nkululeko 0.89.2__tar.gz → 0.90.0__tar.gz

{nkululeko-0.89.2 → nkululeko-0.90.0}/CHANGELOG.md

@@ -1,6 +1,12 @@
 Changelog
 =========
 
+Version 0.90.0
+--------------
+* augmentation can now be done without target
+* random splicing params configurable
+* made kde default for plot continous/categorical plots
+
 Version 0.89.2
 --------------
 * fix shap value calculation

{nkululeko-0.89.2/nkululeko.egg-info → nkululeko-0.90.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: nkululeko
-Version: 0.89.2
+Version: 0.90.0
 Summary: Machine learning audio prediction experiments based on templates
 Home-page: https://github.com/felixbur/nkululeko
 Author: Felix Burkhardt
@@ -356,6 +356,12 @@ F. Burkhardt, Johannes Wagner, Hagen Wierstorf, Florian Eyben and Björn Schulle
 Changelog
 =========
 
+Version 0.90.0
+--------------
+* augmentation can now be done without target
+* random splicing params configurable
+* made kde default for plot continous/categorical plots
+
 Version 0.89.2
 --------------
 * fix shap value calculation

{nkululeko-0.89.2 → nkululeko-0.90.0}/nkululeko/augment.py

@@ -37,8 +37,8 @@ def doit(config_file):
 
     filename = util.config_val("AUGMENT", "result", "augmented.csv")
     filename = f"{expr.data_dir}/{filename}"
-
-    if os.path.exists(filename):
+    no_reuse = eval(util.config_val("DATA", "no_reuse", "False"))
+    if os.path.exists(filename) and not no_reuse:
         util.debug("files already augmented")
     else:
         # load the data

{nkululeko-0.89.2 → nkululeko-0.90.0}/nkululeko/augmenting/randomsplicer.py

@@ -41,14 +41,17 @@ class Randomsplicer:
             * top_db: top db level for silence to be recognized (default: 12)
         """
 
-        p_reverse = 0.3
-        top_db = 12
+        p_reverse = float(self.util.config_val("AUGMENT", "p_reverse", "0.3"))
+        top_db = float(self.util.config_val("AUGMENT", "top_db", "12"))
 
         files = self.df.index.get_level_values(0).values
         store = self.util.get_path("store")
         filepath = f"{store}randomspliced/"
         audeer.mkdir(filepath)
-        self.util.debug(f"random splicing {sample_selection} samples to {filepath}")
+        self.util.debug(
+            f"random splicing {sample_selection} samples to {filepath}, "
+            + f"p_reverse = {p_reverse}, top_db = {top_db}",
+        )
         newpath = ""
         index_map = {}
         for i, f in enumerate(tqdm(files)):

{nkululeko-0.89.2 → nkululeko-0.90.0}/nkululeko/constants.py

@@ -1,2 +1,2 @@
-VERSION="0.89.2"
+VERSION="0.90.0"
 SAMPLING_RATE = 16000

{nkululeko-0.89.2 → nkululeko-0.90.0}/nkululeko/data/dataset.py

@@ -30,8 +30,8 @@ class Dataset:
     def __init__(self, name):
         """Constructor setting up name and configuration"""
         self.name = name
-        self.target = glob_conf.config["DATA"]["target"]
         self.util = Util("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.start_fresh = eval(self.util.config_val("DATA", "no_reuse", "False"))
@@ -127,6 +127,9 @@ class Dataset:
             self.got_gender,
             self.got_age,
         ) = self._get_df_for_lists(self.db, df_files_tables)
+        if df.shape[0] > 0 and self.target == "none":
+            self.df = df
+            return
         if False in {
             self.is_labeled,
             self.got_speaker,
@@ -553,7 +556,10 @@ class Dataset:
             " samples in train/test"
         )
         # because this generates new train/test sample quantaties, the feature extraction has to be done again
-        glob_conf.config["FEATS"]["needs_feature_extraction"] = "True"
+        try:
+            glob_conf.config["FEATS"]["needs_feature_extraction"] = "True"
+        except KeyError:
+            pass
 
     def random_split(self):
         """One way to split train and eval sets: Specify percentage of random samples"""

{nkululeko-0.89.2 → nkululeko-0.90.0}/nkululeko/experiment.py

@@ -101,12 +101,15 @@ class Experiment:
             if data.got_speaker:
                 self.got_speaker = True
             self.datasets.update({d: data})
-        self.target = self.util.config_val("DATA", "target", "emotion")
+        self.target = self.util.config_val("DATA", "target", "none")
         glob_conf.set_target(self.target)
         # print target via debug
         self.util.debug(f"target: {self.target}")
         # print keys/column
         dbs = ",".join(list(self.datasets.keys()))
+        if self.target == "none":
+            self.util.debug(f"loaded databases {dbs}")
+            return
         labels = self.util.config_val("DATA", "labels", False)
         auto_labels = list(next(iter(self.datasets.values())).df[self.target].unique())
         if labels:
@@ -191,7 +194,8 @@ class Experiment:
             self.df_train, self.df_test = pd.DataFrame(), pd.DataFrame()
             for d in self.datasets.values():
                 d.split()
-                d.prepare_labels()
+                if self.target != "none":
+                    d.prepare_labels()
                 if d.df_train.shape[0] == 0:
                     self.util.debug(f"warn: {d.name} train empty")
                 self.df_train = pd.concat([self.df_train, d.df_train])
@@ -207,6 +211,8 @@ class Experiment:
             self.df_test.to_csv(storage_test)
             self.df_train.to_csv(storage_train)
 
+        if self.target == "none":
+            return
         self.util.copy_flags(self, self.df_test)
         self.util.copy_flags(self, self.df_train)
         # Try data checks

{nkululeko-0.89.2 → nkululeko-0.90.0}/nkululeko/plots.py

@@ -263,7 +263,7 @@ class Plots:
 
     def plotcatcont(self, df, cat_col, cont_col, xlab, ylab):
         """Plot relation of categorical distribution with continuous."""
-        dist_type = self.util.config_val("EXPL", "dist_type", "hist")
+        dist_type = self.util.config_val("EXPL", "dist_type", "kde")
         cats, cat_str, es = su.get_effect_size(df, cat_col, cont_col)
         model_type = self.util.get_model_type()
         if dist_type == "hist" and model_type != "tree":

{nkululeko-0.89.2 → nkululeko-0.90.0/nkululeko.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: nkululeko
-Version: 0.89.2
+Version: 0.90.0
 Summary: Machine learning audio prediction experiments based on templates
 Home-page: https://github.com/felixbur/nkululeko
 Author: Felix Burkhardt
@@ -356,6 +356,12 @@ F. Burkhardt, Johannes Wagner, Hagen Wierstorf, Florian Eyben and Björn Schulle
 Changelog
 =========
 
+Version 0.90.0
+--------------
+* augmentation can now be done without target
+* random splicing params configurable
+* made kde default for plot continous/categorical plots
+
 Version 0.89.2
 --------------
 * fix shap value calculation