nkululeko 0.76.0__py3-none-any.whl → 0.77.1__py3-none-any.whl

nkululeko/models/model.py

@@ -1,5 +1,5 @@
 # model.py
-from nkululeko.util import Util
+from nkululeko.utils.util import Util
 import pandas as pd
 import numpy as np
 import nkululeko.glob_conf as glob_conf

nkululeko/models/model_cnn.py

@@ -16,7 +16,7 @@ from sklearn.metrics import recall_score
 from collections import OrderedDict
 from PIL import Image
 
-from nkululeko.util import Util
+from nkululeko.utils.util import Util
 import nkululeko.glob_conf as glob_conf
 from nkululeko.models.model import Model
 from nkululeko.reporter import Reporter

nkululeko/models/model_mlp.py

@@ -1,5 +1,5 @@
 # model_mlp.py
-from nkululeko.util import Util
+from nkululeko.utils.util import Util
 import nkululeko.glob_conf as glob_conf
 from nkululeko.models.model import Model
 from nkululeko.reporter import Reporter

nkululeko/models/model_mlp_regression.py

@@ -1,5 +1,5 @@
 # model_mlp.py
-from nkululeko.util import Util
+from nkululeko.utils.util import Util
 import nkululeko.glob_conf as glob_conf
 from nkululeko.models.model import Model
 from nkululeko.reporter import Reporter

nkululeko/nkululeko.py

@@ -5,17 +5,13 @@ import os.path
 import configparser
 import argparse
 import nkululeko.experiment as exp
-from nkululeko.util import Util
+from nkululeko.utils.util import Util
 from nkululeko.constants import VERSION
 
 
 def main(src_dir):
-    parser = argparse.ArgumentParser(
-        description="Call the nkululeko framework."
-    )
-    parser.add_argument(
-        "--config", default="exp.ini", help="The base configuration"
-    )
+    parser = argparse.ArgumentParser(description="Call the nkululeko framework.")
+    parser.add_argument("--config", default="exp.ini", help="The base configuration")
     args = parser.parse_args()
     if args.config is not None:
         config_file = args.config
@@ -49,9 +45,7 @@ def main(src_dir):
 
     # split into train and test
     expr.fill_train_and_tests()
-    util.debug(
-        f"train shape : {expr.df_train.shape}, test shape:{expr.df_test.shape}"
-    )
+    util.debug(f"train shape : {expr.df_train.shape}, test shape:{expr.df_test.shape}")
 
     # extract features
     expr.extract_feats()
@@ -69,6 +63,4 @@ def main(src_dir):
 
 if __name__ == "__main__":
     cwd = os.path.dirname(os.path.abspath(__file__))
-    main(
-        cwd
-    )  # use this if you want to state the config file path on command line
+    main(cwd)  # use this if you want to state the config file path on command line

nkululeko/plots.py

@@ -6,7 +6,7 @@ import seaborn as sns
 import numpy as np
 import ast
 from scipy import stats
-from nkululeko.util import Util
+from nkululeko.utils.util import Util
 import nkululeko.utils.stats as su
 import nkululeko.glob_conf as glob_conf
 from nkululeko.reporting.report_item import ReportItem
@@ -347,9 +347,18 @@ class Plots:
                     kind="bar", ax=axes, title=f"samples ({sampl_num})"
                 )
             # plt.tight_layout()
-            plt.savefig(f"{fig_dir}{filename}.{self.format}")
+            img_path = f"{fig_dir}{filename}.{self.format}"
+            plt.savefig(img_path)
             fig.clear()
             plt.close(fig)
+            glob_conf.report.add_item(
+                ReportItem(
+                    Header.HEADER_EXPLORE,
+                    f"Overview on {df.shape[0]} samples",
+                    "",
+                    img_path,
+                )
+            )
 
     def scatter_plot(self, feats, label_df, label, dimred_type):
         fig_dir = self.util.get_path("fig_dir") + "../"  # one up because of the runs
@@ -401,6 +410,14 @@ class Plots:
         plt.savefig(filename)
         fig.clear()
         plt.close(fig)
+        glob_conf.report.add_item(
+            ReportItem(
+                Header.HEADER_EXPLORE,
+                f"Scatter plot",
+                f"using {dimred_type}",
+                filename,
+            )
+        )
 
