                        df_target = df_target.loc[df.index.get_level_values(
-                            "file")]
+                        df_target = df_target.loc[df.index.get_level_values("file")]
                         df_target = df_target.set_index(df.index)
                     except KeyError:
                         # just a try...
@@ -214,8 +206,7 @@ class Dataset:
             end = self.df.index.get_level_values(2)
             self.df["duration"] = (end - start).total_seconds()
         elif self.df.duration.dtype == "timedelta64[ns]":
-            self.df["duration"] = self.df["duration"].map(
-                lambda x: x.total_seconds())
+            self.df["duration"] = self.df["duration"].map(lambda x: x.total_seconds())
         # Perform some filtering if desired
         required = self.util.config_val_data(self.name, "required", False)
         if required:
@@ -245,18 +236,15 @@ class Dataset:
                 res.append(abs(n - max))
             return res
 
-        reverse = eval(self.util.config_val_data(
-            self.name, "reverse", "False"))
+        reverse = eval(self.util.config_val_data(self.name, "reverse", "False"))
         if reverse:
-            max = eval(self.util.config_val_data(
-                self.name, "reverse.max", "False"))
+            max = eval(self.util.config_val_data(self.name, "reverse.max", "False"))
             if max:
                 max = float(max)
             else:
                 max = self.df[self.target].values.max()
             self.util.debug(f"reversing target numbers with max values: {max}")
-            self.df[self.target] = reverse_array(
-                self.df[self.target].values, max)
+            self.df[self.target] = reverse_array(self.df[self.target].values, max)
 
         # check if the target variable should be scaled (z-transformed)
         scale = self.util.config_val_data(self.name, "scale", False)
@@ -329,15 +317,13 @@ class Dataset:
                 pass
             try:
                 # also it might be possible that the age is part of the speaker description
-                df_local["age"] = db[table]["speaker"].get(
-                    map="age").astype(int)
+                df_local["age"] = db[table]["speaker"].get(map="age").astype(int)
                 got_age = True
             except (ValueError, audformat.errors.BadKeyError):
                 pass
             try:
                 # same for the target, e.g. "age"
-                df_local[self.target] = db[table]["speaker"].get(
-                    map=self.target)
+                df_local[self.target] = db[table]["speaker"].get(map=self.target)
                 is_labeled = True
             except (ValueError, audformat.core.errors.BadKeyError):
                 pass
@@ -398,10 +384,8 @@ class Dataset:
             testdf = self.db.tables[self.target + ".test"].df
             traindf = self.db.tables[self.target + ".train"].df
             # use only the train and test samples that were not perhaps filtered out by an earlier processing step
-            self.df_test = self.df.loc[self.df.index.intersection(
-                testdf.index)]
-            self.df_train = self.df.loc[self.df.index.intersection(
-                traindf.index)]
+            self.df_test = self.df.loc[self.df.index.intersection(testdf.index)]
+            self.df_train = self.df.loc[self.df.index.intersection(traindf.index)]
         elif split_strategy == "train":
             self.df_train = self.df
             self.df_test = pd.DataFrame()
@@ -424,23 +408,18 @@ class Dataset:
             if entry_train_tables:
                 train_tables = ast.literal_eval(entry_train_tables)
                 for train_table in train_tables:
-                    traindf = pd.concat(
-                        [traindf, self.db.tables[train_table].df])
+                    traindf = pd.concat([traindf, self.db.tables[train_table].df])
             # use only the train and test samples that were not perhaps filtered out by an earlier processing step
             # testdf.index.map(lambda x: os.path.join(self.root, x))
             #            testdf.index = testdf.index.to_series().apply(lambda x: self.root+x)
             testdf = testdf.set_index(
-                audformat.utils.to_segmented_index(
-                    testdf.index, allow_nat=False)
+                audformat.utils.to_segmented_index(testdf.index, allow_nat=False)
             )
             traindf = traindf.set_index(
-                audformat.utils.to_segmented_index(
-                    traindf.index, allow_nat=False)
+                audformat.utils.to_segmented_index(traindf.index, allow_nat=False)
             )
-            self.df_test = self.df.loc[self.df.index.intersection(
-                testdf.index)]
-            self.df_train = self.df.loc[self.df.index.intersection(
-                traindf.index)]
+            self.df_test = self.df.loc[self.df.index.intersection(testdf.index)]
+            self.df_train = self.df.loc[self.df.index.intersection(traindf.index)]
             # it might be necessary to copy the target values
             try:
                 self.df_test[self.target] = testdf[self.target]
@@ -467,12 +446,10 @@ class Dataset:
             self.util.error(f"unknown split strategy: {split_strategy}")
 
