nkululeko 0.93.3__py3-none-any.whl → 0.93.5__py3-none-any.whl

nkululeko/constants.py

@@ -1,2 +1,2 @@
-VERSION="0.93.3"
+VERSION="0.93.5"
 SAMPLING_RATE = 16000

nkululeko/data/dataset.py

@@ -4,12 +4,13 @@ import os
 import os.path
 from random import sample
 
-import audformat
 import numpy as np
 import pandas as pd
 
-import nkululeko.glob_conf as glob_conf
+import audformat
+
 from nkululeko.filter_data import DataFilter
+import nkululeko.glob_conf as glob_conf
 from nkululeko.plots import Plots
 from nkululeko.reporting.report_item import ReportItem
 from nkululeko.utils.util import Util
@@ -32,6 +33,9 @@ class Dataset:
         self.target = self.util.config_val("DATA", "target", "none")
         self.plot = Plots()
         self.limit = int(self.util.config_val_data(self.name, "limit", 0))
+        self.target_tables_append = eval(
+            self.util.config_val_data(self.name, "target_tables_append", "False")
+        )
         self.start_fresh = eval(self.util.config_val("DATA", "no_reuse", "False"))
         self.is_labeled, self.got_speaker, self.got_gender, self.got_age = (
             False,
@@ -321,7 +325,12 @@ class Dataset:
             for column in source_df.columns:
                 if column not in [self.target, "age", "speaker", "gender"]:
                     df_local[column] = source_df[column]
-            df = pd.concat([df, df_local])
+            # ensure segmented index
+            df_local = self.util.make_segmented_index(df_local)
+            if self.target_tables_append:
+                df = pd.concat([df, df_local], axis=0)
+            else:
+                df = pd.concat([df, df_local], axis=1)
         return df, is_labeled, got_speaker, got_gender, got_age
 
     def split(self):

nkululeko/plots.py

@@ -23,6 +23,7 @@ class Plots:
         self.util = Util("plots")
         self.format = self.util.config_val("PLOT", "format", "png")
         self.target = self.util.config_val("DATA", "target", "emotion")
+        self.with_ccc = eval(self.util.config_val("PLOT", "ccc", "False"))
 
     def plot_distributions_speaker(self, df):
         df_speakers = pd.DataFrame()
@@ -254,9 +255,11 @@ class Plots:
         # trunc to three digits
         pearson = int(pearson[0] * 1000) / 1000
         pearson_string = f"PCC: {pearson}"
-        ccc_val = ccc(df[cont1], df[cont2])
-        ccc_val = int(ccc_val * 1000) / 1000
-        ccc_string = f"CCC: {ccc_val}"
+        ccc_string = ""
+        if self.with_ccc:
+            ccc_val = ccc(df[cont1], df[cont2])
+            ccc_val = int(ccc_val * 1000) / 1000
+            ccc_string = f"CCC: {ccc_val}"
         ax = sns.lmplot(data=df, x=cont1, y=cont2, hue=cat)
         caption = f"{ylab} {df.shape[0]}. {pearson_string} {ccc_string}"
         ax.figure.suptitle(caption)
@@ -275,9 +278,11 @@ class Plots:
         # trunc to three digits
         pearson = int(pearson[0] * 1000) / 1000
         pearson_string = f"PCC: {pearson}"
-        ccc_val = ccc(df[col1], df[col2])
-        ccc_val = int(ccc_val * 1000) / 1000
-        ccc_string = f"CCC: {ccc_val}"
+        ccc_string = ""
+        if self.with_ccc:
+            ccc_val = ccc(df[col1], df[col2])
+            ccc_val = int(ccc_val * 1000) / 1000
+            ccc_string = f"CCC: {ccc_val}"
         ax = sns.lmplot(data=df, x=col1, y=col2)
         caption = f"{ylab} {df.shape[0]}. {pearson_string} {ccc_string}"
         ax.figure.suptitle(caption)

{nkululeko-0.93.3.dist-info → nkululeko-0.93.5.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: nkululeko
-Version: 0.93.3
+Version: 0.93.5
 Summary: Machine learning audio prediction experiments based on templates
 Home-page: https://github.com/felixbur/nkululeko
 Author: Felix Burkhardt
@@ -355,6 +355,14 @@ If you use it, please mention the Nkululeko paper:
 Changelog
 =========
 
+Version 0.93.5
+--------------
+* fixed bug in dataset loading
+
+Version 0.93.4
+--------------
+* ccc in plots now configurable
+
 Version 0.93.3
 --------------
 * bugfix in plot

