cesnet-datazoo 0.1.11__tar.gz → 0.1.13__tar.gz

{cesnet_datazoo-0.1.11 → cesnet_datazoo-0.1.13}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: cesnet-datazoo
-Version: 0.1.11
+Version: 0.1.13
 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>
@@ -19,7 +19,7 @@ Requires-Dist: cesnet_models
 Requires-Dist: matplotlib
 Requires-Dist: numpy
 Requires-Dist: pandas
-Requires-Dist: pydantic!=2.10.*,!=2.9.*,<2.12.0,>=2.0
+Requires-Dist: pydantic!=2.9.*,<2.12.0,>=2.0
 Requires-Dist: PyYAML
 Requires-Dist: requests
 Requires-Dist: scikit-learn

{cesnet_datazoo-0.1.11 → cesnet_datazoo-0.1.13}/cesnet_datazoo/config.py

@@ -142,7 +142,7 @@ class DatasetConfig():
         need_test_set: Use to disable the test set. `Default: True`
         train_period_name: Name of the train period. See [instructions][config.DatasetConfig--how-to-configure-train-validation-and-test-sets].
         train_dates: Dates used for creating a train set.
-        train_dates_weigths: To use a non-uniform distribution of samples across train dates.
+        train_dates_weights: To use a non-uniform distribution of samples across train dates.
         val_approach: How a validation set should be created. Either split train data into train and validation or have a separate validation period. `Default: SPLIT_FROM_TRAIN`
         train_val_split_fraction: The fraction of validation samples when splitting from the train set. `Default: 0.2`
         val_period_name: Name of the validation period. See [instructions][config.DatasetConfig--how-to-configure-train-validation-and-test-sets].
@@ -219,7 +219,7 @@ class DatasetConfig():
     need_test_set: bool = True
     train_period_name: str = ""
     train_dates: list[str] = field(default_factory=list)
-    train_dates_weigths: Optional[list[int]] = None
+    train_dates_weights: Optional[list[int]] = None
     val_approach: ValidationApproach = ValidationApproach.SPLIT_FROM_TRAIN
     train_val_split_fraction: float = 0.2
     val_period_name: str = ""
@@ -369,16 +369,16 @@ class DatasetConfig():
                 raise ValueError("QUIC datasets do not support use_tcp_features")
             if self.use_push_flags:
                 raise ValueError("QUIC datasets do not support use_push_flags")
-        # When train_dates_weigths are used, train_size and val_known_size have to be specified
-        if self.train_dates_weigths is not None:
+        # When train_dates_weights are used, train_size and val_known_size have to be specified
+        if self.train_dates_weights is not None:
             if not self.need_train_set:
-                raise ValueError("train_dates_weigths cannot be specified when need_train_set is false")
-            if len(self.train_dates_weigths) != len(self.train_dates):
-                raise ValueError("train_dates_weigths has to have the same length as train_dates")
+                raise ValueError("train_dates_weights cannot be specified when need_train_set is false")
+            if len(self.train_dates_weights) != len(self.train_dates):
+                raise ValueError("train_dates_weights has to have the same length as train_dates")
             if self.train_size == "all":
-                raise ValueError("train_size cannot be 'all' when train_dates_weigths are speficied")
+                raise ValueError("train_size cannot be 'all' when train_dates_weights are speficied")
             if self.val_approach == ValidationApproach.SPLIT_FROM_TRAIN and self.val_known_size == "all":
-                raise ValueError("val_known_size cannot be 'all' when train_dates_weigths are speficied and validation_approach is split-from-train")
+                raise ValueError("val_known_size cannot be 'all' when train_dates_weights are speficied and validation_approach is split-from-train")
         # App selection
         if self.apps_selection == AppSelection.ALL_KNOWN:
             self.val_unknown_size = 0

{cesnet_datazoo-0.1.11 → cesnet_datazoo-0.1.13}/cesnet_datazoo/datasets/cesnet_dataset.py

