update app.py

get_data_info.py

@@ -1,23 +1,54 @@
 import copy
+import numpy as np
 import pandas as pd
 
 
+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"]
+    # 计算新的列的值
+    for col in columns_names[2:]:
+        if col in ["AR", "ER", "CR", "CFM", "SCM", "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"]:
+            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
+    df2.reindex(columns=columns_names)
+
+    if flag:
+        # 保存到Excel文件
+        with pd.ExcelWriter('scores.xlsx') as writer:
+            df2.to_excel(writer, sheet_name="Sheet1", index=False)
+
+    return df2
+
 def plot_data():
     # read df and replace NaN values with an empty string
     leaderboard_df = pd.read_excel(
         'leaderboard.xlsx',
-        sheet_name='Sheet1',
+        sheet_name='Sheet2',
         header=0,
-        usecols='A:P',
+        usecols='A:AS',
         nrows=14)
     leaderboard_df.fillna("-")
 
-    df_nlp = leaderboard_df.iloc[:, [0] + list(range(2, 7))]  # todo
-    df_basic = leaderboard_df.iloc[:, [0] + list(range(7, 13))]  # todo
-    df_complex = leaderboard_df.iloc[:, [0] + list(range(13, 16))]  # todo
+    df = process_plot_data(leaderboard_df)
+
+    df_nlp = df.iloc[:, [0] + list(range(2, 7))]  # todo
+    df_basic = df.iloc[:, [0] + list(range(7, 12))]  # todo
+    df_complex = df.iloc[:, [0] + list(range(12, 15))]  # todo
 
     # Get df_overall
-    df_overall = leaderboard_df.iloc[:, [0] + list(range(2, 16))]
+    df_overall = df.iloc[:, [0] + list(range(2, 15))]
     plot_df_dict = {
         "Overall": df_overall,
         "Basic Legal NLP": df_nlp,
@@ -37,7 +68,7 @@ def tab_data():
         nrows=14)
     leaderboard_df.fillna("-")
 
-    df_nlp = leaderboard_df.iloc[:, [0] + list(range(2, 18))]  # todo
+    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