nkululeko 0.92.0__py3-none-any.whl → 0.92.2__py3-none-any.whl

nkululeko/constants.py

@@ -1,2 +1,2 @@
-VERSION="0.92.0"
+VERSION="0.92.2"
 SAMPLING_RATE = 16000

nkululeko/plots.py

@@ -4,14 +4,14 @@ import ast
 import matplotlib.pyplot as plt
 import numpy as np
 import pandas as pd
-import seaborn as sns
 from scipy import stats
+import seaborn as sns
 from sklearn.manifold import TSNE
 
 import nkululeko.glob_conf as glob_conf
-import nkululeko.utils.stats as su
 from nkululeko.reporting.defines import Header
 from nkululeko.reporting.report_item import ReportItem
+import nkululeko.utils.stats as su
 from nkululeko.utils.util import Util
 
 
@@ -30,8 +30,6 @@ class Plots:
             df_speaker["samplenum"] = df_speaker.shape[0]
             df_speakers = pd.concat([df_speakers, df_speaker.head(1)])
         # plot the distribution of samples per speaker
-        # one up because of the runs
-        fig_dir = self.util.get_path("fig_dir") + "../"
         self.util.debug("plotting samples per speaker")
         if "gender" in df_speakers:
             filename = "samples_value_counts"
@@ -319,6 +317,31 @@ class Plots:
         img_path = f"{fig_dir}{filename}_{sample_selection}.{self.format}"
         plt.savefig(img_path)
         plt.close(fig)
+        self.util.debug(f"plotted durations to {img_path}")
+        glob_conf.report.add_item(
+            ReportItem(
+                Header.HEADER_EXPLORE,
+                caption,
+                title,
+                img_path,
+            )
+        )
+
+    def plot_speakers(self, df, sample_selection):
+        filename = "speakers"
+        caption = "speakers"
+        # one up because of the runs
+        fig_dir = self.util.get_path("fig_dir") + "../"
+        sns.set_style("whitegrid")  # Set style for chart
+        ax = df["speaker"].value_counts().plot(kind="pie", autopct="%1.1f%%")
+        title = f"Speaker distr. for {sample_selection} {df.shape[0]}."
+        ax.set_title(title)
+        fig = ax.figure
+        # plt.tight_layout()
+        img_path = f"{fig_dir}{filename}_{sample_selection}.{self.format}"
+        plt.savefig(img_path)
+        plt.close(fig)
+        self.util.debug(f"plotted speakers to {img_path}")
         glob_conf.report.add_item(
             ReportItem(
                 Header.HEADER_EXPLORE,

nkululeko/segment.py

@@ -23,6 +23,8 @@ import os
 
 import pandas as pd
 
+import audformat
+
 from nkululeko.constants import VERSION
 from nkululeko.experiment import Experiment
 import nkululeko.glob_conf as glob_conf
@@ -63,7 +65,7 @@ def main():
     # segment
     segmented_file = util.config_val("SEGMENT", "result", "segmented.csv")
 
-    segmenter = util.config_val("SEGMENT", "method", "silero")
+    method = util.config_val("SEGMENT", "method", "silero")
     sample_selection = util.config_val("SEGMENT", "sample_selection", "all")
     if sample_selection == "all":
         df = pd.concat([expr.df_train, expr.df_test])
@@ -76,19 +78,33 @@ def main():
             f"unknown segmentation selection specifier {sample_selection},"
             " should be [all | train | test]"
         )
-    util.debug(f"segmenting {sample_selection}: {df.shape[0]} samples with {segmenter}")
-    if segmenter == "silero":
-        from nkululeko.segmenting.seg_silero import Silero_segmenter
-
-        segmenter = Silero_segmenter()
-        df_seg = segmenter.segment_dataframe(df)
-    elif segmenter == "pyannote":
-        from nkululeko.segmenting.seg_pyannote import Pyannote_segmenter
-
-        segmenter = Pyannote_segmenter(config)
-        df_seg = segmenter.segment_dataframe(df)
+    result_file = f"{expr.data_dir}/{segmented_file}"
+    if os.path.exists(result_file):
+        util.debug(f"reusing existing result file: {result_file}")
+        df_seg = audformat.utils.read_csv(result_file)
     else:
-        util.error(f"unknown segmenter: {segmenter}")
+        util.debug(
+            f"segmenting {sample_selection}: {df.shape[0]} samples with {method}"
+        )
+        if method == "silero":
+            from nkululeko.segmenting.seg_silero import Silero_segmenter
+
+            segmenter = Silero_segmenter()
+            df_seg = segmenter.segment_dataframe(df)
+        elif method == "pyannote":
+            from nkululeko.segmenting.seg_pyannote import Pyannote_segmenter
+
+            segmenter = Pyannote_segmenter(config)
+            df_seg = segmenter.segment_dataframe(df)
+        else:
+            util.error(f"unknown segmenter: {method}")
+        # remove encoded labels
+        target = util.config_val("DATA", "target", None)
+        if "class_label" in df_seg.columns:
+            df_seg = df_seg.drop(columns=[target])
+            df_seg = df_seg.rename(columns={"class_label": target})
+        # save file
+        df_seg.to_csv(f"{expr.data_dir}/{segmented_file}")
 