     def plotTsne(self, feats, labels, filename, perplexity=30, learning_rate=200):
         """Make a TSNE plot to see whether features are useful for classification"""
@@ -439,8 +456,10 @@ class Plots:
         return tsne_data
 
     def plot_feature(self, title, feature, label, df_labels, df_features):
+        # remove fullstops in the name
+        feature_name = feature.replace(".", "-")
         fig_dir = self.util.get_path("fig_dir") + "../"  # one up because of the runs
-        filename = f"{fig_dir}feat_dist_{title}_{feature}.{self.format}"
+        filename = f"{fig_dir}feat_dist_{title}_{feature_name}.{self.format}"
         if self.util.is_categorical(df_labels[label]):
             df_plot = pd.DataFrame(
                 {label: df_labels[label], feature: df_features[feature]}
@@ -458,6 +477,16 @@ class Plots:
         plt.savefig(filename)
         fig.clear()
         plt.close(fig)
+        caption = f"Feature plot for feature {feature}"
+        content = caption
+        glob_conf.report.add_item(
+            ReportItem(
+                Header.HEADER_EXPLORE,
+                caption,
+                content,
+                filename,
+            )
+        )
 
     def plot_tree(self, model, features):
         from sklearn import tree
@@ -476,3 +505,11 @@ class Plots:
         fig.savefig(filename)
         fig.clear()
         plt.close(fig)
+        glob_conf.report.add_item(
+            ReportItem(
+                Header.HEADER_EXPLORE,
+                f"Tree plot",
+                f"for feature importance",
+                filename,
+            )
+        )

nkululeko/predict.py

@@ -3,19 +3,15 @@
 
 from nkululeko.experiment import Experiment
 import configparser
-from nkululeko.util import Util
+from nkululeko.utils.util import Util
 from nkululeko.constants import VERSION
 import argparse
 import os
 
 
 def main(src_dir):
-    parser = argparse.ArgumentParser(
-        description="Call the nkululeko framework."
-    )
-    parser.add_argument(
-        "--config", default="exp.ini", help="The base configuration"
-    )
+    parser = argparse.ArgumentParser(description="Call the nkululeko framework.")
+    parser.add_argument("--config", default="exp.ini", help="The base configuration")
     args = parser.parse_args()
     if args.config is not None:
         config_file = args.config
@@ -43,9 +39,7 @@ def main(src_dir):
 
     # split into train and test
     expr.fill_train_and_tests()
-    util.debug(
-        f"train shape : {expr.df_train.shape}, test shape:{expr.df_test.shape}"
-    )
+    util.debug(f"train shape : {expr.df_train.shape}, test shape:{expr.df_test.shape}")
 
     # process the data
     df = expr.autopredict()
@@ -61,6 +55,4 @@ def main(src_dir):
 
 if __name__ == "__main__":
     cwd = os.path.dirname(os.path.abspath(__file__))
-    main(
-        cwd
-    )  # use this if you want to state the config file path on command line
+    main(cwd)  # use this if you want to state the config file path on command line

nkululeko/reporter.py

@@ -21,7 +21,7 @@ import nkululeko.glob_conf as glob_conf
 from nkululeko.reporting.report_item import ReportItem
 from nkululeko.result import Result
 from nkululeko.reporting.defines import Header
-from nkululeko.util import Util
+from nkululeko.utils.util import Util
 
 
 class Reporter:

nkululeko/reporting/latex_writer.py

@@ -6,7 +6,7 @@ print out report as latex file and pdf
 from pylatex import Document, Section, Subsection, Command, Figure
 from pylatex.utils import italic, NoEscape
 from nkululeko.reporting.report_item import ReportItem
-from nkululeko.util import Util
+from nkululeko.utils.util import Util
 
