nkululeko 0.66.4__py3-none-any.whl → 0.66.5__py3-none-any.whl

nkululeko/constants.py

@@ -1,2 +1,2 @@
-VERSION="0.66.4"
+VERSION="0.66.5"
 SAMPLING_RATE = 16000

nkululeko/data/dataset.py

@@ -82,7 +82,9 @@ class Dataset:
             f" {self.got_speaker} ({speaker_num}), got sexes: {self.got_gender}"
         )
         self.util.debug(r_string)
-        glob_conf.report.add_item(ReportItem("Data", "Load report", r_string))
+        if glob_conf.report.initial:
+            glob_conf.report.add_item(ReportItem("Data", "Load report", r_string))
+            glob_conf.report.initial = False
 
     def load(self):
         """Load the dataframe with files, speakers and task labels"""

nkululeko/plots.py

@@ -10,6 +10,7 @@ from nkululeko.util import Util
 import nkululeko.utils.stats as su
 import nkululeko.glob_conf as glob_conf
 from nkululeko.reporting.report_item import ReportItem
+from nkululeko.reporting.defines import Header
 
 
 class Plots:
@@ -26,7 +27,7 @@ class Plots:
             df_speaker = df[df.speaker == s]
             df_speaker["samplenum"] = df_speaker.shape[0]
             df_speakers = pd.concat([df_speakers, df_speaker.head(1)])
-        # plot the distrubution of samples per speaker
+        # plot the distribution of samples per speaker
         fig_dir = self.util.get_path("fig_dir") + "../"  # one up because of the runs
         self.util.debug(f"plotting samples per speaker")
         if "gender" in df_speakers:
@@ -51,7 +52,7 @@ class Plots:
             plt.close(fig)
             glob_conf.report.add_item(
                 ReportItem(
-                    "Data exploration",
+                    Header.HEADER_EXPLORE,
                     "Samples per speaker",
                     f"Samples per speaker ({df_speakers.shape[0]})",
                     img_path,
@@ -81,13 +82,12 @@ class Plots:
             fig.clear()
             glob_conf.report.add_item(
                 ReportItem(
-                    "Data exploration",
+                    Header.HEADER_EXPLORE,
                     "Sample value counts",
                     f"Samples per speaker ({df_speakers.shape[0]})",
                     img_path,
                 )
             )
-
         self.plot_distributions(df_speakers, type="speakers")
 
     def plot_distributions(self, df, type="samples"):
@@ -154,8 +154,8 @@ class Plots:
                 plt.close(fig)
                 glob_conf.report.add_item(
                     ReportItem(
-                        "Data exploration",
-                        f'Correlation of {self.target} and {att[0]}',
+                        Header.HEADER_EXPLORE,
+                        f"Correlation of {self.target} and {att[0]}",
                         caption,
                         img_path,
                     )
@@ -194,7 +194,7 @@ class Plots:
                     f" {att} has more than 2 values"
                 )
 
-    def plot_durations(self, df, filename, sample_selection, caption=''):
+    def plot_durations(self, df, filename, sample_selection, caption=""):
         fig_dir = self.util.get_path("fig_dir") + "../"  # one up because of the runs
         try:
             ax = sns.histplot(df, x="duration", hue="class_label", kde=True)
@@ -207,12 +207,12 @@ class Plots:
         ax.set_ylabel(f"number of samples")
         fig = ax.figure
         plt.tight_layout()
-        img_path = f"{fig_dir}{filename}_{sample_selection}.{self.format}" 
+        img_path = f"{fig_dir}{filename}_{sample_selection}.{self.format}"
         plt.savefig(img_path)
         plt.close(fig)
         glob_conf.report.add_item(
             ReportItem(
-                "Data exploration",
+                Header.HEADER_EXPLORE,
                 caption,
                 title,
                 img_path,

nkululeko/reporter.py

@@ -1,6 +1,7 @@
+import glob
+import math
 import matplotlib.pyplot as plt
 from sklearn.utils import resample
-from nkululeko.util import Util
 import ast
 import json
 import numpy as np
@@ -15,8 +16,8 @@ from sklearn.metrics import classification_report
 from scipy.stats import pearsonr
 from nkululeko.result import Result
 from nkululeko.reporting.report_item import ReportItem
-import glob
-import math
+from nkululeko.reporting.defines import Header
+from nkululeko.util import Util
 
 
 class Reporter:
@@ -55,9 +56,7 @@ class Reporter:
             else:
                 # regression experiment
                 if self.measure == "mse":
-                    self.result.test = mean_squared_error(
-                        self.truths, self.preds
-                    )
+                    self.result.test = mean_squared_error(self.truths, self.preds)
                 elif self.measure == "ccc":
                     self.result.test = self.ccc(self.truths, self.preds)
                     if math.isnan(self.result.test):
@@ -145,15 +144,24 @@ class Reporter:
             reg_res = f", {self.MEASURE}: {self.result.test:.3f}"
 
