nkululeko 0.77.12__py3-none-any.whl → 0.77.14__py3-none-any.whl

nkululeko/constants.py

@@ -1,2 +1,2 @@
-VERSION="0.77.12"
+VERSION="0.77.14"
 SAMPLING_RATE = 16000

nkululeko/experiment.py

@@ -577,6 +577,9 @@ class Experiment:
                 scale_feats,
             )
             self.feats_train, self.feats_test = self.scaler_feats.scale()
+            # store versions
+            self.util.save_to_store(self.feats_train, "feats_train_scaled")
+            self.util.save_to_store(self.feats_test, "feats_test_scaled")
 
     def init_runmanager(self):
         """Initialize the manager object for the runs."""

nkululeko/runmanager.py

@@ -70,7 +70,8 @@ class Runmanager:
             plot_epoch_progression = self.util.config_val(
                 "PLOT", "epoch_progression", 0
             )
-            if plot_epoch_progression:
+            epoch_num = int(self.util.config_val("EXP", "epochs", 1))
+            if epoch_num > 1 and plot_epoch_progression:
                 plot_name_suggest = self.util.get_exp_name()
                 plot_name = (
                     self.util.config_val("PLOT", "name", plot_name_suggest)
@@ -81,7 +82,8 @@ class Runmanager:
             # remember the best run
             best_report = self.get_best_result(self.reports)
             plot_best_model = self.util.config_val("PLOT", "best_model", False)
-            if plot_best_model:
+
+            if epoch_num > 1 and plot_best_model:
                 plot_name_suggest = self.util.get_exp_name()
                 plot_name = (
                     self.util.config_val("PLOT", "name", plot_name_suggest)

nkululeko/scaler.py

@@ -1,8 +1,9 @@
 # scaler.py
 
-
+import numpy as np
 from sklearn.preprocessing import StandardScaler, RobustScaler
 import pandas as pd
+
 from nkululeko.utils.util import Util
 
 
@@ -32,6 +33,8 @@ class Scaler:
             self.scaler = RobustScaler()
         elif scaler_type == "speaker":
             self.scaler = StandardScaler()
+        elif scaler_type == "bins":
+            pass
         else:
             self.util.error("unknown scaler: " + scaler_type)
         self.scaler_type = scaler_type
@@ -56,10 +59,13 @@ class Scaler:
             return self.speaker_scale()
 
     def scale_all(self):
-        self.scaler.fit(self.feats_train.values)
-        self.feats_train = self.scale_df(self.feats_train)
-        if self.feats_test is not None:
-            self.feats_test = self.scale_df(self.feats_test)
+        if self.scaler_type != "bins":
+            self.scaler.fit(self.feats_train.values)
+            self.feats_train = self.scale_df(self.feats_train)
+            if self.feats_test is not None:
+                self.feats_test = self.scale_df(self.feats_test)
+        else:
+            self.bin_to_three()
         return self.feats_train, self.feats_test
 
     def scale_df(self, df):
@@ -80,3 +86,23 @@ class Scaler:
                 feats_df.loc[indices, :]
             )
         return feats_df
+
+    def bin_to_three(self):
+        feats_bin_train = pd.DataFrame(index=self.feats_train.index)
+        feats_bin_test = pd.DataFrame(index=self.feats_test.index)
+        for c in self.feats_train.columns:
+            b1 = np.quantile(self.feats_train[c], 0.33)
+            b2 = np.quantile(self.feats_train[c], 0.66)
+            feats_bin_train[c] = self._bin(self.feats_train[c].values, b1, b2).values
+            feats_bin_test[c] = self._bin(self.feats_test[c].values, b1, b2).values
+        self.feats_train = feats_bin_train
+        self.feats_test = feats_bin_test
+
+    def _bin(self, series, b1, b2):
+        bins = [-1000000, b1, b2, 1000000]
+        labels = [0, 0.5, 1]
+        result = np.digitize(series, bins) - 1
+        result = pd.Series(result)
+        for i, l in enumerate(labels):
+            result = result.replace(i, str(l))
+        return result

nkululeko/utils/util.py

@@ -195,6 +195,7 @@ class Util:
             ["MODEL", "learning_rate"],
             ["MODEL", "k_fold_cross"],
             ["FEATS", "balancing"],
+            ["FEATS", "scale"],
         ]
         for option in options:
             return_string += self._get_value_descript(option[0], option[1])
@@ -306,7 +307,13 @@ class Util:
         elif format == "csv":
             return audformat.utils.read_csv(name)
         else:
-            self.error(f"unkown store format: {format}")
+            self.error(f"unknown store format: {format}")
+
+    def save_to_store(self, df, name):
+        store = self.get_path("store")
+        store_format = self.config_val("FEATS", "store_format", "pkl")
+        storage = f"{store}{name}.{store_format}"
+        self.write_store(df, storage, store_format)
 
     def copy_flags(self, df_source, df_target):
         if hasattr(df_source, "is_labeled"):

{nkululeko-0.77.12.dist-info → nkululeko-0.77.14.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: nkululeko
-Version: 0.77.12
+Version: 0.77.14
 Summary: Machine learning audio prediction experiments based on templates
 Home-page: https://github.com/felixbur/nkululeko
 Author: Felix Burkhardt
@@ -313,6 +313,14 @@ F. Burkhardt, Johannes Wagner, Hagen Wierstorf, Florian Eyben and Björn Schulle
 Changelog
 =========
 
