initial code

Dockerfile

@@ -0,0 +1,10 @@
+FROM python:3.7
+
+WORKDIR /app
+ADD ./ /app/
+
+RUN pip install --upgrade pip -i https://pypi.douban.com/simple/ --no-cache-dir
+RUN pip install -r requirements.txt -i https://pypi.tuna.tsinghua.edu.cn/simple --no-cache-dir
+
+
+CMD ["python3", "run.py"]

config/emission_factor.json

@@ -0,0 +1,30 @@
+{
+    "CO":{
+        "煤粉": 2,
+        "循环流化床": 2,
+        "自动炉排层燃炉": 15,
+        "手动炉排层燃炉 ": 124.3,
+        "default": 2
+    },
+    "VOCs":{
+        "煤粉": 2.16,
+        "循环流化床": 2.16,
+        "自动炉排层燃炉": 2.16,
+        "手动炉排层燃炉 ": 4.53,
+        "default": 2.16
+    },
+    "PM25":{
+        "煤粉": 0.06,
+        "循环流化床": 0.07,
+        "自动炉排层燃炉": 0.1,
+        "手动炉排层燃炉 ": 0.07,
+        "default": 0.06
+    },
+    "PM10":{
+        "煤粉": 0.23,
+        "循环流化床": 0.29,
+        "自动炉排层燃炉": 0.3,
+        "手动炉排层燃炉 ": 0.2,
+        "default": 0.23
+    }
+}

config/object_cols.json

@@ -0,0 +1 @@
+["\u751f\u4ea7\u8bbe\u5907\u7c7b\u578b", "\u6c7d\u8f6e\u673a\u7c7b\u578b", "\u51b7\u5374\u65b9\u5f0f", "\u538b\u529b\u53c2\u6570", "day_of_week", "month", "hour"]