         if epoch != 0:
-            plt.title(
-                f"Confusion Matrix, UAR: {uar:.3f}{reg_res}, Epoch: {epoch}"
-            )
+            plt.title(f"Confusion Matrix, UAR: {uar:.3f}{reg_res}, Epoch: {epoch}")
         else:
             plt.title(f"Confusion Matrix, UAR: {uar:.3f}{reg_res}")
-
-        plt.savefig(f"{fig_dir}{plot_name}.{self.format}")
+        img_path = f"{fig_dir}{plot_name}.{self.format}"
+        plt.savefig(img_path)
         fig.clear()
         plt.close(fig)
+        plt.savefig(img_path)
+        plt.close(fig)
+        glob_conf.report.add_item(
+            ReportItem(
+                Header.HEADER_RESULTS,
+                self.util.get_model_description(),
+                "Confusion matrix",
+                img_path,
+            )
+        )
+
         res_dir = self.util.get_path("res_dir")
         rpt = f"epoch: {epoch}, UAR: {uar}, ACC {acc}"
         file_name = f"{res_dir}{self.util.get_exp_name()}_conf.txt"
@@ -181,8 +189,7 @@ class Reporter:
             except ValueError as e:
                 self.util.debug(
                     "Reporter: caught a ValueError when trying to get"
-                    " classification_report: "
-                    + e
+                    " classification_report: " + e
                 )
                 rpt = self.result.to_string()
             with open(file_name, "w") as text_file:
@@ -196,7 +203,11 @@ class Reporter:
                 rpt_str = f"{json.dumps(rpt)}\n{f1_per_class}"
                 text_file.write(rpt_str)
                 glob_conf.report.add_item(
-                    ReportItem("Results", "Classification result", rpt_str)
+                    ReportItem(
+                        Header.HEADER_RESULTS,
+                        f"Classification result {self.util.get_model_description()}",
+                        rpt_str,
+                    )
                 )
 
         else:  # regression
@@ -213,9 +224,7 @@ class Reporter:
         import imageio
 
         fig_dir = self.util.get_path("fig_dir")
-        filenames = glob.glob(
-            fig_dir + f"{self.util.get_plot_name()}*_?_???_cnf.png"
-        )
+        filenames = glob.glob(fig_dir + f"{self.util.get_plot_name()}*_?_???_cnf.png")
         images = []
         for filename in filenames:
             images.append(imageio.imread(filename))
@@ -269,9 +278,7 @@ class Reporter:
         var_pred = np.var(prediction, 0)
         v_pred = prediction - mean_pred
         v_gt = ground_truth - mean_gt
-        cor = sum(v_pred * v_gt) / (
-            np.sqrt(sum(v_pred**2)) * np.sqrt(sum(v_gt**2))
-        )
+        cor = sum(v_pred * v_gt) / (np.sqrt(sum(v_pred**2)) * np.sqrt(sum(v_gt**2)))
         sd_gt = np.std(ground_truth)
         sd_pred = np.std(prediction)
         numerator = 2 * cor * sd_gt * sd_pred

nkululeko/util.py

@@ -131,8 +131,9 @@ class Util:
     def _get_value_descript(self, section, name):
         if self.config_val(section, name, False):
             val = self.config_val(section, name, False)
-            return f"_{name}-{str(val)}"
-        return ""
+            val = str(val).strip('.')
+            return f'_{name}-{str(val)}'
+        return ''
 
     def get_data_name(self):
         """
@@ -147,9 +148,15 @@ class Util:
             ds = "_".join(ast.literal_eval(self.config["DATA"]["trains"]))
         else:
             ds = "_".join(ast.literal_eval(self.config["DATA"]["databases"]))
-        mt = ""
+        return_string = f"{ds}"
         if not only_data:
-            mt = f'_{self.config["MODEL"]["type"]}'
+            mt = self.get_model_description()
+            return_string = return_string+'_'+mt
+        return return_string.replace("__", "_")
+
+    def get_model_description(self):
+        mt = ""
+        mt = f'{self.config["MODEL"]["type"]}'
         ft = "_".join(ast.literal_eval(self.config["FEATS"]["type"]))
         ft += "_"
         set = self.config_val("FEATS", "set", False)
@@ -158,13 +165,14 @@ class Util:
             set_string += set
         layer_string = ""
         layer_s = self.config_val("MODEL", "layers", False)
-        if layer_s and not only_data:
+        if layer_s:
             layers = ast.literal_eval(layer_s)
             sorted_layers = sorted(layers.items(), key=lambda x: x[1])
             for l in sorted_layers:
                 layer_string += f"{str(l[1])}-"
-        return_string = f"{ds}{mt}_{ft}{set_string}{layer_string[:-1]}"
+        return_string = f"{mt}_{ft}{set_string}{layer_string[:-1]}"
         options = [
+            ["MODEL", "C_val"],
             ["MODEL", "drop"],
             ["MODEL", "loss"],
             ["MODEL", "logo"],
@@ -173,7 +181,7 @@ class Util:
         ]
         for option in options:
             return_string += self._get_value_descript(option[0], option[1])
-        return return_string.replace("__", "")
+        return return_string
 
     def get_plot_name(self):
         try:

{nkululeko-0.66.4.dist-info → nkululeko-0.66.5.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: nkululeko
-Version: 0.66.4
+Version: 0.66.5
 Summary: Machine learning audio prediction experiments based on templates
 Home-page: https://github.com/felixbur/nkululeko
 Author: Felix Burkhardt
@@ -256,11 +256,14 @@ Nkululeko can be used under the [MIT license](https://choosealicense.com/license
 Changelog
 =========
 
+Version 0.66.5
+--------------
+* Latex report now with images
+
 Version 0.66.4
 --------------
 * Pypi version mixup
 
-
 Version 0.66.3
 --------------
 * made path to PDF output relative to experiment root

{nkululeko-0.66.4.dist-info → nkululeko-0.66.5.dist-info}/RECORD

@@ -2,7 +2,7 @@ nkululeko/__init__.py,sha256=62f8HiEzJ8rG2QlTFJXUCMpvuH3fKI33DoJSj33mscc,63
 nkululeko/augment.py,sha256=lZcqCLNTLfC6G47ZjLYQXGcyPFJkmnOUDJOpn6aIJvE,1819
 nkululeko/balancer.py,sha256=WslJxQwMNnVYgZXF1y0ueS5zilRPQJZDhUG72Csb4Gw,11
 nkululeko/cacheddataset.py,sha256=lIJ6hUo5LoxSrzXtWV8mzwO7wRtUETWnOQ4ws2XfL1E,969
-nkululeko/constants.py,sha256=Pf3H7rhOX4PWicuxUETv8qpWK3cQdGYy2epZQW80aHU,38
+nkululeko/constants.py,sha256=Fu_qO9F8IJXYOYQlMl0uWE99ABO4cHIA1Fd-dp3TvrI,38
 nkululeko/demo.py,sha256=6CmLxH_0QJIMazPPg7IZur7ciNdqby6yOlh-6zu6YE0,1951
 nkululeko/demo_predictor.py,sha256=5PknI8SniGBRMzZOrmBOfPTV71rBbI1JCTnA6lXz6IU,2334
 nkululeko/experiment.py,sha256=tooe4nLmR_vA0nK047lVxByH3dph65-dW740H97tV1c,27017
@@ -14,9 +14,9 @@ nkululeko/filter_data.py,sha256=JpvE7lfGEtDG8fDmnxYW6F6gLMENySy1vkfrVyyxX6k,7350
 nkululeko/glob_conf.py,sha256=6MZe83QCgHD_zB79Sl9m6UJQASwfqJlyb-1nqrQ_6Iw,381
 nkululeko/modelrunner.py,sha256=gpEX3D1I31-M0xBsbWZAIENMR7vQbP4OxCDS_fa9cDo,6076
 nkululeko/nkululeko.py,sha256=CKuW2Lh6ioA4IndsxtmXdWromnKr9McJF74LMmgcd_0,1774
-nkululeko/plots.py,sha256=Wmm1YdFH7_qMh1FpA3pNkflO9xdaQhZgE1J06dLD08w,15893
+nkululeko/plots.py,sha256=d6W2I0Cr-dHkQAZPRvBDY0MG_agp8qjkafFHKREIMQg,15950
 nkululeko/predict.py,sha256=kMrQTnQx3_yWh9JVUB_R6DxIo9jkbOrfT2ZGbONoHNs,1926
-nkululeko/reporter.py,sha256=BMqrOvm3zku18vAiEeKr3H4c6QzSwJuUubawa1ZqbmQ,10951
+nkululeko/reporter.py,sha256=t7X9R5FPL9NCl6qg3Z3R5PhlKcErCUuAr9OJdfMHGCM,11318
 nkululeko/resample.py,sha256=7O9q8T_vsEExTiWO6lCt5I-ZGdYrRSPJ3CVzhksyAPE,2235
 nkululeko/result.py,sha256=rEJEdsF9XLdF2DQBaGzvlSTVhLK98q9-NHNOsZOqP0w,447
 nkululeko/runmanager.py,sha256=M1T75M2VCYF1yrN49ozqyvvkCyJJAJYL8BW5cee1P78,7401
@@ -25,7 +25,7 @@ nkululeko/segment.py,sha256=yhlYoFkKWxxOS56r29_InP49uzVxErrksc5BRpmkamE,4874
 nkululeko/syllable_nuclei.py,sha256=Sky-C__MeUDaxqHnDl2TGLLYOYvsahD35TUjWGeG31k,10047
