nkululeko 0.93.4__py3-none-any.whl → 0.93.6__py3-none-any.whl

nkululeko/constants.py

@@ -1,2 +1,2 @@
-VERSION="0.93.4"
+VERSION="0.93.6"
 SAMPLING_RATE = 16000

nkululeko/data/dataset.py

@@ -4,12 +4,13 @@ import os
 import os.path
 from random import sample
 
-import audformat
 import numpy as np
 import pandas as pd
 
-import nkululeko.glob_conf as glob_conf
+import audformat
+
 from nkululeko.filter_data import DataFilter
+import nkululeko.glob_conf as glob_conf
 from nkululeko.plots import Plots
 from nkululeko.reporting.report_item import ReportItem
 from nkululeko.utils.util import Util
@@ -32,6 +33,9 @@ class 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.target_tables_append = eval(
+            self.util.config_val_data(self.name, "target_tables_append", "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,
@@ -158,14 +162,20 @@ class Dataset:
                     except KeyError:
                         # just a try...
                         pass
-                if got_target2:
-                    df[self.target] = df_target[self.target]
-                if got_speaker2:
-                    df["speaker"] = df_target["speaker"]
-                if got_gender2:
-                    df["gender"] = df_target["gender"]
-                if got_age2:
-                    df["age"] = df_target["age"].astype(int)
+                try:
+                    if got_target2:
+                        df[self.target] = df_target[self.target]
+                    if got_speaker2:
+                        df["speaker"] = df_target["speaker"]
+                    if got_gender2:
+                        df["gender"] = df_target["gender"]
+                    if got_age2:
+                        df["age"] = df_target["age"].astype(int)
+                except ValueError as ve:
+                    self.util.error(
+                        f"{ve}\nYou might need to set "
+                        + "data.target_tables_append = True"
+                    )
                 # copy other column
                 for column in df_target.columns:
                     if column not in [self.target, "age", "speaker", "gender"]:
@@ -321,7 +331,12 @@ class Dataset:
             for column in source_df.columns:
                 if column not in [self.target, "age", "speaker", "gender"]:
                     df_local[column] = source_df[column]
-            df = pd.concat([df, df_local])
+            # ensure segmented index
+            df_local = self.util.make_segmented_index(df_local)
+            if self.target_tables_append:
+                df = pd.concat([df, df_local], axis=0)
+            else:
+                df = pd.concat([df, df_local], axis=1)
         return df, is_labeled, got_speaker, got_gender, got_age
 
     def split(self):

nkululeko/resample.py

@@ -1,5 +1,4 @@
-"""
-Resample audio files or INI files (train, test, all) to change the sampling rate.
+"""Resample audio files or INI files (train, test, all) to change the sampling rate.
 
 This script provides a command-line interface to resample audio files or INI files
 containing train, test, and all data. It supports resampling a single file, a
@@ -27,9 +26,10 @@ import argparse
 import configparser
 import os
 
-import audformat
 import pandas as pd
 
+import audformat
+
 from nkululeko.augmenting.resampler import Resampler
 from nkululeko.constants import VERSION
 from nkululeko.experiment import Experiment

{nkululeko-0.93.4.dist-info → nkululeko-0.93.6.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: nkululeko
-Version: 0.93.4
+Version: 0.93.6
 Summary: Machine learning audio prediction experiments based on templates
 Home-page: https://github.com/felixbur/nkululeko
 Author: Felix Burkhardt
@@ -20,7 +20,7 @@ Requires-Dist: audiofile
 Requires-Dist: audiomentations
 Requires-Dist: audmetric
 Requires-Dist: audonnx
-Requires-Dist: confidence-intervals
+Requires-Dist: confidence_intervals
 Requires-Dist: datasets
 Requires-Dist: imageio
 Requires-Dist: matplotlib
@@ -28,12 +28,12 @@ Requires-Dist: numpy
 Requires-Dist: opensmile
 Requires-Dist: pandas
 Requires-Dist: praat-parselmouth
-Requires-Dist: scikit-learn
+Requires-Dist: scikit_learn
 Requires-Dist: scipy
 Requires-Dist: seaborn
 Requires-Dist: sounddevice
 Requires-Dist: tensorflow
-Requires-Dist: tensorflow-hub
+Requires-Dist: tensorflow_hub
 Requires-Dist: torch
 Requires-Dist: torchvision
 Requires-Dist: transformers
@@ -72,7 +72,7 @@ The idea is to have a framework (based on e.g. sklearn and torch) that can be us
 * The latest features can be seen in [the ini-file](./ini_file.md) options that are used to control Nkululeko
 * Below is a [Hello World example](#helloworld) that should set you up fastly, also on [Google Colab](https://colab.research.google.com/drive/1GYNBd5cdZQ1QC3Jm58qoeMaJg3UuPhjw?usp=sharing#scrollTo=4G_SjuF9xeQf), and [with Kaggle](https://www.kaggle.com/felixburk/nkululeko-hello-world-example)
 * [Here's a blog post on how to set up nkululeko on your computer.](http://blog.syntheticspeech.de/2021/08/30/how-to-set-up-your-first-nkululeko-project/)
-* [Here is a slack channel to discuss issues related to nkululeko](https://join.slack.com/t/nkululekoworkspace/shared_invite/zt-1wtvbxtwz-P5YoRJq8whxKSee86ebhJg). Please click the link if interested in contributing.
+* [Here is a slack channel to discuss issues related to nkululeko](https://join.slack.com/t/nkululekoworkspace/shared_invite/zt-2v3q3yfzk-XfNGoqLfp3ts9KfCZpfTyg). Please click the link if interested in contributing.
 * [Here's a slide presentation about nkululeko](docs/nkululeko.pdf)
 * [Here's a video presentation about nkululeko](https://www.youtube.com/playlist?list=PLRceVavtxLg0y2jiLmpnUfiMtfvkK912D)
 * [Here's the 2022 LREC article on nkululeko](http://felix.syntheticspeech.de/publications/Nkululeko_LREC.pdf)
@@ -355,6 +355,14 @@ If you use it, please mention the Nkululeko paper:
 Changelog
 =========
 