@@ -532,7 +532,7 @@ class CesnetDataset():
                                                                                                         servicemap=servicemap,
                                                                                                         disable_indices_cache=disable_indices_cache,)
             # Date weight sampling of train indices
-            if dataset_config.train_dates_weigths is not None:
+            if dataset_config.train_dates_weights is not None:
                 assert dataset_config.train_size != "all"
                 if dataset_config.val_approach == ValidationApproach.SPLIT_FROM_TRAIN:
                     # requested number of samples is train_size + val_known_size when using the split-from-train validation approach
@@ -563,7 +563,7 @@ class CesnetDataset():
                 val_data_path = dataset_config._get_train_data_path()
                 val_unknown_indices = train_unknown_indices
                 train_labels = train_indices[INDICES_APP_FIELD]
-                if dataset_config.train_dates_weigths is not None:
+                if dataset_config.train_dates_weights is not None:
                     assert dataset_config.val_known_size != "all"
                     # When weight sampling is used, val_known_size is kept but the resulting train size can be smaller due to no enough samples in some train dates
                     if dataset_config.val_known_size > len(train_indices):

{cesnet_datazoo-0.1.11 → cesnet_datazoo-0.1.13}/cesnet_datazoo/pytables_data/indices_setup.py

@@ -64,11 +64,11 @@ def subset_and_sort_indices(dataset_config: DatasetConfig, dataset_indices: Indi
 def date_weight_sample_train_indices(dataset_config: DatasetConfig, train_indices: np.ndarray, num_samples: int) -> np.ndarray:
     rng = get_fresh_random_generator(dataset_config=dataset_config, section=RandomizedSection.DATE_WEIGHT_SAMPLING)
     indices_per_date = [train_indices[train_indices[INDICES_TABLE_FIELD] == i] for i in np.unique(train_indices[INDICES_TABLE_FIELD])]
-    weights = np.array(dataset_config.train_dates_weigths)
+    weights = np.array(dataset_config.train_dates_weights)
     weights = weights / weights.sum()
     samples_per_date = np.ceil((weights * (num_samples))).astype(int)
     samples_per_date_clipped = np.clip(samples_per_date, a_max=list(map(len, indices_per_date)), a_min=0)
-    df = pd.DataFrame(data={"Dates": dataset_config.train_dates, "Weights": dataset_config.train_dates_weigths, "Requested Samples": samples_per_date, "Available Samples": samples_per_date_clipped})
+    df = pd.DataFrame(data={"Dates": dataset_config.train_dates, "Weights": dataset_config.train_dates_weights, "Requested Samples": samples_per_date, "Available Samples": samples_per_date_clipped})
     log.info(f"Weight sampling per date with requsted total number of samples {num_samples} (train_size + val_known_size when using the split-from-train validation approach; train_size otherwise)")
     for l in df.to_string(index=False).splitlines():
         log.info(l)

{cesnet_datazoo-0.1.11 → cesnet_datazoo-0.1.13}/cesnet_datazoo.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: cesnet-datazoo
-Version: 0.1.11
+Version: 0.1.13
 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>
@@ -19,7 +19,7 @@ Requires-Dist: cesnet_models
 Requires-Dist: matplotlib
 Requires-Dist: numpy
 Requires-Dist: pandas
-Requires-Dist: pydantic!=2.10.*,!=2.9.*,<2.12.0,>=2.0
+Requires-Dist: pydantic!=2.9.*,<2.12.0,>=2.0
 Requires-Dist: PyYAML
 Requires-Dist: requests
 Requires-Dist: scikit-learn

{cesnet_datazoo-0.1.11 → cesnet_datazoo-0.1.13}/cesnet_datazoo.egg-info/requires.txt

@@ -2,7 +2,7 @@ cesnet_models
 matplotlib
 numpy
 pandas
-pydantic!=2.10.*,!=2.9.*,<2.12.0,>=2.0
+pydantic!=2.9.*,<2.12.0,>=2.0
 PyYAML
 requests
 scikit-learn

{cesnet_datazoo-0.1.11 → cesnet_datazoo-0.1.13}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "cesnet-datazoo"
-version = "0.1.11"
+version = "0.1.13"
 authors = [
   {name = "Jan Luxemburk", email = "luxemburk@cesnet.cz"},
   {name = "Karel Hynek", email = "hynekkar@cesnet.cz"},
@@ -32,7 +32,7 @@ dependencies = [
   "matplotlib",
   "numpy",
   "pandas",
-  "pydantic >=2.0, !=2.9.*, !=2.10.*, <2.12.0",
+  "pydantic >=2.0, !=2.9.*, <2.12.0",
   "PyYAML",
   "requests",
   "scikit-learn",