nkululeko 0.81.0__tar.gz → 0.81.2__tar.gz

{nkululeko-0.81.0 → nkululeko-0.81.2}/CHANGELOG.md

@@ -1,6 +1,16 @@
 Changelog
 =========
 
+Version 0.81.2
+--------------
+* added a parselmouth.Praat error if pitch out of range
+* changed file path for demo_predictor
+
+Version 0.81.1
+--------------
+* fixed bugs in demo module 
+* made kernel for SVM/SVR configurable
+
 Version 0.81.0
 --------------
 * added test selection to test module

{nkululeko-0.81.0/nkululeko.egg-info → nkululeko-0.81.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: nkululeko
-Version: 0.81.0
+Version: 0.81.2
 Summary: Machine learning audio prediction experiments based on templates
 Home-page: https://github.com/felixbur/nkululeko
 Author: Felix Burkhardt
@@ -321,6 +321,16 @@ F. Burkhardt, Johannes Wagner, Hagen Wierstorf, Florian Eyben and Björn Schulle
 Changelog
 =========
 
+Version 0.81.2
+--------------
+* added a parselmouth.Praat error if pitch out of range
+* changed file path for demo_predictor
+
+Version 0.81.1
+--------------
+* fixed bugs in demo module 
+* made kernel for SVM/SVR configurable
+
 Version 0.81.0
 --------------
 * added test selection to test module

{nkululeko-0.81.0 → nkululeko-0.81.2}/nkululeko/constants.py

@@ -1,2 +1,2 @@
-VERSION="0.81.0"
+VERSION="0.81.2"
 SAMPLING_RATE = 16000

{nkululeko-0.81.0 → nkululeko-0.81.2}/nkululeko/data/dataset.py

@@ -162,7 +162,10 @@ class Dataset:
                     if column not in [self.target, "age", "speaker", "gender"]:
                         df[column] = df_target[column]
             except audformat.core.errors.BadKeyError:
-                pass
+                if not self.is_labeled:
+                    self.util.error(
+                        f"Giving up: no target ({self.target}) column found"
+                    )
 
         if self.is_labeled:
             # remember the target in case they get labelencoded later

{nkululeko-0.81.0 → nkululeko-0.81.2}/nkululeko/demo_predictor.py

@@ -1,3 +1,4 @@
+import os
 import pandas as pd
 import numpy as np
 import audiofile
@@ -52,13 +53,16 @@ class Demo_predictor:
                                 file_list.append(line)
                 for file_name in file_list:
                     test_folder = glob_conf.config["DATA"]["test_folder"]
-                    file_path = test_folder + file_name.strip()
+                    file_path = os.path.join(test_folder, file_name.strip())
                     sig, sr = audiofile.read(file_path)
                     print(f"predicting file {file_path}")
                     res_dict = self.predict_signal(sig, sr)
-                    df_tmp = pd.DataFrame(res_dict, index=[file_path])
+                    df_tmp = pd.DataFrame(res_dict, index=[file_name.strip()])
                     df_res = pd.concat([df_res, df_tmp], ignore_index=False)
                 df_res = df_res.set_index(df_res.index.rename("file"))
+                # save only filename and prediction (df_tmp) by default
+                # drop other columns
+                # df_res = df_res[["predicted"]]
                 if self.outfile is not None:
                     df_res.to_csv(self.outfile)
                 else:
@@ -94,7 +98,7 @@ class Demo_predictor:
                 return result_dict
         else:
             # experiment is regression and returns one estimation
-            dict_2["predicted"] = result_dict[0]
+            dict_2["predicted"] = result_dict
             print(dict_2)
             return dict_2
 

{nkululeko-0.81.0 → nkululeko-0.81.2}/nkululeko/feat_extract/feinberg_praat.py

@@ -294,8 +294,8 @@ def compute_features(file_index):
                 f4_median,
             ) = measureFormants(sound, 75, 300)
             #        file_list.append(wave_file) # make an ID list
-        except statistics.StatisticsError as se:
-            print(f"error on file {wave_file}: {se}")
+        except (statistics.StatisticsError, parselmouth.PraatError) as errors:
+            print(f"error on file {wave_file}: {errors}")
 
         duration_list.append(duration)  # make duration list
         mean_F0_list.append(meanF0)  # make a mean F0 list

{nkululeko-0.81.0 → nkululeko-0.81.2}/nkululeko/models/model.py

@@ -269,19 +269,24 @@ class Model:
         )
         return report
 
+    def get_type(self):
+        return "generic"
+
     def predict_sample(self, features):
         """Predict one sample"""
         prediction = {}
         if self.util.exp_is_classification():
             # get the class probabilities
-            predictions = self.clf.predict_proba([features])
+            if not self.get_type() == "xgb":
+                features = [features]
+            predictions = self.clf.predict_proba(features)
             # pred = self.clf.predict(features)
             for i in range(len(self.clf.classes_)):
                 cat = self.clf.classes_[i]
                 prediction[cat] = predictions[0][i]
         else:
             predictions = self.clf.predict(features)
-            prediction["result"] = predictions[0]
+            prediction = predictions[0]
         return prediction
 
     def store(self):