 
 class LatexWriter:
@@ -27,15 +27,20 @@ class LatexWriter:
                 with self.doc.create(Subsection(ri.caption)):
                     self.doc.append(ri.contents)
                     if ri.has_image:
-                        with self.doc.create(Figure(position='h!')) as pic:
-                            pic.add_image(ri.image, width='250px')
+                        with self.doc.create(Figure(position="h!")) as pic:
+                            pic.add_image(ri.image, width="250px")
                             pic.add_caption(ri.caption)
+                            # reference = pic.dumps_as_content()
+                            # self.doc.append(f"See figure: {reference}")
 
     def finish_doc(self):
-        target_filename = self.util.config_val(
-            "REPORT", "latex", "nkululeko_latex"
-        )
+        from subprocess import CalledProcessError
+
+        target_filename = self.util.config_val("REPORT", "latex", "nkululeko_latex")
         target_dir = self.util.get_exp_dir()
-        path = '/'.join([target_dir, target_filename])
-        self.util.debug(f'Generated latex report to {path}')
-        self.doc.generate_pdf(path, clean_tex=False)
+        path = "/".join([target_dir, target_filename])
+        self.util.debug(f"Generated latex report to {path}")
+        try:
+            self.doc.generate_pdf(path, clean_tex=False)
+        except CalledProcessError as e:
+            self.util.debug(f"Error while generating PDF file: {e}")

nkululeko/reporting/report.py

@@ -4,10 +4,11 @@ report.py
 Collector class for report items collected during module processing.
 
 """
-from nkululeko.util import Util
+from nkululeko.utils.util import Util
 from nkululeko.reporting.report_item import ReportItem
 from nkululeko.reporting.latex_writer import LatexWriter
 
+
 class Report:
     def __init__(self):
         self.report_items = {}

nkululeko/resample.py

@@ -3,7 +3,7 @@
 
 from nkululeko.experiment import Experiment
 import configparser
-from nkululeko.util import Util
+from nkululeko.utils.util import Util
 from nkululeko.constants import VERSION
 import argparse
 import os
@@ -12,12 +12,8 @@ from nkululeko.augmenting.resampler import Resampler
 
 
 def main(src_dir):
-    parser = argparse.ArgumentParser(
-        description="Call the nkululeko framework."
-    )
-    parser.add_argument(
-        "--config", default="exp.ini", help="The base configuration"
-    )
+    parser = argparse.ArgumentParser(description="Call the nkululeko framework.")
+    parser.add_argument("--config", default="exp.ini", help="The base configuration")
     args = parser.parse_args()
     if args.config is not None:
         config_file = args.config
@@ -50,9 +46,7 @@ def main(src_dir):
 
     # split into train and test
     expr.fill_train_and_tests()
-    util.debug(
-        f"train shape : {expr.df_train.shape}, test shape:{expr.df_test.shape}"
-    )
+    util.debug(f"train shape : {expr.df_train.shape}, test shape:{expr.df_test.shape}")
 
     sample_selection = util.config_val("RESAMPLE", "sample_selection", "all")
     if sample_selection == "all":
@@ -74,6 +68,4 @@ def main(src_dir):
 
 if __name__ == "__main__":
     cwd = os.path.dirname(os.path.abspath(__file__))
-    main(
-        cwd
-    )  # use this if you want to state the config file path on command line
+    main(cwd)  # use this if you want to state the config file path on command line

nkululeko/runmanager.py

@@ -1,7 +1,7 @@
 # runmanager.py
 
 from nkululeko.reporter import Reporter
-from nkululeko.util import Util
+from nkululeko.utils.util import Util
 import nkululeko.glob_conf as glob_conf
 from nkululeko.modelrunner import Modelrunner
 

nkululeko/scaler.py

@@ -3,7 +3,7 @@
 
 from sklearn.preprocessing import StandardScaler, RobustScaler
 import pandas as pd
-from nkululeko.util import Util
+from nkululeko.utils.util import Util
 
 
 class Scaler:

nkululeko/segment.py

@@ -6,7 +6,7 @@ import os
 import pandas as pd
 import configparser
 from nkululeko.experiment import Experiment
-from nkululeko.util import Util
+from nkululeko.utils.util import Util
 from nkululeko.constants import VERSION
 import nkululeko.glob_conf as glob_conf
 from nkululeko.reporting.report_item import ReportItem

nkululeko/segmenting/seg_silero.py

@@ -7,11 +7,11 @@ segment a dataset with the Silero segmenter
 
 import torch
 import pandas as pd
-from tqdm import tqdm  
+from tqdm import tqdm
 import audformat
 from audformat.utils import to_filewise_index
 from audformat import segmented_index
-from nkululeko.util import Util
+from nkululeko.utils.util import Util
 
