nkululeko 0.77.4__py3-none-any.whl → 0.77.6__py3-none-any.whl

nkululeko/aug_train.py

@@ -11,15 +11,7 @@ import nkululeko.glob_conf as glob_conf
 from nkululeko.augment import doit as augment
 
 
-def main(src_dir):
-    parser = argparse.ArgumentParser(description="Call the nkululeko framework.")
-    parser.add_argument("--config", default="exp.ini", help="The base configuration")
-    args = parser.parse_args()
-    if args.config is not None:
-        config_file = args.config
-    else:
-        config_file = f"{src_dir}/exp.ini"
-
+def doit(config_file):
     # test if the configuration file exists
     if not os.path.isfile(config_file):
         print(f"ERROR: no such file: {config_file}")
@@ -87,6 +79,17 @@ def main(src_dir):
     print("DONE")
 
 
+def main(src_dir):
+    parser = argparse.ArgumentParser(description="Call the nkululeko framework.")
+    parser.add_argument("--config", default="exp.ini", help="The base configuration")
+    args = parser.parse_args()
+    if args.config is not None:
+        config_file = args.config
+    else:
+        config_file = f"{src_dir}/exp.ini"
+    doit(config_file)
+
+
 if __name__ == "__main__":
     cwd = os.path.dirname(os.path.abspath(__file__))
     main(cwd)  # use this if you want to state the config file path on command line

nkululeko/augmenting/augmenter.py

@@ -60,7 +60,15 @@ class Augmenter:
             audiofile.write(new_full_name, signal=sig_aug, sampling_rate=sr)
             index_map[f] = new_full_name
         df_ret = self.df.copy()
-        file_index = df_ret.index.levels[0].map(lambda x: index_map[x]).values
-        df_ret = df_ret.set_index(df_ret.index.set_levels(file_index, level="file"))
+
+        file_index = df_ret.index.to_series().map(lambda x: index_map[x[0]]).values
+        # workaround because i just couldn't get this easier...
+        arrays = [
+            file_index,
+            list(df_ret.index.get_level_values(1)),
+            list(df_ret.index.get_level_values(2)),
+        ]
+        new_index = pd.MultiIndex.from_arrays(arrays, names=("file", "start", "end"))
+        df_ret = df_ret.set_index(new_index)
 
         return df_ret

nkululeko/augmenting/randomsplicer.py

@@ -68,6 +68,15 @@ class Randomsplicer:
             index_map[f] = new_full_name
 
         df_ret = self.df.copy()
-        file_index = df_ret.index.levels[0].map(lambda x: index_map[x]).values
-        df_ret = df_ret.set_index(df_ret.index.set_levels(file_index, level="file"))
+
+        file_index = df_ret.index.to_series().map(lambda x: index_map[x[0]]).values
+        # workaround because i just couldn't get this easier...
+        arrays = [
+            file_index,
+            list(df_ret.index.get_level_values(1)),
+            list(df_ret.index.get_level_values(2)),
+        ]
+        new_index = pd.MultiIndex.from_arrays(arrays, names=("file", "start", "end"))
+        df_ret = df_ret.set_index(new_index)
+
         return df_ret

nkululeko/constants.py

@@ -1,2 +1,2 @@
-VERSION="0.77.4"
+VERSION="0.77.6"
 SAMPLING_RATE = 16000

nkululeko/experiment.py

@@ -261,11 +261,11 @@ class Experiment:
                 if type(test_cats) == np.ndarray:
                     self.util.debug(f"Categories test (nd.array): {test_cats}")
                 else:
-                    self.util.debug(f"Categories test (list): {test_cats.to_list()}")
+                    self.util.debug(f"Categories test (list): {list(test_cats)}")
             if type(train_cats) == np.ndarray:
                 self.util.debug(f"Categories train (nd.array): {train_cats}")
             else:
-                self.util.debug(f"Categories train (list): {train_cats.to_list()}")
+                self.util.debug(f"Categories train (list): {list(train_cats)}")
 
