added cv enrichments

cifar100-enrichment-cv.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bc7e67b598b765cce75309f7c414a13ca9fcc8004f436a0490822c899bfa66c
+size 544628

prepare.py

@@ -4,15 +4,6 @@ import os
 import pandas as pd
 from cleanvision.imagelab import Imagelab
 
-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"
@@ -25,12 +16,8 @@ if __name__ == "__main__":
         dataset = datasets.load_dataset("renumics/cifar100-enriched", split="test")
         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)    
+        df = dataset.to_pandas()  
+ 
        
 
         # Save dataset to cache

run.py

@@ -6,10 +6,15 @@ import pandas as pd
 
 if __name__ == "__main__":
     cache_file = "dataset_cache.parquet"
+    cache_file_enrichment="cifar100-enrichment-cv.parquet"
+    cache_file_issues="sliceline.pkl"
+    
     if os.path.exists(cache_file):
         # Load dataset from cache
         df = pd.read_parquet(cache_file) 
         
+
+        
         print("Dataset loaded from cache.")
     else:
         # Load dataset using datasets.load_dataset()
@@ -25,7 +30,11 @@ if __name__ == "__main__":
 
         print("Dataset saved to cache.")
 
-
+    df_cv=pd.read_parquet(cache_file) 
+     
+    with open(issue_cache_file, "rb") as issue_file:
+        issues = pickle.load(issue_file)
+            
     #df = dataset.to_pandas()
     df_show = df.drop(columns=['embedding', 'probabilities'])
     while True: