Duplicate from renumics/emodb-model-debugging

.gitattributes

@@ -0,0 +1,35 @@
+*.whl filter=lfs diff=lfs merge=lfs -text
+*.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 +1,20 @@
+FROM python:3.9
+
+WORKDIR /code
+ENV HOME=/code
+COPY ./renumics_spotlight-1.3.0.post116+a49d537-py3-none-any.whl /code/renumics_spotlight-1.3.0.post116+a49d537-py3-none-any.whl
+# 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-1.3.0.post116+a49d537-py3-none-any.whl
+
+
+RUN pip install pyarrow datasets 
+
+COPY . .
+RUN mkdir -p /code/.cache
+RUN chmod -R 777 /code
+RUN python prepare.py
+CMD ["python", "run.py"]

README.md

@@ -0,0 +1,19 @@
+---
+title: Debug a voice analytics model
+emoji: 📊
+colorFrom: gray
+colorTo: blue
+sdk: docker
+pinned: false
+license: mit
+app_file: run.py
+datasets:
+- renumics/emodb
+tags:
+- renumics
+- spotlight
+- data-centric-ai
+duplicated_from: renumics/emodb-model-debugging
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

emodb_embedding_issues.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f4a5b1d01f9e233e28b90b00cf5c797cc28b469ea8ee266c76db02ed436c44f
+size 1607

emodb_full_results.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a0abe6f42c0bc929838e1f56ac956b34b7d75ff4c45e01d3a53a5459d8fa7fa
+size 11141947

emodb_metadata_issues.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ae74f1f53f539a5ea1418210e8126bf6849b3b2a5366b170f9558893fca9953
+size 3695

layout-model-comparison.json

@@ -0,0 +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

@@ -0,0 +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

@@ -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/emodb", split="all")
+        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.")
+

renumics_spotlight-1.3.0.post116+a49d537-py3-none-any.whl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1229d32fdd502c860bf93232e8f526c1132ba7cde7ee796338e0dea004977d00
+size 2525800

requirements.txt

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

run.py

@@ -0,0 +1,43 @@
+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="emodb_full_results.parquet"
+    cache_file_issues="emodb_metadata_issues.pkl"
+    
+    if os.path.exists(cache_file):
+        # Load dataset from cache
+        df_db = pd.read_parquet(cache_file) 
+        print("Dataset loaded from cache.")
+    else:
+        # Load dataset using datasets.load_dataset()
+        dataset = datasets.load_dataset("renumics/emodb", split="all")
+        print("Dataset loaded using datasets.load_dataset().")
+        
+        df_db = dataset.to_pandas()  
+
+        # Save dataset to cache
+        df_db.to_parquet(cache_file)
+
+        print("Dataset saved to cache.")
+    
+    df=pd.read_parquet(cache_file_enrichment) 
+    
+    df['audio'] = df_db['audio']
+     
+    with open(cache_file_issues, "rb") as issue_file:
+        issues = pickle.load(issue_file)
+
+
+    while True:
+        dtypes = dtype={"audio": spotlight.Audio, 
+                'm1_embedding':spotlight.Embedding, 
+                'm2_embedding':spotlight.Embedding, 
+                'embedding_emotion':spotlight.Embedding}
+        view = spotlight.show(df, issues=issues, port=7860, host="0.0.0.0", layout="layout-model-comparison.json",
+                    dtype=dtypes, allow_filebrowsing=False)
+        view.close()