 # from nkululeko.constants import SAMPLING_RATE
 
@@ -44,9 +44,7 @@ class Silero_segmenter:
         SAMPLING_RATE = 16000
         if self.no_testing:
             min_length = float(self.util.config_val("SEGMENT", "min_length", 2))
-            max_length = float(
-                self.util.config_val("SEGMENT", "max_length", 10)
-            )
+            max_length = float(self.util.config_val("SEGMENT", "max_length", 10))
         else:
             min_length = 2
             max_length = 10

nkululeko/test.py

@@ -3,19 +3,15 @@
 
 from nkululeko.experiment import Experiment
 import configparser
-from nkululeko.util import Util
+from nkululeko.utils.util import Util
 from nkululeko.constants import VERSION
 import argparse
 import os
 
 
 def main(src_dir):
-    parser = argparse.ArgumentParser(
-        description="Call the nkululeko framework."
-    )
-    parser.add_argument(
-        "--config", default="exp.ini", help="The base configuration"
-    )
+    parser = argparse.ArgumentParser(description="Call the nkululeko framework.")
+    parser.add_argument("--config", default="exp.ini", help="The base configuration")
     parser.add_argument(
         "--outfile",
         default="my_results.csv",
@@ -54,6 +50,4 @@ def main(src_dir):
 
 if __name__ == "__main__":
     cwd = os.path.dirname(os.path.abspath(__file__))
-    main(
-        cwd
-    )  # use this if you want to state the config file path on command line
+    main(cwd)  # use this if you want to state the config file path on command line

nkululeko/test_predictor.py

@@ -3,7 +3,7 @@
 
 """
 import nkululeko.glob_conf as glob_conf
-from nkululeko.util import Util
+from nkululeko.utils.util import Util
 import pandas as pd
 from nkululeko.data.dataset import Dataset
 from nkululeko.feature_extractor import FeatureExtractor

nkululeko/utils/stats.py

@@ -85,3 +85,11 @@ def cohens_D_to_string(val):
     else:
         rval = "large effect"
     return f"Cohen's d: {rval}"
+
+
+def normalize(values):
+    """Do a z-transformation of a distribution, so that mean = 0 and variance = 1"""
+    from sklearn.preprocessing import StandardScaler
+
+    scaler = StandardScaler()
+    return scaler.fit_transform(values)

{nkululeko-0.76.0.dist-info → nkululeko-0.77.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: nkululeko
-Version: 0.76.0
+Version: 0.77.1
 Summary: Machine learning audio prediction experiments based on templates
 Home-page: https://github.com/felixbur/nkululeko
 Author: Felix Burkhardt
@@ -33,6 +33,7 @@ Requires-Dist: scikit-learn
 Requires-Dist: scipy
 Requires-Dist: seaborn
 Requires-Dist: sounddevice
+Requires-Dist: splitutils
 Requires-Dist: tensorflow
 Requires-Dist: tensorflow-hub
 Requires-Dist: torch
@@ -308,6 +309,16 @@ F. Burkhardt, Johannes Wagner, Hagen Wierstorf, Florian Eyben and Björn Schulle
 Changelog
 =========
 
+Version 0.77.1
+--------------
+* added permutation algorithm to compute feature importance
+* shifted util.py to utils
+
+Version 0.77.0
+--------------
+* added more latex report output
+* got splitutils from a package
+
 Version 0.76.0
 --------------
 * added possibility to aggregate feature importance models