             # encode the labels as numbers
             self.label_encoder = LabelEncoder()

nkululeko/feat_extract/feats_analyser.py

@@ -7,7 +7,6 @@ from sklearn.tree import DecisionTreeClassifier
 from sklearn.linear_model import LinearRegression
 from sklearn.tree import DecisionTreeRegressor
 import matplotlib.pyplot as plt
-from xgboost import XGBClassifier, XGBRegressor
 from nkululeko.utils.util import Util
 from nkululeko.utils.stats import normalize
 from nkululeko.plots import Plots
@@ -126,6 +125,8 @@ class FeatureAnalyser:
                         plots = Plots()
                         plots.plot_tree(model, self.features)
                 elif model_s == "xgb":
+                    from xgboost import XGBClassifier
+
                     model = XGBClassifier(enable_categorical=True, tree_method="hist")
                     self.labels = self.labels.astype("category")
                     result_importances[model_s] = self._get_importance(
@@ -171,6 +172,8 @@ class FeatureAnalyser:
                         model, permutation
                     )
                 elif model_s == "xgr":
+                    from xgboost import XGBClassifier
+
                     model = XGBRegressor()
                     result_importances[model_s] = self._get_importance(
                         model, permutation

nkululeko/models/model.py

@@ -137,11 +137,11 @@ class Model:
             groups=annos["fold"],
         ):
             train_x = feats.iloc[train_index].to_numpy()
-            train_y = targets[train_index]
+            train_y = targets.iloc[train_index]
             self.clf.fit(train_x, train_y)
 
             truth_x = feats.iloc[test_index].to_numpy()
-            truth_y = targets[test_index]
+            truth_y = targets.iloc[test_index]
             predict_y = self.clf.predict(truth_x)
             report = Reporter(truth_y.astype(float), predict_y, self.run, self.epoch)
             result = report.get_result().get_test_result()

nkululeko/models/model_cnn.py

@@ -113,7 +113,7 @@ class CNN_model(Model):
             img_path = self.df_feats.iloc[idx, 0]
             image = Image.open(img_path)
             # Get emotion label
-            label = self.df_labels[self.target][idx]
+            label = self.df_labels[self.target].iloc[idx]
             if self.transform:
                 image = self.transform(image)
             return image, label

nkululeko/models/model_mlp.py

@@ -115,7 +115,7 @@ class MLP_model(Model):
     def get_loader(self, df_x, df_y, shuffle):
         data = []
         for i in range(len(df_x)):
-            data.append([df_x.values[i], df_y[self.target][i]])
+            data.append([df_x.values[i], df_y[self.target].iloc[i]])
         return torch.utils.data.DataLoader(
             data, shuffle=shuffle, batch_size=self.batch_size
         )

nkululeko/nkululeko.py

@@ -9,15 +9,7 @@ from nkululeko.utils.util import Util
 from nkululeko.constants import VERSION
 
 
-def main(src_dir):
-    parser = argparse.ArgumentParser(description="Call the nkululeko framework.")
-    parser.add_argument("--config", default="exp.ini", help="The base configuration")
-    args = parser.parse_args()
-    if args.config is not None:
-        config_file = args.config
-    else:
-        config_file = f"{src_dir}/exp.ini"
-
+def doit(config_file):
     # test if the configuration file exists
     if not os.path.isfile(config_file):
         print(f"ERROR: no such file: {config_file}")
@@ -54,11 +46,22 @@ def main(src_dir):
     expr.init_runmanager()
 
     # run the experiment
-    expr.run()
-
+    reports = expr.run()
+    result = reports[-1].result.test
     expr.store_report()
-
     print("DONE")
+    return result
+
+
+def main(src_dir):
+    parser = argparse.ArgumentParser(description="Call the nkululeko framework.")
+    parser.add_argument("--config", default="exp.ini", help="The base configuration")
+    args = parser.parse_args()
+    if args.config is not None:
+        config_file = args.config
+    else:
+        config_file = f"{src_dir}/exp.ini"
+    doit(config_file)
 
 
 if __name__ == "__main__":

nkululeko/plots.py

@@ -279,7 +279,7 @@ class Plots:
         res_pval = int(res_pval[1] * 1000) / 1000
         caption = f"{ylab} {df.shape[0]}. P-val chi2: {res_pval}"
         ax = (
-            df.groupby(col1)[col2]
+            df.groupby(col1, observed=False)[col2]
             .value_counts()
             .unstack()
             .plot(kind="bar", stacked=True, title=caption, rot=0)

nkululeko/utils/util.py

@@ -11,9 +11,24 @@ import audformat
 
 class Util:
     # a list of words that need not to be warned upon if default values are used
-    stopvals = [False, "False", "classification", "png", "audio_path"]
+    stopvals = [
+        "all",
+        False,
+        "False",
+        "classification",
+        "png",
+        "audio_path",
+        "kde",
+        "pkl",
+        "eGeMAPSv02",
+        "functionals",
+    ]
 
     def __init__(self, caller=None, has_config=True):
+        if caller is not None:
+            self.caller = caller
+        else:
+            self.caller = ""
         if has_config:
             import nkululeko.glob_conf as glob_conf
 
