convert to cae dataset

Dockerfile

@@ -8,12 +8,10 @@ ENV HOME=/code
 RUN apt install curl
 RUN pip install pip -U
 
-RUN pip install renumics-spotlight==1.3.0rc8 pyarrow
-
-RUN pip install datasets cleanvision
+RUN pip install renumics-spotlight==1.3.0
 
 COPY . .
 RUN mkdir -p /code/.cache
 RUN chmod -R 777 /code
-RUN python prepare.py
+#RUN python prepare.py
 CMD ["python", "run.py"]

README.md

@@ -1,5 +1,5 @@
 ---
-title: Explore data slices in the CIFAR-100 benchmark
+title: Explore issues in a crash simulation dataset
 emoji: 📊
 colorFrom: gray
 colorTo: blue
@@ -8,14 +8,13 @@ pinned: false
 license: mit
 app_file: run.py
 datasets:
-- renumics/cifar100-enriched
-- cifar100
 tags:
 - renumics
 - spotlight
-- sliceline
+- simulation
+- CAE
 - data-centric-ai
-duplicated_from: renumics/cifar100-sliceline-demo
+
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

cifar100-enrichment-cv.parquet → converted_cae_dataset.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bc7e67b598b765cce75309f7c414a13ca9fcc8004f436a0490822c899bfa66c
-size 544628
+oid sha256:1b4c599f0fcd7715b7bc76da66fa1591053693edfad7035cf7050192cac57d79
+size 799730101

sliceline.pkl → issues.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e55a43568ba74521a1b62c44329c8b8dccf862715a5d067cc68844bc28e52d7
-size 8738
+oid sha256:5072424adc9edb6027ab8cf3eb8cb6677681b38433db5be35677a60c1e789030
+size 428

requirements.txt

@@ -1,3 +1 @@
 renumics-spotlight
-datasets
-fastparquet

run.py

@@ -5,36 +5,16 @@ import os
 import pandas as pd
 
 if __name__ == "__main__":
-    cache_file = "dataset_cache.parquet"
-    cache_file_enrichment="cifar100-enrichment-cv.parquet"
-    cache_file_issues="sliceline.pkl"
-    
-    if os.path.exists(cache_file):
-        # Load dataset from cache
-        df = pd.read_parquet(cache_file) 
-        print("Dataset loaded from cache.")
-    else:
-        # Load dataset using datasets.load_dataset()
-        dataset = datasets.load_dataset("renumics/cifar100-enriched", split="test")
-        print("Dataset loaded using datasets.load_dataset().")
-        
-        df = dataset.to_pandas()  
-
-        # Save dataset to cache
-        df.to_parquet(cache_file)
-
-        print("Dataset saved to cache.")
-    
-    df_cv=pd.read_parquet(cache_file_enrichment) 
-    
-    df = pd.concat([df, df_cv], axis=1)
+    cache_file = "converted_cae_dataset.h5"
+    cache_file_issues="issues.pkl"    
+  
      
     with open(cache_file_issues, "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, issues=issues, port=7860, host="0.0.0.0", layout="sliceline-layout.json",
-                    dtype={"image": spotlight.Image, "embedding_reduced": spotlight.Embedding}, allow_filebrowsing=False)
+        view = spotlight.show(cache_file, issues=issues, port=7860, host="0.0.0.0", #layout="cae-layout.json",
+                    allow_filebrowsing=False)
         view.close()

sliceline-layout.json

@@ -1 +0,0 @@
-{"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"}]}}]}]}