nkululeko-0.77.1.dist-info/RECORD

@@ -0,0 +1,104 @@
+nkululeko/__init__.py,sha256=62f8HiEzJ8rG2QlTFJXUCMpvuH3fKI33DoJSj33mscc,63
+nkululeko/augment.py,sha256=IZFawvv5GgSfK0QsrQfVkIfEm0kjoK4DWj8vP9GnU8M,2686
+nkululeko/cacheddataset.py,sha256=lIJ6hUo5LoxSrzXtWV8mzwO7wRtUETWnOQ4ws2XfL1E,969
+nkululeko/constants.py,sha256=rnEDMLKd0n74AGnMGQoidO0S-qk4TOQTN8rGc_3kp8E,39
+nkululeko/demo.py,sha256=FFR8qHMCY8kKKRWDTa8xA7A8mWeYalRKYNtV5rjGg44,1915
+nkululeko/demo_predictor.py,sha256=j4ySWWcIxW7ZAIBH86m9BfRFokzrUNkRD6fpsvAQGTw,2629
+nkululeko/experiment.py,sha256=3kgZ59U5XnTrZWv3o9vdB1bcUScKBiP_oE2FPGXmjc0,28720
+nkululeko/explore.py,sha256=pfciOL66e0T4Bk0RTkwDyE6pK_baSUdjMo2Ybpst3L4,2202
+nkululeko/export.py,sha256=mHeEAAmtZuxdyebLlbSzPrHSi9OMgJHbk35d3DTxRBc,4632
+nkululeko/feature_extractor.py,sha256=tKv1b1-o7xNMgBavTR8VY8_H5HKoJEnnosS-KcjmOEU,7281
+nkululeko/file_checker.py,sha256=LoLnL8aHpW-axMQ46qbqrManTs5otG9ShpEZuz9iRSk,3474
+nkululeko/filter_data.py,sha256=w-X2mhKdYr5DxDIz50E5yzO6Jmzk4jjDBoXsgOOVtcA,7222
+nkululeko/glob_conf.py,sha256=6MZe83QCgHD_zB79Sl9m6UJQASwfqJlyb-1nqrQ_6Iw,381
+nkululeko/modelrunner.py,sha256=KZPoalwtl9k2SCVPhpaAjUGtPafzjUxhtYSGc75OUwk,9037
+nkululeko/nkululeko.py,sha256=MyjjbCg8qgLHHpvwJOEHBGNCDKf0GTv7gnXX27L56R4,1724
+nkululeko/plots.py,sha256=l-bxUoChkCIMsLPK4hMZyIWfuPNN_n-3g8Usc4sJ85A,21262
+nkululeko/predict.py,sha256=dRXX-sQVESa7cNi_56S6UkUOa_pV1g_K4xYtYVM1SJs,1876
+nkululeko/reporter.py,sha256=wrtWbU_UKDwhKQNMi7Q_Ix5N_UTzTagRwZikgUGk1c8,11606
+nkululeko/resample.py,sha256=C2S3aOTwlx5iYah_hs0JARHBC8Cq4Z5cH_mnDMb5RKk,2185
+nkululeko/result.py,sha256=HeiOrrqf9W2yxMryN33zgEmQejNWRxNmm589AYt6-eM,499
+nkululeko/runmanager.py,sha256=HjAesq19ZbDg5imMOjhqnt063W7JGggm6bY06h6bfM8,7085
+nkululeko/scaler.py,sha256=HVXMjmzDAj87K9O4aPU6aeqBk-ACVzQBTHOf1RwDCaM,3055
+nkululeko/segment.py,sha256=DfJYZsCEH41gwKyjpMgv8kWUzfVkmC0wWTbgHOL4i4g,4787
+nkululeko/syllable_nuclei.py,sha256=Sky-C__MeUDaxqHnDl2TGLLYOYvsahD35TUjWGeG31k,10047
+nkululeko/test.py,sha256=cRtOn_d3Fh2kZmnT4nnQeGzZTRtpr5jRhowykOwunME,1421
+nkululeko/test_predictor.py,sha256=8eyHJ_YNIwR2OfICkqo7zF2f7UP8nL0nzCwC-8XnkZY,2409
+nkululeko/augmenting/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+nkululeko/augmenting/augmenter.py,sha256=hk5jkFGdmCg2IgE4UQPsv0kFdgefO5pSrq9QjCjA5Io,2306
+nkululeko/augmenting/randomsplicer.py,sha256=OIBmfzyx1vhKl1cUQGlQw-CWZwsCV8XG9miITb41CT0,2395