 nkululeko/test.py,sha256=Z00CQrJ6Pp9zycKSLrCFjzew-_AXll3pud2o0xur_KY,1457
 nkululeko/test_predictor.py,sha256=mO-jm1ViTtZY8QfWhJLyEboU1nn_CfKQ9c7-dgUxMp0,2403
-nkululeko/util.py,sha256=AJ8dp-35n5cvDT_tawaYoG_gdEQ9vHeO5ZhMRHFXW-U,10082
+nkululeko/util.py,sha256=fxQePaou68_BFq6tND5mvVt0vPqp1BWdKa2s1YryeF0,10320
 nkululeko/augmenting/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nkululeko/augmenting/augmenter.py,sha256=S6LUbHz33WFQW8rawSRtMZABEvucjml7ezFG6Zeyq6s,2647
 nkululeko/augmenting/randomsplicer.py,sha256=6QAl1gV8IODA4_ecgAc_qidtBaqUxUnH0k0ItQLNdnE,2705
@@ -44,7 +44,7 @@ nkululeko/autopredict/ap_stoi.py,sha256=KbGe5D0-uCtulhXA-IEMtkUcAYNeaIBsa5TpZvEX
 nkululeko/autopredict/ap_valence.py,sha256=qDsgfb8dF-gM080aP9fDedHC63Yw5cgtlnSqb-0M_Jw,1040
 nkululeko/autopredict/estimate_snr.py,sha256=kJbvkt2alMN5ouS03USheU7hJ2l7U9JF0s9AtNT1Vx0,4818
 nkululeko/data/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-nkululeko/data/dataset.py,sha256=34I5AgUqEuzxi0fSBWtjZdUlJlF5gKf0peYYFjaZ1w8,22131
+nkululeko/data/dataset.py,sha256=scvmYzvQC-kEFxfzS9-R3-NCWWqlkq9LXcwDtuD9Gwo,22217
 nkululeko/data/dataset_csv.py,sha256=MgmpADmS2jNBtmKSzCDLAV_sH4MRjMwyNmBLOfS9c3A,3034
 nkululeko/feat_extract/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nkululeko/feat_extract/feats_agender.py,sha256=sDfsvSC2zt1JLn5rmB7bdck1JmXIIol3oIwN90TossM,2867
@@ -92,8 +92,8 @@ nkululeko/segmenting/seg_silero.py,sha256=So2D5eOVoeXwJSpmyA9PSAmnylLCeWuLR2Dg-c
 nkululeko/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nkululeko/utils/files.py,sha256=UiGAtZRWYjHSvlmPaTMtzyNNGE6qaLaxQkybctS7iRM,4021
 nkululeko/utils/stats.py,sha256=pbFynlmFvRL2k01CpsqY6S2LvpG9ESNTSv7o4UwgCms,2242
-nkululeko-0.66.4.dist-info/LICENSE,sha256=0zGP5B_W35yAcGfHPS18Q2B8UhvLRY3dQq1MhpsJU_U,1076
-nkululeko-0.66.4.dist-info/METADATA,sha256=9Eg3BRFl5fiLqqQWkbfYg9h88WMWIZs1pWlrvMuGg2M,24421
-nkululeko-0.66.4.dist-info/WHEEL,sha256=yQN5g4mg4AybRjkgi-9yy4iQEFibGQmlz78Pik5Or-A,92
-nkululeko-0.66.4.dist-info/top_level.txt,sha256=DPFNNSHPjUeVKj44dVANAjuVGRCC3MusJ08lc2a8xFA,10
-nkululeko-0.66.4.dist-info/RECORD,,
+nkululeko-0.66.5.dist-info/LICENSE,sha256=0zGP5B_W35yAcGfHPS18Q2B8UhvLRY3dQq1MhpsJU_U,1076
+nkululeko-0.66.5.dist-info/METADATA,sha256=rquTxkHeeRpzwW2RJTz67zJECSqpWyFRoz_Pyob54ro,24482
+nkululeko-0.66.5.dist-info/WHEEL,sha256=yQN5g4mg4AybRjkgi-9yy4iQEFibGQmlz78Pik5Or-A,92
+nkululeko-0.66.5.dist-info/top_level.txt,sha256=DPFNNSHPjUeVKj44dVANAjuVGRCC3MusJ08lc2a8xFA,10
+nkululeko-0.66.5.dist-info/RECORD,,