nkululeko 0.81.0__py3-none-any.whl → 0.81.2__py3-none-any.whl

nkululeko/constants.py

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

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/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/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/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/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/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/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/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/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.dist-info → nkululeko-0.81.2.dist-info}/METADATA

@@ -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.dist-info → nkululeko-0.81.2.dist-info}/RECORD

@@ -2,10 +2,10 @@ nkululeko/__init__.py,sha256=62f8HiEzJ8rG2QlTFJXUCMpvuH3fKI33DoJSj33mscc,63
 nkululeko/aug_train.py,sha256=YhuZnS_WVWnun9G-M6g5n6rbRxoVREz6Zh7k6qprFNQ,3194
 nkululeko/augment.py,sha256=4MG0apTAG5RgkuJrYEjGgDdbodZWi_HweSPNI1JJ5QA,3051
 nkululeko/cacheddataset.py,sha256=lIJ6hUo5LoxSrzXtWV8mzwO7wRtUETWnOQ4ws2XfL1E,969
-nkululeko/constants.py,sha256=pA2Wijj2MuEHU3MRfBhne0rARFs9qnjCZzbVKVMQLTc,39
+nkululeko/constants.py,sha256=zujT9J62h5BIBCxzigDt23S5plsfoyutXsGMdK_xkAM,39
 nkululeko/demo.py,sha256=me8EdjN-zrzClVy9FEmqbTQyDDON88W8vPpWEE8T0cI,2500
 nkululeko/demo_feats.py,sha256=sAeGFojhEj9WEDFtG3SzPBmyYJWLF2rkbpp65m8Ujo4,2025
-nkululeko/demo_predictor.py,sha256=XlaMAuxrDuMIUZdKL2wlKRVqvKl5aUOR6BPmSdj-qcI,4547
+nkululeko/demo_predictor.py,sha256=CQL6DO7QxwmwoB_6DlgDS-pdG1KuvemYJ1NEpMjmMk8,4733
 nkululeko/experiment.py,sha256=NVhtywaGT5vtreJNlrezp4sq-KIN_gxOjUChvBa7Z38,29575
 nkululeko/explore.py,sha256=5c89hGpjt5mRMN7w2Ajjnr2VjoFF0hOFs0O1BQruw80,2250
 nkululeko/export.py,sha256=mHeEAAmtZuxdyebLlbSzPrHSi9OMgJHbk35d3DTxRBc,4632
@@ -45,7 +45,7 @@ nkululeko/autopredict/ap_stoi.py,sha256=It0Lk-ki-gohA2AzD8nkLAN2WahYvD9rPDGTQuvd
 nkululeko/autopredict/ap_valence.py,sha256=n-hctRKySzhmJtowuMOTUu0T_ld3uK5pnfOzWeWW4VM,1024
 nkululeko/autopredict/estimate_snr.py,sha256=kJbvkt2alMN5ouS03USheU7hJ2l7U9JF0s9AtNT1Vx0,4818
 nkululeko/data/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-nkululeko/data/dataset.py,sha256=t0f_i1UhHE7U9LDzDmqzqKFZaVskwVCs-Bz_jxnyZno,27110
+nkululeko/data/dataset.py,sha256=n6v_vVdA0EsZ-NaTgnYfPlCT4QCcD02mJJb-oD7SaSU,27265
 nkululeko/data/dataset_csv.py,sha256=v3lSjF23EVjoP460QOfhdcqbWAlBQWlBOuaYujZoS4s,3407
 nkululeko/feat_extract/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nkululeko/feat_extract/feats_agender.py,sha256=_lAL6IxJDJH2bhIvd7yarTqQryx7FjbQXAgY0mJP-KI,3192
@@ -69,12 +69,12 @@ nkululeko/feat_extract/feats_trill.py,sha256=PpygJK_W6QoBNeSah9npQPiQlJxLWFn6TSO
 nkululeko/feat_extract/feats_wav2vec2.py,sha256=sFf-WkLUgKUQsFxGO9m2hS3uYoGkv95mZavCEZyWFGA,5072
 nkululeko/feat_extract/feats_wavlm.py,sha256=RhI0oWIsknnxTVmdnNS_xJO1NnUUR0CUNDWH1yTpNLk,4683
 nkululeko/feat_extract/featureset.py,sha256=-ynkdor8iX7BFx10aIbB3LfwxrrzPoBGz9kXwyAJO9M,1375
-nkululeko/feat_extract/feinberg_praat.py,sha256=-pgY8Koq7dFaz-99cjkNqsQn1bsKgPInEuwrfmR0ebA,21253
+nkululeko/feat_extract/feinberg_praat.py,sha256=7V1VhVMu4QrXkdcXpmqCbpStXfpmOHtfx5GzxXWukz8,21287
 nkululeko/losses/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nkululeko/losses/loss_ccc.py,sha256=NOK0y0fxKUnU161B5geap6Fmn8QzoPl2MqtPiV8IuJE,976
