nkululeko 0.82.4__py3-none-any.whl → 0.83.0__py3-none-any.whl

nkululeko/constants.py

@@ -1,2 +1,2 @@
-VERSION="0.82.4"
+VERSION="0.83.0"
 SAMPLING_RATE = 16000

nkululeko/experiment.py

@@ -23,7 +23,7 @@ from nkululeko.plots import Plots
 from nkululeko.reporting.report import Report
 from nkululeko.runmanager import Runmanager
 from nkululeko.scaler import Scaler
-from nkululeko.test_predictor import Test_predictor
+from nkululeko.test_predictor import TestPredictor
 from nkululeko.utils.util import Util
 
 
@@ -672,7 +672,7 @@ class Experiment:
     def predict_test_and_save(self, result_name):
         model = self.runmgr.get_best_model()
         model.set_testdata(self.df_test, self.feats_test)
-        test_predictor = Test_predictor(
+        test_predictor = TestPredictor(
             model, self.df_test, self.label_encoder, result_name
         )
         test_predictor.predict_and_store()

nkululeko/modelrunner.py

@@ -2,18 +2,16 @@
 
 import pandas as pd
 
-from nkululeko.utils.util import Util
 from nkululeko import glob_conf
-import nkululeko.glob_conf as glob_conf
+from nkululeko.utils.util import Util
 
 
 class Modelrunner:
-    """
-    Class to model one run
-    """
+    """Class to model one run."""
 
     def __init__(self, df_train, df_test, feats_train, feats_test, run):
-        """Constructor setting up the dataframes
+        """Constructor setting up the dataframes.
+
         Args:
             df_train: train dataframe
             df_test: test dataframe

nkululeko/reporter.py

@@ -3,7 +3,6 @@
 This module contains the Reporter class which is responsible for generating reports.
 """
 
-
 import ast
 import glob
 import json
@@ -12,16 +11,14 @@ import math
 import matplotlib.pyplot as plt
 import numpy as np
 from scipy.stats import pearsonr
-from sklearn.metrics import (
-    ConfusionMatrixDisplay,
-    accuracy_score,
-    classification_report,
-    confusion_matrix,
-    mean_absolute_error,
-    mean_squared_error,
-    r2_score,
-    recall_score,
-)
+from sklearn.metrics import ConfusionMatrixDisplay
+from sklearn.metrics import accuracy_score
+from sklearn.metrics import classification_report
+from sklearn.metrics import confusion_matrix
+from sklearn.metrics import mean_absolute_error
+from sklearn.metrics import mean_squared_error
+from sklearn.metrics import r2_score
+from sklearn.metrics import recall_score
 from sklearn.utils import resample
 
 import nkululeko.glob_conf as glob_conf
@@ -70,11 +67,9 @@ 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 == "mae":
-                    self.result.test = mean_absolute_error(
-                        self.truths, self.preds)
+                    self.result.test = mean_absolute_error(self.truths, self.preds)
                 elif self.measure == "ccc":
                     self.result.test = self.ccc(self.truths, self.preds)
                     if math.isnan(self.result.test):
@@ -115,7 +110,7 @@ def plot_per_speaker(self, result_df, plot_name, function):
     Args:
         * result_df: a pandas dataframe with columns: preds, truths and speaker
         * plot_name: a string with the name of the plot
-        * function: a string with the function to use for each speaker, 
+        * function: a string with the function to use for each speaker,
         can be 'mode' or 'mean'
 
     Returns:
@@ -185,8 +180,7 @@ def plot_per_speaker(self, result_df, plot_name, function):
             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}")
         img_path = f"{fig_dir}{plot_name}.{self.format}"
@@ -265,8 +259,7 @@ def plot_per_speaker(self, result_df, plot_name, function):
         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))
@@ -322,8 +315,7 @@ def plot_per_speaker(self, result_df, plot_name, function):
         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/reporting/reporter.py

