sps44 commited on
Commit
8770ed5
0 Parent(s):

Duplicate from renumics/emodb-model-debugging

Browse files
.gitattributes ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.whl filter=lfs diff=lfs merge=lfs -text
2
+ *.7z filter=lfs diff=lfs merge=lfs -text
3
+ *.arrow filter=lfs diff=lfs merge=lfs -text
4
+ *.bin filter=lfs diff=lfs merge=lfs -text
5
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
6
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
7
+ *.ftz filter=lfs diff=lfs merge=lfs -text
8
+ *.gz filter=lfs diff=lfs merge=lfs -text
9
+ *.h5 filter=lfs diff=lfs merge=lfs -text
10
+ *.joblib filter=lfs diff=lfs merge=lfs -text
11
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
12
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
13
+ *.model filter=lfs diff=lfs merge=lfs -text
14
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
15
+ *.npy filter=lfs diff=lfs merge=lfs -text
16
+ *.npz filter=lfs diff=lfs merge=lfs -text
17
+ *.onnx filter=lfs diff=lfs merge=lfs -text
18
+ *.ot filter=lfs diff=lfs merge=lfs -text
19
+ *.parquet filter=lfs diff=lfs merge=lfs -text
20
+ *.pb filter=lfs diff=lfs merge=lfs -text
21
+ *.pickle filter=lfs diff=lfs merge=lfs -text
22
+ *.pkl filter=lfs diff=lfs merge=lfs -text
23
+ *.pt filter=lfs diff=lfs merge=lfs -text
24
+ *.pth filter=lfs diff=lfs merge=lfs -text
25
+ *.rar filter=lfs diff=lfs merge=lfs -text
26
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
27
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
.gitignore ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+
2
+ .venv/
Dockerfile ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ FROM python:3.9
2
+
3
+ WORKDIR /code
4
+ ENV HOME=/code
5
+ COPY ./renumics_spotlight-1.3.0.post116+a49d537-py3-none-any.whl /code/renumics_spotlight-1.3.0.post116+a49d537-py3-none-any.whl
6
+ # RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt
7
+
8
+ RUN apt install curl
9
+ RUN pip install pip -U
10
+
11
+ RUN pip install renumics_spotlight-1.3.0.post116+a49d537-py3-none-any.whl
12
+
13
+
14
+ RUN pip install pyarrow datasets
15
+
16
+ COPY . .
17
+ RUN mkdir -p /code/.cache
18
+ RUN chmod -R 777 /code
19
+ RUN python prepare.py
20
+ CMD ["python", "run.py"]
README.md ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ title: Debug a voice analytics model
3
+ emoji: 📊
4
+ colorFrom: gray
5
+ colorTo: blue
6
+ sdk: docker
7
+ pinned: false
8
+ license: mit
9
+ app_file: run.py
10
+ datasets:
11
+ - renumics/emodb
12
+ tags:
13
+ - renumics
14
+ - spotlight
15
+ - data-centric-ai
16
+ duplicated_from: renumics/emodb-model-debugging
17
+ ---
18
+
19
+ Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
emodb_embedding_issues.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f4a5b1d01f9e233e28b90b00cf5c797cc28b469ea8ee266c76db02ed436c44f
3
+ size 1607
emodb_full_results.parquet ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a0abe6f42c0bc929838e1f56ac956b34b7d75ff4c45e01d3a53a5459d8fa7fa
3
+ size 11141947
emodb_metadata_issues.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ae74f1f53f539a5ea1418210e8126bf6849b3b2a5366b170f9558893fca9953
3
+ size 3695
