sinapsis-data-readers 0.1.16__py3-none-any.whl → 0.1.19__py3-none-any.whl

sinapsis_data_readers/templates/datasets_readers/sklearn_datasets.py

@@ -135,7 +135,7 @@ class SKLearnDatasets(BaseDynamicWrapperTemplate):
     @staticmethod
     def split_dataset(
         results: pd.DataFrame, feature_name_cols: list, target_name_cols: list, n_features: int, split_size: float
-    ) -> TabularDatasetSplit:
+    ) -> dict:
         """Method to split the dataset into training and testing samples"""
         if feature_name_cols:
             X = results[feature_name_cols]
@@ -144,8 +144,7 @@ class SKLearnDatasets(BaseDynamicWrapperTemplate):
             X = results.iloc[:, :n_features]
             y = results.iloc[:, n_features:]
 
-        # x_vals = results.drop(columns=[TARGET], axis=1)
-        # y_vals = results[TARGET]
+
         x_train, x_test, y_train, y_test = train_test_split(X, y, train_size=split_size, random_state=0)
         split_data = TabularDatasetSplit(
             x_train=pd.DataFrame(x_train),
@@ -154,7 +153,7 @@ class SKLearnDatasets(BaseDynamicWrapperTemplate):
             y_test=pd.DataFrame(y_test),
         )
 
-        return split_data
+        return split_data.model_dump_json(indent=2)
 
     def execute(self, container: DataContainer) -> DataContainer:
         sklearn_dataset = self.wrapped_callable.__func__(**self.dataset_attributes.model_dump())

sinapsis_data_readers/templates/datasets_readers/sktime_datasets.py

@@ -94,7 +94,7 @@ class SKTimeDatasets(BaseDynamicWrapperTemplate):
 
     def initialize_attributes(self):
         return getattr(self.attributes, self.wrapped_callable.__name__)
-    def split_time_series_dataset(self, dataset: Any) -> TabularDatasetSplit:
+    def split_time_series_dataset(self, dataset: Any) -> dict:
         """Split a time series dataset into training and testing sets
 
         Args:
@@ -104,12 +104,13 @@ class SKTimeDatasets(BaseDynamicWrapperTemplate):
             TabularDatasetSplit: Object containing the split time series data
         """
         y_train, y_test = temporal_train_test_split(dataset, train_size=self.attributes.train_size)
-        return TabularDatasetSplit(
+        split_dataset =  TabularDatasetSplit(
             x_train=pd.DataFrame(index=y_train.index),
             x_test=pd.DataFrame(index=y_test.index),
             y_train=pd.DataFrame(y_train),
             y_test=pd.DataFrame(y_test),
         )
+        return split_dataset.model_dump_json(indent=2)
 
     def split_classification_dataset(self, X: Any, y: Any) -> TabularDatasetSplit:
         """Split a classification dataset into training and testing sets

sinapsis_data_readers/templates/image_readers/coco_dataset_reader.py

@@ -55,8 +55,7 @@ class CocoImageDatasetBaseCV2(FolderImageDatasetCV2):
         annotations_path: str
 
     def __init__(self, attributes: TemplateAttributeType) -> None:
-        self.annotations_file = os.path.join(attributes.get("root_dir", SINAPSIS_CACHE_DIR),
-                                             attributes.get("data_dir"), attributes.get("annotations_path"))
+        self.annotations_file = os.path.join(attributes.get("root_dir", SINAPSIS_CACHE_DIR), attributes.get("data_dir"), attributes.get("annotations_path"))
         self.raw_annotations_dict: list[dict[str, dict[str, Any]]] = self.read_annotations_file(self.annotations_file)
         self.annotations = self.images_annotations()
         super().__init__(attributes)

sinapsis_data_readers/templates/video_readers/video_reader_dali.py

@@ -134,19 +134,19 @@ class VideoReaderDali(BaseVideoReader):
             del self.video_reader
 
     def _read_video_frames(self) -> list[ImagePacket]:
-        """Reads video frames from the dali pipeline.
-
-        This method runs the video reader pipeline and adds the frames to a list
-        of ImagePacket objects.
-
-        Returns:
-            list[ImagePacket]: A list of ImagePacket objects representing the video frames.
-        """
+        """Reads video frames from the dali pipeline."""
         video_frames: list[ImagePacket] = []
         sequences_out = self.video_reader.run()
+        tensor_batch = sequences_out[0]
+
+        shape_result = tensor_batch.shape()
+        batch_size = shape_result[0][0]
 
