space adjusted to new enrichment repo

Dockerfile

@@ -9,9 +9,6 @@ RUN pip install pip -U
 COPY requirements.txt .
 RUN pip install -r requirements.txt
 
-COPY prepare.py .
-RUN python prepare.py
-
 COPY . .
 RUN mkdir -p /code/.cache
 RUN chmod -R 777 /code

prepare.py

@@ -1,29 +0,0 @@
-import pickle
-import datasets
-import os
-import umap
-
-#force restart
-if __name__ == "__main__":
-    cache_file = "dataset_cache.pkl"
-    if os.path.exists(cache_file):
-        # Load dataset from cache
-        with open(cache_file, "rb") as file:
-            dataset = pickle.load(file)
-        print("Dataset loaded from cache.")
-    else:
-        # Load dataset using datasets.load_dataset()
-        ds_train = datasets.load_dataset("renumics/speech_commands_enriched", split="train")
-        ds_test = datasets.load_dataset("renumics/speech_commands_enriched", split="test")
-        ds_validation = datasets.load_dataset("renumics/speech_commands_enriched", split="validation")
-        joined_dataset_enrichment = datasets.concatenate_datasets([ds_train, ds_validation, ds_test])
-        print("Dataset loaded using datasets.load_dataset().")
-
-        df = joined_dataset_enrichment.to_pandas()
-
-        # Save dataset to cache
-        with open(cache_file, "wb") as file:
-            pickle.dump(df, file)
-
-        print("Dataset saved to cache.")
-

run.py

@@ -1,34 +1,22 @@
-import pickle
+import datasets
 from renumics import spotlight
 from renumics.spotlight import layout
-import os
-
-if __name__ == "__main__":
-    cache_file = "dataset_cache.pkl"
-    if os.path.exists(cache_file):
-        # Load dataset from cache
-        with open(cache_file, "rb") as file:
-            df = pickle.load(file)
-        print("Dataset loaded from cache.")
-
-
-        while True:
-            dtypes = {
-                "full_audio": spotlight.Audio,
-                "embedding_reduced": spotlight.Embedding
-            }
-            view = spotlight.show(
-                df,
-                dtype=dtypes,
-                layout= layout.parse("spotlight-layout.json"),
-                port=7860, 
-                host="0.0.0.0",
-                allow_filebrowsing=False 
-            )
-
-            view.close()
-
-    else:
-        print(f"Dataset {cache_file} not found. Please run prepare.py first.")
+from renumics.spotlight.layouts import debug_classification
 
+dataset = datasets.load_dataset("renumics/speech_commands_enrichment_only", "raw_and_enrichment_combined")
+stacked_ds = datasets.concatenate_datasets([dataset["train"], dataset["validation"], dataset["test"]])
+print(dataset)
+while True:
+    layout = debug_classification(label='label_string', prediction='prediction', embedding='embedding_reduced', 
+                                    features=["label", "prediction", "probability"], inspect={'audio': spotlight.Audio})
+    dtypes = {
+        "audio": spotlight.Audio,
+        "embedding_reduced": spotlight.Embedding
+    }
+    view = spotlight.show(
+        stacked_ds,
+        dtype=dtypes,
+        layout= layout
+    )
 
+    view.close()