{nkululeko-0.93.3.dist-info → nkululeko-0.93.5.dist-info}/RECORD

@@ -2,7 +2,7 @@ nkululeko/__init__.py,sha256=62f8HiEzJ8rG2QlTFJXUCMpvuH3fKI33DoJSj33mscc,63
 nkululeko/aug_train.py,sha256=FoMbBrfyOZd4QAw7oIHl3X6-UpsqAKWVDIolCA7qOWs,3196
 nkululeko/augment.py,sha256=3RzaxB3gRxovgJVjHXi0glprW01J7RaHhUkqotW2T3U,2955
 nkululeko/cacheddataset.py,sha256=XFpWZmbJRg0pvhnIgYf0TkclxllD-Fctu-Ol0PF_00c,969
-nkululeko/constants.py,sha256=xkELXQg1phRJClie00O45xP9PEuZrgYAjtasyw7ugh4,39
+nkululeko/constants.py,sha256=C8IWm94GcdzMn6m8oSMid5_Ge80ZE0G3kHVztYte-Zg,39
 nkululeko/demo-ft.py,sha256=iD9Pzp9QjyAv31q1cDZ75vPez7Ve8A4Cfukv5yfZdrQ,770
 nkululeko/demo.py,sha256=4Yzhg6pCPBYPGJrP7JX2TysVosl_R1llpVDKc2P_gUA,4955
 nkululeko/demo_feats.py,sha256=BvZjeNFTlERIRlq34OHM4Z96jdDQAhB01BGQAUcX9dM,2026
@@ -20,7 +20,7 @@ nkululeko/modelrunner.py,sha256=lJy-xM4QfDDWeL0dLTE_VIb4sYrnd_Z_yJRK3wwohQA,1119
 nkululeko/multidb.py,sha256=sO6OwJn8sn1-C-ig3thsIL8QMWHdV9SnJhDodKjeKrI,6876
 nkululeko/nkuluflag.py,sha256=PGWSmZz-PiiHLgcZJAoGOI_Y-sZDVI1ksB8p5r7riWM,3725
 nkululeko/nkululeko.py,sha256=M7baIq2nAoi6dEoBL4ATEuqAs5U1fvl_hyqAl5DybAQ,2040
-nkululeko/plots.py,sha256=Qt81dEo0yW6Cms8prLv-qRerlSDaATYTPwjCxQpurdM,25076
+nkululeko/plots.py,sha256=emn2NpZyOGlC8pw0NdAGRbUkPzZzbOKFO50HZ7vJG40,25275
 nkululeko/predict.py,sha256=MLnHEyFmSiHLLs-HDczag8Vu3zKF5T1rXLKdZZJ6py8,2083
 nkululeko/resample.py,sha256=akSAjJ3qn-O5NAyLJHVHdsK7MUZPGaZUvM2TwMSmj2M,5194
 nkululeko/runmanager.py,sha256=AswmORVUkCIH0gTx6zEyufvFATQBS8C5TXo2erSNdVg,7611
@@ -49,7 +49,7 @@ nkululeko/autopredict/ap_stoi.py,sha256=UEQg1ZV0meAsxgdWB8ieRs9GPXHqArmsaOyCGRwp
 nkululeko/autopredict/ap_valence.py,sha256=WrW4Ltqi_odW49_4QEVKkfnrcztLIVZ4cXIEHu4dBN8,1026
 nkululeko/autopredict/estimate_snr.py,sha256=1k9-XadABudnsNOeFZD_Fg0E64-GUQVS7JEp82MLQS4,4995
 nkululeko/data/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-nkululeko/data/dataset.py,sha256=Hz2IOsdcESG-P3aP7r4d1xj_gIP6fyGCYOwukoQ7SM8,29321
+nkululeko/data/dataset.py,sha256=BiSKTnEOy6izgL2KOGNPfyq10MfGEWRqud1ksBdFaVU,29684
 nkululeko/data/dataset_csv.py,sha256=p2b4eS5R2Q5zdOIc56NRRU2PTFXSRt0qrdHGafHkWKo,4830
 nkululeko/feat_extract/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nkululeko/feat_extract/feats_agender.py,sha256=onfAQ6-xx_mFMJXEF1IX8cHBmGtGeX6weJmxbkfh1_o,3184
@@ -112,9 +112,9 @@ nkululeko/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nkululeko/utils/files.py,sha256=SrrYaU7AB80MZHiV1jcB0h_zigvYLYgSVNTXV4ao38g,4593
 nkululeko/utils/stats.py,sha256=vCRzhCR0Gx5SiJyAGbj1TIto8ocGz58CM5Pr3LltagA,2948
 nkululeko/utils/util.py,sha256=wFDslqxpCVDwi6LBakIFDDy1kYsxt5G7ykE38CocmtA,16880
-nkululeko-0.93.3.dist-info/LICENSE,sha256=0zGP5B_W35yAcGfHPS18Q2B8UhvLRY3dQq1MhpsJU_U,1076
-nkululeko-0.93.3.dist-info/METADATA,sha256=7yXY_U3k5TXa_ief57WrmWiLS7ov_FtviWCCH9LUoBg,42147
-nkululeko-0.93.3.dist-info/WHEEL,sha256=R06PA3UVYHThwHvxuRWMqaGcr-PuniXahwjmQRFMEkY,91
-nkululeko-0.93.3.dist-info/entry_points.txt,sha256=lNTkFEdh6Kjo5o95ZAWf_0Lq-4ztGoAoMVSDuPtuyS0,442
-nkululeko-0.93.3.dist-info/top_level.txt,sha256=DPFNNSHPjUeVKj44dVANAjuVGRCC3MusJ08lc2a8xFA,10
-nkululeko-0.93.3.dist-info/RECORD,,
+nkululeko-0.93.5.dist-info/LICENSE,sha256=0zGP5B_W35yAcGfHPS18Q2B8UhvLRY3dQq1MhpsJU_U,1076
+nkululeko-0.93.5.dist-info/METADATA,sha256=M_KF6W0eH4I4Iou871Dj9AKEAdfLacQyigFpVJeqz2w,42272
+nkululeko-0.93.5.dist-info/WHEEL,sha256=R06PA3UVYHThwHvxuRWMqaGcr-PuniXahwjmQRFMEkY,91
+nkululeko-0.93.5.dist-info/entry_points.txt,sha256=lNTkFEdh6Kjo5o95ZAWf_0Lq-4ztGoAoMVSDuPtuyS0,442
+nkululeko-0.93.5.dist-info/top_level.txt,sha256=DPFNNSHPjUeVKj44dVANAjuVGRCC3MusJ08lc2a8xFA,10
+nkululeko-0.93.5.dist-info/RECORD,,