Merge branch 'master' of github.com:bagustris/nkululeko

.github/workflows/basic_tests_for_aud_csv.yaml

@@ -36,8 +36,9 @@ jobs:
     - name: Run csv-ravdess-praat-xgb
       run: |
         cd data/ravdess
-        wget https://zenodo.org/record/1188976/files/Audio_Speech_Actors_01-24.zip
-        unzip Audio_Speech_Actors_01-24.zip
+        # wget https://zenodo.org/record/1188976/files/Audio_Speech_Actors_01-24.zip
+        wget https://zenodo.org/records/11063852/files/Audio_Speech_Actors_01-24_16k.zip
+        unzip Audio_Speech_Actors_01-24_16k.zip
         cd ../..
         python3 -m nkululeko.nkululeko --config data/ravdess/exp_praat_xgb.ini > output1.txt
         if grep -q "DONE" output1.txt; then

CHANGELOG.md

@@ -1,6 +1,43 @@
 Changelog
 =========
 
+Version 0.84.0
+--------------
+* added SHAP analysis
+* started with finetuning
+
+Version 0.83.3
+--------------
+* fixed a naming error in trill features that prevented storage of experiment
+
+Version 0.83.2
+--------------
+* added default cuda if present and not stated
+
+Version 0.83.1
+--------------
+* add test module to nkuluflag
+
+Version 0.83.0
+--------------
+* test module now prints out reports
+
+Version 0.82.4
+--------------
+* fixed bug in wavlm 
+
+Version 0.82.3
+--------------
+* fixed another audformat peculiarity to interprete time values as nanoseconds
+
+Version 0.82.2
+--------------
+* fixed audformat peculiarity that dataframes can have only one column
+
+Version 0.82.1
+--------------
+* Add more test for GC action
+
 Version 0.82.0
 --------------
 * added nkuluflag module

CODE_OF_CONDUCT.md

@@ -0,0 +1,72 @@
+# Code of Conduct
+
+In the interest of fostering an open and welcoming environment, we as
+contributors and maintainers pledge to making participation in our project and
+our community a harassment-free experience for everyone, regardless of age, body
+size, disability, ethnicity, gender identity and expression, level of
+experience, education, socioeconomic status, nationality, personal appearance,
+race, religion, or sexual identity and orientation.
+
+## Our Standards
+
+Examples of behavior that contributes to creating a positive environment
+include:
+
+* using welcoming and inclusive language,
+* being respectful of differing viewpoints and experiences,
+* gracefully accepting constructive criticism,
+* focusing on what is best for the community, and
+* showing empathy towards other community members.
+
+Examples of unacceptable behavior by participants include:
+
+* the use of sexualized language or imagery and unwelcome sexual
+  attention or advances,
+* trolling, insulting/derogatory comments, and personal or political
+  attacks,
+* public or private harassment,
+* publishing others' private information, such as a physical or
+  electronic address, without explicit permission, and
+* other conduct which could reasonably be considered inappropriate in
+  a professional setting
+
+## Our Responsibilities
+
+Project maintainers are responsible for clarifying the standards of acceptable
+behavior and are expected to take appropriate and fair corrective action in
+response to any instances of unacceptable behavior.
+
+Project maintainers have the right and responsibility to remove, edit, or reject
+comments, commits, code, wiki edits, issues, and other contributions that are
+not aligned to this Code of Conduct, or to ban temporarily or permanently any
+contributor for other behaviors that they deem inappropriate, threatening,
+offensive, or harmful.
+
+## Scope
+
+This Code of Conduct applies both within project spaces and in public spaces
+when an individual is representing the project or its community. Examples of
+representing a project or community include using an official project email
+address, posting via an official social media account, or acting as an appointed
+representative at an online or offline event. Representation of a project may be
+further defined and clarified by project maintainers.
+
+## Enforcement
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be
+reported by emailing the project team. All complaints will be reviewed
+and investigated and will result in a response that is deemed necessary and
+appropriate to the circumstances. The project team is obligated to maintain
+confidentiality with regard to the reporter of an incident.  Further details of
+specific enforcement policies may be posted separately.
+
+Project maintainers who do not follow or enforce the Code of Conduct in good
+faith may face temporary or permanent repercussions as determined by other
+members of the project's leadership.
+
+## Attribution
+
+This Code of Conduct is adapted from the [Contributor Covenant][contributor_covenant]
+version 1.4.
+
+[contributor_covenant]: https://www.contributor-covenant.org/

data/crema-d/load_db.py

@@ -8,4 +8,4 @@
 audb.config.CACHE_ROOT = cwd
 
 # load the latest version of the data
-db = audb.load("crema-d", format="wav", sampling_rate=16000, mixdown=True)
+db = audb.load("crema-d", version="1.3.0", verbose=True)

data/ravdess/README.md

@@ -5,10 +5,14 @@ I used the version downloadable from [Zenodo](https://zenodo.org/record/1188976)
 
 Download and unzip the file Audio_Speech_Actors_01-24.zip
 ```bash
+# download original dataset in 48k
 $ wget https://zenodo.org/record/1188976/files/Audio_Speech_Actors_01-24.zip
 $ unzip Audio_Speech_Actors_01-24.zip
 ```
 