     def calc_dur(x):
         starts = x[1]
@@ -100,6 +116,11 @@ def main():
     df_seg["duration"] = df_seg.index.to_series().map(lambda x: calc_dur(x))
     num_before = df.shape[0]
     num_after = df_seg.shape[0]
+    util.debug(
+        f"saved {segmented_file} to {expr.data_dir}, {num_after} samples (was"
+        f" {num_before})"
+    )
+
     # plot distributions
     from nkululeko.plots import Plots
 
@@ -110,18 +131,10 @@ def main():
     plots.plot_durations(
         df_seg, "segmented_durations", sample_selection, caption="Segmented durations"
     )
-    print("")
-    # remove encoded labels
-    target = util.config_val("DATA", "target", None)
-    if "class_label" in df_seg.columns:
-        df_seg = df_seg.drop(columns=[target])
-        df_seg = df_seg.rename(columns={"class_label": target})
-    # save file
-    df_seg.to_csv(f"{expr.data_dir}/{segmented_file}")
-    util.debug(
-        f"saved {segmented_file} to {expr.data_dir}, {num_after} samples (was"
-        f" {num_before})"
-    )
+    if method == "pyannote":
+        util.debug(df_seg[["speaker", "duration"]].groupby(["speaker"]).sum())
+        plots.plot_speakers(df_seg, sample_selection)
+
     glob_conf.report.add_item(
         ReportItem(
             "Data",

{nkululeko-0.92.0.dist-info → nkululeko-0.92.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: nkululeko
-Version: 0.92.0
+Version: 0.92.2
 Summary: Machine learning audio prediction experiments based on templates
 Home-page: https://github.com/felixbur/nkululeko
 Author: Felix Burkhardt
@@ -355,6 +355,14 @@ F. Burkhardt, Johannes Wagner, Hagen Wierstorf, Florian Eyben and Björn Schulle
 Changelog
 =========
 
+Version 0.92.2
+--------------
+* added some output to automatic speaker id
+
+Version 0.92.1
+--------------
+* added a speaker plot to pyannote results 
+
 Version 0.92.0
 --------------
 * added first version of automatic speaker prediction/segmentation