{nkululeko-0.81.0 → nkululeko-0.81.2}/nkululeko/models/model_mlp_regression.py

@@ -247,4 +247,4 @@ class MLP_Reg_model(Model):
             features = np.reshape(features, (-1, 1)).T
             logits = self.model(features.to(self.device)).reshape(-1)
         a = logits.numpy()
-        return a
+        return a[0]

{nkululeko-0.81.0 → nkululeko-0.81.2}/nkululeko/models/model_svm.py

@@ -12,8 +12,17 @@ class SVM_model(Model):
     def __init__(self, df_train, df_test, feats_train, feats_test):
         super().__init__(df_train, df_test, feats_train, feats_test)
         c = float(self.util.config_val("MODEL", "C_val", "0.001"))
+        if eval(self.util.config_val("MODEL", "class_weight", "False")):
+            class_weight = "balanced"
+        else:
+            class_weight = None
+        kernel = self.util.config_val("MODEL", "kernel", "rbf")
         self.clf = svm.SVC(
-            kernel="linear", C=c, gamma="scale", probability=True
+            kernel=kernel,
+            C=c,
+            gamma="scale",
+            probability=True,
+            class_weight=class_weight,
         )  # set up the classifier
 
     def set_C(self, c):

{nkululeko-0.81.0 → nkululeko-0.81.2}/nkululeko/models/model_svr.py

@@ -12,7 +12,9 @@ class SVR_model(Model):
     def __init__(self, df_train, df_test, feats_train, feats_test):
         super().__init__(df_train, df_test, feats_train, feats_test)
         c = float(self.util.config_val("MODEL", "C_val", "0.001"))
-        self.clf = svm.SVR(kernel="rbf", C=c, probability=True)  # set up the classifier
+        #  kernel{‘linear’, ‘poly’, ‘rbf’, ‘sigmoid’, ‘precomputed’} or callable, default=’rbf’
+        kernel = self.util.config_val("MODEL", "kernel", "rbf")
+        self.clf = svm.SVR(kernel=kernel, C=c)  # set up the classifier
 
     def set_C(self, c):
         """Set the C parameter"""

{nkululeko-0.81.0 → nkululeko-0.81.2}/nkululeko/models/model_xgb.py

@@ -10,3 +10,6 @@ class XGB_model(Model):
     is_classifier = True
 
     clf = XGBClassifier()  # set up the classifier
+
+    def get_type(self):
+        return "xgb"

{nkululeko-0.81.0 → nkululeko-0.81.2}/nkululeko/utils/util.py

@@ -175,10 +175,6 @@ class Util:
         mt = f'{self.config["MODEL"]["type"]}'
         ft = "_".join(ast.literal_eval(self.config["FEATS"]["type"]))
         ft += "_"
-        set = self.config_val("FEATS", "set", False)
-        set_string = ""
-        if set:
-            set_string += set
         layer_string = ""
         layer_s = self.config_val("MODEL", "layers", False)
         if layer_s:
@@ -186,16 +182,19 @@ class Util:
             sorted_layers = sorted(layers.items(), key=lambda x: x[1])
             for l in sorted_layers:
                 layer_string += f"{str(l[1])}-"
-        return_string = f"{mt}_{ft}{set_string}{layer_string[:-1]}"
+        return_string = f"{mt}_{ft}{layer_string[:-1]}"
         options = [
             ["MODEL", "C_val"],
+            ["MODEL", "kernel"],
             ["MODEL", "drop"],
+            ["MODEL", "class_weight"],
             ["MODEL", "loss"],
             ["MODEL", "logo"],
             ["MODEL", "learning_rate"],
             ["MODEL", "k_fold_cross"],
             ["FEATS", "balancing"],
             ["FEATS", "scale"],
+            ["FEATS", "set"],
             ["FEATS", "wav2vec2.layer"],
         ]
         for option in options:

{nkululeko-0.81.0 → nkululeko-0.81.2/nkululeko.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: nkululeko
-Version: 0.81.0
+Version: 0.81.2
 Summary: Machine learning audio prediction experiments based on templates
 Home-page: https://github.com/felixbur/nkululeko
 Author: Felix Burkhardt
@@ -321,6 +321,16 @@ F. Burkhardt, Johannes Wagner, Hagen Wierstorf, Florian Eyben and Björn Schulle
 Changelog
 =========
 
+Version 0.81.2
+--------------
+* added a parselmouth.Praat error if pitch out of range
+* changed file path for demo_predictor
+
+Version 0.81.1
+--------------
+* fixed bugs in demo module 
+* made kernel for SVM/SVR configurable
+
 Version 0.81.0
 --------------
 * added test selection to test module