@@ -25,10 +40,7 @@ class Util:
                     self.error(f"no such file: {self.got_data_roots}")
                 self.data_roots = configparser.ConfigParser()
                 self.data_roots.read(self.got_data_roots)
-        if caller is not None:
-            self.caller = caller
-        else:
-            self.caller = ""
+                self.debug(f"getting data roots from {self.got_data_roots}")
 
     def get_path(self, entry):
         """

{nkululeko-0.77.4.dist-info → nkululeko-0.77.6.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: nkululeko
-Version: 0.77.4
+Version: 0.77.6
 Summary: Machine learning audio prediction experiments based on templates
 Home-page: https://github.com/felixbur/nkululeko
 Author: Felix Burkhardt
@@ -19,6 +19,7 @@ Requires-Dist: audinterface
 Requires-Dist: audiofile
 Requires-Dist: audiomentations
 Requires-Dist: audonnx
+Requires-Dist: cylimiter
 Requires-Dist: datasets
 Requires-Dist: imageio
 Requires-Dist: imbalanced-learn
@@ -188,6 +189,7 @@ Here is an overview of the interfaces:
 * **nkululeko.test**: predict a series of files with the current best model
 * **nkululeko.explore**: perform data exploration
 * **nkululeko.augment**: augment the current training data
+* **nkululeko.aug_train**: augment the current training data and do a training including this data
 * **nkululeko.predict**: predict features like SNR, MOS, arousal/valence, age/gender, with DNN models
 * **nkululeko.segment**: segment a database based on VAD (voice activity detection)
 * **nkululeko.resample**: check on all sampling rates and change to 16kHz 
@@ -309,6 +311,14 @@ F. Burkhardt, Johannes Wagner, Hagen Wierstorf, Florian Eyben and Björn Schulle
 Changelog
 =========
 
+Version 0.77.6
+--------------
+* added functions to call modules with config file path directly
+
+Version 0.77.5
+--------------
+* fixed augmentation bug for python version 10
+
 Version 0.77.4
 --------------
 * made traditional augmentations (audiomentation module) configurable

