update results

app.py

@@ -66,7 +66,7 @@ def launch_gradio(df1, df2):
 
         with gr.Row():
             for key, df in df1.items():
-                if key == "Overall" or key == "Basic Legal NLP":
+                if key == "Overall" or key == "Basic Information Retrieval":
                     df = df.replace('', 0)
                     new_df = df[[val for val in df.columns]].copy()
                     # new_df = reindex_cols(Task_COLS, new_df)
@@ -77,7 +77,7 @@ def launch_gradio(df1, df2):
 
         with gr.Row():
             for key, df in df1.items():
-                if key == "Basic Legal Application" or key == "Complex Legal Application":
+                if key == "Legal Foundation Inference" or key == "Complex Legal Application":
                     # if True:
                     df = df.replace('', 0)
                     new_df = df[[val for val in df.columns]].copy()

get_data_info.py

@@ -8,13 +8,11 @@ def process_plot_data(df, flag=False):
     df2 = df[["Model", "Domain"]].copy()
 
     columns_names = ["Model", "Domain", "AR", "ER", "NER", "JS", "CR", "CFM", "SCM",
-                     "CJP", "CTP", "LQA", "JRG", "CU", "LC", "JRG-TAG", "LC-TAG"]
+                     "CP", "PTP", "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"]:
+        if col in ["AR", "ER", "CR", "CFM", "SCM", "CP", "PTP", "CTP", "LQA"]:
             df2[col] = df[f"{col}-F1"] * 100
-        if col == "CJP":
-            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", "JS", "CU", "JRG-TAG", "LC-TAG"]:
@@ -46,17 +44,17 @@ def plot_data():
     df = process_plot_data(leaderboard_df)
     # df.drop(df[df['Model'] == 'Baichuan-7B'].index, inplace=True)
 
-    df_nlp = df.iloc[:, [0] + list(range(2, 7))]
-    df_basic = df.iloc[:, [0] + list(range(7, 12))]
-    df_complex = df.iloc[:, [0] + list(range(12, 15))]
+    df_BIR = df.iloc[:, [0] + list(range(2, 7))]
+    df_LFI = df.iloc[:, [0] + list(range(7, 13))]
+    df_CLA = df.iloc[:, [0] + list(range(13, 16))]
 
     # Get df_overall
     df_overall = df.iloc[:, [0] + list(range(2, 15))]
     plot_df_dict = {
         "Overall": df_overall,
-        "Basic Legal NLP": df_nlp,
-        "Basic Legal Application": df_basic,
-        "Complex Legal Application": df_complex,
+        "Basic Information Retrieval": df_BIR,
+        "Legal Foundation Inference": df_LFI,
+        "Complex Legal Application": df_CLA,
     }
     return plot_df_dict
 
@@ -72,19 +70,19 @@ def tab_data():
     leaderboard_df.fillna("-")
     # leaderboard_df.drop(leaderboard_df[leaderboard_df['Model'] == 'Baichuan-7B'].index, inplace=True)
 
-    df_nlp = leaderboard_df.iloc[:, list(range(0, 18))]
-    df_basic = leaderboard_df.iloc[:, list(range(0, 2)) + list(range(18, 42))]
-    df_complex = leaderboard_df.iloc[:, list(range(0, 2)) + list(range(42, 56))]
+    df_BIR = leaderboard_df.iloc[:, list(range(0, 18))]
+    df_LFI = leaderboard_df.iloc[:, list(range(0, 2)) + list(range(18, 42))]
+    df_CLA = leaderboard_df.iloc[:, list(range(0, 2)) + list(range(42, 56))]
 
     # Get df_overall
     df_overall = leaderboard_df.iloc[:, list(range(0, 56))]
-    plot_df_dict = {
+    table_df_dict = {
         "Overall": df_overall,
-        "Basic Legal NLP": df_nlp,
-        "Basic Legal Application": df_basic,
-        "Complex Legal Application": df_complex,
+        "Basic Information Retrieval": df_BIR,
+        "Legal Foundation Inference": df_LFI,
+        "Complex Legal Application": df_CLA,
     }
-    return plot_df_dict
+    return table_df_dict
 
 
 if __name__ == "__main__":