soeren commited on
Commit
c31d083
β€’
1 Parent(s): e5b11d9

implemented scripts and Dockerfile

Browse files
Files changed (7) hide show
  1. .gitignore +2 -0
  2. Dockerfile +18 -0
  3. README.md +13 -4
  4. prepare.py +26 -0
  5. requirements.txt +2 -0
  6. run.py +33 -0
  7. spotlight-layout.json +1 -0
.gitignore ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ test.py
2
+ Pipfile*
Dockerfile ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ FROM python:3.9
2
+
3
+ WORKDIR /code
4
+ ENV HOME=/code
5
+
6
+ RUN apt install curl
7
+ RUN pip install pip -U
8
+
9
+ RUN pip install renumics-spotlight==1.2.0rc2
10
+
11
+ RUN pip install datasets
12
+ COPY prepare.py .
13
+ RUN python prepare.py
14
+
15
+ COPY . .
16
+ RUN mkdir -p /code/.cache
17
+ RUN chmod -R 777 /code
18
+ CMD ["python", "run.py"]
README.md CHANGED
@@ -1,11 +1,20 @@
1
  ---
2
  title: Speech Commands Enriched
3
- emoji: πŸƒ
4
- colorFrom: yellow
5
- colorTo: indigo
6
  sdk: docker
7
  pinned: false
8
- license: openrail
 
 
 
 
 
 
 
 
 
9
  ---
10
 
11
  Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
 
1
  ---
2
  title: Speech Commands Enriched
3
+ emoji: πŸ“Š
4
+ colorFrom: gray
5
+ colorTo: blue
6
  sdk: docker
7
  pinned: false
8
+ license: mit
9
+ app_file: run.py
10
+ datasets:
11
+ - renumics/cifar100-outlier
12
+ - cifar100
13
+ tags:
14
+ - renumics
15
+ - spotlight
16
+ - EDA
17
+ - outliers
18
  ---
19
 
20
  Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
prepare.py ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import pickle
2
+ import datasets
3
+ import os
4
+ import umap
5
+
6
+
7
+ if __name__ == "__main__":
8
+ cache_file = "dataset_cache.pkl"
9
+ if os.path.exists(cache_file):
10
+ # Load dataset from cache
11
+ with open(cache_file, "rb") as file:
12
+ dataset = pickle.load(file)
13
+ print("Dataset loaded from cache.")
14
+ else:
15
+ # Load dataset using datasets.load_dataset()
16
+ ds = datasets.load_dataset("renumics/speech_commands_enriched", split="train")
17
+ print("Dataset loaded using datasets.load_dataset().")
18
+
19
+ df = ds.to_pandas()
20
+
21
+ # Save dataset to cache
22
+ with open(cache_file, "wb") as file:
23
+ pickle.dump(df, file)
24
+
25
+ print("Dataset saved to cache.")
26
+
requirements.txt ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ renumics-spotlight
2
+ datasets
run.py ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import pickle
2
+ from renumics import spotlight
3
+ import os
4
+
5
+ if __name__ == "__main__":
6
+ cache_file = "dataset_cache.pkl"
7
+ if os.path.exists(cache_file):
8
+ # Load dataset from cache
9
+ with open(cache_file, "rb") as file:
10
+ df = pickle.load(file)
11
+ print("Dataset loaded from cache.")
12
+
13
+
14
+ while True:
15
+ dtypes = {
16
+ "full_audio": spotlight.Audio,
17
+ "embedding_reduced": spotlight.Embedding
18
+ }
19
+ view = spotlight.show(
20
+ df,
21
+ dtype=dtypes,
22
+ layout="https://spotlight.renumics.com/resources/layout_pre_post_ft_hf.json",
23
+ port=7860,
24
+ host="0.0.0.0",
25
+ allow_filebrowsing=False
26
+ )
27
+
28
+ view.close()
29
+
30
+ else:
31
+ print(f"Dataset {cache_file} not found. Please run prepare.py first.")
32
+
33
+
spotlight-layout.json ADDED
@@ -0,0 +1 @@
 
 
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}}]}]}