cjj-table

app.py

@@ -198,98 +198,71 @@ This leaderboard is used to show the performance of the <strong>automatic evalua
 <p>The Leaderboard will be updated daily around 24:00 Beijing Time.</p>
 </p>
     """, unsafe_allow_html=True)
-    index = pd.MultiIndex.from_tuples([
-        ('', 'teamId'),
-        ('', 'methods'),
-        ('', 'overall'),
-        ('Dialogue Generation', 'accuracy'),
-        ('Dialogue Generation', 'kendall'),
-        ('Dialogue Generation', 'spearman'),
-        # ('Text Expansion', 'accuracy'),
-        # ('Text Expansion', 'kendall\'s tau'),
-        # ('Text Expansion', 'spearman'),
-        # ('Summary Generation', 'accuracy'),
-        # ('Summary Generation', 'kendall\'s tau'),
-        # ('Summary Generation', 'spearman'),
-        # ('Non-Factoid QA', 'accuracy'),
-        # ('Non-Factoid QA', 'kendall\'s tau'),
-        # ('Non-Factoid QA', 'spearman')
-    ])
-
-    data = {
-        ('', 'teamId'): ['baseline', 'baseline', 'baseline', 'baseline'],
-        ('', 'methods'): ["chatglm3-6b", "baichuan2-13b", "chatglm-pro", "gpt-4o-mini"],
-        ('', 'overall'): [0,0,0,0],
-        ('Dialogue Generation', 'accuracy'): [0.5806, 0.5483, 0.6001, 0.6472],
-        ('Dialogue Generation', 'kendall'): [0.3243, 0.1739, 0.3042, 0.4167],
-        ('Dialogue Generation', 'spearman'): [0.3505, 0.1857, 0.3264, 0.4512],
-        # ('Text Expansion', 'accuracy'): [0.5107, 0.5050, 0.5461, 0.5581],
-        # ('Text Expansion', 'kendall\'s tau'): [0.1281, 0.0635, 0.2716, 0.3864],
-        # ('Text Expansion', 'spearman'): [0.1352, 0.0667, 0.2867, 0.4157],
-        # ('Summary Generation', 'accuracy'): [0.6504, 0.6014, 0.7162, 0.7441],
-        # ('Summary Generation', 'kendall\'s tau'): [0.3957, 0.2688, 0.5092, 0.5001],
-        # ('Summary Generation', 'spearman'): [0.4188, 0.2817, 0.5403, 0.5405],
-        # ('Non-Factoid QA', 'accuracy'): [0.5935, 0.5817, 0.7000, 0.7203],
-        # ('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]
+    df = {
+        "TeamId": ["baseline", "baseline", "baseline", "baseline"],
+        "Methods": ["chatglm3-6b", "baichuan2-13b", "chatglm-pro", "gpt-4o-mini"],
+        "Average (all 4 datatsets)": [],
+        "Average (Dialogue Generation)": [],
+        "Accuracy (Dialogue Generation)": [],
+        "Kendall's Tau (Dialogue Generation)": [],
+        "Spearman (Dialogue Generation)": [],
+        "Average (Text Expansion)": [],
+        "Accuracy (Text Expansion)": [],
+        "Kendall's Tau (Text Expansion)": [],
+        "Spearman (Text Expansion)": [],
+        "Average (Summary Generation)": [],
+        "Accuracy (Summary Generation)": [],
+        "Kendall's Tau (Summary Generation)": [],
+        "Spearman (Summary Generation)": [],
+        "Average (Non-Factoid QA)": [],
+        "Accuracy (Non-Factoid QA)": [],
+        "Kendall's Tau (Non-Factoid QA)": [],
+        "Spearman (Non-Factoid QA)": [],
     }
-    # 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 = {
-    #     "teamId": ["baseline1", "baseline2", "baseline3", "baseline4"],
-    #     "methods": ["chatglm3-6b", "baichuan2-13b", "chatglm-pro", "gpt-4o-mini"],
-    #     "accuracy": [0.5806, 0.5483, 0.6001, 0.6472],
-    #     "kendall's tau": [0.3243, 0.1739, 0.3042, 0.4167],
-    #     "spearman": [0.3505, 0.1857, 0.3264, 0.4512]
-    # }
 
-    # df1 = pd.DataFrame(DG)
+    # teamId 唯一标识码
+    DG = {
+        "TeamId": ["baseline1", "baseline2", "baseline3", "baseline4"],
+        "Methods": ["chatglm3-6b", "baichuan2-13b", "chatglm-pro", "gpt-4o-mini"],
+        "Accuracy": [0.5806, 0.5483, 0.6001, 0.6472],
+        "Kendall's Tau": [0.3243, 0.1739, 0.3042, 0.4167],
+        "Spearman": [0.3505, 0.1857, 0.3264, 0.4512]
+    }
+    df1 = pd.DataFrame(DG)
 