+nkululeko/augmenting/randomsplicing.py,sha256=ldym9vZNsZIU5BAAaJVaOmAgmVHNs4a5i5K3bW-WAQU,1791
+nkululeko/augmenting/resampler.py,sha256=cRrn27w_f2I6aN0CftlTuHT2edi7pTREh3Yc6BxhcGU,3335
+nkululeko/autopredict/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+nkululeko/autopredict/ap_age.py,sha256=2Wn5E-Jd49sTn40WqaMcYtUEl4zEq3OY75XmjOpdxsA,1095
+nkululeko/autopredict/ap_arousal.py,sha256=ymt0diu4v1osw3VxJbSglsVKDAJYRzebQ2TTfFMKKxk,1024
+nkululeko/autopredict/ap_dominance.py,sha256=CIMjbHpYfJBV_F2y0Hen5U7WastuArDOkBmXY437efs,1039
+nkululeko/autopredict/ap_gender.py,sha256=gVCMYHpcVp56xWIeI4HA0MJLLINRgvzrKC_wladnbiE,1008
+nkululeko/autopredict/ap_mos.py,sha256=tmFBIKO0lW19fciH9syLnOLI699I_WU0yn1axdo6iEw,1104
+nkululeko/autopredict/ap_pesq.py,sha256=3Zvl47jyCLv7NXwbaDlOhltVcpskcHoU8CcjCJWGkMc,1137
+nkululeko/autopredict/ap_sdr.py,sha256=qpgvJGl0NYMa8o7zHS4qU4dfY1Ey_R1p-0T8BnX3uNs,1185
+nkululeko/autopredict/ap_snr.py,sha256=xHb7mmGfa4wF1r0GK7dIZ1d9m4cEz0LcpK0n3sLF9pQ,1107
+nkululeko/autopredict/ap_stoi.py,sha256=It0Lk-ki-gohA2AzD8nkLAN2WahYvD9rPDGTQuvdLRA,1184
+nkululeko/autopredict/ap_valence.py,sha256=n-hctRKySzhmJtowuMOTUu0T_ld3uK5pnfOzWeWW4VM,1024
+nkululeko/autopredict/estimate_snr.py,sha256=kJbvkt2alMN5ouS03USheU7hJ2l7U9JF0s9AtNT1Vx0,4818
+nkululeko/data/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+nkululeko/data/dataset.py,sha256=-HLten8BFwb2T03CqSNaU4h98UbrXIkqlX7J8H95b6Y,27035
+nkululeko/data/dataset_csv.py,sha256=9ysujWHQnOHLWtJxGtvdpHE3c_sM_l9svFYWYCpamVs,3094
+nkululeko/feat_extract/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+nkululeko/feat_extract/feats_agender.py,sha256=sDfsvSC2zt1JLn5rmB7bdck1JmXIIol3oIwN90TossM,2867
+nkululeko/feat_extract/feats_agender_agender.py,sha256=UYATYWE-zCt9F1qA4xQbYZ2qM7DT2nwGxk7vSiyhit4,2953
+nkululeko/feat_extract/feats_analyser.py,sha256=d3CKceTwT-wVtk1Zyeow3nFyTevBwfaWsmzEh-fXGZ4,10007
+nkululeko/feat_extract/feats_audmodel.py,sha256=sZD8NBC3qId4ygzBvW5RvKVgCC1zxvO_cyFazYOEwCk,2901
+nkululeko/feat_extract/feats_audmodel_dim.py,sha256=z48s-FXokREnir_dNMl8fNI5PLCXzOhvmjgfCjTDjh8,2817
+nkululeko/feat_extract/feats_clap.py,sha256=v82mbjdjGDSKUUBggttw7jW0oka22fWAmfUf-4VmaDU,3379
+nkululeko/feat_extract/feats_hubert.py,sha256=uL-9mgQHuGPQi1nuUaw6aNU9DscsO89uJAmBdmnCegM,5205
+nkululeko/feat_extract/feats_import.py,sha256=SqTuNdbInOO_oXucSlwCTfNz6OUCNyJfUrGX_cS9Mn0,2054
+nkululeko/feat_extract/feats_mld.py,sha256=Vvu7GZOkn7Vda8eIOXqHjg78zegkFe3vTUaCXyVM0eA,2021
