nkululeko 0.95.6__tar.gz → 0.95.8__tar.gz

{nkululeko-0.95.6 → nkululeko-0.95.8}/CHANGELOG.md

@@ -1,6 +1,16 @@
 Changelog
 =========
 
+Version 0.95.8 (25-07-14)
+--------------------------
+* fix bug that bool was not detected as categorical
+
+
+Version 0.95.7 (25-07-11)
+--------------------------
+* infer gender and age from audb misc table
+* fix result plots in run folder
+
 Version 0.95.6 (25-07-10)
 --------------------------
 * added uncertainty_threshold plot

{nkululeko-0.95.6/nkululeko.egg-info → nkululeko-0.95.8}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: nkululeko
-Version: 0.95.6
+Version: 0.95.8
 Summary: Machine learning audio prediction experiments based on templates
 Home-page: https://github.com/felixbur/nkululeko
 Author: Felix Burkhardt

{nkululeko-0.95.6 → nkululeko-0.95.8}/nkululeko/constants.py

@@ -1,2 +1,2 @@
-VERSION="0.95.6"
+VERSION="0.95.8"
 SAMPLING_RATE = 16000

{nkululeko-0.95.6 → nkululeko-0.95.8}/nkululeko/data/dataset.py

@@ -294,12 +294,21 @@ class Dataset:
                 # try to get the gender values
                 if "gender" in source_df:
                     df_local["gender"] = source_df["gender"]
-                    got_gender = True
+                else:
+                    # try to get the gender via the speaker description
+                    gender_map = db['speaker'].get().to_dict()['gender']
+                    df_local['gender'] = df_local['speaker'].map(gender_map).astype(str)
+                got_gender = True
             except (KeyError, ValueError, audformat.errors.BadKeyError):
                 pass
             try:
                 # try to get the age values
-                df_local["age"] = source_df["age"].astype(int)
+                if "age" in source_df:
+                    df_local["age"] = source_df["age"].astype(int)
+                else:
+                    # try to get the age via the speaker description
+                    age_map = db['speaker'].get().to_dict()['age']
+                    df_local['age'] = df_local['speaker'].map(age_map).astype(int)
                 got_age = True
             except (KeyError, ValueError, audformat.errors.BadKeyError):
                 pass

{nkululeko-0.95.6 → nkululeko-0.95.8}/nkululeko/explore.py

@@ -65,6 +65,7 @@ def main():
     try:
         # load the experiment
         expr.load(f"{util.get_save_name()}")
+        expr.util.set_config(config)
         needs_feats = True
         experiment_loaded = True
     except FileNotFoundError:

{nkululeko-0.95.6 → nkululeko-0.95.8}/nkululeko/plots.py

@@ -9,6 +9,7 @@ from scipy import stats
 import seaborn as sns
 from sklearn.manifold import TSNE
 
+import audeer
 from audmetric import concordance_cc as ccc
 
 import nkululeko.glob_conf as glob_conf
@@ -27,7 +28,10 @@ class Plots:
         self.with_ccc = eval(self.util.config_val("PLOT", "ccc", "False"))
         self.type_s = "samples"
 
-    def plot_distributions_speaker(self, df):
+    def plot_distributions_speaker(self, df: pd.DataFrame):
+        if df.empty:
+            self.util.warn("plot_distributions_speaker: empty DataFrame, nothing to plot")
+            return
         self.type_s = "speaker"
         df_speakers = pd.DataFrame()
         pd.options.mode.chained_assignment = None  # default='warn'
@@ -86,7 +90,10 @@ class Plots:
 
         self.plot_distributions(df_speakers, type_s="speakers")
 
-    def plot_distributions(self, df, type_s="samples"):
+    def plot_distributions(self, df: pd.DataFrame, type_s: str = "samples"):
+        if df.empty:
+            self.util.warn("plot_distributions: empty DataFrame, nothing to plot")
+            return
         class_label, df = self._check_binning("class_label", df)
         value_counts_conf = self.util.config_val("EXPL", "value_counts", False)
         if not isinstance(value_counts_conf, str):
@@ -218,7 +225,7 @@ class Plots:
 
     def save_plot(self, ax, caption, header, filename, type_s):
         # one up because of the runs
-        fig_dir = os.path.dirname(self.util.get_path("fig_dir"))
+        fig_dir = audeer.path(self.util.get_path("fig_dir"), "..")
         fig_plots = ax.figure
         # avoid warning
         # plt.tight_layout()

{nkululeko-0.95.6 → nkululeko-0.95.8}/nkululeko/utils/util.py

@@ -189,8 +189,11 @@ class Util:
 
     def is_categorical(self, pd_series):
         """Check if a dataframe column is categorical."""
-        return pd_series.dtype.name == "object" or isinstance(
-            pd_series.dtype, pd.CategoricalDtype
+        return (
+            pd_series.dtype.name == "object"
+            or pd_series.dtype.name == "bool"
+            or isinstance(pd_series.dtype, pd.CategoricalDtype)
+            or isinstance(pd_series.dtype, pd.BooleanDtype)
         )
 
     def get_name(self):

{nkululeko-0.95.6 → nkululeko-0.95.8/nkululeko.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: nkululeko
-Version: 0.95.6
+Version: 0.95.8
 Summary: Machine learning audio prediction experiments based on templates
 Home-page: https://github.com/felixbur/nkululeko
 Author: Felix Burkhardt

{nkululeko-0.95.6 → nkululeko-0.95.8}/pyproject.toml

@@ -7,7 +7,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "nkululeko"
-version = "0.95.6"
+version = "0.95.8"
 description = "Machine learning audio prediction experiments based on templates"
 authors = [
     {name = "Felix Burkhardt", email = "fxburk@gmail.com"},