+Version 0.93.6
+--------------
+* added error message and hint for data.target_tables_append
+
+Version 0.93.5
+--------------
+* fixed bug in dataset loading
+
 Version 0.93.4
 --------------
 * ccc in plots now configurable

{nkululeko-0.93.4.dist-info → nkululeko-0.93.6.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=IgnX0Wy81d5r7fZn_FKbdv78UmFITOMd-J_szX4AMKc,39
+nkululeko/constants.py,sha256=CBvqIM1vafeKeZJAFI4K96rOgsKVLyvRhUJoNEsmOIo,39
 nkululeko/demo-ft.py,sha256=iD9Pzp9QjyAv31q1cDZ75vPez7Ve8A4Cfukv5yfZdrQ,770
 nkululeko/demo.py,sha256=4Yzhg6pCPBYPGJrP7JX2TysVosl_R1llpVDKc2P_gUA,4955
 nkululeko/demo_feats.py,sha256=BvZjeNFTlERIRlq34OHM4Z96jdDQAhB01BGQAUcX9dM,2026
@@ -22,7 +22,7 @@ nkululeko/nkuluflag.py,sha256=PGWSmZz-PiiHLgcZJAoGOI_Y-sZDVI1ksB8p5r7riWM,3725
 nkululeko/nkululeko.py,sha256=M7baIq2nAoi6dEoBL4ATEuqAs5U1fvl_hyqAl5DybAQ,2040
 nkululeko/plots.py,sha256=emn2NpZyOGlC8pw0NdAGRbUkPzZzbOKFO50HZ7vJG40,25275
 nkululeko/predict.py,sha256=MLnHEyFmSiHLLs-HDczag8Vu3zKF5T1rXLKdZZJ6py8,2083
-nkululeko/resample.py,sha256=akSAjJ3qn-O5NAyLJHVHdsK7MUZPGaZUvM2TwMSmj2M,5194
+nkululeko/resample.py,sha256=rn3-M1A-iwVGibfQNGyeYNa7briD24lIN9Szq_1uTJo,5194
 nkululeko/runmanager.py,sha256=AswmORVUkCIH0gTx6zEyufvFATQBS8C5TXo2erSNdVg,7611
 nkululeko/scaler.py,sha256=7VOZ4sREMoQtahfETt9RyuR29Fb7PCwxlYVjBbdCVFc,4101
 nkululeko/segment.py,sha256=DRjC6b7SeInYgwBcDPXpTXPvXPS-J8kFQO7H095bK80,4945
@@ -49,7 +49,7 @@ 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=Hz2IOsdcESG-P3aP7r4d1xj_gIP6fyGCYOwukoQ7SM8,29321
+nkululeko/data/dataset.py,sha256=Sqk5XVArXVjwN-6B9uT0T9OkUPyoQwklJPqgDPPQgNE,29954
 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
@@ -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-0.93.4.dist-info/LICENSE,sha256=0zGP5B_W35yAcGfHPS18Q2B8UhvLRY3dQq1MhpsJU_U,1076
-nkululeko-0.93.4.dist-info/METADATA,sha256=0xLv3PmFcHyVfO0DqDtELse_fMHnx1vZUqrR1lWVZgM,42210
-nkululeko-0.93.4.dist-info/WHEEL,sha256=R06PA3UVYHThwHvxuRWMqaGcr-PuniXahwjmQRFMEkY,91
-nkululeko-0.93.4.dist-info/entry_points.txt,sha256=lNTkFEdh6Kjo5o95ZAWf_0Lq-4ztGoAoMVSDuPtuyS0,442
-nkululeko-0.93.4.dist-info/top_level.txt,sha256=DPFNNSHPjUeVKj44dVANAjuVGRCC3MusJ08lc2a8xFA,10
-nkululeko-0.93.4.dist-info/RECORD,,
+nkululeko-0.93.6.dist-info/LICENSE,sha256=0zGP5B_W35yAcGfHPS18Q2B8UhvLRY3dQq1MhpsJU_U,1076
+nkululeko-0.93.6.dist-info/METADATA,sha256=Dx6ZisILoZzC7-BXKBskHm-mBPzjY8CEaiRVOo2vlc0,42364
+nkululeko-0.93.6.dist-info/WHEEL,sha256=PZUExdf71Ui_so67QXpySuHtCi3-J3wvF4ORK6k_S8U,91
+nkululeko-0.93.6.dist-info/entry_points.txt,sha256=lNTkFEdh6Kjo5o95ZAWf_0Lq-4ztGoAoMVSDuPtuyS0,442
+nkululeko-0.93.6.dist-info/top_level.txt,sha256=DPFNNSHPjUeVKj44dVANAjuVGRCC3MusJ08lc2a8xFA,10
+nkululeko-0.93.6.dist-info/RECORD,,

{nkululeko-0.93.4.dist-info → nkululeko-0.93.6.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (75.5.0)
+Generator: setuptools (75.6.0)
 Root-Is-Purelib: true
 Tag: py3-none-any