{nkululeko-0.92.0.dist-info → nkululeko-0.92.2.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=trIGnE99KWCznIwZEph-SDuz9A8bzck2v0Md4VgZzMY,39
+nkululeko/constants.py,sha256=HBBuhT6kpIHhRMiSBkU07cszGO7kO2A8qTYrN6zH9rw,39
 nkululeko/demo-ft.py,sha256=iD9Pzp9QjyAv31q1cDZ75vPez7Ve8A4Cfukv5yfZdrQ,770
 nkululeko/demo.py,sha256=4Yzhg6pCPBYPGJrP7JX2TysVosl_R1llpVDKc2P_gUA,4955
 nkululeko/demo_feats.py,sha256=BvZjeNFTlERIRlq34OHM4Z96jdDQAhB01BGQAUcX9dM,2026
@@ -20,12 +20,12 @@ 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=sR061gOsyvuh8UBYS52FINSal4CYNQgvq3B4WOSimDw,23092
+nkululeko/plots.py,sha256=dK3jVwsZufqXgHwAvDYt6uDg_KYk5cfxlP1Fo8kb9HA,23935
 nkululeko/predict.py,sha256=MLnHEyFmSiHLLs-HDczag8Vu3zKF5T1rXLKdZZJ6py8,2083
 nkululeko/resample.py,sha256=akSAjJ3qn-O5NAyLJHVHdsK7MUZPGaZUvM2TwMSmj2M,5194
 nkululeko/runmanager.py,sha256=AswmORVUkCIH0gTx6zEyufvFATQBS8C5TXo2erSNdVg,7611
 nkululeko/scaler.py,sha256=7VOZ4sREMoQtahfETt9RyuR29Fb7PCwxlYVjBbdCVFc,4101
-nkululeko/segment.py,sha256=CEKfvKrvq-XbciluOkgGLLe7DQO9PLSFGw8rMsFpDVQ,4476
+nkululeko/segment.py,sha256=DRjC6b7SeInYgwBcDPXpTXPvXPS-J8kFQO7H095bK80,4945
 nkululeko/syllable_nuclei.py,sha256=5w_naKxNxz66a_qLkraemi2fggM-gWesiiBPS47iFcE,9931
 nkululeko/test.py,sha256=1w624vo5KTzmFC8BUStGlLDmIEAFuJUz7J0W-gp7AxI,1677
 nkululeko/test_predictor.py,sha256=DEHE_D3A6m6KJTrpDKceA1n655t_UZV3WQd57K4a3Ho,2863
@@ -112,9 +112,9 @@ nkululeko/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nkululeko/utils/files.py,sha256=UiGAtZRWYjHSvlmPaTMtzyNNGE6qaLaxQkybctS7iRM,4021
 nkululeko/utils/stats.py,sha256=vCRzhCR0Gx5SiJyAGbj1TIto8ocGz58CM5Pr3LltagA,2948
 nkululeko/utils/util.py,sha256=XFZdhCc_LM4EmoZ5tKKaBCQLXclcNmvHwhfT_CXB98c,16723
-nkululeko-0.92.0.dist-info/LICENSE,sha256=0zGP5B_W35yAcGfHPS18Q2B8UhvLRY3dQq1MhpsJU_U,1076
-nkululeko-0.92.0.dist-info/METADATA,sha256=-So3jBO4lGif0bmb4KgDxFV4p-EyR7u1eejB8mEhotA,41682
-nkululeko-0.92.0.dist-info/WHEEL,sha256=P9jw-gEje8ByB7_hXoICnHtVCrEwMQh-630tKvQWehc,91
-nkululeko-0.92.0.dist-info/entry_points.txt,sha256=lNTkFEdh6Kjo5o95ZAWf_0Lq-4ztGoAoMVSDuPtuyS0,442
-nkululeko-0.92.0.dist-info/top_level.txt,sha256=DPFNNSHPjUeVKj44dVANAjuVGRCC3MusJ08lc2a8xFA,10
-nkululeko-0.92.0.dist-info/RECORD,,
+nkululeko-0.92.2.dist-info/LICENSE,sha256=0zGP5B_W35yAcGfHPS18Q2B8UhvLRY3dQq1MhpsJU_U,1076
+nkululeko-0.92.2.dist-info/METADATA,sha256=pwdxFGECc-W2WdmnXxgJz6Jy3CbvwzeHASfu7WxFK7g,41832
+nkululeko-0.92.2.dist-info/WHEEL,sha256=P9jw-gEje8ByB7_hXoICnHtVCrEwMQh-630tKvQWehc,91
+nkululeko-0.92.2.dist-info/entry_points.txt,sha256=lNTkFEdh6Kjo5o95ZAWf_0Lq-4ztGoAoMVSDuPtuyS0,442
+nkululeko-0.92.2.dist-info/top_level.txt,sha256=DPFNNSHPjUeVKj44dVANAjuVGRCC3MusJ08lc2a8xFA,10
+nkululeko-0.92.2.dist-info/RECORD,,