add batch predction
This commit is contained in:
parent
527f92cdbe
commit
d3779c8f9a
109
README.md
109
README.md
|
|
@ -6,22 +6,26 @@
|
|||
输入为json串，具体内容如下：
|
||||
```
|
||||
{
|
||||
"key": "xxxx",
|
||||
"data":{
|
||||
"time": "",
|
||||
"boiler": "",
|
||||
... //以下省略
|
||||
}
|
||||
"key": ['company', 'unit', 'time', 'boiler', 'steam', ..., 'lat']
|
||||
"data":[
|
||||
[第一条数据，顺序与key相同],
|
||||
[第二条数据],
|
||||
...
|
||||
[第n条数据],
|
||||
]
|
||||
}
|
||||
```
|
||||
其中`key`字段可用于并发时确认请求来源，`data`字段为传入的机组和排放参数，具体如下：
|
||||
`key`字段表示输入数据的列名，`data`字段为传入的机组和排放值的二维数组，具体如下：
|
||||
|字段|类型|含义|是否由爬虫获取|
|
||||
|----|----|----|----|
|
||||
|company|str|电厂名称|否|
|
||||
|unit|str|机组编号|否|
|
||||
|time|str|时间，'yyyy-mm-dd hh:MM:ss'|是|
|
||||
|boiler|str|锅炉类型|否|
|
||||
|steam|str|汽轮机类型|否|
|
||||
|cold|str|冷却方式|否|
|
||||
|pressure|str|压力参数|否|
|
||||
|capacity|float|装机容量|否|
|
||||
|nox|float|氮氧化物($NO_x$)浓度数值($mg/m^3$)|是|
|
||||
|so2|float|二氧化硫($SO_2$)浓度数值($mg/m^3$)|是|
|
||||
|smoke|float|烟气浓度($mg/m^3$)|是|
|
||||
|
|
@ -38,14 +42,16 @@
|
|||
```
|
||||
{
|
||||
"code": 200, # 若调用错误，code为406
|
||||
"request_key": "xxxx",
|
||||
"msg": "若code为406，返回该字段",
|
||||
"data": {...} # 若code为200，返回该字段
|
||||
"data": {"company": [], "unit":[], "coal":[], ..., "pm10":[]} # 若code为200，返回该字段
|
||||
}
|
||||
```
|
||||
其中`key`字段可用于并发时确认请求来源，data字段对应模型返回的当前时刻的结果，具体如下：
|
||||
`data`字段对应模型返回的当前时刻的结果，具体如下：
|
||||
|字段|类型|含义|
|
||||
|----|----|----|
|
||||
|company|str|电厂名称|
|
||||
|unit|str|机组编号|
|
||||
|time|str|时间，'yyyy-mm-dd hh:MM:ss'|
|
||||
|coal|float|该时刻对应的煤耗(t)|
|
||||
|co|float|一氧化碳排放量(kg)|
|
||||
|co2|float|二氧化碳排放量(kg)|
|
||||
|
|
@ -57,39 +63,67 @@
|
|||
### 输入示例
|
||||
```
|
||||
{
|
||||
"key": "123456",
|
||||
"data": {
|
||||
"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"
|
||||
}
|
||||
"key": ["boiler",
|
||||
"steam",
|
||||
"cold",
|
||||
"pressure",
|
||||
"nox",
|
||||
"so2",
|
||||
"smoke",
|
||||
"flow",
|
||||
"o2",
|
||||
"temp",
|
||||
"evaporation",
|
||||
"caloric",
|
||||
"capacity",
|
||||
"lon",
|
||||
"lat",
|
||||
"time",
|
||||
"company",
|
||||
"unit"],
|
||||
"data": [
|
||||
["煤粉", "凝气式", "空冷-直接空冷", "超超临界", 3.68, 21.42, 3.60, 1644322.11, 6.78, 56.01, 2080.0, 12.96, 600, 118.72, 43.59, "2023-06-28 11:21:07", "浙江秀舟热电", "1"],
|
||||
["W火焰炉", "凝气式", "空冷-间接空冷", "超临界", 4.68, 12.42, 2.60, 1147852.11, 9.32, 56.01, 1060.0, 12.96, 1000, 118.72, 43.59, "2023-06-28 11:21:07", "浙江秀舟热电", "2"],
|
||||
]
|
||||
}
|
||||
```
|
||||
### 输出示例（调用成功）
|
||||
```
|
||||
{
|
||||
"code": 200,
|
||||
"key": "123456",
|
||||
"data": {
|
||||
"coal": 31.213128645837465,
|
||||
"co": 62.42625729167493,
|
||||
"vocs": 67.42035787500893,
|
||||
"pm25": 0.72,
|
||||
"pm10": 2.7600000000000002,
|
||||
"co2": 65.24910397752144
|
||||
"company": [
|
||||
"浙江秀舟热电",
|
||||
"浙江秀舟热电"
|
||||
],
|
||||
"unit": [
|
||||
"1",
|
||||
"2"
|
||||
],
|
||||
"time": [
|
||||
"2023-06-28 11:21:07",
|
||||
"2023-06-28 11:21:07"
|
||||
]
|
||||
"coal": [
|
