Initial upload

app.py

@@ -0,0 +1,52 @@
+import streamlit as st
+import pandas as pd
+import joblib
+from sklearn.preprocessing import LabelEncoder
+from sklearn.metrics import accuracy_score
+
+def load_model(model_path):
+    # 加载保存的模型
+    model = joblib.load(model_path)
+    return model
+
+def preprocess_data(uploaded_file, features):
+    # 读取并预处理新数据集
+    new_data = pd.read_csv(uploaded_file)
+    X_new = new_data[features]
+    return X_new, new_data['point_victor']
+
+def main():
+    st.title('ML Model Prediction Demo with XGBoost')
+
+    # 文件上传器
+    uploaded_file = st.file_uploader("Upload your input CSV file", type="csv")
+    
+    if uploaded_file is not None:
+        # 指定特征列和模型路径
+        features = [
+            'elapsed_time', 'set_no', 'game_no', 'game_advantage', 'set_advantage', 
+            'p1_cumulative_distance', 'p2_cumulative_distance', 
+            'p1_max_continuous_scoring', 'p2_max_continuous_scoring', 
+            'p1_total_errors', 'p2_total_errors'
+        ]
+        model_path = './models/xgboost.pkl'
+        
+        # 加载模型
+        xgb_model = load_model(model_path)
+        
+        # 预处理数据
+        X_new, y_new = preprocess_data(uploaded_file, features)
+        
+        # 如果目标变量也需要编码转换，确保使用与训练数据相同的方式进行转换
+        label_encoder = LabelEncoder()
+        y_new_encoded = label_encoder.fit_transform(y_new)
+
+        # 使用加载的模型进行预测
+        predictions = xgb_model.predict(X_new)
+
+        # 计算并显示正确率
+        accuracy = accuracy_score(y_new_encoded, predictions)
+        st.write("Accuracy on new data:", accuracy)
+
+if __name__ == '__main__':
+    main()

requirements.txt

@@ -0,0 +1,7 @@
+pandas
+matplotlib
+numpy
+scipy
+seaborn
+scicket-learn
+joblib