 nkululeko/losses/loss_softf1loss.py,sha256=5gW-PuiqeAZcRgfwjueIOQtMokOjZWgQnVIv59HKTCo,1309
 nkululeko/models/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-nkululeko/models/model.py,sha256=Hq40hq5K8sTa1aIevx-o3ok32ngncMDQx_f-q0MmdXs,11517
+nkululeko/models/model.py,sha256=SZ2HQ3KiF5fcmrTcvko1E95EQQeFIaPCG90DvZVHbBA,11638
 nkululeko/models/model_bayes.py,sha256=wI7-sCwibqXMCHviu349TYjgJXXNXym-Z6ZM83uxlFQ,378
 nkululeko/models/model_cnn.py,sha256=iyXeRsAMVeRST1j_D2AUngE02CtVkg6vWwQc1BOaBl0,9716
 nkululeko/models/model_gmm.py,sha256=onovzGBeguwZ-upXtuDLaBw9sd6fDDQslVBOrz1Z8TE,645
@@ -82,12 +82,12 @@ nkululeko/models/model_knn.py,sha256=5tGqiPo2JTw9VLmD-MXNZKFJ5RTLA6uv_blJDJ9lScA
 nkululeko/models/model_knn_reg.py,sha256=Fbuk6Ku6eyrbbMEk7rB5dwfhvQOMsdZk6HI_0T0gYPw,580
 nkululeko/models/model_lin_reg.py,sha256=NBTnY2ULuhUBt5ArYQwskZ2Vq4BBDGkqd9SYBFl7Ql4,392
 nkululeko/models/model_mlp.py,sha256=IjiiupLxm5ddb73-eU5Ad79Gb6enurR1fgGY-7NkbFc,9097
-nkululeko/models/model_mlp_regression.py,sha256=OFsGQXS4EhRMq3exZAMLF-vJARxIWH6TZjMKoueUkLs,10051
-nkululeko/models/model_svm.py,sha256=-5DHtdm4q6JqbBY60a38sRUg6wSoPtm_TGnekGQlBTM,572
-nkululeko/models/model_svr.py,sha256=qPG54wqccIM-Yse-95wKGTQdTZDa1bUHpZky110KlSY,532
+nkululeko/models/model_mlp_regression.py,sha256=F0SaU1qAjnGmTTg-ti1s-XmFYVUYxSV0TJw0_jMxlKU,10054
+nkululeko/models/model_svm.py,sha256=dqDQbfRCtlW3RNqpHDGVsj3ikc131gKURHj5VzAcCr0,867
+nkululeko/models/model_svr.py,sha256=p-Mb4Bn54yOe1upuHQKNpfj4ttOmQnm9pCB7ECkJkJQ,699
 nkululeko/models/model_tree.py,sha256=soXjV523eRvRZ-jbX7X_3S73Wto1B9bm7ZzzDmgYzTc,390
 nkululeko/models/model_tree_reg.py,sha256=QxkQEz3LOuCLkXw5xH9IwFg4IcTL3Y5RK03qKe4TtGQ,397
-nkululeko/models/model_xgb.py,sha256=tzcksyGP9-XQGOBqt5gYSrQZsbtbcm5qwSkjnxsIX3I,221
+nkululeko/models/model_xgb.py,sha256=yPJFD2jxOGcPDKuBeqJSmh83eKrfbnD_n722i6g39_g,267
 nkululeko/models/model_xgr.py,sha256=yY6wZV8jdiQCIYQCjYSb8gE0jjeiY44eh3rERe2HDvg,227
 nkululeko/reporting/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nkululeko/reporting/defines.py,sha256=IsY1YgKRMaABpylVKjBJgJ5bNCEbGCVA_E6pivraqSU,648
@@ -100,9 +100,9 @@ nkululeko/segmenting/seg_silero.py,sha256=lLytS38KzARS17omwv8VBw-zz60RVSXGSvZ5Ev
 nkululeko/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nkululeko/utils/files.py,sha256=UiGAtZRWYjHSvlmPaTMtzyNNGE6qaLaxQkybctS7iRM,4021
 nkululeko/utils/stats.py,sha256=29otJpUp1VqbtDKmlLkPPzBmVfTFiHZ70rUdR4860rM,2788
-nkululeko/utils/util.py,sha256=Hn27x0f2rjSR-iae2h9_70J4SdXKJTduLFIH13w3db0,12363
-nkululeko-0.81.0.dist-info/LICENSE,sha256=0zGP5B_W35yAcGfHPS18Q2B8UhvLRY3dQq1MhpsJU_U,1076
-nkululeko-0.81.0.dist-info/METADATA,sha256=yaassogO9-2QPBkYPPjT7AUtJZeoTT6L1BNJmZjr5VM,34298
-nkululeko-0.81.0.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
-nkululeko-0.81.0.dist-info/top_level.txt,sha256=DPFNNSHPjUeVKj44dVANAjuVGRCC3MusJ08lc2a8xFA,10
-nkululeko-0.81.0.dist-info/RECORD,,
+nkululeko/utils/util.py,sha256=_Z6OMJ3f-8TdETW9eqJYY5hwNRS5XCt9azzRnqoTTZE,12330
+nkululeko-0.81.2.dist-info/LICENSE,sha256=0zGP5B_W35yAcGfHPS18Q2B8UhvLRY3dQq1MhpsJU_U,1076
+nkululeko-0.81.2.dist-info/METADATA,sha256=-Oo7DH0SM9gF8F0c65DLjGIt6rnUUPF_Ah_OgJrxDRA,34523
+nkululeko-0.81.2.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
+nkululeko-0.81.2.dist-info/top_level.txt,sha256=DPFNNSHPjUeVKj44dVANAjuVGRCC3MusJ08lc2a8xFA,10
+nkululeko-0.81.2.dist-info/RECORD,,