||||
473.88829463709556,
|
||||
444.42982231624063
|
||||
],
|
||||
"co": [
|
||||
947.7765892741911,
|
||||
888.8596446324813
|
||||
],
|
||||
"vocs": [
|
||||
1023.5987164161264,
|
||||
959.9684162030799
|
||||
],
|
||||
"pm25": [
|
||||
0.35560232895598914,
|
||||
0.28232093872217645
|
||||
],
|
||||
"pm10": [
|
||||
1.3631422609979584,
|
||||
1.0822302651016766
|
||||
]
|
||||
}
|
||||
}
|
||||
```
|
||||
|
|
@ -97,7 +131,6 @@
|
|||
```
|
||||
{
|
||||
"code": 406,
|
||||
"key": "123456",
|
||||
"msg": "Input is None, please check!"
|
||||
"msg": "Input is None, please check!" # or other Exception
|
||||
}
|
||||
```
|
||||
|
|
@ -0,0 +1,17 @@
|
|||
{
|
||||
"boiler": "生产设备类型",
|
||||
"steam": "汽轮机类型",
|
||||
"cold": "冷却方式",
|
||||
"pressure": "压力参数",
|
||||
"nox": "0_r_NOx",
|
||||
"so2": "0_r_SO2",
|
||||
"smoke": "0_r_smoke",
|
||||
"flow": "0_flow",
|
||||
"o2": "0_O2",
|
||||
"temp": "0_temp",
|
||||
"evaporation": "额定蒸发量_t/h",
|
||||
"caloric": "低位发热量",
|
||||
"capacity": "单机容量（MW）",
|
||||
"lon": "lon",
|
||||
"lat": "lat"
|
||||
}
|
||||
12962
data/data_sample.csv
12962
data/data_sample.csv
File diff suppressed because it is too large
Load Diff
Binary file not shown.
|
|
@ -81,28 +81,53 @@ def predict(his_data, input_data, model:lgb.Booster, object_cols, emission_facto
|
|||
co2 = cal_CO2(coal_cost, caloric)
|
||||
return {'coal': coal_cost, 'co':co, 'vocs':vocs, 'pm25':pm25, 'pm10':pm10, 'co2':co2}
|
||||
|
||||
|
||||
|
||||
def predict_df(his_data, input_data:pd.DataFrame, model:lgb.Booster, object_cols:list, emission_factors):
|
||||
feature_names = model.feature_name()
|
||||
input_data_cp = input_data.copy()
|
||||
ignore_cols = ['company', 'unit', 'time']
|
||||
input_data['time'] = pd.to_datetime(input_data['time'])
|
||||
input_data['day_of_week'] = input_data['time'].apply(lambda x: x.weekday())
|
||||
input_data['month'] = input_data['time'].apply(lambda x: x.month)
|
||||
input_data['hour'] = input_data['time'].apply(lambda x: x.hour)
|
||||
input_data.drop(columns='time', inplace=True)
|
||||
# for col in object_cols:
|
||||
# input_data[col] = input_data[col].apply(lambda x: str(x).strip())
|
||||
num_cols = [x for x in input_data.columns if x not in ignore_cols and x not in object_cols]
|
||||
for col in num_cols:
|
||||
input_data[col] = input_data[col].astype(float)
|
||||
input_data['0_c_NOx'] = input_data.apply(lambda x:x['0_r_NOx'] * x['0_flow'], axis=1)
|
||||
input_data['0_c_SO2'] = input_data.apply(lambda x:x['0_r_SO2'] * x['0_flow'], axis=1)
|
||||
input_data['0_c_smoke'] = input_data.apply(lambda x:x['0_r_smoke'] * x['0_flow'], axis=1)
|
||||
input_data['低位发热量'] = input_data['低位发热量'].apply(lambda x: (x/1000 if x > 9999 else x))
|
||||
num_cols = [x for x in input_data.columns if x not in ignore_cols and x not in object_cols]
|
||||
new_data = input_data.copy()
|
||||
for col in num_cols:
|
||||
new_data[col] = np.log1p(new_data[col])
|
||||
total_data = pd.concat([his_data, new_data])
