switch to parquet save

prepare.py

@@ -3,20 +3,22 @@ import datasets
 import os
 
 if __name__ == "__main__":
-    cache_file = "dataset_cache.pkl"
+    cache_file = "dataset_cache.parquet"
     if os.path.exists(cache_file):
         # Load dataset from cache
-        with open(cache_file, "rb") as file:
-            dataset = pickle.load(file)
+        df = pd.read_parquet(cache_file)
         print("Dataset loaded from cache.")
     else:
         # Load dataset using datasets.load_dataset()
-        dataset = datasets.load_dataset("renumics/cifar100-enriched", split="train")
+        dataset = datasets.load_dataset("renumics/cifar100-enriched", split="test")
         print("Dataset loaded using datasets.load_dataset().")
+        
+        df = dataset.to_pandas()       
+       
 
         # Save dataset to cache
-        with open(cache_file, "wb") as file:
-            pickle.dump(dataset, file)
+        #save df as parquet
+        df.to_parquet(cache_file)
 
         print("Dataset saved to cache.")
 

run.py

@@ -4,25 +4,28 @@ from renumics import spotlight
 import os
 
 if __name__ == "__main__":
-    cache_file = "dataset_cache.pkl"
+    cache_file = "dataset_cache.parquet"
     if os.path.exists(cache_file):
         # Load dataset from cache
-        with open(cache_file, "rb") as file:
-            dataset = pickle.load(file)
+        df = pd.read_parquet(cache_file) 
+        
         print("Dataset loaded from cache.")
     else:
         # Load dataset using datasets.load_dataset()
-        dataset = datasets.load_dataset("renumics/cifar100-enriched", split="train")
+        dataset = datasets.load_dataset("renumics/cifar100-enriched", split="test")
         print("Dataset loaded using datasets.load_dataset().")
+        
+        df = dataset.to_pandas()       
+       
 
         # Save dataset to cache
-        with open(cache_file, "wb") as file:
-            pickle.dump(dataset, file)
+        #save df as parquet
+        df.to_parquet(cache_file)
 
         print("Dataset saved to cache.")
 
 
-    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",