Fix batching for stackid assignment

mirar/data/base_data.py

@@ -37,6 +37,9 @@ def __getitem__(self, item):
     def __setitem__(self, key, value):
         raise NotImplementedError
 
+    def __str__(self):
+        return f"<An {self.__class__.__name__} object, built from {self.get_name()}>"
+
     def get_name(self) -> str:
         """Function to retrieve the :variable:`mirar.paths.BASE_NAME_KEY`
         of the parent image

mirar/data/image_data.py

@@ -107,9 +107,6 @@ def get_cache_path(self) -> Path:
         name = f"{hashlib.sha1(base.encode()).hexdigest()}.npy"
         return cache.get_cache_dir().joinpath(name)
 
-    def __str__(self):
-        return f"<An {self.__class__.__name__} object, built from {self.get_name()}>"
-
     def set_data(self, data: np.ndarray):
         """
         Set the data with cache

mirar/pipelines/winter/blocks.py

@@ -296,7 +296,11 @@
 save_raw = [
     ImageSaver(output_dir_name="raw_unpacked", write_mask=False),
     DatabaseImageInserter(db_table=Raw, duplicate_protocol="replace"),
+    # Group into planned stacks, and label each image with the intended stackid
+    ImageRebatcher(["BOARD_ID", "FILTER", "EXPTIME", TARGET_KEY, "SUBCOORD"]),
     CustomImageBatchModifier(winter_stackid_annotator),
+    # Process each raw image in parallel
+    ImageRebatcher(BASE_NAME_KEY),
     ImageSaver(output_dir_name="raw_unpacked", write_mask=False),
     HeaderAnnotator(input_keys=LATEST_SAVE_KEY, output_key=RAW_IMG_KEY),
     ImageRejector(("BOARD_ID", "0")),
@@ -444,7 +448,7 @@
 
 stack_dithers = [
     CustomImageBatchModifier(winter_boardid_6_demasker),
-    ImageRebatcher(["BOARD_ID", "FILTER", "EXPTIME", TARGET_KEY, "SUBCOORD"]),
+    ImageRebatcher("STACKID"),
     Swarp(
         swarp_config_path=swarp_config_path,
         calculate_dims_in_swarp=True,

mirar/processors/utils/image_loader.py

@@ -181,6 +181,7 @@ def _apply_to_images(
         for image in batch:
             new_image_file = image.header[self.header_key]
             new_image = self.load_image(new_image_file)
+
             if self.copy_header_keys is not None:
                 for key in self.copy_header_keys:
                     new_image.header[key] = image.header[key]
@@ -219,7 +220,10 @@ def __init__(
         self.load_image = load_image
 
     def description(self):
-        return f"Processor to load {len(self.img_list)} images from list"
+        return (
+            f"Load {len(self.img_list)} images from "
+            f"list of {len(self.img_list)} files"
+        )
 
     def _apply_to_images(self, batch: ImageBatch) -> ImageBatch:
         """

mirar/processors/utils/image_selector.py

@@ -119,7 +119,11 @@ def split_images_into_batches(
             groups[uid] = [image]
         else:
             groups[uid] += [image]
-    logger.debug(groups)
+
+    logger.debug(
+        " & ".join(f"({key}: {[str(x) for x in val]})" for key, val in groups.items())
+    )
+
     res = Dataset([ImageBatch(x) for x in groups.values()])
 
     return res