|
||||
new_inputs = pd.get_dummies(total_data, columns=object_cols)
|
||||
input_data_cp['coal'] = np.expm1(model.predict(new_inputs.iloc[-input_data.shape[0]:][feature_names]))
|
||||
input_data_cp['co'] = input_data_cp.apply(lambda x: cal_coal_cost_emission(x['coal'], x['生产设备类型'], emission_factors.get('co')), axis=1)
|
||||
input_data_cp['vocs'] = input_data_cp.apply(lambda x: cal_coal_cost_emission(x['coal'], x['生产设备类型'], emission_factors.get('vocs')), axis=1)
|
||||
|
||||
input_data_cp['pm25'] = input_data.apply(lambda x: cal_PM(x['0_c_smoke'], x['生产设备类型'], emission_factors.get('pm25')), axis=1)
|
||||
input_data_cp['pm10'] = input_data.apply(lambda x: cal_PM(x['0_c_smoke'], x['生产设备类型'], emission_factors.get('pm10')), axis=1)
|
||||
assert 'coal' in input_data_cp.columns
|
||||
input_data_cp['co2'] = input_data_cp.apply(lambda x: cal_CO2(x['coal'], x['低位发热量']), axis=1)
|
||||
out_cols = ['company', 'unit', 'time', 'coal', 'co', 'vocs', 'pm25', 'pm10']
|
||||
rst = input_data_cp[out_cols].to_dict(orient='list')
|
||||
return rst
|
||||
|
||||
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))
|
||||
inputs = history.iloc[:2]
|
||||
for col in inputs.columns[8:]:
|
||||
inputs[col] = np.expm1(inputs[col])
|
||||
inputs['time'] = dt.datetime.now()
|
||||
inputs['company'] = '浙江秀舟热电'
|
||||
inputs['unit'] = '1'
|
||||
print(inputs.columns)
|
||||
print(predict_df(history, inputs, model, object_cols, emission_factors))
|
||||
16
run.py
16
run.py
|
|
@ -4,17 +4,19 @@ os.environ['CUDA_VISIBLE_DEVICES'] = '-1'
|
|||
import json
|
||||
from flask import Flask, request, make_response
|
||||
from logzero import logger
|
||||
import pandas as pd
|
||||
|
||||
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
|
||||
from models.lgb_predict import load_config, load_history_data, load_lgb_model, predict_df
|
||||
|
||||
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")
|
||||
col_dict =load_config(f"{current_path}/config/columns_dict.json")
|
||||
|
||||
app = Flask(__name__)
|
||||
|
||||
|
|
@ -24,13 +26,15 @@ def run_case_check():
|
|||
resp_info = dict()
|
||||
if request.method == "POST":
|
||||
data = request.json.get('data')
|
||||
key = request.json.get('key')
|
||||
resp_info['key'] = key
|
||||
logger.info("request key: {key}")
|
||||
logger.info(data)
|
||||
columns = request.json.get('key')
|
||||
new_cols = [col_dict.get(x) if x in col_dict else x for x in columns]
|
||||
print(new_cols)
|
||||
df = pd.DataFrame.from_records(data, columns=new_cols)
|
||||
logger.info(f"request key: {columns}")
|
||||
logger.info(f"传入{len(data)}条数据")
|
||||
if data is not None and len(data) != 0:
|
||||
try:
|
||||
rst = predict(history_data, data, lgb_model, object_cols, emission_factors)
|
||||
rst = predict_df(history_data, df, lgb_model, object_cols, emission_factors)
|
||||
resp_info["code"] = 200
|
||||
resp_info["data"] = rst
|
||||
except Exception as e:
|
||||
|
|
|
|||
Loading…
Reference in New Issue