+Version 0.77.14
+--------------
+* fixed bug preventing bin scaling to work
+
+Version 0.77.13
+--------------
+* added bins scaler
+
 Version 0.77.12
 --------------
 * fixed bug with scatter plots for numeric targets

{nkululeko-0.77.12.dist-info → nkululeko-0.77.14.dist-info}/RECORD

@@ -2,10 +2,10 @@ nkululeko/__init__.py,sha256=62f8HiEzJ8rG2QlTFJXUCMpvuH3fKI33DoJSj33mscc,63
 nkululeko/aug_train.py,sha256=uUCqtAGhT6P1dyrPpwT409wEhxfzsxpCiq_v_zdmfOI,3103
 nkululeko/augment.py,sha256=sHWG4Jmb4BjnaaXXnRYMP7Jkk0qlaZ2ohsArP8uW_d8,3003
 nkululeko/cacheddataset.py,sha256=lIJ6hUo5LoxSrzXtWV8mzwO7wRtUETWnOQ4ws2XfL1E,969
-nkululeko/constants.py,sha256=JTIgRsrAXrRFfjOclO-_iuTezcoxwsNZnEJMftgAcL4,40
+nkululeko/constants.py,sha256=Kax1gid7oVUaohOaTJKyxLVvRCHD3meNk_AuLxVrhV0,40
 nkululeko/demo.py,sha256=FFR8qHMCY8kKKRWDTa8xA7A8mWeYalRKYNtV5rjGg44,1915
 nkululeko/demo_predictor.py,sha256=j4ySWWcIxW7ZAIBH86m9BfRFokzrUNkRD6fpsvAQGTw,2629
-nkululeko/experiment.py,sha256=g-GdcvcWyQKj70VutyFPuzSxmsD-Tk_-vY-5FM7dszs,28644
+nkululeko/experiment.py,sha256=znrMTpGqNeBQWD0F7sUHzQyRjCxsRH9t3V_8NhAtzrg,28823
 nkululeko/explore.py,sha256=pfciOL66e0T4Bk0RTkwDyE6pK_baSUdjMo2Ybpst3L4,2202
 nkululeko/export.py,sha256=mHeEAAmtZuxdyebLlbSzPrHSi9OMgJHbk35d3DTxRBc,4632
 nkululeko/feature_extractor.py,sha256=tKv1b1-o7xNMgBavTR8VY8_H5HKoJEnnosS-KcjmOEU,7281
@@ -20,8 +20,8 @@ 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
 nkululeko/result.py,sha256=HeiOrrqf9W2yxMryN33zgEmQejNWRxNmm589AYt6-eM,499
-nkululeko/runmanager.py,sha256=HjAesq19ZbDg5imMOjhqnt063W7JGggm6bY06h6bfM8,7085
-nkululeko/scaler.py,sha256=HVXMjmzDAj87K9O4aPU6aeqBk-ACVzQBTHOf1RwDCaM,3055
+nkululeko/runmanager.py,sha256=WoZ4cRyHV7kAhtt-55RAAj6D3iXqEvvEMm6Ll4YkV2E,7192
+nkululeko/scaler.py,sha256=4nkIqoajkIkuTPK0Z02ifMN_awl6fP_i-GBYdoGYgGM,4101
 nkululeko/segment.py,sha256=DfJYZsCEH41gwKyjpMgv8kWUzfVkmC0wWTbgHOL4i4g,4787
 nkululeko/syllable_nuclei.py,sha256=Sky-C__MeUDaxqHnDl2TGLLYOYvsahD35TUjWGeG31k,10047
 nkululeko/test.py,sha256=cRtOn_d3Fh2kZmnT4nnQeGzZTRtpr5jRhowykOwunME,1421
@@ -99,9 +99,9 @@ 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=TuMXUXAxB8lkra8ttc1TssPIsJA0K6vh7JhfKEqBwPs,11953
-nkululeko-0.77.12.dist-info/LICENSE,sha256=0zGP5B_W35yAcGfHPS18Q2B8UhvLRY3dQq1MhpsJU_U,1076
-nkululeko-0.77.12.dist-info/METADATA,sha256=bGkRQ6NFwjZ0t_IqUDEqn2jEVr0OQre6bWiIbDNeJog,31409
-nkululeko-0.77.12.dist-info/WHEEL,sha256=oiQVh_5PnQM0E3gPdiz09WCNmwiHDMaGer_elqB3coM,92
-nkululeko-0.77.12.dist-info/top_level.txt,sha256=DPFNNSHPjUeVKj44dVANAjuVGRCC3MusJ08lc2a8xFA,10
-nkululeko-0.77.12.dist-info/RECORD,,
+nkululeko/utils/util.py,sha256=Ibwco798iDhmamO7SjVStfxOl-DNBdzkKl2HniYgoNE,12238
+nkululeko-0.77.14.dist-info/LICENSE,sha256=0zGP5B_W35yAcGfHPS18Q2B8UhvLRY3dQq1MhpsJU_U,1076
+nkululeko-0.77.14.dist-info/METADATA,sha256=OOdBC4qOLKkaM4QbNYdGilyrrrdMUFpEedmpyr9wU9A,31536
+nkululeko-0.77.14.dist-info/WHEEL,sha256=oiQVh_5PnQM0E3gPdiz09WCNmwiHDMaGer_elqB3coM,92
+nkululeko-0.77.14.dist-info/top_level.txt,sha256=DPFNNSHPjUeVKj44dVANAjuVGRCC3MusJ08lc2a8xFA,10
+nkululeko-0.77.14.dist-info/RECORD,,