         # check if train or test set should be ignored
-        as_test = eval(self.util.config_val_data(
-            self.name, "as_test", "False"))
+        as_test = eval(self.util.config_val_data(self.name, "as_test", "False"))
         if as_test:
             self.df_train = pd.DataFrame()
-        as_train = eval(self.util.config_val_data(
-            self.name, "as_train", "False"))
+        as_train = eval(self.util.config_val_data(self.name, "as_train", "False"))
         if as_train:
             self.df_test = pd.DataFrame()
 
@@ -503,8 +480,7 @@ class Dataset:
 
         seed = 42
         k = 30
-        test_size = int(self.util.config_val_data(
-            self.name, "test_size", 20)) / 100.0
+        test_size = int(self.util.config_val_data(self.name, "test_size", 20)) / 100.0
         df = self.df
         # split target
         targets = df[self.target].to_numpy()
@@ -520,8 +496,7 @@ class Dataset:
         stratif_vars = self.util.config_val("DATA", "balance", False)
         stratif_vars_array = {}
         if not stratif_vars:
-            self.util.error(
-                "balanced split needs stratif_vars to stratify the splits")
+            self.util.error("balanced split needs stratif_vars to stratify the splits")
         else:
             stratif_vars = ast.literal_eval(stratif_vars)
             for stratif_var in stratif_vars.keys():
@@ -530,8 +505,7 @@ class Dataset:
                     continue
                 else:
                     data = df[stratif_var].to_numpy()
-                    bins = self.util.config_val(
-                        "DATA", f"{stratif_var}_bins", False)
+                    bins = self.util.config_val("DATA", f"{stratif_var}_bins", False)
                     if bins:
                         data = binning(data, nbins=int(bins))
                     stratif_vars_array[stratif_var] = data
@@ -582,8 +556,7 @@ class Dataset:
 
     def split_speakers(self):
         """One way to split train and eval sets: Specify percentage of evaluation speakers"""
-        test_percent = int(self.util.config_val_data(
-            self.name, "test_size", 20))
+        test_percent = int(self.util.config_val_data(self.name, "test_size", 20))
         df = self.df
         s_num = df.speaker.nunique()
         test_num = int(s_num * (test_percent / 100))
@@ -602,8 +575,7 @@ class Dataset:
 
     def random_split(self):
         """One way to split train and eval sets: Specify percentage of random samples"""
-        test_percent = int(self.util.config_val_data(
-            self.name, "test_size", 20))
+        test_percent = int(self.util.config_val_data(self.name, "test_size", 20))
         df = self.df
         s_num = len(df)
         test_num = int(s_num * (test_percent / 100))
@@ -707,8 +679,7 @@ class Dataset:
         if df.empty:
             return
         if self.check_continuous_classification():
-            self.util.debug(
-                f"{self.name}: binning continuous variable to categories")
+            self.util.debug(f"{self.name}: binning continuous variable to categories")
             cat_vals = self.util.continuous_to_categorical(df[self.target])
             df[self.target] = cat_vals.values
             labels = ast.literal_eval(glob_conf.config["DATA"]["labels"])

nkululeko/feat_extract/feats_analyser.py

@@ -4,8 +4,10 @@ import ast
 import matplotlib.pyplot as plt
 import pandas as pd
 from sklearn.inspection import permutation_importance
-from sklearn.linear_model import LinearRegression, LogisticRegression
-from sklearn.tree import DecisionTreeClassifier, DecisionTreeRegressor
+from sklearn.linear_model import LinearRegression
+from sklearn.linear_model import LogisticRegression
+from sklearn.tree import DecisionTreeClassifier
+from sklearn.tree import DecisionTreeRegressor
 
