nkululeko 0.93.4__tar.gz → 0.93.6__tar.gz

{nkululeko-0.93.4 → nkululeko-0.93.6}/CHANGELOG.md

@@ -1,6 +1,14 @@
 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/nkululeko.egg-info → nkululeko-0.93.6}/PKG-INFO

@@ -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
@@ -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 → nkululeko-0.93.6}/README.md

@@ -29,7 +29,7 @@ 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)

{nkululeko-0.93.4 → nkululeko-0.93.6}/nkululeko/constants.py

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

{nkululeko-0.93.4 → nkululeko-0.93.6}/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-0.93.4 → nkululeko-0.93.6}/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 → nkululeko-0.93.6/nkululeko.egg-info}/PKG-INFO

@@ -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
@@ -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