{nkululeko-0.77.4.dist-info → nkululeko-0.77.6.dist-info}/RECORD

@@ -1,11 +1,11 @@
 nkululeko/__init__.py,sha256=62f8HiEzJ8rG2QlTFJXUCMpvuH3fKI33DoJSj33mscc,63
-nkululeko/aug_train.py,sha256=zlaGdWFyaFCpHZ8h_mqPVFcdaOPyK0iXgEkr6eIBqMQ,2976
+nkululeko/aug_train.py,sha256=Z8AYr1E-zjRVrB7uRF_eKTvc0vYXVYGuy3BtzjSIL64,3022
 nkululeko/augment.py,sha256=sHWG4Jmb4BjnaaXXnRYMP7Jkk0qlaZ2ohsArP8uW_d8,3003
 nkululeko/cacheddataset.py,sha256=lIJ6hUo5LoxSrzXtWV8mzwO7wRtUETWnOQ4ws2XfL1E,969
-nkululeko/constants.py,sha256=rvUnKw3Xc-nto6fPV0AMxGXyhmvKh8-LgsanR3fMg-0,39
+nkululeko/constants.py,sha256=p_G6aEcoN8S7E9aX4sOtHKmywY_uhLXbm6h0iJqfjuY,39
 nkululeko/demo.py,sha256=FFR8qHMCY8kKKRWDTa8xA7A8mWeYalRKYNtV5rjGg44,1915
 nkululeko/demo_predictor.py,sha256=j4ySWWcIxW7ZAIBH86m9BfRFokzrUNkRD6fpsvAQGTw,2629
-nkululeko/experiment.py,sha256=bDRTZTm3LvTxeMNmC1_xOIspLhrh1JwXJfiAxLJfIzE,28657
+nkululeko/experiment.py,sha256=natQpQ_lETWoSea8rTM77g2G_xO_1KXNkES5eYU6GdM,28649
 nkululeko/explore.py,sha256=pfciOL66e0T4Bk0RTkwDyE6pK_baSUdjMo2Ybpst3L4,2202
 nkululeko/export.py,sha256=mHeEAAmtZuxdyebLlbSzPrHSi9OMgJHbk35d3DTxRBc,4632
 nkululeko/feature_extractor.py,sha256=tKv1b1-o7xNMgBavTR8VY8_H5HKoJEnnosS-KcjmOEU,7281
@@ -13,8 +13,8 @@ nkululeko/file_checker.py,sha256=LoLnL8aHpW-axMQ46qbqrManTs5otG9ShpEZuz9iRSk,347
 nkululeko/filter_data.py,sha256=w-X2mhKdYr5DxDIz50E5yzO6Jmzk4jjDBoXsgOOVtcA,7222
 nkululeko/glob_conf.py,sha256=6MZe83QCgHD_zB79Sl9m6UJQASwfqJlyb-1nqrQ_6Iw,381
 nkululeko/modelrunner.py,sha256=TQW08f72-GjBEIFTE3_8B8qMCWvTJUqJ1fveygmYnXI,9278
-nkululeko/nkululeko.py,sha256=MyjjbCg8qgLHHpvwJOEHBGNCDKf0GTv7gnXX27L56R4,1724
-nkululeko/plots.py,sha256=l-bxUoChkCIMsLPK4hMZyIWfuPNN_n-3g8Usc4sJ85A,21262
+nkululeko/nkululeko.py,sha256=5EfguOjCMt3xDttBJOw-B9upwOHcrN4z3yGKZH5OtoU,1833
+nkululeko/plots.py,sha256=Ci8brbxGXsCp1lnJdGkPUXoyWA6qUqUUwuxKOYEaqR8,21278
 nkululeko/predict.py,sha256=dRXX-sQVESa7cNi_56S6UkUOa_pV1g_K4xYtYVM1SJs,1876
 nkululeko/reporter.py,sha256=wrtWbU_UKDwhKQNMi7Q_Ix5N_UTzTagRwZikgUGk1c8,11606
 nkululeko/resample.py,sha256=C2S3aOTwlx5iYah_hs0JARHBC8Cq4Z5cH_mnDMb5RKk,2185
@@ -26,8 +26,8 @@ nkululeko/syllable_nuclei.py,sha256=Sky-C__MeUDaxqHnDl2TGLLYOYvsahD35TUjWGeG31k,
 nkululeko/test.py,sha256=cRtOn_d3Fh2kZmnT4nnQeGzZTRtpr5jRhowykOwunME,1421
 nkululeko/test_predictor.py,sha256=8eyHJ_YNIwR2OfICkqo7zF2f7UP8nL0nzCwC-8XnkZY,2409
 nkululeko/augmenting/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-nkululeko/augmenting/augmenter.py,sha256=PxXYbpgopkdPSdd8dMr9iKDKvIA12Ty7hDrOtdpkm6M,2632
-nkululeko/augmenting/randomsplicer.py,sha256=OIBmfzyx1vhKl1cUQGlQw-CWZwsCV8XG9miITb41CT0,2395
+nkululeko/augmenting/augmenter.py,sha256=XAt0dpmlnKxqyysqCgV3rcz-pRIvOz7rU7dmGDCVAzs,2905
+nkululeko/augmenting/randomsplicer.py,sha256=Z5rxdKKUpuncLWuTS6xVfVKUeVbeiYU_dLRHQ5fcg4Y,2669
 nkululeko/augmenting/randomsplicing.py,sha256=ldym9vZNsZIU5BAAaJVaOmAgmVHNs4a5i5K3bW-WAQU,1791
 nkululeko/augmenting/resampler.py,sha256=cRrn27w_f2I6aN0CftlTuHT2edi7pTREh3Yc6BxhcGU,3335
