cjj-leaderboard

app.py

@@ -219,7 +219,7 @@ This leaderboard is used to show the performance of the <strong>automatic evalua
     data = {
         ('', 'teamId'): ['baseline', 'baseline', 'baseline', 'baseline'],
         ('', 'methods'): ["chatglm3-6b", "baichuan2-13b", "chatglm-pro", "gpt-4o-mini"],
-        ('', 'overall'): [],
+        ('', 'overall'): [0,0,0,0],
         ('Dialogue Generation', 'accuracy'): [0.5806, 0.5483, 0.6001, 0.6472],
         ('Dialogue Generation', "kendall's tau"): [0.3243, 0.1739, 0.3042, 0.4167],
         ('Dialogue Generation', 'spearman'): [0.3505, 0.1857, 0.3264, 0.4512],
@@ -233,17 +233,18 @@ This leaderboard is used to show the performance of the <strong>automatic evalua
         ('Non-Factoid QA', "kendall's tau"): [0.2332, 0.2389, 0.4440, 0.4235],
         ('Non-Factoid QA', 'spearman'): [0.2443, 0.2492, 0.4630, 0.4511]
     }
-    overall = [0, 0, 0, 0]
-    for d in data:
-        if d != ('', 'teamId') and d != ('', 'methods') and d != ('', 'overall'):
-            for i in range(4):
-                    overall[i] += data[d][i]
-    overall = [i / (3*4) for i in overall]
-    data[('', 'overall')] = overall
-    for d in data:
-        if d != ('', 'teamId') and d != ('', 'methods'):
-            for col in range(len(data[d])):
-                data[d][col] = "{:.4f}".format(data[d][col])
+    # overall = [0, 0, 0, 0]
+    # for d in data:
+    #     if d != ('', 'teamId') and d != ('', 'methods') and d != ('', 'overall'):
+    #         for i in range(4):
+    #                 overall[i] += data[d][i]
+    # overall = [i / (3*4) for i in overall]
+    # data[('', 'overall')] = overall
+    # for d in data:
+    #     if d != ('', 'teamId') and d != ('', 'methods'):
+    #         for col in range(len(data[d])):
+    #             data[d][col] = "{:.4f}".format(data[d][col])
+    # print(data)
     st.dataframe(data, use_container_width=True)
     # # teamId 唯一标识码
     # DG = {

test.py

@@ -1,7 +1,7 @@
 data = {
         ('', 'teamId'): ['baseline', 'baseline', 'baseline', 'baseline'],
         ('', 'methods'): ["chatglm3-6b", "baichuan2-13b", "chatglm-pro", "gpt-4o-mini"],
-        ('', 'overall'): [],
+        ('', 'overall'): [0,0,0,0],
         ('Dialogue Generation', 'accuracy'): [0.5806, 0.5483, 0.6001, 0.6472],
         ('Dialogue Generation', "kendall's tau"): [0.3243, 0.1739, 0.3042, 0.4167],
         ('Dialogue Generation', 'spearman'): [0.3505, 0.1857, 0.3264, 0.4512],
@@ -17,11 +17,14 @@ data = {
     }
 
 overall = [0, 0, 0, 0]
-
 for d in data:
     if d != ('', 'teamId') and d != ('', 'methods') and d != ('', 'overall'):
-       for i in range(4):
-            overall[i] += data[d][i]
-
+        for i in range(4):
+                overall[i] += data[d][i]
 overall = [i / (3*4) for i in overall]
-print(overall)
+data[('', 'overall')] = overall
+for d in data:
+    if d != ('', 'teamId') and d != ('', 'methods'):
+        for col in range(len(data[d])):
+            data[d][col] = "{:.4f}".format(data[d][col])
+print(data)