+Or, if you prefer the dataset in 16k, you can download from this link:
+https://zenodo.org/records/11063852/files/Audio_Speech_Actors_01-24_16k.zip  
+
 run the file
 ```bash
 python3 process_database.py

data/ravdess/exp_praat_xgb.ini

@@ -10,10 +10,12 @@ dev = ./data/ravdess/ravdess_dev.csv
 dev.type = csv
 dev.absolute_path = False
 dev.split_strategy = train
+dev.audio_path = Audio_Speech_Actors_01-24_16k/
 test = ./data/ravdess/ravdess_test.csv
 test.type = csv
 test.absolute_path = False
 test.split_strategy = test
+test.audio_path = Audio_Speech_Actors_01-24_16k/
 target = emotion
 labels = ['angry', 'happy', 'neutral', 'sad']
 [FEATS]

ini_file.md

@@ -330,7 +330,9 @@
 * **dist_type**: type of plot for value counts, either histogram or density estimation (kde)
   * dist_type = hist
 * **spotlight**: open a web-browser window to inspect the data with the [spotlight software](https://github.com/Renumics/spotlight). Needs package *renumics-spotlight* to be installed!
-  * spotlight = False 
+  * spotlight = False
+* **shap**: comopute [SHAP](https://shap.readthedocs.io/en/latest/) values
+  * shap = False
 ### [PREDICT](#predict) 
 * **targets**: Speaker/speech characteristics to be predicted by some models
   * targets = ['gender', 'age', 'snr', 'arousal', 'valence', 'dominance', 'pesq', 'mos']

meta/demos/multiple_exeriments/do_experiments.py → meta/demos/multiple_experiments/do_experiments.py

@@ -19,13 +19,13 @@
     # {'--feat': 'os',
     # '--set': 'ComParE_2016',
     # },
-    {"--feat": "audmodel"},
+    {"--feat": "praat"},
 ]
 
 
 for c in classifiers:
     for f in features:
-        cmd = "python -m nkululeko.nkuluflag --config exp.ini "
+        cmd = "python -m nkululeko.nkuluflag --config meta/demos/multiple_exeriments/exp.ini "
         for item in c:
             cmd += f"{item} {c[item]} "
         for item in f:

meta/demos/multiple_exeriments/exp.ini → meta/demos/multiple_experiments/exp.ini

@@ -11,6 +11,7 @@ emodb.train_tables = ['emotion.categories.train.gold_standard']
 emodb.test_tables = ['emotion.categories.test.gold_standard']
 target = emotion
 labels = ['anger', 'happiness']
+tests = ['emodb']
 [FEATS]
 [MODEL]
 C_val = .001

meta/demos/multiple_experiments/tmp.ini

@@ -0,0 +1,28 @@
+[EXP]
+root = ./
+name = results
+runs = 1
+epochs = 1
+
+[DATA]
+databases = ['emodb']
+emodb = ../../../data/emodb/emodb
+emodb.split_strategy = specified
+emodb.train_tables = ['emotion.categories.train.gold_standard']
+emodb.test_tables = ['emotion.categories.test.gold_standard']
+target = emotion
+labels = ['anger', 'happiness']
+
+[FEATS]
+type = ['praat']
+
+[MODEL]
+c_val = .001
+learning_rate = 0.0001
+store = True
+patience = 5
+type = svm
+
+[PLOT]
+best_model = True
+

nkululeko/constants.py

@@ -1,2 +1,2 @@
-VERSION="0.82.0"
+VERSION="0.84.0"
 SAMPLING_RATE = 16000

nkululeko/data/dataset_csv.py

@@ -22,7 +22,18 @@ def load(self):
         #     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", "")
-        df = audformat.utils.read_csv(data_file)
+        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:
+            index = audformat.segmented_index(
+                df.file.values, df.start.values, df.end.values
+            )
+            df = df.set_index(index)
+            df = df.drop(columns=["file", "start", "end"])
+        else:
+            df = audformat.utils.read_csv(data_file)
+        if isinstance(df, pd.Series):
+            df = df.to_frame()
         rename_cols = self.util.config_val_data(self.name, "colnames", False)
         if rename_cols:
             col_dict = ast.literal_eval(rename_cols)

nkululeko/demo.py

@@ -2,8 +2,9 @@
 # Demonstration code to use the ML-experiment framework
 # Test the loading of a previously trained model and demo mode
 # needs the project config file to run before
-"""
-This script is used to test the loading of a previously trained model and run it in demo mode.
+"""This script is used to test the loading of a previously trained model.
+
+And run it in demo mode.
 It requires the project config file to be run before.
 
 Usage:  
@@ -20,17 +21,15 @@
 import configparser
 import os
 
-import nkululeko.glob_conf as glob_conf
 from nkululeko.constants import VERSION
 from nkululeko.experiment import Experiment
+import nkululeko.glob_conf as glob_conf
 from nkululeko.utils.util import Util
 
 
 def main(src_dir):
-    parser = argparse.ArgumentParser(
-        description="Call the nkululeko DEMO framework.")
-    parser.add_argument("--config", default="exp.ini",
-                        help="The base configuration")
+    parser = argparse.ArgumentParser(description="Call the nkululeko DEMO framework.")
+    parser.add_argument("--config", default="exp.ini", help="The base configuration")
     parser.add_argument(
         "--file", help="A file that should be processed (16kHz mono wav)"
     )

nkululeko/demo_predictor.py

@@ -1,18 +1,19 @@
 # demo_predictor.py
 import os
 
-import audformat
-import audiofile
 import numpy as np
 import pandas as pd
 
+import audformat
+import audiofile
+
 import nkululeko.glob_conf as glob_conf
 from nkululeko.utils.util import Util
 
 
 class Demo_predictor:
     def __init__(self, model, file, is_list, feature_extractor, label_encoder, outfile):
-        """Constructor setting up name and configuration"""
+        """Constructor setting up name and configuration."""
         self.model = model
         self.feature_extractor = feature_extractor
         self.label_encoder = label_encoder