 import nkululeko.glob_conf as glob_conf
 from nkululeko.plots import Plots

nkululeko/feat_extract/feats_wav2vec2.py

@@ -49,6 +49,7 @@ class Wav2vec2(Featureset):
         hidden_layer = int(self.util.config_val("FEATS", "wav2vec2.layer", "0"))
         config.num_hidden_layers = layer_num - hidden_layer
         self.util.debug(f"using hidden layer #{config.num_hidden_layers}")
+
         self.processor = Wav2Vec2FeatureExtractor.from_pretrained(model_path)
         self.model = Wav2Vec2Model.from_pretrained(model_path, config=config).to(
             self.device

nkululeko/plots.py

@@ -297,6 +297,9 @@ class Plots:
         if cat_col == "class_label":
             plot_df = plot_df.rename(columns={cat_col: self.target})
             cat_col = self.target
+        elif cont_col == "class_label":
+            plot_df = plot_df.rename(columns={cont_col: self.target})
+            cont_col = self.target
         dist_type = self.util.config_val("EXPL", "dist_type", "kde")
         cats, cat_str, es = su.get_effect_size(plot_df, cat_col, cont_col)
         model_type = self.util.get_model_type()
@@ -327,7 +330,7 @@ class Plots:
         if col2 == "class_label":
             plot_df = plot_df.rename(columns={col2: self.target})
             col2 = self.target
-        if col1 == "class_label":
+        elif col1 == "class_label":
             plot_df = plot_df.rename(columns={col1: self.target})
             col1 = self.target
         crosstab = pd.crosstab(index=plot_df[col1], columns=plot_df[col2])

nkululeko-0.93.13.dist-info/METADATA

@@ -0,0 +1,39 @@
+Metadata-Version: 2.2
+Name: nkululeko
+Version: 0.93.13
+Summary: Machine learning audio prediction experiments based on templates
+Home-page: https://github.com/felixbur/nkululeko
+Author: Felix Burkhardt
+Author-email: fxburk@gmail.com
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Development Status :: 3 - Alpha
+Classifier: Topic :: Scientific/Engineering
+Requires-Python: >=3.9
+License-File: LICENSE
+Requires-Dist: audeer
+Requires-Dist: audformat
+Requires-Dist: audinterface
+Requires-Dist: audiofile
+Requires-Dist: audiomentations
+Requires-Dist: audmetric
+Requires-Dist: audonnx
+Requires-Dist: confidence_intervals
+Requires-Dist: datasets
+Requires-Dist: imageio
+Requires-Dist: matplotlib
+Requires-Dist: numpy
+Requires-Dist: opensmile
+Requires-Dist: pandas
+Requires-Dist: praat-parselmouth
+Requires-Dist: scikit_learn
+Requires-Dist: scipy
+Requires-Dist: seaborn
+Requires-Dist: sounddevice
+Requires-Dist: torch
+Requires-Dist: torchvision
+Requires-Dist: transformers
+Requires-Dist: umap-learn
+Requires-Dist: xgboost
+Requires-Dist: pylatex