+nkululeko/feat_extract/feats_mos.py,sha256=XZI7U99QcSuzd1v5pVAo0JwdcrXrRICUNt_K5G6eRPU,4149
+nkululeko/feat_extract/feats_opensmile.py,sha256=yDRGSiUQV3K3oLxVqq8Cxj5bkc-RiLzDYbAGKC9I5vc,4140
+nkululeko/feat_extract/feats_oxbow.py,sha256=7W26NbEJnSckZzedolsIW1PJPSdCHhuh8YM19kOxaMA,4734
+nkululeko/feat_extract/feats_praat.py,sha256=dqPhAUceze_6LN6vivXJFT2PPDXZKjmzYx0XnYKYGE8,3039
+nkululeko/feat_extract/feats_snr.py,sha256=T2ID_AtlSg8QA086ys4gg83Z4MzMTThhGToGEpHU8eo,2771
+nkululeko/feat_extract/feats_spectra.py,sha256=PLKoc_S3v3wibodUCiOnFFdF87U2rk2sfndRo2mmG64,3656
+nkululeko/feat_extract/feats_spkrec.py,sha256=VK4ma3uWzM0YZStsgRTirfkbzjWIfRWSgsYI038QlRY,4803
+nkululeko/feat_extract/feats_squim.py,sha256=cbaXMX4DtjxQ6sRDYy_OWPku6I2wStwGeSZTYQ8Yr9M,4309
+nkululeko/feat_extract/feats_trill.py,sha256=X9a6Z5rmZtvHDjmQXqQ2nzWjm3O9Dna1t9OZuf8RiKQ,2888
+nkululeko/feat_extract/feats_wav2vec2.py,sha256=r-HQ-oV6x9Ioe00gNMCTEI5iZuMyHvSUyKFDK_iXrdA,4728
+nkululeko/feat_extract/feats_wavlm.py,sha256=QoLQNYLFJ8BgEyx0lVgb48HHH9LYUOX7pJtKbgNLk1I,4509
+nkululeko/feat_extract/featureset.py,sha256=-ynkdor8iX7BFx10aIbB3LfwxrrzPoBGz9kXwyAJO9M,1375
+nkululeko/feat_extract/feinberg_praat.py,sha256=-pgY8Koq7dFaz-99cjkNqsQn1bsKgPInEuwrfmR0ebA,21253
+nkululeko/losses/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+nkululeko/losses/loss_ccc.py,sha256=NOK0y0fxKUnU161B5geap6Fmn8QzoPl2MqtPiV8IuJE,976
+nkululeko/losses/loss_softf1loss.py,sha256=5gW-PuiqeAZcRgfwjueIOQtMokOjZWgQnVIv59HKTCo,1309
+nkululeko/models/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+nkululeko/models/model.py,sha256=7hrPyqWdgQ5TbQKZTcr-XwK83070IZdWy5Ek7FeeVpQ,11311
+nkululeko/models/model_bayes.py,sha256=N-pWe888RyweS-p7AjfqJjjHgqn9LKr_XgpfhS4mk20,441
+nkululeko/models/model_cnn.py,sha256=ObNSQpADBx3X5m31KPUw0U8q7ztAcc56uBVE2-QSjYo,9249
+nkululeko/models/model_gmm.py,sha256=onovzGBeguwZ-upXtuDLaBw9sd6fDDQslVBOrz1Z8TE,645
+nkululeko/models/model_knn.py,sha256=5tGqiPo2JTw9VLmD-MXNZKFJ5RTLA6uv_blJDJ9lScA,573
+nkululeko/models/model_knn_reg.py,sha256=Fbuk6Ku6eyrbbMEk7rB5dwfhvQOMsdZk6HI_0T0gYPw,580
+nkululeko/models/model_mlp.py,sha256=0Fm1wZd69HoNTrsi3MpS5cOm2Cd7wJALSxoUcr3ELak,8494
+nkululeko/models/model_mlp_regression.py,sha256=nFJwch23tUTCxAlgi3YkT-6KSPPLAE7wFK2zF2gg3F4,9457
+nkululeko/models/model_svm.py,sha256=J1d8mf5T4QHtilkUTBkhegVB_0D2kRY0BiBGz-LUJmw,554
+nkululeko/models/model_svr.py,sha256=au5AtzjEpaY9_7Fz6CQoIZ3s6OAvLUxjAXuqHF9dRbk,514
