cesnet-datazoo 0.1.5__tar.gz → 0.1.7__tar.gz

{cesnet_datazoo-0.1.5 → cesnet_datazoo-0.1.7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: cesnet-datazoo
-Version: 0.1.5
+Version: 0.1.7
 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>
@@ -18,14 +18,14 @@ Description-Content-Type: text/markdown
 License-File: LICENCE
 Requires-Dist: cesnet_models
 Requires-Dist: matplotlib
-Requires-Dist: numpy
+Requires-Dist: numpy<2.0
 Requires-Dist: pandas
 Requires-Dist: pydantic>=2.0
 Requires-Dist: PyYAML
 Requires-Dist: requests
 Requires-Dist: scikit-learn
 Requires-Dist: seaborn
-Requires-Dist: tables>=3.8.0
+Requires-Dist: tables<=3.9.2,>=3.8.0
 Requires-Dist: torch>=1.10
 Requires-Dist: tqdm
 Provides-Extra: dev

{cesnet_datazoo-0.1.5 → cesnet_datazoo-0.1.7}/cesnet_datazoo/config.py

@@ -8,6 +8,7 @@ import warnings
 from dataclasses import InitVar, field
 from datetime import datetime
 from enum import Enum
+from importlib.metadata import version
 from typing import TYPE_CHECKING, Callable, Literal, Optional
 
 import yaml
@@ -83,6 +84,7 @@ class DataLoaderOrder(Enum):
 
 @dataclass(frozen=True)
 class TrainDataParams():
+    datazoo_version: str
     database_filename: str
     train_period_name: str
     train_tables_paths: list[str]
@@ -97,6 +99,7 @@ class TrainDataParams():
 
 @dataclass(frozen=True)
 class TestDataParams():
+    datazoo_version: str
     database_filename: str
     test_period_name: str
     test_tables_paths: list[str]
@@ -497,14 +500,12 @@ class DatasetConfig():
         return params_hash
 
     def _get_train_data_path(self) -> str:
-        if self.need_train_set:
-            params_hash = self._get_train_data_hash()
-            return os.path.join(self.data_root, "train-data", f"{params_hash}_{self.random_state}", f"fold_{self.fold_id}")
-        else:
-            return os.path.join(self.data_root, "train-data", "default")
+        params_hash = self._get_train_data_hash()
+        return os.path.join(self.data_root, "train-data", f"{params_hash}_{self.random_state}", f"fold_{self.fold_id}")
 
     def _get_train_data_params(self) -> TrainDataParams:
         return TrainDataParams(
+            datazoo_version=version("cesnet_datazoo"),
             database_filename=self.database_filename,
             train_period_name=self.train_period_name,
             train_tables_paths=self._get_train_tables_paths(),
@@ -520,6 +521,7 @@ class DatasetConfig():
     def _get_val_data_params_and_path(self, known_apps: list[str], unknown_apps: list[str]) -> tuple[TestDataParams, str]:
         assert self.val_approach == ValidationApproach.VALIDATION_DATES
         val_data_params = TestDataParams(
+            datazoo_version=version("cesnet_datazoo"),
             database_filename=self.database_filename,
             test_period_name=self.val_period_name,
             test_tables_paths=self._get_val_tables_paths(),
@@ -532,6 +534,7 @@ class DatasetConfig():
 
     def _get_test_data_params_and_path(self, known_apps: list[str], unknown_apps: list[str]) -> tuple[TestDataParams, str]:
         test_data_params = TestDataParams(
+            datazoo_version=version("cesnet_datazoo"),
             database_filename=self.database_filename,
             test_period_name=self.test_period_name,
             test_tables_paths=self._get_test_tables_paths(),

{cesnet_datazoo-0.1.5 → cesnet_datazoo-0.1.7}/cesnet_datazoo.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: cesnet-datazoo
-Version: 0.1.5
+Version: 0.1.7
 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>
@@ -18,14 +18,14 @@ Description-Content-Type: text/markdown
 License-File: LICENCE
 Requires-Dist: cesnet_models
 Requires-Dist: matplotlib
-Requires-Dist: numpy
+Requires-Dist: numpy<2.0
 Requires-Dist: pandas
 Requires-Dist: pydantic>=2.0
 Requires-Dist: PyYAML
 Requires-Dist: requests
 Requires-Dist: scikit-learn
 Requires-Dist: seaborn
-Requires-Dist: tables>=3.8.0
+Requires-Dist: tables<=3.9.2,>=3.8.0
 Requires-Dist: torch>=1.10
 Requires-Dist: tqdm
 Provides-Extra: dev

{cesnet_datazoo-0.1.5 → cesnet_datazoo-0.1.7}/cesnet_datazoo.egg-info/requires.txt

@@ -1,13 +1,13 @@
 cesnet_models
 matplotlib
-numpy
+numpy<2.0
 pandas
 pydantic>=2.0
 PyYAML
 requests
 scikit-learn
 seaborn
-tables>=3.8.0
+tables<=3.9.2,>=3.8.0
 torch>=1.10
 tqdm
 

{cesnet_datazoo-0.1.5 → cesnet_datazoo-0.1.7}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "cesnet-datazoo"
-version = "0.1.5"
+version = "0.1.7"
 authors = [
   {name = "Jan Luxemburk", email = "luxemburk@cesnet.cz"},
   {name = "Karel Hynek", email = "hynekkar@cesnet.cz"},
@@ -31,14 +31,14 @@ requires-python = ">=3.10"
 dependencies = [
   "cesnet_models",
   "matplotlib",
-  "numpy",
+  "numpy<2.0",
   "pandas",
   "pydantic>=2.0",
   "PyYAML",
   "requests",
   "scikit-learn",
   "seaborn",
-  "tables>=3.8.0",
+  "tables>=3.8.0, <=3.9.2",
   "torch>=1.10",
   "tqdm",
 ]