@@ -55,6 +55,7 @@ class Reporter:
         self.run = run
         self.epoch = epoch
         self.__set_measure()
+        self.filenameadd = ""
         self.cont_to_cat = False
         if len(self.truths) > 0 and len(self.preds) > 0:
             if self.util.exp_is_classification():
@@ -206,7 +207,7 @@ class Reporter:
                 f"Confusion Matrix, UAR: {uar_str} "
                 + f"(+-{up_str}/{low_str}) {reg_res}"
             )
-        img_path = f"{fig_dir}{plot_name}.{self.format}"
+        img_path = f"{fig_dir}{plot_name}{self.filenameadd}.{self.format}"
         plt.savefig(img_path)
         fig.clear()
         plt.close(fig)
@@ -228,14 +229,17 @@ class Reporter:
         )
         # print(rpt)
         self.util.debug(rpt)
-        file_name = f"{res_dir}{self.util.get_exp_name()}_conf.txt"
+        file_name = f"{res_dir}{self.util.get_exp_name()}{self.filenameadd}_conf.txt"
         with open(file_name, "w") as text_file:
             text_file.write(rpt)
 
+    def set_filename_add(self, my_string):
+        self.filenameadd = f"_{my_string}"
+
     def print_results(self, epoch):
         """Print all evaluation values to text file."""
         res_dir = self.util.get_path("res_dir")
-        file_name = f"{res_dir}{self.util.get_exp_name()}_{epoch}.txt"
+        file_name = f"{res_dir}{self.util.get_exp_name()}_{epoch}{self.filenameadd}.txt"
         if self.util.exp_is_classification():
             labels = glob_conf.labels
             try:

nkululeko/test_predictor.py

@@ -1,21 +1,25 @@
-""" test_predictor.py
+"""test_predictor.py.
+
     Predict targets from a model and save as csv file.
 
 """
 
-import nkululeko.glob_conf as glob_conf
-from nkululeko.utils.util import Util
+import ast
+
+import numpy as np
 import pandas as pd
+from sklearn.preprocessing import LabelEncoder
+
 from nkululeko.data.dataset import Dataset
 from nkululeko.feature_extractor import FeatureExtractor
+import nkululeko.glob_conf as glob_conf
 from nkululeko.scaler import Scaler
-import numpy as np
-from sklearn.preprocessing import LabelEncoder
+from nkululeko.utils.util import Util
 
 
-class Test_predictor:
+class TestPredictor:
     def __init__(self, model, orig_df, labenc, name):
-        """Constructor setting up name and configuration"""
+        """Constructor setting up name and configuration."""
         self.model = model
         self.orig_df = orig_df
         self.label_encoder = labenc
@@ -49,7 +53,14 @@ class Test_predictor:
             df[self.target] = labelenc.inverse_transform(predictions.tolist())
             df.to_csv(self.name)
         else:
+            test_dbs = ast.literal_eval(glob_conf.config["DATA"]["tests"])
+            test_dbs_string = "_".join(test_dbs)
             predictions = self.model.get_predictions()
+            report = self.model.predict()
+            report.set_filename_add(f"test-{test_dbs_string}")
+            self.util.print_best_results([report])
+            report.plot_confmatrix(self.util.get_plot_name(), 0)
+            report.print_results(0)
             # print(predictions)
             # df = pd.DataFrame(index=self.orig_df.index)
             # df["speaker"] = self.orig_df["speaker"]

{nkululeko-0.82.4.dist-info → nkululeko-0.83.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: nkululeko
-Version: 0.82.4
+Version: 0.83.0
 Summary: Machine learning audio prediction experiments based on templates
 Home-page: https://github.com/felixbur/nkululeko
 Author: Felix Burkhardt
@@ -333,6 +333,10 @@ F. Burkhardt, Johannes Wagner, Hagen Wierstorf, Florian Eyben and Björn Schulle
 Changelog
 =========
 
+Version 0.83.0
+--------------
+* test module now prints out reports
+
 Version 0.82.4
 --------------
 * fixed bug in wavlm 