+nkululeko/models/model_tree.py,sha256=soXjV523eRvRZ-jbX7X_3S73Wto1B9bm7ZzzDmgYzTc,390
+nkululeko/models/model_tree_reg.py,sha256=QxkQEz3LOuCLkXw5xH9IwFg4IcTL3Y5RK03qKe4TtGQ,397
+nkululeko/models/model_xgb.py,sha256=tzcksyGP9-XQGOBqt5gYSrQZsbtbcm5qwSkjnxsIX3I,221
+nkululeko/models/model_xgr.py,sha256=yY6wZV8jdiQCIYQCjYSb8gE0jjeiY44eh3rERe2HDvg,227
+nkululeko/reporting/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+nkululeko/reporting/defines.py,sha256=IsY1YgKRMaABpylVKjBJgJ5bNCEbGCVA_E6pivraqSU,648
+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/segmenting/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+nkululeko/segmenting/seg_inaspeechsegmenter.py,sha256=pmLHuXsaqvcdYxB4PSW9l1mbQWZZBJFhi_CGabqydas,1947
+nkululeko/segmenting/seg_silero.py,sha256=lLytS38KzARS17omwv8VBw-zz60RVSXGSvZ5EvWlcWQ,3301
+nkululeko/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+nkululeko/utils/files.py,sha256=UiGAtZRWYjHSvlmPaTMtzyNNGE6qaLaxQkybctS7iRM,4021
+nkululeko/utils/stats.py,sha256=29otJpUp1VqbtDKmlLkPPzBmVfTFiHZ70rUdR4860rM,2788
+nkululeko/utils/util.py,sha256=CY7vfFFa2XnWexq0HoIUIMxxwJ_JkATa2eQplyfqOX4,11293
+nkululeko-0.77.1.dist-info/LICENSE,sha256=0zGP5B_W35yAcGfHPS18Q2B8UhvLRY3dQq1MhpsJU_U,1076
+nkululeko-0.77.1.dist-info/METADATA,sha256=sTdBab1r2GxsamQQWDxym-LjXyYpH4Wl_qpmmU-o_jw,30112
+nkululeko-0.77.1.dist-info/WHEEL,sha256=oiQVh_5PnQM0E3gPdiz09WCNmwiHDMaGer_elqB3coM,92
+nkululeko-0.77.1.dist-info/top_level.txt,sha256=DPFNNSHPjUeVKj44dVANAjuVGRCC3MusJ08lc2a8xFA,10
+nkululeko-0.77.1.dist-info/RECORD,,

nkululeko/balancer.py

@@ -1 +0,0 @@
-# balancer

nkululeko/split/__init__.py

@@ -1,3 +0,0 @@
-from nkululeko.constants import VERSION
-
-__version__ = VERSION

nkululeko/split/example_binning.py

@@ -1,27 +0,0 @@
-"""
-Code copyright by Uwe Reichel
-"""
-
-import numpy as np
-from split_utils import binning, optimize_traindevtest_split
-
-np.random.seed(42)
-y = np.random.rand(10)
-
-# intrinsic binning by equidistant percentiles
-yci = binning(y, nbins=3)
-
-# extrinsic binning by explicit lower boundaries
-yce = binning(y, lower_boundaries=[0, 0.3, 0.8])
-
-print("yci:", yci)
-print("yce:", yce)
-
-"""
- yci: [0 2 2 1 0 0 0 2 1 2]
- yce: [1 2 1 1 0 0 0 2 1 1]
-
- now yci or yce can be used for stratification, e.g.
-stratify_on = {"target": yci, ...}
-... = optimize_traindevtest_split(..., y=y, stratify_on=stratify_on, ...)
-"""