Duplicate from renumics/cifar100-sliceline-demo

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,2 @@
+
+.venv/

Dockerfile

@@ -0,0 +1,19 @@
+FROM python:3.9
+
+WORKDIR /code
+ENV HOME=/code
+# COPY ./requirements.txt /code/requirements.txt
+# RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt
+
+RUN apt install curl
+RUN pip install pip -U
+
+RUN pip install renumics-spotlight==1.3.0rc8 pyarrow
+
+RUN pip install datasets cleanvision
+
+COPY . .
+RUN mkdir -p /code/.cache
+RUN chmod -R 777 /code
+RUN python prepare.py
+CMD ["python", "run.py"]

README.md

@@ -0,0 +1,21 @@
+---
+title: Explore data slices in the CIFAR-100 benchmark
+emoji: 📊
+colorFrom: gray
+colorTo: blue
+sdk: docker
+pinned: false
+license: mit
+app_file: run.py
+datasets:
+- renumics/cifar100-enriched
+- cifar100
+tags:
+- renumics
+- spotlight
+- sliceline
+- 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

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

prepare.py

@@ -0,0 +1,23 @@
+import pickle
+import datasets
+import os
+import pandas as pd
+
+if __name__ == "__main__":
+    cache_file = "dataset_cache.parquet"
+    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.")
+

requirements.txt

@@ -0,0 +1,3 @@
+renumics-spotlight
+datasets
+fastparquet

run.py

@@ -0,0 +1,40 @@
+import pickle
+import datasets
+from renumics import spotlight
+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)
+     
+    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.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

spotlight-layout.json

@@ -0,0 +1 @@
+{"orientation":"vertical","children":[{"kind":"split","weight":55.52608311229001,"orientation":"horizontal","children":[{"kind":"tab","weight":41.16700201207244,"children":[{"kind":"widget","name":"Table","type":"table","config":{"tableView":"full","visibleColumns":["coarse_label_str","fine_label_prediction_str","fine_label_str","image","__idx__"],"sorting":[["__idx__","DESC"]],"orderByRelevance":false,"columnWidths":{"coarse_label":92,"coarse_label_str":165,"embedding_reduced":128,"fine_label":92,"fine_label_prediction":92,"fine_label_prediction_error":92,"fine_label_prediction_str":244,"fine_label_str":194,"full_image":256,"image":200,"split":256,"__idx__":92,"__last_edited_at__":192,"__last_edited_by__":256}}}]},{"kind":"tab","weight":33.66487769877306,"children":[{"kind":"widget","name":"Similarity Map","type":"similaritymap","config":{"placeBy":null,"reductionMethod":null,"colorBy":"fine_label_str","sizeBy":null,"filter":false,"umapNNeighbors":20,"umapMetric":null,"umapMinDist":0.15,"pcaNormalization":null,"umapMenuLocalGlobalBalance":null,"umapMenuIsAdvanced":false}},{"kind":"widget","name":"Scatter Plot","type":"scatterplot","config":{"xAxisColumn":null,"yAxisColumn":null,"colorBy":null,"sizeBy":null,"filter":false}}]},{"kind":"tab","weight":25.168120289154498,"children":[{"kind":"widget","name":"Histogram","type":"histogram","config":{"columnKey":"fine_label_str","stackByColumnKey":"fine_label_prediction_error","filter":false}}]}]},{"kind":"tab","weight":44.47391688770999,"children":[{"kind":"widget","name":"Inspector","type":"inspector","config":{"views":[{"view":"ImageView","key":"es3NP2fbYeG5TzTQqCzZKL","name":"image","columns":["image"]},{"view":"TextLens","columns":["fine_label_str"],"name":"view","key":"7262001a-1270-467c-bfe8-6b6883adbc7d"},{"view":"TextLens","columns":["fine_label_prediction_str"],"name":"view","key":"f72a8ae9-17c4-4097-b454-79a6f60865db"},{"view":"ScalarView","columns":["fine_label_prediction_error"],"name":"view","key":"be4d6afe-9093-4581-b363-df11d3c6d34a"}],"visibleColumns":4}}]}]}