{nkululeko-0.82.4.dist-info → nkululeko-0.83.0.dist-info}/RECORD

@@ -2,31 +2,31 @@ nkululeko/__init__.py,sha256=62f8HiEzJ8rG2QlTFJXUCMpvuH3fKI33DoJSj33mscc,63
 nkululeko/aug_train.py,sha256=YhuZnS_WVWnun9G-M6g5n6rbRxoVREz6Zh7k6qprFNQ,3194
 nkululeko/augment.py,sha256=4MG0apTAG5RgkuJrYEjGgDdbodZWi_HweSPNI1JJ5QA,3051
 nkululeko/cacheddataset.py,sha256=lIJ6hUo5LoxSrzXtWV8mzwO7wRtUETWnOQ4ws2XfL1E,969
-nkululeko/constants.py,sha256=kp-581CniawYq15MP-eOYf2iEPJCoCdhJ8W3kRUgPhs,39
+nkululeko/constants.py,sha256=NNx53OyRpXv780Ycj6Cdw4bDJfdvEn180CaN2PcmQkY,39
 nkululeko/demo.py,sha256=55kNFA2helMhOxD4yZuKg1JWDtlUUpxm-6uAnroIydI,3264
 nkululeko/demo_feats.py,sha256=sAeGFojhEj9WEDFtG3SzPBmyYJWLF2rkbpp65m8Ujo4,2025
 nkululeko/demo_predictor.py,sha256=-ggSHc3DXxRzjzcGB4qFBOMvKsfUdTkkde50BDrS9dA,4755
-nkululeko/experiment.py,sha256=CSEvQxK2_tzJyND5sUHQSc6MkRp1g6EVam8JX8txqps,29576
+nkululeko/experiment.py,sha256=SRcB0ni0XLK910NSWTyRAe-Eoa6fVSKDCJlDJKyCzMc,29574
 nkululeko/explore.py,sha256=2wdoGRqldvsN1zCiWk0quSDgHHHUoF2UZOWQ1r-2OLM,2310
 nkululeko/export.py,sha256=mHeEAAmtZuxdyebLlbSzPrHSi9OMgJHbk35d3DTxRBc,4632
 nkululeko/feature_extractor.py,sha256=8mssYKmo4LclVI-hiLmJEDZ0ZPyDavFG2YwtXcrGzwM,3976
 nkululeko/file_checker.py,sha256=LoLnL8aHpW-axMQ46qbqrManTs5otG9ShpEZuz9iRSk,3474
 nkululeko/filter_data.py,sha256=w-X2mhKdYr5DxDIz50E5yzO6Jmzk4jjDBoXsgOOVtcA,7222
 nkululeko/glob_conf.py,sha256=iHiVSxDYgmYwdx6z0HuGUMSWrfZfufPHxHb60q2dLRY,453
-nkululeko/modelrunner.py,sha256=GuYsmUGSmJ0QxXxR8k0TZ47IDMtdGIMbm5nMq4Ix6tU,9335
+nkululeko/modelrunner.py,sha256=GwDXcE2gDQXat4W0-HhHQ1BcUNCRBXMBQ4QycfHp_5c,9288
 nkululeko/multidb.py,sha256=fG3VukEWP1vreVN4gB1IRXxwwg4jLftsSEYtu0o1f78,5634
 nkululeko/nkuluflag.py,sha256=FCetTfgH69u4AwENgeCKVi3vBIR10Di67SfbupGQqfc,3354
 nkululeko/nkululeko.py,sha256=Kn3s2E3yyH8cJ7z6lkMxrnqtCxTu7-qfe9Zr_ONTD5g,1968
 nkululeko/plots.py,sha256=K88ZRPFGX_r03BT742H06Dde20xZYdltv7dxjgUiAFA,23025
 nkululeko/predict.py,sha256=sF091sSSLnEWcISx9ZcULLie3tY5XeFsQJd6b3vrxFg,2409
-nkululeko/reporter.py,sha256=mCy8er8z4e5hJ7XbOyy6BgZYZM6Lz-EKXHh4zlT0Zc8,12427
+nkululeko/reporter.py,sha256=8mlIaKep4hM-tdRv8t98tK80rx3zOmVGXSORhiPc3as,12483
 nkululeko/resample.py,sha256=3WbxkwgyTe_fW38046Rjxk3knOkFdhqn2C4nfhbUurQ,2287
 nkululeko/runmanager.py,sha256=eTM1DNQKt1lxYhzt4vZyZluPXW9sWlIJHNQzex4lkJU,7624
 nkululeko/scaler.py,sha256=4nkIqoajkIkuTPK0Z02ifMN_awl6fP_i-GBYdoGYgGM,4101
 nkululeko/segment.py,sha256=YLKckX44tbvTb3LrdgYw9X4guzuF27sutl92z9DkpZU,4835
 nkululeko/syllable_nuclei.py,sha256=Sky-C__MeUDaxqHnDl2TGLLYOYvsahD35TUjWGeG31k,10047
 nkululeko/test.py,sha256=JRoLgqQJEhAIGetw-qlOUihSTTQ7O8DYafB0FlQESIQ,1525
-nkululeko/test_predictor.py,sha256=L2njNydYTX85_7RhHjfk1MN4JwE21tsBVuX4fY-XEjc,2753
+nkululeko/test_predictor.py,sha256=L8XKrIweTf-oKeaGuDw_ZhtvzRUxFuWmOhva6jgf7-s,3148
 nkululeko/augmenting/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nkululeko/augmenting/augmenter.py,sha256=XAt0dpmlnKxqyysqCgV3rcz-pRIvOz7rU7dmGDCVAzs,2905
 nkululeko/augmenting/randomsplicer.py,sha256=Z5rxdKKUpuncLWuTS6xVfVKUeVbeiYU_dLRHQ5fcg4Y,2669
@@ -95,7 +95,7 @@ nkululeko/reporting/defines.py,sha256=IsY1YgKRMaABpylVKjBJgJ5bNCEbGCVA_E6pivraqS
 nkululeko/reporting/latex_writer.py,sha256=qiCRSmB4KOD_za4oHu5x-PhwjZohzfo8wecMOwlXZwc,1886
 nkululeko/reporting/report.py,sha256=W0rcigDdjBvxZQ3pZja_gvToILYvaZ1BFtnN2qFRfYI,1060
 nkululeko/reporting/report_item.py,sha256=siWeGNgo4bAE46YBMNcsdf3jTMTy76BO9Fi6DTvDig4,533
-nkululeko/reporting/reporter.py,sha256=wwpY0gA-8E8d26XH3DSmXm3X0BkBw2Y0YyEiUiNU_Y0,12670
+nkululeko/reporting/reporter.py,sha256=eLqwKEUTQ7v5CedzhZP2617qmXGcvi0rjyyFLOBdxtQ,12841
 nkululeko/reporting/result.py,sha256=nSN5or-Py2GPRWHkWpGRh7UCi1W0er7WLEHz8fYLk-A,742
 nkululeko/segmenting/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nkululeko/segmenting/seg_inaspeechsegmenter.py,sha256=pmLHuXsaqvcdYxB4PSW9l1mbQWZZBJFhi_CGabqydas,1947
@@ -104,8 +104,8 @@ nkululeko/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nkululeko/utils/files.py,sha256=UiGAtZRWYjHSvlmPaTMtzyNNGE6qaLaxQkybctS7iRM,4021
 nkululeko/utils/stats.py,sha256=1yUq0FTOyqkU8TwUocJRYdJaqMU5SlOBBRUun9STo2M,2829
 nkululeko/utils/util.py,sha256=_Z6OMJ3f-8TdETW9eqJYY5hwNRS5XCt9azzRnqoTTZE,12330
-nkululeko-0.82.4.dist-info/LICENSE,sha256=0zGP5B_W35yAcGfHPS18Q2B8UhvLRY3dQq1MhpsJU_U,1076
-nkululeko-0.82.4.dist-info/METADATA,sha256=iVA5K6coH1oLy918OgAZoq6wqFXcfYIcuZBV1dOnI2g,35950
-nkululeko-0.82.4.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
-nkululeko-0.82.4.dist-info/top_level.txt,sha256=DPFNNSHPjUeVKj44dVANAjuVGRCC3MusJ08lc2a8xFA,10
-nkululeko-0.82.4.dist-info/RECORD,,
+nkululeko-0.83.0.dist-info/LICENSE,sha256=0zGP5B_W35yAcGfHPS18Q2B8UhvLRY3dQq1MhpsJU_U,1076
+nkululeko-0.83.0.dist-info/METADATA,sha256=20S7IpMbLE7irV0ikdaFNfdqdBEEywH7jjlJwur8smA,36018
+nkululeko-0.83.0.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
+nkululeko-0.83.0.dist-info/top_level.txt,sha256=DPFNNSHPjUeVKj44dVANAjuVGRCC3MusJ08lc2a8xFA,10
+nkululeko-0.83.0.dist-info/RECORD,,