nkululeko 0.94.2__py3-none-any.whl → 0.94.3__py3-none-any.whl

nkululeko/augmenting/resampler.py

@@ -17,7 +17,7 @@ class Resampler:
     def __init__(self, df, replace, not_testing=True):
         self.SAMPLING_RATE = 16000
         self.df = df
-        self.util = Util("resampler", has_config=not_testing)
+        self.util = Util("resampler", has_config=not not_testing)
         self.util.warn(f"all files might be resampled to {self.SAMPLING_RATE}")
         self.not_testing = not_testing
         self.replace = (
@@ -30,7 +30,7 @@ class Resampler:
         files = self.df.index.get_level_values(0).values
         # replace = eval(self.util.config_val("RESAMPLE", "replace", "False"))
         replace = self.replace
-        if self.not_testing:
+        if not self.not_testing:
             store = self.util.get_path("store")
         else:
             store = "./"
@@ -67,17 +67,25 @@ class Resampler:
             self.df = self.df.set_index(
                 self.df.index.set_levels(new_files, level="file")
             )
-            target_file = self.util.config_val("RESAMPLE", "target", "resampled.csv")
-            # remove encoded labels
-            target = self.util.config_val("DATA", "target", "emotion")
-            if "class_label" in self.df.columns:
-                self.df = self.df.drop(columns=[target])
-                self.df = self.df.rename(columns={"class_label": target})
-            # save file
-            self.df.to_csv(target_file)
-            self.util.debug(
-                "saved resampled list of files to" f" {os.path.abspath(target_file)}"
-            )
+            if not self.not_testing:
+                target_file = self.util.config_val("RESAMPLE", "target", "resampled.csv")
+                # remove encoded labels
+                target = self.util.config_val("DATA", "target", "emotion")
+                if "class_label" in self.df.columns:
+                    self.df = self.df.drop(columns=[target])
+                    self.df = self.df.rename(columns={"class_label": target})
+                # save file
+                self.df.to_csv(target_file)
+                self.util.debug(
+                    "saved resampled list of files to" f" {os.path.abspath(target_file)}"
+                )
+            else:
+                # When running from command line, save to simple resampled.csv
+                target_file = "resampled.csv"
+                self.df.to_csv(target_file)
+                self.util.debug(
+                    f"saved resampled list of files to {os.path.abspath(target_file)}"
+                )
         self.util.debug(f"resampled {succes} files, {error} errors")
 
 
@@ -91,7 +99,7 @@ def main():
         df_sample.index, allow_nat=False
     )
     df_sample.head(10)
-    resampler = Resampler(df_sample, not_testing=False)
+    resampler = Resampler(df_sample, False, not_testing=False)
     resampler.resample()
     shutil.copyfile(testfile, "tmp.resample_result.wav")
     shutil.copyfile("tmp.wav", testfile)

nkululeko/constants.py

@@ -1,2 +1,2 @@
-VERSION="0.94.2"
+VERSION="0.94.3"
 SAMPLING_RATE = 16000

nkululeko/models/model.py

@@ -3,11 +3,15 @@ import ast
 import pickle
 import random
 
+from joblib import parallel_backend
 import numpy as np
 import pandas as pd
+from sklearn.model_selection import GridSearchCV
+from sklearn.model_selection import LeaveOneGroupOut
+from sklearn.model_selection import StratifiedKFold
 import sklearn.utils
-from joblib import parallel_backend
-from sklearn.model_selection import GridSearchCV, LeaveOneGroupOut, StratifiedKFold
+
+import audeer
 
 import nkululeko.glob_conf as glob_conf
 from nkululeko.reporting.reporter import Reporter
@@ -301,8 +305,15 @@ class Model:
     def get_type(self):
         return "generic"
 
