revert to template space

prepare.py

@@ -1,28 +1,22 @@
 import pickle
 import datasets
 import os
-import pandas as pd
-from cleanvision.imagelab import Imagelab
 
-    
 if __name__ == "__main__":
-    cache_file = "dataset_cache.parquet"
+    cache_file = "dataset_cache.pkl"
     if os.path.exists(cache_file):
         # Load dataset from cache
-        df = pd.read_parquet(cache_file)
+        with open(cache_file, "rb") as file:
+            dataset = pickle.load(file)
         print("Dataset loaded from cache.")
     else:
         # Load dataset using datasets.load_dataset()
-        dataset = datasets.load_dataset("renumics/cifar100-enriched", split="test")
+        dataset = datasets.load_dataset("renumics/cifar100-enriched", split="train")
         print("Dataset loaded using datasets.load_dataset().")
-        
-        df = dataset.to_pandas()  
- 
-       
 
         # Save dataset to cache
-        #save df as parquet
-        df.to_parquet(cache_file)
+        with open(cache_file, "wb") as file:
+            pickle.dump(dataset, file)
 
         print("Dataset saved to cache.")
 

run.py

@@ -2,40 +2,27 @@ 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"
-    
+    cache_file = "dataset_cache.pkl"
     if os.path.exists(cache_file):
         # Load dataset from cache
-        df = pd.read_parquet(cache_file) 
-        
-
-        
+        with open(cache_file, "rb") as file:
+            dataset = pickle.load(file)
         print("Dataset loaded from cache.")
     else:
         # Load dataset using datasets.load_dataset()
-        dataset = datasets.load_dataset("renumics/cifar100-enriched", split="test")
+        dataset = datasets.load_dataset("renumics/cifar100-enriched", split="train")
         print("Dataset loaded using datasets.load_dataset().")
-        
-        df = dataset.to_pandas()       
-       
 
         # Save dataset to cache
-        #save df as parquet
-        df.to_parquet(cache_file)
+        with open(cache_file, "wb") as file:
+            pickle.dump(dataset, file)
 
         print("Dataset saved to cache.")
 
-    #df_cv=pd.read_parquet(cache_file) 
-     
-    #with open(cache_file_issues, "rb") as issue_file:
-    #    issues = pickle.load(issue_file)
-            
-    #df = dataset.to_pandas()
+
+    df = dataset.to_pandas()
     df_show = df.drop(columns=['embedding', 'probabilities'])
     while True:
         view = spotlight.show(df_show.sample(5000, random_state=1), port=7860, host="0.0.0.0",