-        for idx, frame in enumerate(sequences_out[0]):
+        for idx in range(batch_size):
+            frame_tensor = tensor_batch.at(idx)
+            frame = torch.as_tensor(frame_tensor, device="cuda")
             video_frames.append(self._make_image_packet(frame, frame_index=self.frame_count + idx))
+
         return video_frames
 
     def reset_state(self, template_name: str | None = None) -> None:

{sinapsis_data_readers-0.1.16.dist-info → sinapsis_data_readers-0.1.19.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: sinapsis-data-readers
-Version: 0.1.16
+Version: 0.1.19
 Summary: Templates to read data in different formats
 Author-email: SinapsisAI <dev@sinapsis.tech>
 Project-URL: Homepage, https://sinapsis.tech
@@ -14,8 +14,8 @@ Requires-Dist: sinapsis>=0.1.1
 Provides-Extra: nvidia-dali
 Requires-Dist: nvidia-dali-cuda120>=1.43.0; extra == "nvidia-dali"
 Provides-Extra: torch-codec
-Requires-Dist: torch<=2.5.1; extra == "torch-codec"
-Requires-Dist: torchcodec>=0.3.0; extra == "torch-codec"
+Requires-Dist: torch>=2.4.1; extra == "torch-codec"
+Requires-Dist: torchcodec>=0.0.3; extra == "torch-codec"
 Provides-Extra: sklearn-datasets
 Requires-Dist: pandas>=2.2.3; extra == "sklearn-datasets"
 Requires-Dist: scikit-learn>=1.5.2; extra == "sklearn-datasets"

{sinapsis_data_readers-0.1.16.dist-info → sinapsis_data_readers-0.1.19.dist-info}/RECORD

