Update app.py

app.py

@@ -113,6 +113,34 @@ def get_match_with_longest_game(df: pd.DataFrame, is_tournament: bool) -> Option
     return df.loc[[np.argmax(df.scores.apply(get_max_int))]]
 
 
+def get_win_loss_record_str(group_df) -> str:
+    if len(group_df) > 0:
+        win_loss_counts = group_df.value_counts()
+        n_wins = win_loss_counts.Won if hasattr(win_loss_counts, "Won") else 0
+        n_losses = win_loss_counts.Lost if hasattr(win_loss_counts, "Lost") else 0
+    else:
+        n_wins = 0
+        n_losses = 0
+
+    return f"{n_wins}, {n_losses}"
+
+
+def get_most_frequent_opponents(df: pd.DataFrame, top_n: int = 5) -> pd.DataFrame:
+    df_with_opponents = df.loc[df.opponent != "-, -"]
+
+    most_common_opponents_df = df_with_opponents.groupby('opponent').agg({"result": [get_win_loss_record_str, "size"]})
+    most_common_opponents_df.columns = most_common_opponents_df.columns.get_level_values(1)
+    most_common_opponents_df.rename({"get_win_loss_record_str": "Win/loss record", "size": "Number of matches"}, axis=1,
+                                    inplace=True)
+    most_common_opponents_df["Opponent"] = most_common_opponents_df.index
+    return most_common_opponents_df.sort_values("Number of matches", ascending=False)[
+        ["Opponent", "Number of matches", "Win/loss record"]].head(top_n)
+
+
+def get_highest_rated_opponent(df: pd.DataFrame) -> pd.DataFrame:
+    return df.iloc[df.opponent_rating.idxmax()].to_frame().transpose()
+
+
 def get_opponent_rating_distr_fig(df: pd.DataFrame):
     fig = plt.figure()
     plt.title('Opponent rating distribution')
@@ -159,6 +187,8 @@ def usatt_rating_analyzer(file_obj):
     matches_per_competition_fig = get_matches_per_competition_fig(df, is_tournament)
     opponent_name_word_cloud_fig = get_opponent_name_word_cloud_fig(df)
     competition_name_word_cloud_fig = get_competition_name_word_cloud_fig(df, is_tournament)
+    most_frequent_opponents = get_most_frequent_opponents(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)
     opponent_rating_distr_fig = get_opponent_rating_distr_fig(df)
@@ -169,6 +199,8 @@ def usatt_rating_analyzer(file_obj):
             matches_per_competition_fig,
             opponent_name_word_cloud_fig,
             competition_name_word_cloud_fig,
+            most_frequent_opponents,
+            highest_rated_opponent,
             rating_over_time_fig,
             match_with_longest_game,
             opponent_rating_distr_fig,
@@ -213,6 +245,11 @@ with gr.Blocks() as demo:
             with gr.Column():
                 comp_names_plot = gr.Plot(label="Competition names")
 
+        with gr.Row():
+            with gr.Column():
+                most_frequent_opponents_gdf = gr.Dataframe(label="Most frequent opponents", 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)
 
         with gr.Row():
@@ -228,12 +265,15 @@ with gr.Blocks() as demo:
         matches_per_comp_plot,
         opponent_names_plot,
         comp_names_plot,
+        most_frequent_opponents_gdf,
+        highest_rated_opponent_gdf,
         rating_over_time_plot,
         match_longest_game_gdf,
         opponent_rating_dist_plot,
         opponent_rating_dist_over_time_plot,
     ]
 
+
     btn.click(usatt_rating_analyzer, inputs=inputs, outputs=outputs)
 
 if __name__ == "__main__":