python_algorithm/模型调用.py

from flask import Flask, request, jsonify
import joblib
import pandas as pd

app = Flask(__name__)
model = joblib.load("defrost_time_corrector.pkl")

feature_columns = ["w", "rho_coal", "rho_ice", "C_coal", "C_ice", "L",
                   "k_coal", "k_ice", "h", "T_air", "T_initial", "T_m",
                   "a", "b", "c"]
# 加载训练过的样本信息（用于判断是否相同物料）
csv_path = 'C:\\Users\\Administrator\\Desktop\\defrost\\feedback_data.csv'
df_train = pd.read_csv(csv_path, parse_dates=["t_formula", "t_real"], encoding='utf-8')
df_train["material_name"] = df_train["material_name"].astype(str)
df_train["manufactured_goods"] = df_train["manufactured_goods"].astype(str)

@app.route("/predict_defrost_time", methods=["POST"])
def predict():
    data = request.get_json()
    material = str(data.get("material_name", "")).strip()
    goods = str(data.get("manufactured_goods", "")).strip()

    print("传递的物料名称为"+material)
    print("传递的制造品名称为"+goods)
    # 强制要求必须传物料+制造品名
    if not material or not goods:
        return jsonify({
            "error": "请提供 material_name 和 manufactured_goods 字段"
        }), 400

    # 判断是否是训练数据中见过的组合
    is_known = ((df_train["material_name"] == material) &
                (df_train["manufactured_goods"] == goods)).any()

    if not is_known:
        return jsonify({
            "predicted_hours": None,
            "is_known_sample": False,
            "error": "未知物料组合，无法预测"
        })

    # 进行预测
    df = pd.DataFrame([data])
    X = df[feature_columns]
    y_pred = model.predict(X)[0]

    return jsonify({
        "predicted_hours": round(y_pred, 2),
        "is_known_sample": True
    })

if __name__ == '__main__':
    app.run(host='127.0.0.1', port=9994)