deployed v1.0.2

app.py

@@ -23,6 +23,8 @@ sns.set(style="whitegrid")
 def preprocess_and_predict(model, data, match_id, features):
     # 筛选出特定match_id的数据
     specific_match_data = data[data['match_id'] == match_id]
+    specific_match_data = specific_match_data.drop_duplicates(subset=['elapsed_time'], keep='first')
+    specific_match_data = specific_match_data[specific_match_data['server'] != 0]
 
     if specific_match_data.empty:
         st.write(f"No data found for match_id {match_id}.")
@@ -106,9 +108,19 @@ def main():
     st.title('Momentum Catcher')
 
     uploaded_file = st.file_uploader("Upload your input CSV data", type="csv")
-    match_id_input = st.text_input("Enter the match_id you want to analyze", "2023-wimbledon-1301")
+    # match_id_input = st.text_input("Enter the match_id you want to analyze", "2023-wimbledon-1301")
 
     if uploaded_file is not None:
+        new_data = pd.read_csv(uploaded_file)
+        new_data.dropna()
+        
+        # 新增：提取所有唯一的match_id
+        unique_match_ids = new_data['match_id'].unique()
+        
+        # 新增：让用户从所有match_id中选择一个
+        match_id_input = st.selectbox("Select the match_id you want to analyze", unique_match_ids)
+
+        # 模型信息
         repo_id = "Nagi-ovo/Momentum-XGboost"
         filename = "xgboost.pkl"
         
@@ -116,8 +128,6 @@ def main():
         xgb_model = load_model(repo_id, filename)
         features = ['PAI_diff', 'normalized_rally', 'is_game_point']
         
-        # 读取上传的CSV文件
-        new_data = pd.read_csv(uploaded_file)
         new_data['is_game_point'] = abs(new_data['p1_facing_game_point'] - new_data['p2_facing_game_point'])
         new_data['PAI_diff'] = new_data['p1_PAI'] - new_data['p2_PAI']