initial

README.md

@@ -1,5 +1,5 @@
 ---
-title: Explore CIFAR-100 Enriched with Spotlight
+title: Explore data slices in the CIFAR-100 benchmark
 emoji: 📊
 colorFrom: gray
 colorTo: blue
@@ -13,9 +13,8 @@ datasets:
 tags:
 - renumics
 - spotlight
-- EDA
-- enriched
-duplicated_from: renumics/cifar100-enriched
+- sliceline
+- data-centric-ai
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

prepare.py

@@ -11,7 +11,7 @@ if __name__ == "__main__":
         print("Dataset loaded from cache.")
     else:
         # Load dataset using datasets.load_dataset()
-        dataset = datasets.load_dataset("renumics/cifar100-enriched", split="train")
+        dataset = datasets.load_dataset("renumics/cifar100-enriched", split="test")
         print("Dataset loaded using datasets.load_dataset().")
 
         # Save dataset to cache

run.py

@@ -5,6 +5,7 @@ import os
 
 if __name__ == "__main__":
     cache_file = "dataset_cache.pkl"
+    issue_cache_file="sliceline.pkl"
     if os.path.exists(cache_file):
         # Load dataset from cache
         with open(cache_file, "rb") as file:
@@ -20,11 +21,13 @@ if __name__ == "__main__":
             pickle.dump(dataset, file)
 
         print("Dataset saved to cache.")
-
+    
+    with open(issue_cache_file, "rb") as issue_file:
+         issues = pickle.load(issue_file)
 
     df = dataset.to_pandas()
     df_show = df.drop(columns=['embedding', 'probabilities'])
     while True:
-        view = spotlight.show(df_show.sample(5000, random_state=1), port=7860, host="0.0.0.0", 
+        view = spotlight.show(df_show, port=7860, host="0.0.0.0", issues=issues,
                     dtype={"image": spotlight.Image, "embedding_reduced": spotlight.Embedding}, allow_filebrowsing=False)
         view.close()

sliceline-layout.json

@@ -0,0 +1 @@
+{"orientation":"vertical","children":[{"kind":"split","weight":1,"orientation":"horizontal","children":[{"kind":"tab","weight":1,"children":[{"kind":"widget","name":"Table","type":"table","config":{"tableView":"selected","visibleColumns":null,"sorting":null,"orderByRelevance":false}}]},{"kind":"tab","weight":1,"children":[{"kind":"widget","name":"Similarity Map","type":"similaritymap","config":{"placeBy":null,"reductionMethod":null,"colorBy":"fine_label_prediction_error","sizeBy":null,"filter":false,"umapNNeighbors":20,"umapMetric":null,"umapMinDist":0.15,"pcaNormalization":null,"umapMenuLocalGlobalBalance":null,"umapMenuIsAdvanced":false}}]},{"kind":"tab","weight":1,"children":[{"kind":"widget","name":"Issues","type":"IssuesWidget","config":null}]}]},{"kind":"tab","weight":1,"children":[{"kind":"widget","name":"Inspector","type":"inspector","config":{"views":[{"view":"ArrayLens","key":"12MuLXBrGWyR1UqByhSAGR","name":"embedding_reduced","columns":["embedding_reduced"]},{"view":"ImageView","key":"tuCdyeyADoxB7jtazsiLt2","name":"image","columns":["image"]},{"view":"TextLens","columns":["fine_label_prediction_str"],"name":"view","key":"45099023-3dcc-4f56-baa3-b0447a98a3c6"},{"view":"TextLens","columns":["fine_label_str"],"name":"view","key":"f057b3df-7920-4adb-bf6f-03c260a56b94"}]}}]}]}

sliceline.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af9bff1ba785b9effd303824617bb3c79ee1113d1bf7786d2c878541340d2eb1
+size 8504