parquet save

prepare.py

@@ -1,13 +1,13 @@
 import pickle
 import datasets
 import os
+import pandas as pd
 
 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()
@@ -15,8 +15,7 @@ if __name__ == "__main__":
         print("Dataset loaded using datasets.load_dataset().")
 
         # Save dataset to cache
-        with open(cache_file, "wb") as file:
-            pickle.dump(dataset, file)
+        df.to_parquet(cache_file)
 
         print("Dataset saved to cache.")
 

run.py

@@ -2,13 +2,13 @@ import pickle
 import datasets
 from renumics import spotlight
 import os
+import pandas as pd
 
 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()
@@ -16,13 +16,12 @@ if __name__ == "__main__":
         print("Dataset loaded using datasets.load_dataset().")
 
         # Save dataset to cache
-        with open(cache_file, "wb") as file:
-            pickle.dump(dataset, file)
+        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",