Small changes

app.py

@@ -38,8 +38,10 @@ def filter_dataframe(dataframe, eval_dataset, cont_source, checkboxes):
             | (dataframe["Test Split"] > 0.0)
         ]
 
+    dataframe = dataframe.sort_values("Test Split", ascending=False)
+
     return dataframe.style.format(
-        {"Train Split": "{:.1%}", "Development Split": "{:.1%}", "Test Split": "{:.1%}"}
+        {"Train Split": "{:.1%}", "Development Split": "{:.1%}", "Test Split": "{:.1%}"}, na_rep="Unknown"
     )
 
 

contamination_report.csv

@@ -1,4 +1 @@
-Evaluation Dataset;Contaminated Source;Model or corpus;Train Split;Development Split;Test Split;Approach;Citation;PR Link
-conll2003;google/gemma-7b;model;1.0;1.0;1.0;model-based;https://hitz-zentroa.github.io/lm-contamination/blog/;
-conll2003;EleutherAI/the_pile_deduplicated;corpus;1.0;1.0;1.0;data-based;https://aclanthology.org/2023.findings-emnlp.722/;www.google.com
-Test;lololol;corpus;1.0;1.0;1.0;data-based;https://arxiv.org/abs/2310.03668;
+Evaluation Dataset;Subset;Contaminated Source;Model or corpus;Train Split;Development Split;Test Split;Approach;Reference;PR

dataset.py

@@ -207,7 +207,7 @@ def get_dataframe():
     favicon_dict = {}
 
     # Update the favicon dictionary
-    favicon_dict = update_favicon_cache([get_base_url(x) for x in data["Citation"]])
+    favicon_dict = update_favicon_cache([get_base_url(x) for x in data["Reference"]])
 
     # Update the model url dictionary
     model_url_dict = update_model_url_cache(
@@ -221,7 +221,7 @@ def get_dataframe():
     )
 
     # Add favicons URLs to the dataframe in a vectorized manner
-    data["Citation"] = data["Citation"].apply(
+    data["Reference"] = data["Reference"].apply(
         lambda x: build_text_icon(
             text=get_domain_name(x),
             url=x,
@@ -229,7 +229,7 @@ def get_dataframe():
         )
     )
 
-    data["PR Link"] = data["PR Link"].apply(
+    data["PR"] = data["PR"].apply(
         lambda x: build_text_icon(
             text="",
             url=x if x == x else "no link",
@@ -245,6 +245,13 @@ def get_dataframe():
         )
     )
 
+    data["Evaluation Dataset"] = data.apply(
+        lambda x: x["Evaluation Dataset"] + f" ({x['Subset']})" if pd.notna(x["Subset"]) else x["Evaluation Dataset"],
+        axis=1,
+    )
+
+    del data["Subset"]
+
     # For "Contaminated Source" use build_dataset_url if "Model or corpus" is "corpus" and build_model_url if "Model or corpus" is "model"
     data["Contaminated Source"] = data.apply(
         lambda x: build_text_icon(
@@ -257,4 +264,8 @@ def get_dataframe():
         axis=1,
     )
 
+    data["Train Split"] = data["Train Split"].apply(lambda x: x/100 if x else x)
+    data["Development Split"] = data["Development Split"].apply(lambda x: x/100 if x else x)
+    data["Test Split"] = data["Test Split"].apply(lambda x: x/100 if x else x)
+
     return data

utils.py

@@ -38,6 +38,9 @@ def get_domain_name(url: str) -> str:
     domain = "{uri.netloc}".format(uri=parsed_uri)
     if domain.startswith("www."):
         domain = domain[4:]
+
+    # Remove last domain
+    domain = ".".join(domain.split(".")[:-1])
     # First latter in uppercase
     return domain.capitalize()