cesnet-datazoo 0.1.9__py3-none-any.whl → 0.1.10__py3-none-any.whl

cesnet_datazoo/datasets/cesnet_dataset.py

@@ -176,7 +176,7 @@ class CesnetDataset():
             raise ValueError(f"Found {len(available_applications)} applications in the servicemap (omitting background traffic classes), but expected {self.metadata.application_count}. Please report this issue.")
         self.available_classes = available_applications + self.metadata.background_traffic_classes
 
-    def set_dataset_config_and_initialize(self, dataset_config: DatasetConfig, disable_indices_cache: bool = False) -> None:
+    def set_dataset_config_and_initialize(self, dataset_config: DatasetConfig, disable_indices_cache: bool = False, silent_warning: bool = False) -> None:
         """
         Initialize train, validation, and test sets. Data cannot be accessed before calling this method.
 
@@ -184,6 +184,11 @@ class CesnetDataset():
             dataset_config: Desired configuration of the dataset.
             disable_indices_cache: Whether to disable caching of the dataset indices. This is useful when the dataset is used in many different configurations and you want to save disk space.
         """
+        if self.name.startswith("CESNET-TLS-Year22") and not silent_warning:
+            warnings.warn("The CESNET-TLS-Year22 dataset contains traffic from the entire year of 2022. During the dataset collection, in week 10 (7.3.2022 - 13.3.2022), " + \
+                          "the used flow exporter was updated with new features resulting in a change in the distribution of packet sequence data. " + \
+                          "This can lead to a decrease in model performance when a model is trained on traffic before week 10 and tested on traffic after week 10. " + \
+                          "More details can be found in the paper at https://doi.org/10.1038/s41597-024-03927-4. To disable this warning set silent_warning=True.")
         self.dataset_config = dataset_config
         self._clear()
         self._initialize_train_val_test(disable_indices_cache=disable_indices_cache)

{cesnet_datazoo-0.1.9.dist-info → cesnet_datazoo-0.1.10.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: cesnet-datazoo
-Version: 0.1.9
+Version: 0.1.10
 Summary: A toolkit for large network traffic datasets
 Author-email: Jan Luxemburk <luxemburk@cesnet.cz>, Karel Hynek <hynekkar@cesnet.cz>
 Maintainer-email: Jan Luxemburk <luxemburk@cesnet.cz>, Karel Hynek <hynekkar@cesnet.cz>

{cesnet_datazoo-0.1.9.dist-info → cesnet_datazoo-0.1.10.dist-info}/RECORD

@@ -2,7 +2,7 @@ cesnet_datazoo/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 cesnet_datazoo/config.py,sha256=wkpD_OL3gRXX2t0WDfDMsBD2A3vEdAjSm4yXhzsR8T0,38536
 cesnet_datazoo/constants.py,sha256=6GhcIyjVnWYrVnxRgTlGuiWRtvwZL1KqyzMJS26ge2E,1481
 cesnet_datazoo/datasets/__init__.py,sha256=8ziQ3EUzUh5fMfWWXwk0cqYk0lOUNU7zbi0Gom3bLnI,443
-cesnet_datazoo/datasets/cesnet_dataset.py,sha256=14uKWWSGIkH3GM_BDUSYyCIoOh1L-I4bH0zu0m3DkkQ,46988
+cesnet_datazoo/datasets/cesnet_dataset.py,sha256=V2rBE4Mh2gaMw-NjQ4xHp6ViuuvCdEzB-ymX3CYyfkc,47762
 cesnet_datazoo/datasets/datasets.py,sha256=Bn4SU1k5og6AsUlnPapFPeu4uGlpRH-IaOSafz0ZT2k,3617
 cesnet_datazoo/datasets/datasets_constants.py,sha256=1P54Ns8wCQMemdKNe8OH7cVUfkxs3vL29ugSmOLXceI,29154
 cesnet_datazoo/datasets/loaders.py,sha256=9KgRY-Y8CcgtXbgqWpAaG7gyOAsSf278w7b1eHwTSyE,1854
@@ -23,8 +23,8 @@ cesnet_datazoo/utils/class_info.py,sha256=H5UgyRqXIepBJmkLQ1gAIXV4owKSoIllguRiqF
 cesnet_datazoo/utils/download.py,sha256=hG5V1ZYZGtqCzlVV76NMgOZkSKOywdOFiq9Lagkgego,1441
 cesnet_datazoo/utils/fileutils.py,sha256=XA_VWDuTiCXnoOgHPUzsmbnLFgrlxOo5cvUY_OBJUR8,642
 cesnet_datazoo/utils/random.py,sha256=Dqgm_T25ljbew-OJozK90PsiXKnd4Kw6lcUexxF6vIc,575
-cesnet_datazoo-0.1.9.dist-info/LICENCE,sha256=69Wc69APiM1YKrFOIipG7jjU2lk89WQuO_U0AXKU8KE,1541
-cesnet_datazoo-0.1.9.dist-info/METADATA,sha256=tulO0ucEAPIvMEXqBTmlCuqDWU5-0XsYat7WDrQazkQ,12606
-cesnet_datazoo-0.1.9.dist-info/WHEEL,sha256=OVMc5UfuAQiSplgO0_WdW7vXVGAt9Hdd6qtN4HotdyA,91
-cesnet_datazoo-0.1.9.dist-info/top_level.txt,sha256=bu1Z8zaI_1Id_ZaYyvJnxIBa87OSrdlZ8J2OBMggK5o,15
-cesnet_datazoo-0.1.9.dist-info/RECORD,,
+cesnet_datazoo-0.1.10.dist-info/LICENCE,sha256=69Wc69APiM1YKrFOIipG7jjU2lk89WQuO_U0AXKU8KE,1541
+cesnet_datazoo-0.1.10.dist-info/METADATA,sha256=bLlT6pX60aaLzugba31DzwW5mk0zurk05g6dqRLC0OQ,12607
+cesnet_datazoo-0.1.10.dist-info/WHEEL,sha256=P9jw-gEje8ByB7_hXoICnHtVCrEwMQh-630tKvQWehc,91
+cesnet_datazoo-0.1.10.dist-info/top_level.txt,sha256=bu1Z8zaI_1Id_ZaYyvJnxIBa87OSrdlZ8J2OBMggK5o,15
+cesnet_datazoo-0.1.10.dist-info/RECORD,,

{cesnet_datazoo-0.1.9.dist-info → cesnet_datazoo-0.1.10.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (75.2.0)
+Generator: setuptools (75.3.0)
 Root-Is-Purelib: true
 Tag: py3-none-any