{nkululeko-0.93.12.dist-info → nkululeko-0.93.13.dist-info}/RECORD

@@ -2,7 +2,7 @@ nkululeko/__init__.py,sha256=62f8HiEzJ8rG2QlTFJXUCMpvuH3fKI33DoJSj33mscc,63
 nkululeko/aug_train.py,sha256=FoMbBrfyOZd4QAw7oIHl3X6-UpsqAKWVDIolCA7qOWs,3196
 nkululeko/augment.py,sha256=3RzaxB3gRxovgJVjHXi0glprW01J7RaHhUkqotW2T3U,2955
 nkululeko/cacheddataset.py,sha256=XFpWZmbJRg0pvhnIgYf0TkclxllD-Fctu-Ol0PF_00c,969
-nkululeko/constants.py,sha256=T9YZzqdg_ltKpuIf2XZdrqFmmlZQmhak97DpM5GQQhI,40
+nkululeko/constants.py,sha256=B_SoEW_E21VyJqFUyh_XG4GvVYNPEsgUF31slyJ2fFY,40
 nkululeko/demo-ft.py,sha256=iD9Pzp9QjyAv31q1cDZ75vPez7Ve8A4Cfukv5yfZdrQ,770
 nkululeko/demo.py,sha256=4Yzhg6pCPBYPGJrP7JX2TysVosl_R1llpVDKc2P_gUA,4955
 nkululeko/demo_feats.py,sha256=BvZjeNFTlERIRlq34OHM4Z96jdDQAhB01BGQAUcX9dM,2026
@@ -20,7 +20,7 @@ nkululeko/modelrunner.py,sha256=lJy-xM4QfDDWeL0dLTE_VIb4sYrnd_Z_yJRK3wwohQA,1119
 nkululeko/multidb.py,sha256=sO6OwJn8sn1-C-ig3thsIL8QMWHdV9SnJhDodKjeKrI,6876
 nkululeko/nkuluflag.py,sha256=PGWSmZz-PiiHLgcZJAoGOI_Y-sZDVI1ksB8p5r7riWM,3725
 nkululeko/nkululeko.py,sha256=M7baIq2nAoi6dEoBL4ATEuqAs5U1fvl_hyqAl5DybAQ,2040
-nkululeko/plots.py,sha256=Mm30pDLBb55iE9SYaSg76KFBKnebZTlypFQIBo26wuY,25991
+nkululeko/plots.py,sha256=2G5yNR3Q3qWDt8ncKwKUZBLE-O1rbGUiG6omwfFudVk,26138
 nkululeko/predict.py,sha256=MLnHEyFmSiHLLs-HDczag8Vu3zKF5T1rXLKdZZJ6py8,2083
 nkululeko/resample.py,sha256=rn3-M1A-iwVGibfQNGyeYNa7briD24lIN9Szq_1uTJo,5194
 nkululeko/runmanager.py,sha256=AswmORVUkCIH0gTx6zEyufvFATQBS8C5TXo2erSNdVg,7611
@@ -49,12 +49,12 @@ nkululeko/autopredict/ap_stoi.py,sha256=UEQg1ZV0meAsxgdWB8ieRs9GPXHqArmsaOyCGRwp
 nkululeko/autopredict/ap_valence.py,sha256=WrW4Ltqi_odW49_4QEVKkfnrcztLIVZ4cXIEHu4dBN8,1026
 nkululeko/autopredict/estimate_snr.py,sha256=1k9-XadABudnsNOeFZD_Fg0E64-GUQVS7JEp82MLQS4,4995
 nkululeko/data/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-nkululeko/data/dataset.py,sha256=H65rvQ8sPwEwv_T-FqOEa7FeQ3JBn88v3xOzBOjARe4,30582
+nkululeko/data/dataset.py,sha256=G6RFK2msSVHxpzDm8gZSAD4GK6ieMS5fTbqVS-NOFuY,30081
 nkululeko/data/dataset_csv.py,sha256=p2b4eS5R2Q5zdOIc56NRRU2PTFXSRt0qrdHGafHkWKo,4830
 nkululeko/feat_extract/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nkululeko/feat_extract/feats_agender.py,sha256=onfAQ6-xx_mFMJXEF1IX8cHBmGtGeX6weJmxbkfh1_o,3184
 nkululeko/feat_extract/feats_agender_agender.py,sha256=_YQv1qw--3uQfnyTQDCwlmPRnrhdMhgXbYK2yQtseW0,3464
-nkululeko/feat_extract/feats_analyser.py,sha256=luTV2-yw7rk0aQPI88vvtW1GLV8cGypp7LJW1v_YBrw,13450