layout-model-comparison.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"orientation":"horizontal","children":[{"kind":"split","weight":19.132176677590795,"orientation":"vertical","children":[{"kind":"tab","weight":50,"children":[{"kind":"widget","name":"Table","type":"table","config":{"tableView":"full","visibleColumns":null,"sorting":null,"orderByRelevance":false}}]},{"kind":"tab","weight":50,"children":[{"kind":"widget","name":"Embedding on emotion model","type":"similaritymap","config":{"placeBy":null,"reductionMethod":null,"colorBy":"m2_gender_prediction_error","sizeBy":null,"filter":false,"umapNNeighbors":20,"umapMetric":null,"umapMinDist":0.15,"pcaNormalization":null,"umapMenuLocalGlobalBalance":null,"umapMenuIsAdvanced":false}}]}]},{"kind":"split","weight":14.89969874351945,"orientation":"vertical","children":[{"kind":"split","weight":6.546302818342063,"orientation":"horizontal","children":[{"kind":"tab","weight":50,"children":[{"kind":"widget","name":"Accuracy","type":"Metric","config":{"metric":"accuracy","columns":["gender_bool","m1_gender_pred_bool"]}}]},{"kind":"tab","weight":50,"children":[{"kind":"widget","name":"F1","type":"Metric","config":{"metric":"F1","columns":["gender_bool","m1_gender_pred_bool"]}}]}]},{"kind":"tab","weight":25.584633033153384,"children":[{"kind":"widget","name":"Confusion Matrix","type":"ConfusionMatrix","config":{"xColumn":"gender","yColumn":"m1_gender_prediction_string"}}]},{"kind":"tab","weight":25.584633033153384,"children":[{"kind":"widget","name":"Confusion Matrix (2)","type":"ConfusionMatrix","config":{"xColumn":"gender_bool","yColumn":"m2_gender_pred_bool"}}]}]},{"kind":"split","weight":15.312004107540265,"orientation":"vertical","children":[{"kind":"tab","weight":54.21436004162331,"children":[{"kind":"widget","name":"Model 1 vs Model 2 prediction errors","type":"ConfusionMatrix","config":{"xColumn":"m1_gender_prediction_error","yColumn":"m2_gender_prediction_error"}}]},{"kind":"tab","weight":45.78563995837669,"children":[{"kind":"widget","name":"Issues from Sliceguard","type":"IssuesWidget","config":null}]}]},{"kind":"tab","weight":16.634733093151677,"children":[{"kind":"widget","name":"Inspector","type":"inspector","config":{"views":[{"view":"AudioView","columns":["audio"],"name":"audio","key":"tY8GHhvKXUvWMumcC6aEK4"},{"view":"ScalarView","columns":["gender"],"name":"view","key":"464686a8-db0d-40a5-a31d-38323f66e99a"},{"view":"TextLens","columns":["m1_gender_prediction_string"],"name":"view","key":"9ced1617-7d59-4abf-acb0-c9a8ed393ebf"},{"view":"SpectrogramView","columns":["audio"],"name":"view","key":"95aead50-93b4-4a80-a9b2-38a5ba1521f6"}],"visibleColumns":4}}]}]}
layout-model-debug.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"orientation":"horizontal","children":[{"kind":"split","weight":22.1951801110117,"orientation":"vertical","children":[{"kind":"tab","weight":50,"children":[{"kind":"widget","name":"Table","type":"table","config":{"tableView":"full","visibleColumns":null,"sorting":null,"orderByRelevance":false}}]},{"kind":"tab","weight":50,"children":[{"kind":"widget","name":"Embedding on emotion model","type":"similaritymap","config":{"placeBy":null,"reductionMethod":null,"colorBy":null,"sizeBy":null,"filter":false,"umapNNeighbors":20,"umapMetric":null,"umapMinDist":0.15,"pcaNormalization":null,"umapMenuLocalGlobalBalance":null,"umapMenuIsAdvanced":false}}]}]},{"kind":"split","weight":15.587276091496047,"orientation":"vertical","children":[{"kind":"split","weight":11.751097808946518,"orientation":"horizontal","children":[{"kind":"tab","weight":50,"children":[{"kind":"widget","name":"Accuracy","type":"Metric","config":{"metric":"accuracy","columns":["gender_bool","m1_gender_prediction_error"]}}]},{"kind":"tab","weight":50,"children":[{"kind":"widget","name":"F1","type":"Metric","config":{"metric":"F1","columns":["gender_bool","m1_gender_prediction_error"]}}]}]},{"kind":"tab","weight":45.964471075702306,"children":[{"kind":"widget","name":"Confusion