revert to simple cifar

prepare.py

@@ -1,44 +1,22 @@
 import pickle
 import datasets
 import os
-from cleanvision.imagelab import Imagelab
-import pandas as pd
-
-
-
-
-def cv_issues_cleanvision(df, image_name='image'):
-
-    image_paths = df['image'].to_list()
-    imagelab = Imagelab(filepaths=image_paths)
-    imagelab.find_issues()
-
-    df_cv=imagelab.issues.reset_index()
-
-    return df_cv
-    
 
 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()
-        
-        df=df.reset_index(drop=True)
-        
-        df_cv=cv_issues_cleanvision(df)
-        df = pd.concat([df, df_cv], axis=1)
 
         # 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

@@ -1,26 +1,21 @@
+import pickle
+import datasets
 import os
-import pandas as pd
-import pickle 
-from renumics import spotlight
 
 if __name__ == "__main__":
-    cache_file = "dataset_cache.parquet"
-    issue_cache_file="sliceline.pkl"
-    
-    print('starting up')
+    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()
+        dataset = datasets.load_dataset("renumics/cifar100-enriched", split="train")
+        print("Dataset loaded using datasets.load_dataset().")
 
-    #load dataframe from parquet
-    df = pd.read_parquet(cache_file)    
-    
- 
-    df_show = df.drop(columns=['embedding', 'probabilities'])
-    
-    with open(issue_cache_file, "rb") as file:
-        issues = pickle.load(file)
-        print('issues loaded')
-    
-    while True:
-        view = spotlight.show(df_show, port=7860, host="0.0.0.0", issues=issues, layout="sliceline-layout.json",
-                    dtype={"image": spotlight.Image, "embedding_reduced": spotlight.Embedding}, allow_filebrowsing=False)
-        
-        view.close()
+        # Save dataset to cache
+        with open(cache_file, "wb") as file:
+            pickle.dump(dataset, file)
+
+        print("Dataset saved to cache.")