+nkululeko/feat_extract/feats_analyser.py,sha256=txuIEgO4uprle35RzBczvZm5Hc7iUl2p9oBEfdrvg_I,13506
 nkululeko/feat_extract/feats_ast.py,sha256=w62xEoLiFtU-rj6SXkqXAktmoFaXcAcAWpUyEjp8JWo,4652
 nkululeko/feat_extract/feats_auddim.py,sha256=CGLp_aYhudfwoU5522vjrvjPxfZcyw593A8xLjYefV8,3134
 nkululeko/feat_extract/feats_audmodel.py,sha256=OsZyB1rdcG0Fai2gAwBlbuubmWor1_-P4IDkZLqgPKE,3161
@@ -71,7 +71,7 @@ nkululeko/feat_extract/feats_spectra.py,sha256=6WhFUpB0WTutg7OFMlAw9lSwVU5OBYCDc
 nkululeko/feat_extract/feats_spkrec.py,sha256=o_6bdU4lIkj64S5Kdjf1iyuo1VASeYxE4XdxV94a8gE,4732
 nkululeko/feat_extract/feats_squim.py,sha256=yJifsp9kj9iJjW_UAKr3LlvVhX5rv7el4bepn0wN2a8,4578
 nkululeko/feat_extract/feats_trill.py,sha256=JgyUQ8ihIL5PlUpxjchlbC9547GI0SyUwkFEquya85Q,3197
-nkululeko/feat_extract/feats_wav2vec2.py,sha256=WYB9XlRzgDi8cGSKzhV5jahA0GZ_SiWgaQ25IcEemto,5296
+nkululeko/feat_extract/feats_wav2vec2.py,sha256=q1QzMD3KbhF2SOmxdwI7CiViRmhlFRyghxN_6SmUc0E,5297
 nkululeko/feat_extract/feats_wavlm.py,sha256=O9cfc39VF5aPJRRATKb37pHT4W11i2cu5O1mY9LOjIA,4755
 nkululeko/feat_extract/feats_whisper.py,sha256=n3ESZtva7wshs8E8diBlQYa9xCH_P0UY1DncSrxz-FY,4508
 nkululeko/feat_extract/featureset.py,sha256=clcBv9rzBRW-bfw7JC_FYTjU5uUS-c0UE1XtQLYYRiE,1615
@@ -112,9 +112,9 @@ nkululeko/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nkululeko/utils/files.py,sha256=SrrYaU7AB80MZHiV1jcB0h_zigvYLYgSVNTXV4ao38g,4593
 nkululeko/utils/stats.py,sha256=vCRzhCR0Gx5SiJyAGbj1TIto8ocGz58CM5Pr3LltagA,2948
 nkululeko/utils/util.py,sha256=wFDslqxpCVDwi6LBakIFDDy1kYsxt5G7ykE38CocmtA,16880
-nkululeko-0.93.12.dist-info/LICENSE,sha256=0zGP5B_W35yAcGfHPS18Q2B8UhvLRY3dQq1MhpsJU_U,1076
-nkululeko-0.93.12.dist-info/METADATA,sha256=jjO-vG0POWF3v_v3QfliA4uT8jzZPikwmEj2O6v6rhg,42823
-nkululeko-0.93.12.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
-nkululeko-0.93.12.dist-info/entry_points.txt,sha256=lNTkFEdh6Kjo5o95ZAWf_0Lq-4ztGoAoMVSDuPtuyS0,442
-nkululeko-0.93.12.dist-info/top_level.txt,sha256=DPFNNSHPjUeVKj44dVANAjuVGRCC3MusJ08lc2a8xFA,10
-nkululeko-0.93.12.dist-info/RECORD,,
+nkululeko-0.93.13.dist-info/LICENSE,sha256=0zGP5B_W35yAcGfHPS18Q2B8UhvLRY3dQq1MhpsJU_U,1076
+nkululeko-0.93.13.dist-info/METADATA,sha256=G0DPQrKRoSO4lB0NjR5hjc715sggueUA3lcokR1NyUQ,1148
+nkululeko-0.93.13.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
+nkululeko-0.93.13.dist-info/entry_points.txt,sha256=lNTkFEdh6Kjo5o95ZAWf_0Lq-4ztGoAoMVSDuPtuyS0,442
+nkululeko-0.93.13.dist-info/top_level.txt,sha256=DPFNNSHPjUeVKj44dVANAjuVGRCC3MusJ08lc2a8xFA,10
+nkululeko-0.93.13.dist-info/RECORD,,