Matrix","type":"ConfusionMatrix","config":{"xColumn":"gender","yColumn":"m1_gender_prediction_string"}}]},{"kind":"tab","weight":42.28443111535119,"children":[{"kind":"widget","name":"Issues from Sliceguard","type":"IssuesWidget","config":null}]}]},{"kind":"split","weight":11.561423326142764,"orientation":"vertical","children":[{"kind":"tab","weight":50,"children":[{"kind":"widget","name":"Gender vs. Emotion","type":"ConfusionMatrix","config":{"xColumn":"gender","yColumn":"emotion"}}]},{"kind":"tab","weight":50,"children":[{"kind":"widget","name":"Confusion Matrix (2)","type":"ConfusionMatrix","config":{"xColumn":"gender","yColumn":"age"}}]}]},{"kind":"tab","weight":16.634733093151677,"children":[{"kind":"widget","name":"Inspector","type":"inspector","config":{"views":[{"view":"AudioView","columns":["audio"],"name":"audio","key":"tY8GHhvKXUvWMumcC6aEK4"},{"view":"ScalarView","columns":["gender"],"name":"view","key":"464686a8-db0d-40a5-a31d-38323f66e99a"},{"view":"TextLens","columns":["m1_gender_prediction_string"],"name":"view","key":"9ced1617-7d59-4abf-acb0-c9a8ed393ebf"},{"view":"SpectrogramView","columns":["audio"],"name":"view","key":"95aead50-93b4-4a80-a9b2-38a5ba1521f6"}],"visibleColumns":4}}]}]}
prepare.py ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import pickle
2
+ import datasets
3
+ import os
4
+ import pandas as pd
5
+
6
+ if __name__ == "__main__":
7
+ cache_file = "dataset_cache.parquet"
8
+ if os.path.exists(cache_file):
9
+ # Load dataset from cache
10
+ df = pd.read_parquet(cache_file)
11
+ print("Dataset loaded from cache.")
12
+ else:
13
+ # Load dataset using datasets.load_dataset()
14
+ dataset = datasets.load_dataset("renumics/emodb", split="all")
15
+ print("Dataset loaded using datasets.load_dataset().")
16
+
17
+ df = dataset.to_pandas()
18
+
19
+ # Save dataset to cache
20
+ df.to_parquet(cache_file)
21
+
22
+ print("Dataset saved to cache.")
23
+
renumics_spotlight-1.3.0.post116+a49d537-py3-none-any.whl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1229d32fdd502c860bf93232e8f526c1132ba7cde7ee796338e0dea004977d00
3
+ size 2525800
requirements.txt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ renumics-spotlight
2
+ datasets
3
+ fastparquet
run.py ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import pickle
2
+ import datasets
3
+ from renumics import spotlight
4
+ import os
5
+ import pandas as pd
6
+
7
+ if __name__ == "__main__":
8
+ cache_file = "dataset_cache.parquet"
9
+ cache_file_enrichment="emodb_full_results.parquet"
10
+ cache_file_issues="emodb_metadata_issues.pkl"
11
+
12
+ if os.path.exists(cache_file):
13
+ # Load dataset from cache
14
+ df_db = pd.read_parquet(cache_file)
15
+ print("Dataset loaded from cache.")
16
+ else:
17
+ # Load dataset using datasets.load_dataset()
18
+ dataset = datasets.load_dataset("renumics/emodb", split="all")
19
+ print("Dataset loaded using datasets.load_dataset().")
20
+
21
+ df_db = dataset.to_pandas()
22
+
23
+ # Save dataset to cache
24
+ df_db.to_parquet(cache_file)
25
+
26
+ print("Dataset saved to cache.")
27
+
28
+ df=pd.read_parquet(cache_file_enrichment)
29
+
30
+ df['audio'] = df_db['audio']
31
+
32
+ with open(cache_file_issues, "rb") as issue_file:
33
+ issues = pickle.load(issue_file)
34
+
35
+
36
+ while True:
37
+ dtypes = dtype={"audio": spotlight.Audio,
38
+ 'm1_embedding':spotlight.Embedding,
39
+ 'm2_embedding':spotlight.Embedding,
40
+ 'embedding_emotion':spotlight.Embedding}
41
+ view = spotlight.show(df, issues=issues, port=7860, host="0.0.0.0", layout="layout-model-comparison.json",
42
+ dtype=dtypes, allow_filebrowsing=False)
43
+ view.close()