models/lgb_predict.py

@@ -0,0 +1,108 @@
+# -*-coding:utf-8 -*-
+import lightgbm as lgb
+import numpy as np
+import pandas as pd
+import json
+import datetime as dt
+
+
+def load_history_data(data_path:str):
+    data = pd.read_csv(data_path)
+    return data
+
+def load_config(cfg_path:str):
+    with open(cfg_path, 'r', encoding='utf-8') as fr:
+        config = json.load(fr)
+    return config
+
+def load_lgb_model(model_path:str):
+    return lgb.Booster(model_file=model_path)
+
+def cal_CO2(coal_cost, ncv):
+    return coal_cost * ncv * 26.37e-3 * 0.94 * 44 / 12
+
+def cal_coal_cost_emission(coal_cost, boiler, emission_factors):
+    factor = emission_factors.get(boiler)
+    if factor is not None:
+        return coal_cost * factor
+    else:
+        return emission_factors.get("default") * coal_cost
+
+def cal_PM(r_smoke, boiler, emission_factors):
+    factor = emission_factors.get(boiler)
+    if factor is not None:
+        return r_smoke * factor
+    else:
+        return emission_factors.get("default") * r_smoke
+
+def predict(his_data, input_data, model:lgb.Booster, object_cols, emission_factors):
+    feature_names = model.feature_name()
+    date = dt.datetime.strptime(input_data.get('time'), '%Y-%m-%d %H:%M:%S')
+    r_NOx = float(input_data.get('NOx'))
+    r_SO2 = float(input_data.get('SO2'))
+    r_smoke = float(input_data.get('smoke'))
+    flow = float(input_data.get('flow'))
+    c_NOx, c_SO2, c_smoke = flow * np.asarray([r_NOx, r_SO2, r_smoke])
+    caloric = float(input_data.get("caloric"))
+    if caloric > 1000:
+        caloric = caloric / 1000
+    inputs = {
+        "生产设备类型": input_data.get('boiler'),
+        "汽轮机类型": input_data.get('steam'),
+        "冷却方式": input_data.get('cold'),
+        "压力参数": input_data.get('pressure'),
+        "day_of_week": date.weekday(),
+        "month": date.month,
+        "hour": date.hour,
+        "0_r_NOx":np.log1p(float(r_NOx)),
+        "0_r_SO2":np.log1p(float(r_SO2)),
+        "0_r_smoke":np.log1p(float(r_smoke)),
+        "0_c_NOx": np.log1p(float(c_NOx)),
+        "0_c_SO2": np.log1p(float(c_SO2)),
+        "0_c_smoke": np.log1p(float(c_smoke)),
+        "0_flow": np.log1p(float(flow)),
+        "0_O2": np.log1p(float(input_data.get("O2"))),
+        "0_temp": np.log1p(float(input_data.get("temp"))),
+        "额定蒸发量_t/h": np.log1p(float(input_data.get("evaporation"))),
+        "低位发热量": np.log1p(caloric),
+        "单机容量（MW）": np.log1p(float(input_data.get("capacity"))),
+        "lon": np.log1p(float(input_data.get("lon"))),
+        "lat": np.log1p(float(input_data.get("lat"))),
+    }
+    new_df = pd.DataFrame.from_dict(inputs, orient='index').T
+    total_data = pd.concat([his_data, new_df])
+    new_inputs = pd.get_dummies(total_data, columns=object_cols)
+    new_inputs = new_inputs[feature_names].iloc[-1].values
+    coal_cost = np.expm1(model.predict([new_inputs])[0])
+    co = cal_coal_cost_emission(coal_cost, input_data.get('boiler'), emission_factors.get('CO'))
+    vocs = cal_coal_cost_emission(coal_cost, input_data.get('boiler'), emission_factors.get('VOCs'))
+    pm25 = cal_PM(r_smoke, input_data.get('boiler'), emission_factors.get('PM25'))
+    pm10 = cal_PM(r_smoke, input_data.get('boiler'), emission_factors.get('PM10'))
+    co2 = cal_CO2(coal_cost, caloric)
+    return {'coal': coal_cost, 'co':co, 'vocs':vocs, 'pm25':pm25, 'pm10':pm10, 'co2':co2}
+
+    
+if __name__ == '__main__':
+    history = load_history_data('../data/data_sample.csv')
+    object_cols = load_config('../config/object_cols.json')
+    model = load_lgb_model('../model_files/hour_best_model.txt')
+    emission_factors = load_config('../config/emission_factor.json')
+    inputs = {
+        "time": "2023-01-02 03:04:05",
+        "boiler": "循环流化床锅炉",
+        "steam": "凝气式",
+        "cold": "水冷-开式循环",
+        "pressure": "超超临界",
+        "NOx": "12",
+        "SO2":"0.15",
+        "smoke":"12",
+        "flow":"5000000",
+        "O2": "23",
+        "temp": "55",
+        "evaporation": "123",
+        "caloric": "23",
+        "capacity": "234",
+        "lon": "122",
+        "lat":"33",
+    }
+    print(predict(history, inputs, model, object_cols, emission_factors))

requirements.txt

@@ -0,0 +1,5 @@
+lightgbm==3.2.1
+numpy==1.19.5
+pandas==1.3.5
+logzero==1.7.0
+Flask==2.1.0

run.py

@@ -0,0 +1,43 @@
+# -*-coding:utf-8-*-
+import os
+os.environ['CUDA_VISIBLE_DEVICES'] = '-1'
+import json
+from flask import Flask, request, make_response
+from logzero import logger
+
+current_path = os.path.dirname(os.path.abspath(__file__)) # for local
+# current_path = "/app"  # for docker
+logger.info(f"{current_path}")
+
+from models.lgb_predict import load_config, load_history_data, load_lgb_model, predict
+
+lgb_model = load_lgb_model(model_path=f"{current_path}/model_files/hour_best_model.txt")
+object_cols = load_config(f"{current_path}/config/object_cols.json")
+history_data = load_history_data(data_path=f"{current_path}/data/data_sample.csv")
+emission_factors = load_config(f"{current_path}/config/emission_factor.json")
+
+app = Flask(__name__)
+
+
+@app.route('/emission/', methods=["POST"])
+def run_case_check():
+    resp_info = dict()
+    if request.method == "POST":
+        data = request.json.get('data')
+        logger.info(data)
+        if data is not None and len(data) != 0:
+            rst = predict(history_data, data, lgb_model, object_cols, emission_factors)
+            resp_info["code"] = 200
+            resp_info["data"] = rst
+        else:
+            resp_info["msg"] = "Input is None, please check !"
+            resp_info["code"] = 406
+    resp = make_response(json.dumps(resp_info))
+    resp.status_code = 200
+    return resp
+
+
+
+
+if __name__ == '__main__':
+    app.run(host='0.0.0.0', port=8788, debug=False)