-    def predict_sample(self, features):
-        """Predict one sample"""
+    def predict_sample(self, features: np.ndarray) -> dict | float:
+        """Predict a single sample using the trained model.
+
+        Args:
+            features (np.ndarray): The feature vector of the sample to predict.
+
+        Returns:
+            dict: A dictionary containing the predicted class probabilities or value.
+        """
         prediction = {}
         if self.util.exp_is_classification():
             # get the class probabilities
@@ -336,3 +347,30 @@ class Model:
         self.set_id(run, epoch)
         with open(path, "rb") as handle:
             self.clf = pickle.load(handle)
+
+    # next function exports the model to onnx
+    def export_onnx(self, onnx_path, input_shape=None):
+        """Export the trained sklearn model to ONNX format.
+
+        Args:
+            onnx_path (str): Path to save the ONNX model.
+            input_shape (tuple, optional): Shape of the input features. If None, inferred from feats_train.
+        """
+        import skl2onnx
+        from skl2onnx import convert_sklearn
+        from skl2onnx.common.data_types import FloatTensorType
+
+        if not hasattr(self, "clf"):
+            self.util.error("No trained model found to export.")
+            return
+
+        if input_shape is None:
+            n_features = self.feats_train.shape[1]
+            initial_type = [("input", FloatTensorType([None, n_features]))]
+        else:
+            initial_type = [("input", FloatTensorType(input_shape))]
+
+        onnx_model = convert_sklearn(self.clf, initial_types=initial_type)
+        with open(audeer.path(onnx_path), "wb") as f:
+            f.write(onnx_model.SerializeToString())
+        self.util.debug(f"Model exported to ONNX at {onnx_path}")

nkululeko/models/model_xgb.py

@@ -1,4 +1,4 @@
-# xgbmodel.py
+# model_xgb.py
 
 from xgboost import XGBClassifier
 

nkululeko/nkululeko.py

@@ -54,6 +54,15 @@ def doit(config_file):
     reports, last_epochs = expr.run()
     result = expr.get_best_report(reports).result.test
     expr.store_report()
+
+    # check if we want to export the model
+    o_path = util.config_val("EXP", "export_onnx", "False")
+    if eval(o_path):
+        print(f"Exporting ONNX model to {o_path}")
+        o_path = o_path.replace('"', '')
+        expr.runmgr.get_best_model().export_onnx(str(o_path))
+
+
     print("DONE")
     return result, int(np.asarray(last_epochs).min())
 

nkululeko/runmanager.py

@@ -181,7 +181,7 @@ class Runmanager:
         """
         # self.load_model(report)
         # report = self.model.predict()
-        self.util.debug(f"plotting conf matrix to {plot_name}")
+        self.util.debug(f"plotting conf matrix as {plot_name}")
         report.plot_confmatrix(plot_name, epoch=report.epoch)
         report.print_results(report.epoch, file_name=plot_name)
         report.print_probabilities(file_name=plot_name)

{nkululeko-0.94.2.dist-info → nkululeko-0.94.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: nkululeko
-Version: 0.94.2
+Version: 0.94.3
 Summary: Machine learning audio prediction experiments based on templates
 Home-page: https://github.com/felixbur/nkululeko
 Author: Felix Burkhardt