@@ -4,7 +4,6 @@ sinapsis_data_readers/helpers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5N
 sinapsis_data_readers/helpers/coco_dataclasses.py,sha256=D5HVWQP95TdHpa9UnTYAClfaqsIYrODKDGbITCvYXsc,2290
 sinapsis_data_readers/helpers/csv_reader.py,sha256=f_fk2Wgukdh93Um1Q5qczUD27iC3A71vKbhWxXe6Fyk,558
 sinapsis_data_readers/helpers/file_path_helpers.py,sha256=ayuFe-AAEa4immcY19FcubAtKzZ3BtYkBus-QP5dADo,2205
-sinapsis_data_readers/helpers/image_color_space_converter.py,sha256=SABsol7jp6veA_T13MSr0fQFVrI-NJdXkNYyX4YL90E,2099
 sinapsis_data_readers/helpers/sklearn_dataset_subset.py,sha256=XpzdVTBr5OgG57oOz3W7eLpoj2vWlTKbX6NIH0OP3qc,792
 sinapsis_data_readers/helpers/sktime_datasets_subset.py,sha256=aMmsaPuHuWkEP5BCAzeP6vV--y0UehBZL_fRHlDJweA,397
 sinapsis_data_readers/helpers/tags.py,sha256=YeddHmiX9kq2wDUhQ6-elIDNxt3ojBs8oHQugzyjM3s,620
@@ -19,11 +18,11 @@ sinapsis_data_readers/templates/audio_readers/base_audio_reader.py,sha256=-3biMc
 sinapsis_data_readers/templates/datasets_readers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 sinapsis_data_readers/templates/datasets_readers/csv_datasets.py,sha256=jn2x8QXpDn-wLoXML24xcfJ29WHT2OhRuFNrU105lOs,1210
 sinapsis_data_readers/templates/datasets_readers/dataset_splitter.py,sha256=6FqN1x6V748Q_ESFfxfaCRJKJQY8cK-gwRHvzuYdVqI,8860
-sinapsis_data_readers/templates/datasets_readers/sklearn_datasets.py,sha256=yQqQFL_mfcRzdPX6Ebq1ZflvMVt5Fpq573_ZhOGWEx8,8325
-sinapsis_data_readers/templates/datasets_readers/sktime_datasets.py,sha256=lkH55Fhc4u6w0FlRW23Z41K_g3iTkxeXTAWrUy3Vb8s,9450
+sinapsis_data_readers/templates/datasets_readers/sklearn_datasets.py,sha256=Nr3RjdXxjtRz-mf2SwLDlpZ_AvWsno476n0j9GuLaOc,8244
+sinapsis_data_readers/templates/datasets_readers/sktime_datasets.py,sha256=TEUQVBP7sCYh6hvCX3W1N6c3Cn_v012dfaFKzJFqek4,9500
 sinapsis_data_readers/templates/image_readers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 sinapsis_data_readers/templates/image_readers/base_image_folder_data_loader.py,sha256=UM2SmBX7B2RE1OgwRtBn-GZdKmrgZILdN32itHIJKQI,4832
-sinapsis_data_readers/templates/image_readers/coco_dataset_reader.py,sha256=_UnV7NyQp_Qms-4MG7iBVabTvygEGyy6r2yNacFkKgk,14720
+sinapsis_data_readers/templates/image_readers/coco_dataset_reader.py,sha256=cFVP50LeRSu9tppy4RYZbAmN775f6AuGUdDTzAHRf3k,14675
 sinapsis_data_readers/templates/image_readers/csv_dataset_reader.py,sha256=k2eVDSLnX3dDkkq0ILgaB6X_sf0wgPyYbKTFX3rGBxo,4966
 sinapsis_data_readers/templates/image_readers/image_folder_reader_cv2.py,sha256=XLoYT_5AZvqxaltek_MMUgA0gtJIzyKLL7YpUIvHaIU,2337
 sinapsis_data_readers/templates/image_readers/image_folder_reader_kornia.py,sha256=LxrveCcVjtM7d3-tely03sfmATfSXOm0Smzdm7EugZI,2466
@@ -32,11 +31,11 @@ sinapsis_data_readers/templates/text_readers/text_input.py,sha256=d3NXeErhNqY9dY
 sinapsis_data_readers/templates/video_readers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 sinapsis_data_readers/templates/video_readers/base_video_reader.py,sha256=QhW_VDzqA5YCDKdOxqzFFyEW8-LC1XAdeRGuQYWvMlw,14422
 sinapsis_data_readers/templates/video_readers/video_reader_cv2.py,sha256=n3EYBYgKNC2zua7IHF6KCcIj41Mqpjp5sFRZLuPNeUs,4037
-sinapsis_data_readers/templates/video_readers/video_reader_dali.py,sha256=0nmHGPLCC4DXolwLpYdL5vExms3jOGyY_54HGPUXWHM,8815
+sinapsis_data_readers/templates/video_readers/video_reader_dali.py,sha256=TIsV1h4eYVOocdwC8tqW3aYz_9l5XJq5nTVc4rWlFUQ,8804
 sinapsis_data_readers/templates/video_readers/video_reader_ffmpeg.py,sha256=uAnV02i9gy7p9mxTVcx20F6ily4JhBtJSDJ93Reyi4w,5046
 sinapsis_data_readers/templates/video_readers/video_reader_torchcodec.py,sha256=wMCjRCaMknDYPOsspuf7NVEhy49h818lVq__AHTsFA8,4036
-sinapsis_data_readers-0.1.16.dist-info/licenses/LICENSE,sha256=hIahDEOTzuHCU5J2nd07LWwkLW7Hko4UFO__ffsvB-8,34523
-sinapsis_data_readers-0.1.16.dist-info/METADATA,sha256=7Xlsk_TmpRiYG4SNYDB0h-TTKWK9XP8YTFa2Hzm3ddA,6520
-sinapsis_data_readers-0.1.16.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-sinapsis_data_readers-0.1.16.dist-info/top_level.txt,sha256=3R3oDiABqDVBW2Fc-SpWXYHkRdYFGZjT_wo6Q0Uqnhw,41
-sinapsis_data_readers-0.1.16.dist-info/RECORD,,
+sinapsis_data_readers-0.1.19.dist-info/licenses/LICENSE,sha256=hIahDEOTzuHCU5J2nd07LWwkLW7Hko4UFO__ffsvB-8,34523
+sinapsis_data_readers-0.1.19.dist-info/METADATA,sha256=BAgUowN5EKwL35zhcJQB-O3YazivmRbiEpDtRBGWALs,6520
+sinapsis_data_readers-0.1.19.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+sinapsis_data_readers-0.1.19.dist-info/top_level.txt,sha256=3R3oDiABqDVBW2Fc-SpWXYHkRdYFGZjT_wo6Q0Uqnhw,41
+sinapsis_data_readers-0.1.19.dist-info/RECORD,,

sinapsis_data_readers/helpers/image_color_space_converter.py

@@ -1,53 +0,0 @@
-# -*- coding: utf-8 -*-
-from enum import Enum
-
-import cv2
-from sinapsis_core.data_containers.data_packet import ImageColor, ImagePacket
-from sinapsis_core.utils.logging_utils import sinapsis_logger
-
-color_mapping = {
-    (ImageColor.RGB, ImageColor.BGR): cv2.COLOR_RGB2BGR,
-    (ImageColor.RGB, ImageColor.GRAY): cv2.COLOR_RGB2GRAY,
-    (ImageColor.RGB, ImageColor.RGBA): cv2.COLOR_RGB2RGBA,
-    (ImageColor.BGR, ImageColor.RGB): cv2.COLOR_BGR2RGB,
-    (ImageColor.BGR, ImageColor.GRAY): cv2.COLOR_BGR2GRAY,
-    (ImageColor.BGR, ImageColor.RGBA): cv2.COLOR_BGR2RGBA,
-    (ImageColor.GRAY, ImageColor.RGB): cv2.COLOR_GRAY2RGB,
-    (ImageColor.GRAY, ImageColor.BGR): cv2.COLOR_GRAY2BGR,
-    (ImageColor.GRAY, ImageColor.RGBA): cv2.COLOR_GRAY2RGBA,
-    (ImageColor.RGBA, ImageColor.RGB): cv2.COLOR_RGBA2RGB,
-    (ImageColor.RGBA, ImageColor.BGR): cv2.COLOR_RGBA2BGR,
-    (ImageColor.RGBA, ImageColor.GRAY): cv2.COLOR_RGBA2GRAY,
-}
-
-
-def convert_color_space_cv(image: ImagePacket, desired_color_space: Enum) -> ImagePacket:
-    """Converts an image from one color space to another, provided
-        they are in the color mapping options.
-
-    Args:
-        image (ImagePacket): Image packet to apply the conversion
-        desired_color_space (Enum): Color space to convert the image
-
-    Returns:
-        ImagePacket: Updated ImagePacket with content converted into the new color space
-        
-    Raises:
-         ValueError: If the conversion is not possible, return an error.
-
-    """
-    current_color_space = image.color_space
-
-    if (current_color_space, desired_color_space) in color_mapping:
-        conversion_code = color_mapping[(current_color_space, desired_color_space)]
-        try:
-            image.content = cv2.cvtColor(image.content, conversion_code)
-            image.color_space = desired_color_space
-
-        except cv2.error:
-            sinapsis_logger.error(f"Invalid conversion between {current_color_space} and {desired_color_space}")
-
-    else:
-        raise ValueError(f"Conversion from {current_color_space} to {desired_color_space} is not supported.")
-
-    return image