update leaderboard

get_data_info.py

@@ -7,7 +7,8 @@ def process_plot_data(df, flag=False):
     # 保留"Model"和"Domain"列，删除其他列
     df2 = df[["Model", "Domain"]].copy()
 
-    columns_names = ["Model", "Domain", "AR", "ER", "NER", "JS", "CR", "CFM", "SCM", "CJP", "CTP", "LQA", "JRG", "CU", "LC"]
+    columns_names = ["Model", "Domain", "AR", "ER", "NER", "JS", "CR", "CFM", "SCM",
+                     "CJP", "CTP", "LQA", "JRG", "CU", "LC", "JRG-TAG", "LC-TAG"]
     # 计算新的列的值
     for col in columns_names[2:]:
         if col in ["AR", "ER", "CR", "CFM", "SCM", "CTP", "LQA"]:
@@ -16,14 +17,15 @@ def process_plot_data(df, flag=False):
             df2[col] = df[[f"{col}-CP-F1", f"{col}-PTP-F1"]].mean(axis=1) * 100
         if col == "NER":
             df2[col] = df[f"{col}-Acc"] * 100
-        if col in ["JRG", "LC"]:
+        if col in ["JRG", "LC", "JS", "CU", "JRG-TAG", "LC-TAG"]:
             rouge_mean = df[[f"{col}-ROUGE-1", f"{col}-ROUGE-2", f"{col}-ROUGE-L"]].replace('-', np.nan).mean(axis=1)
             df2.loc[df[f"{col}-ROUGE-1"] == '-', col] = '-'
             df2.loc[df[f"{col}-ROUGE-1"] != '-', col] = rouge_mean * 100
-        if col in ["JS", "CU"]:
-            df2[col] = df[[f"{col}-ROUGE-1", f"{col}-ROUGE-2", f"{col}-ROUGE-L"]].mean(axis=1) * 100
+        # if col in ["JS", "CU"]:
+        #     df2[col] = df[[f"{col}-ROUGE-1", f"{col}-ROUGE-2", f"{col}-ROUGE-L"]].mean(axis=1) * 100
     df2.reindex(columns=columns_names)
 
+    flag = True
     if flag:
         # 保存到Excel文件
         with pd.ExcelWriter('scores.xlsx') as writer:
@@ -37,8 +39,8 @@ def plot_data():
         'leaderboard.xlsx',
         sheet_name='Sheet2',
         header=0,
-        usecols='A:AS',
-        nrows=14)
+        usecols='A:BE',
+        nrows=18)
     leaderboard_df.fillna("-")
 
     df = process_plot_data(leaderboard_df)
@@ -64,16 +66,16 @@ def tab_data():
         'leaderboard.xlsx',
         sheet_name='Sheet2',
         header=0,
-        usecols='A:AS',
-        nrows=14)
+        usecols='A:BE',
+        nrows=18)
     leaderboard_df.fillna("-")
 
-    df_nlp = leaderboard_df.iloc[:, [0] + list(range(2, 9)) + list(range(12, 18))]  # todo
-    df_basic = leaderboard_df.iloc[:, [0] + list(range(18, 36))]  # todo
-    df_complex = leaderboard_df.iloc[:, [0] + list(range(36, 45))]  # todo
+    df_nlp = leaderboard_df.iloc[:, list(range(0, 18))]  # todo
+    df_basic = leaderboard_df.iloc[:, list(range(0, 2)) + list(range(18, 42))]  # todo
+    df_complex = leaderboard_df.iloc[:, list(range(0, 2)) + list(range(42, 56))]  # todo
 
     # Get df_overall
-    df_overall = leaderboard_df.iloc[:, [0] + list(range(2, 45))]
+    df_overall = leaderboard_df.iloc[:, list(range(0, 56))]
     plot_df_dict = {
         "Overall": df_overall,
         "Basic Legal NLP": df_nlp,