{nkululeko-0.94.2.dist-info → nkululeko-0.94.3.dist-info}/RECORD

@@ -3,7 +3,7 @@ nkululeko/__init__.py,sha256=62f8HiEzJ8rG2QlTFJXUCMpvuH3fKI33DoJSj33mscc,63
 nkululeko/aug_train.py,sha256=wpiHCJ7zsW38kumg3ypwXZe2HQrhUblAnv7P2QeJnAc,3525
 nkululeko/augment.py,sha256=3RzaxB3gRxovgJVjHXi0glprW01J7RaHhUkqotW2T3U,2955
 nkululeko/cacheddataset.py,sha256=XFpWZmbJRg0pvhnIgYf0TkclxllD-Fctu-Ol0PF_00c,969
-nkululeko/constants.py,sha256=1uXTovFvHp9PGrpkAyOYxPPZcMM5ojIHW2L7u92ADUo,39
+nkululeko/constants.py,sha256=KCqkmtwj--gcAdaRwj_Zb44_ewVNp06Hfp8-YGDG8iI,39
 nkululeko/demo-ft.py,sha256=iD9Pzp9QjyAv31q1cDZ75vPez7Ve8A4Cfukv5yfZdrQ,770
 nkululeko/demo.py,sha256=tu7Al2l5MCLVegkDC-NE2wcuc_YE7NRbgOlPW3yhGEs,4940
 nkululeko/demo_feats.py,sha256=BvZjeNFTlERIRlq34OHM4Z96jdDQAhB01BGQAUcX9dM,2026
@@ -20,11 +20,11 @@ nkululeko/glob_conf.py,sha256=KL9YJQTHvTztxo1vr25qRRgaPnx4NTg0XrdbovKGMmw,525
 nkululeko/modelrunner.py,sha256=NpDgXfKkn8dOrQzhUiEfGI56Qrb1sOtWTD31II4Zgbk,11550
 nkululeko/multidb.py,sha256=sO6OwJn8sn1-C-ig3thsIL8QMWHdV9SnJhDodKjeKrI,6876
 nkululeko/nkuluflag.py,sha256=PGWSmZz-PiiHLgcZJAoGOI_Y-sZDVI1ksB8p5r7riWM,3725
-nkululeko/nkululeko.py,sha256=6ALPMMIz6l0O3IRaP0q4b59ZUxpfzNqLQUqZMf5t3Zo,1976
+nkululeko/nkululeko.py,sha256=FaLimlbx47rJgWgDEd0ZROAiXy2cOypliVdqJn-Bvws,2257
 nkululeko/plots.py,sha256=i9VIkviBWLgncfnyK44TUMzg2Xa0_UhfL0LnMF1vHTw,27022
 nkululeko/predict.py,sha256=MLnHEyFmSiHLLs-HDczag8Vu3zKF5T1rXLKdZZJ6py8,2083
 nkululeko/resample.py,sha256=rn3-M1A-iwVGibfQNGyeYNa7briD24lIN9Szq_1uTJo,5194
-nkululeko/runmanager.py,sha256=-QI7pGLVnNAPMAIobcEip9zQNQdO2u0sp0Yd4XH4mBE,8902
+nkululeko/runmanager.py,sha256=YtGQP0UyyQTKkilncB1XYM-T8oatzGcZEOcj5SorjJw,8902
 nkululeko/scaler.py,sha256=a4lKwWT436TV4VEvqtP1uQ58Yz67XVHr1HjO5gp3xLI,5109
 nkululeko/segment.py,sha256=7UrJEwdLmh9wDL5iBwpdJyJm9dwSxidHrHt-_D2qtxw,4949
 nkululeko/syllable_nuclei.py,sha256=5w_naKxNxz66a_qLkraemi2fggM-gWesiiBPS47iFcE,9931
@@ -35,7 +35,7 @@ nkululeko/augmenting/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hS
 nkululeko/augmenting/augmenter.py,sha256=TUUznEz0pe9DSMC9r7LoBckuvsJTprvypeV5-8zLn20,2846
 nkululeko/augmenting/randomsplicer.py,sha256=TQTy4RBt6XbWiuUu5Ic913DMvmwTUwEufldBJjo7i1s,2801
 nkululeko/augmenting/randomsplicing.py,sha256=GXCpCDdOsOyWACDJ3ujmFZBVe6ISvkoQLefBNPgxxow,1750
-nkululeko/augmenting/resampler.py,sha256=gcjyyTD6QtJK6s_xoOQpsu5adpn0uSJwHxJTHMskfOM,3541
+nkululeko/augmenting/resampler.py,sha256=j2yuB9h9UwGQHqwF8CZPSGqAfOiyQV3979WQjU2toVM,3962
 nkululeko/autopredict/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nkululeko/autopredict/ap_age.py,sha256=yzd8sF6gi0hnqNawyLBCIkt-pKgl9gYPlZHsrLGfz0U,1098
 nkululeko/autopredict/ap_arousal.py,sha256=lpv3jTSVEVCcR226JevNM6S7e0_uMZXHb_8Wpup1yj8,1027
@@ -84,7 +84,7 @@ nkululeko/losses/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,
 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=2STBD3jtLKeNSk7arCFJdaV6FL-nuLR1qpsjvZ4W-9A,12975
+nkululeko/models/model.py,sha256=0O6H-kME1yVHU-EKu5iOZVBB7fFNg3lfagvGgMrldxM,14426
 nkululeko/models/model_bayes.py,sha256=tQUXEsXoS6WnfapQjP78S_gxNBssTOqE78A2iG8SfLU,407
 nkululeko/models/model_cnn.py,sha256=TKj43865epsiK7a0COyfBDaFHKOYgWgnPpMVCPWUhCM,10497
 nkululeko/models/model_gmm.py,sha256=mhHFNtTzHuJvqYSA0h5YhvjA--KhnN6MTU_S0G3-d1c,1332
@@ -98,7 +98,7 @@ nkululeko/models/model_svr.py,sha256=FEwYRdgqwgGhZdkpRnT7Ef12lklWi6GZL28PyV99xWs
 nkululeko/models/model_tree.py,sha256=6L3PD3aIiiQz1RPWS6z3Edx4f0gnR7AOfBKOJzf0BNU,433
 nkululeko/models/model_tree_reg.py,sha256=IMaQpNImoRqP8Biw1CsJevxpV_PVpKblsKtYlMW5d_U,429
 nkululeko/models/model_tuned.py,sha256=VuRyNqw3XTpQ2eHsWOJN8X-V98AN8Wqiq7UgwT5BQRU,23763
-nkululeko/models/model_xgb.py,sha256=ytBaSHZH8r7VvRYdmrBrQnzRM6V4HyCJ8O-v20J8G_g,448
+nkululeko/models/model_xgb.py,sha256=zfZM3lqH5uttVB18b1MRIhP9CCeCuIh1ycgOuFMcqUM,449
 nkululeko/models/model_xgr.py,sha256=H01FJCRgmX2unvambMs5TTCS9sI6VDB9ip9G6rVGt2c,419
 nkululeko/models/tests/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nkululeko/models/tests/test_model_svm.py,sha256=spDlZmeBKBdK4EFBpOgEkaAfGeGH9kau6CqSWOY6Uag,1856
@@ -118,9 +118,9 @@ nkululeko/utils/files.py,sha256=SrrYaU7AB80MZHiV1jcB0h_zigvYLYgSVNTXV4ao38g,4593
 nkululeko/utils/stats.py,sha256=3Fyx8q8BSKYmiufT6OkRug9RATWmGrr9BaX_y8jziWo,3074
 nkululeko/utils/unzip.py,sha256=G68f5120TjwACZC3bQcneMniddnwubPbBdMc2L5KBOo,1206
 nkululeko/utils/util.py,sha256=6NDKhOx0fV5fKyhSoY4hem96p7OuPcmhCDQR9EzkQhw,17829
-nkululeko-0.94.2.dist-info/licenses/LICENSE,sha256=0zGP5B_W35yAcGfHPS18Q2B8UhvLRY3dQq1MhpsJU_U,1076
-nkululeko-0.94.2.dist-info/METADATA,sha256=YmvStXvJdODIXXgDRQSmzhmJzl_SuX7donWfg66KZBI,2874
-nkululeko-0.94.2.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-nkululeko-0.94.2.dist-info/entry_points.txt,sha256=lNTkFEdh6Kjo5o95ZAWf_0Lq-4ztGoAoMVSDuPtuyS0,442
-nkululeko-0.94.2.dist-info/top_level.txt,sha256=bf1k1YKkqcXemNX_cUgoyKqQ3_GVErPqAY-53J36jkM,19
-nkululeko-0.94.2.dist-info/RECORD,,
+nkululeko-0.94.3.dist-info/licenses/LICENSE,sha256=0zGP5B_W35yAcGfHPS18Q2B8UhvLRY3dQq1MhpsJU_U,1076
+nkululeko-0.94.3.dist-info/METADATA,sha256=QeZ9ZMTqwgdDvwRTCvgFO7X55_J84AWZh7jVf9uV-6M,2874
+nkululeko-0.94.3.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+nkululeko-0.94.3.dist-info/entry_points.txt,sha256=lNTkFEdh6Kjo5o95ZAWf_0Lq-4ztGoAoMVSDuPtuyS0,442
+nkululeko-0.94.3.dist-info/top_level.txt,sha256=bf1k1YKkqcXemNX_cUgoyKqQ3_GVErPqAY-53J36jkM,19
+nkululeko-0.94.3.dist-info/RECORD,,