feat: add biggest upsets

app.py

@@ -142,6 +142,12 @@ def get_best_wins(df: pd.DataFrame, top_n: int = 5) -> pd.DataFrame:
     return df.loc[df.result == 'Won'].sort_values("opponent_rating", ascending=False).head(top_n)
 
 
+def get_biggest_upsets(df: pd.DataFrame, top_n: int = 5) -> pd.DataFrame:
+    """Get the top-n wins sorted by rating difference."""
+    df['rating_difference'] = df['opponent_rating'] - df['rating']
+    return df.loc[df.result == 'Won'].sort_values("rating_difference", ascending=False).head(top_n)
+
+
 def get_highest_rated_opponent(df: pd.DataFrame) -> pd.DataFrame:
     return df.iloc[df.opponent_rating.idxmax()].to_frame().transpose()
 
@@ -194,6 +200,7 @@ def usatt_rating_analyzer(file_obj):
     competition_name_word_cloud_fig = get_competition_name_word_cloud_fig(df, is_tournament)
     most_frequent_opponents = get_most_frequent_opponents(df)
     best_wins = get_best_wins(df)
+    biggest_upsets = get_biggest_upsets(df)
     highest_rated_opponent = get_highest_rated_opponent(df)
     rating_over_time_fig = get_rating_over_time_fig(df, is_tournament)
     match_with_longest_game = get_match_with_longest_game(df, is_tournament)
@@ -207,6 +214,7 @@ def usatt_rating_analyzer(file_obj):
             competition_name_word_cloud_fig,
             most_frequent_opponents,
             best_wins,
+            biggest_upsets,
             highest_rated_opponent,
             rating_over_time_fig,
             match_with_longest_game,
@@ -257,6 +265,8 @@ with gr.Blocks() as demo:
                 most_frequent_opponents_gdf = gr.Dataframe(label="Most frequent opponents", max_rows=5)
                 best_wins_gdf = gr.Dataframe(label="Best wins (matches won sorted by opponent post-competition rating)", 
                                              max_rows=5)
+                biggest_upsets_gdf = gr.Dataframe(label="Biggest upsets (matches won sorted by rating - opponent post-competition rating)",
+                                                  max_rows=5)
                 highest_rated_opponent_gdf = gr.Dataframe(label="Best opponent", max_rows=1)
 
         match_longest_game_gdf = gr.Dataframe(label="Match with longest game", max_rows=1)
@@ -276,6 +286,7 @@ with gr.Blocks() as demo:
         comp_names_plot,
         most_frequent_opponents_gdf,
         best_wins_gdf,
+        biggest_upsets_gdf,
         highest_rated_opponent_gdf,
         rating_over_time_plot,
         match_longest_game_gdf,