CHORE: remove duplicate clearml task config

dataPrep/data_preparation.py

@@ -53,7 +53,8 @@ task = Task.init(
 task.set_random_seed(SEED)
 clearml_logger = task.get_logger()
 
-# --- Track full configuration in ClearML ---
+
+# -------- Track full configuration in ClearML --------
 task.connect({
     "seed": SEED,
     "dataset": {
@@ -77,12 +78,6 @@ data_plants, prototyping_dataset, features, clearml_dataset = make_subset(
     DATASET_LINK, DATASET_SUBSET_RATIO, clearml_logger
 )
 
-# Log subset config to ClearML
-task.connect_configuration(
-    {"subset_ratio": DATASET_SUBSET_RATIO},
-    name="Data subsetting"
-)
-
 
 # ---- Exploratory data analysis (EDA) ----
 
@@ -145,7 +140,7 @@ clearml_logger.report_matplotlib_figure(
 # ----------------------------------------------------------------------
 if __name__ == "__main__":
     
-    # ------------------- Dataset splits ----------------------------------
+    # ---------------- Dataset splits ----------------
     aug_config = {
         'rotation': ROTATION,
         'brightness': BRIGHTNESS,

dataPrep/helpers/create_dataset.py

@@ -9,7 +9,11 @@ from datasets import load_dataset
 from clearml import Dataset
 
 
-# Load a DS from HuggingFace Link and subset the DS - upload both to ClearML
+'''
+Load a DS from HuggingFace Link & randomly subset it - upload subset to ClearML
+Subset indicies are uploaded to ClearML for reproducibility
+REPRODUCE: Load full DS, then load indicies from ClearML to get same subset
+'''
 def make_subset(dataset_link, subset_ratio, clearml_logger):
 
     # Load dataset