 nkululeko/autopredict/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -48,7 +48,7 @@ nkululeko/data/dataset_csv.py,sha256=9ysujWHQnOHLWtJxGtvdpHE3c_sM_l9svFYWYCpamVs
 nkululeko/feat_extract/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nkululeko/feat_extract/feats_agender.py,sha256=sDfsvSC2zt1JLn5rmB7bdck1JmXIIol3oIwN90TossM,2867
 nkululeko/feat_extract/feats_agender_agender.py,sha256=UYATYWE-zCt9F1qA4xQbYZ2qM7DT2nwGxk7vSiyhit4,2953
-nkululeko/feat_extract/feats_analyser.py,sha256=82CCFTViP3XCEUS5Mku_0P358jEsm2-AIt5lAvlQQmY,11335
+nkululeko/feat_extract/feats_analyser.py,sha256=nD2-7K4c0hFJvVCfmpsoU-SnePyb4m_JIPsf0uTzE0M,11397
 nkululeko/feat_extract/feats_audmodel.py,sha256=sZD8NBC3qId4ygzBvW5RvKVgCC1zxvO_cyFazYOEwCk,2901
 nkululeko/feat_extract/feats_audmodel_dim.py,sha256=z48s-FXokREnir_dNMl8fNI5PLCXzOhvmjgfCjTDjh8,2817
 nkululeko/feat_extract/feats_clap.py,sha256=v82mbjdjGDSKUUBggttw7jW0oka22fWAmfUf-4VmaDU,3379
@@ -72,14 +72,14 @@ 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=7hrPyqWdgQ5TbQKZTcr-XwK83070IZdWy5Ek7FeeVpQ,11311
+nkululeko/models/model.py,sha256=jg6t-0fXCPQv0cQZjyye4OZlkwf-iAN8HBikTHU1MBA,11321
 nkululeko/models/model_bayes.py,sha256=wI7-sCwibqXMCHviu349TYjgJXXNXym-Z6ZM83uxlFQ,378
-nkululeko/models/model_cnn.py,sha256=ObNSQpADBx3X5m31KPUw0U8q7ztAcc56uBVE2-QSjYo,9249
+nkululeko/models/model_cnn.py,sha256=B02NPo6a_4SwLbnzd25drQZqUpC15ecXGrb1rXv5VOE,9254
 nkululeko/models/model_gmm.py,sha256=onovzGBeguwZ-upXtuDLaBw9sd6fDDQslVBOrz1Z8TE,645
 nkululeko/models/model_knn.py,sha256=5tGqiPo2JTw9VLmD-MXNZKFJ5RTLA6uv_blJDJ9lScA,573
 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=0Fm1wZd69HoNTrsi3MpS5cOm2Cd7wJALSxoUcr3ELak,8494
+nkululeko/models/model_mlp.py,sha256=hgAy1WtTw1nUFxjOmfEDBzpe7IF2APsICIip_si6nv8,8499
 nkululeko/models/model_mlp_regression.py,sha256=nFJwch23tUTCxAlgi3YkT-6KSPPLAE7wFK2zF2gg3F4,9457
 nkululeko/models/model_svm.py,sha256=J1d8mf5T4QHtilkUTBkhegVB_0D2kRY0BiBGz-LUJmw,554
 nkululeko/models/model_svr.py,sha256=au5AtzjEpaY9_7Fz6CQoIZ3s6OAvLUxjAXuqHF9dRbk,514
@@ -98,9 +98,9 @@ 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=icfzPBoBjrvcycrfVqLZ-m8nUp2-Kj6P00cs96ogqTo,11411
-nkululeko-0.77.4.dist-info/LICENSE,sha256=0zGP5B_W35yAcGfHPS18Q2B8UhvLRY3dQq1MhpsJU_U,1076
-nkululeko-0.77.4.dist-info/METADATA,sha256=tYGi3pYZWpWN1lahin-XjlACBNcziWNOWmbYvnQFUPg,30364
-nkululeko-0.77.4.dist-info/WHEEL,sha256=oiQVh_5PnQM0E3gPdiz09WCNmwiHDMaGer_elqB3coM,92
-nkululeko-0.77.4.dist-info/top_level.txt,sha256=DPFNNSHPjUeVKj44dVANAjuVGRCC3MusJ08lc2a8xFA,10
-nkululeko-0.77.4.dist-info/RECORD,,
+nkululeko/utils/util.py,sha256=lpaM7_KnLjquFFtMPH6swdisF1kqSHBLpHh3CzgGtLw,11625
+nkululeko-0.77.6.dist-info/LICENSE,sha256=0zGP5B_W35yAcGfHPS18Q2B8UhvLRY3dQq1MhpsJU_U,1076
+nkululeko-0.77.6.dist-info/METADATA,sha256=jVeWsnVWyiRsVCYFxbyK_UYgqyLsDNNKTXg_XaQIK7A,30662
+nkululeko-0.77.6.dist-info/WHEEL,sha256=oiQVh_5PnQM0E3gPdiz09WCNmwiHDMaGer_elqB3coM,92
+nkululeko-0.77.6.dist-info/top_level.txt,sha256=DPFNNSHPjUeVKj44dVANAjuVGRCC3MusJ08lc2a8xFA,10
+nkululeko-0.77.6.dist-info/RECORD,,