-    # TE = {
-    #     "teamId": ["baseline1", "baseline2", "baseline3", "baseline4"],
-    #     "methods": ["chatglm3-6b", "baichuan2-13b", "chatglm-pro", "gpt-4o-mini"],
-    #     "accuracy": [0.5107, 0.5050, 0.5461, 0.5581],
-    #     "kendall's tau": [0.1281, 0.0635, 0.2716, 0.3864],
-    #     "spearman": [0.1352, 0.0667, 0.2867, 0.4157]
-    # }
-    # df2 = pd.DataFrame(TE)
+    TE = {
+        "TeamId": ["baseline1", "baseline2", "baseline3", "baseline4"],
+        "Methods": ["chatglm3-6b", "baichuan2-13b", "chatglm-pro", "gpt-4o-mini"],
+        "Accuracy": [0.5107, 0.5050, 0.5461, 0.5581],
+        "Kendall's Tau": [0.1281, 0.0635, 0.2716, 0.3864],
+        "Spearman": [0.1352, 0.0667, 0.2867, 0.4157]
+    }
+    df2 = pd.DataFrame(TE)
 
-    # SG = {
-    #     "teamId": ["baseline1", "baseline2", "baseline3", "baseline4"],
-    #     "methods": ["chatglm3-6b", "baichuan2-13b", "chatglm-pro", "gpt-4o-mini"],
-    #     "accuracy": [0.6504, 0.6014, 0.7162, 0.7441],
-    #     "kendall's tau": [0.3957, 0.2688, 0.5092, 0.5001],
-    #     "spearman": [0.4188, 0.2817, 0.5403, 0.5405],
-    # }
-    # df3 = pd.DataFrame(SG)
+    SG = {
+        "TeamId": ["baseline1", "baseline2", "baseline3", "baseline4"],
+        "Methods": ["chatglm3-6b", "baichuan2-13b", "chatglm-pro", "gpt-4o-mini"],
+        "Accuracy": [0.6504, 0.6014, 0.7162, 0.7441],
+        "Kendall's Tau": [0.3957, 0.2688, 0.5092, 0.5001],
+        "Spearman": [0.4188, 0.2817, 0.5403, 0.5405],
+    }
+    df3 = pd.DataFrame(SG)
 
-    # NFQA = {
-    #     "teamId": ["baseline1", "baseline2", "baseline3", "baseline4"],
-    #     "methods": ["chatglm3-6b", "baichuan2-13b", "chatglm-pro", "gpt-4o-mini"],
-    #     "accuracy": [0.5935, 0.5817, 0.7000, 0.7203],
-    #     "kendall's tau": [0.2332, 0.2389, 0.4440, 0.4235],
-    #     "spearman": [0.2443, 0.2492, 0.4630, 0.4511]
-    # }
-    # df4 = pd.DataFrame(NFQA)
+    NFQA = {
+        "TeamId": ["baseline1", "baseline2", "baseline3", "baseline4"],
+        "Methods": ["chatglm3-6b", "baichuan2-13b", "chatglm-pro", "gpt-4o-mini"],
+        "Accuracy": [0.5935, 0.5817, 0.7000, 0.7203],
+        "Kendall's Tau": [0.2332, 0.2389, 0.4440, 0.4235],
+        "Spearman": [0.2443, 0.2492, 0.4630, 0.4511]
+    }
+    df4 = pd.DataFrame(NFQA)
 
     # df = [df1, df2, df3, df4]
     # for d in df:
     #     for col in d.select_dtypes(include=['float64', 'int64']).columns:
     #         d[col] = d[col].apply(lambda x: f"{x:.4f}")
 
-    # 创建标签页
+    # # 创建标签页
     # tab1, tab2, tab3, tab4 = st.tabs(["DG", "TE", "SG", "NFQA"])
 
     # with tab1:
@@ -307,6 +280,27 @@ This leaderboard is used to show the performance of the <strong>automatic evalua
     # with tab4:
     #     st.markdown("""<p class='main-text'>Task: Non-Factoid QA; Dataset: NF_CATS</p>""", unsafe_allow_html=True)
     #     st.dataframe(df4, use_container_width=True)
+    
+    data = [DG, NFQA, SG, TE]
+    task = ["Dialogue Generation", "Non-Factoid QA", "Summary Generation", "Text Expansion"]
+    metric = ["Accuracy", "Kendall's Tau", "Spearman"]
+
+    overall_total = [0] * len(df["TeamId"])
+    for i, d in enumerate(data): # 每种数据集
+        total = [0] * len(df["TeamId"]) # 长度初始化为方法数
+        for j in range(len(metric)): # 每种指标
+            index = f"{metric[j]} ({task[i]})"
+            df[index] = d[metric[j]]
+            for k in range(len[df["TeamId"]]):
+                total[k] += d[metric[j]][k]
+        average_index = f"Average ({task[i]})"
+        df[average_index] = [k / len(metric) for k in total]
+        for k in range(len[df["TeamId"]]):
+            overall_total[k] += df[average_index][k]
+
+    df["Average (all 4 datatsets)"] = [k / len(task) for k in overall_total]
+    
+    st.dataframe(pd.DataFrame(df), use_container_width=True)
     st.markdown("A baseline example can be found in the [baseline_example](https://huggingface.co/spaces/THUIR/AEOLLM/tree/main/baseline_example) folder.")
     # 获取北京时间
     time_placeholder = st.empty()