up

LIB/MIDDLE/InfoChrgDrive/Charge/V1_0_0/coreV0.py

@@ -1,4 +1,4 @@
-
+#充电基础表单所需库
 import datetime
 import pandas as pd   
 import numpy as np
@@ -7,7 +7,8 @@ import math
 from LIB.MIDDLE.CellStateEstimation.Common.V1_0_1 import BatParam
 import requests
 import re
-
+#预测充电环境所需库
+import joblib  #sklearn模型的保存与加载
 
 def process(data_ori_temp,cellvolt_list,celltemp_name,sn):
     data_ori_temp=data_ori_temp.drop(['GSM信号','故障等级','故障代码','开关状态','绝缘电阻','定位类型','速度[km/h]','有效位','外电压','总输出状态','上锁状态','加热状态','航向'],axis=1,errors='ignore')
@@ -24,7 +25,7 @@ def process(data_ori_temp,cellvolt_list,celltemp_name,sn):
     data_ori_delnone=data_ori_temp.fillna(method ='backfill', axis = 0)
     if data_ori_delnone.loc[0,'经度'] is None:
         data_ori_delnone['经度']=116.417
-        data_ori_delnone['纬度']=39.917
+        data_ori_delnone['纬度']=39.917                               
     data_ori_delnone = data_ori_delnone.dropna(axis = 1)
     for name_col in cellvolt_list:
         data_ori_delnone = data_ori_delnone.drop(data_ori_delnone[(data_ori_delnone[name_col] < 2000)].index)
@@ -36,6 +37,9 @@ def process(data_ori_temp,cellvolt_list,celltemp_name,sn):
 def city(df_sts_chrg,gpscity):
     listcity=[]
     data_sta=df_sts_chrg.reset_index(drop=True)
+    if '经度' not in list(data_sta.columns):
+        data_sta['经度']=116.417
+        data_sta['纬度']=39.917
     for i in range(len(data_sta)):
         dist=[]
         for j in range(len(gpscity)):
@@ -55,10 +59,22 @@ def gpstemp_new(data_sta):
     headers = {
         'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.183 Safari/537.36',
     }
-    if data_sta.loc[0,'city'][:2]=='北京':
-        response = requests.get('http://www.weather.com.cn/html/weather/101010100.shtml',headers=headers)
-    elif data_sta.loc[0,'city'][:2]=='苏州':
-        response = requests.get('http://www.weather.com.cn/html/weather/101190401.shtml',headers=headers)
+    r = requests.get('http://www.cma.gov.cn/',headers=headers)
+    r.encoding = r.apparent_encoding
+
+
+    city = re.findall('c\[\d{,2}\] = new Array\("选择城市",(.*?)\)',r.text)
+    city = re.findall('"([\u4e00-\u9fa5]*?)"',str(city))
+    # 不存在佛山的网页
+    city.remove('佛山')
+
+    sign = re.findall('n\[\d{,2}\] = new Array.*?\("0",(.*?)\)',r.text,re.S)
+    sign = re.findall('"(\d*?)"',str(sign))
+
+    city_sign = dict(zip(city,sign))
+    city= data_sta.loc[0,'city'][:2]
+    response = requests.get('http://www.weather.com.cn/html/weather/'+city_sign[city]+'.shtml',headers=headers)
+    
     response.encoding = response.apparent_encoding
     # 时间，需要反转一下，因为最后一条数据对应第一个
     x_time = re.findall('"od21":"(.*?)"',response.text)
@@ -289,9 +305,9 @@ def chrgst_time(data_split):   #重新计算前后闲置时长
 def chrgdr(data_split):   #根据充电信息结果合并相连同状态
     chrg=pd.DataFrame()
     if data_split.loc[0,'data_status']=='charge':
-        chrg=chrg.append(data_split.iloc[k]) 
+        chrg=chrg.append(data_split.iloc[0]) 
 
-    for k in range(1,len(data_split)-1):
+    for k in range(1,len(data_split)):
         if data_split.loc[k,'data_status']=='charge':
             if data_split.loc[k-1,'data_status']=='stand':
                 chrg=chrg.append(data_split.iloc[k-2:k+1]) 
@@ -315,54 +331,54 @@ def makedf_chrgdr(df_splice_chrg,data_new):   #每个status取所有时间戳的
     return df_chrg
 
 def change_new(df_sts_chrg,chrg_last):
+    chrg_last=pd.DataFrame()
     df_sts_chrg.reset_index(drop=True,inplace=True)
-    time_last=chrg_last['time_end']
-    time_first=df_sts_chrg.loc[0,'time_st']
-    time_last=datetime.datetime.strptime(time_last,'%Y-%m-%d %H:%M:%S')
-    if (chrg_last['status']==df_sts_chrg.loc[0,'status']) & ((time_first-time_last).total_seconds()/60<10) & \
-        (round(chrg_last['gps_lat'],2)==round(df_sts_chrg.loc[0,'gps_lat'],2)) & \
-        (round(chrg_last['gps_lon'],2)==round(df_sts_chrg.loc[0,'gps_lon'],2)) :
-        chrg_last['time_end']=df_sts_chrg.loc[0,'time_end']
-        chrg_last['delta_time']=chrg_last['delta_time']+df_sts_chrg.loc[0,'delta_time']
-        chrg_last['soc_end']=df_sts_chrg.loc[0,'soc_end']
-        chrg_last['volt_end']=df_sts_chrg.loc[0,'volt_end']
-        chrg_last['diffvolt_end']=df_sts_chrg.loc[0,'diffvolt_end']
-        chrg_last['temp_max']=np.max([df_sts_chrg.loc[0,'temp_max'],chrg_last['temp_max']])
-        chrg_last['temp_min']=np.min([df_sts_chrg.loc[0,'temp_min'],chrg_last['temp_min']])
-        chrg_last['temp_incr']=df_sts_chrg.loc[0,'temp_incr']+chrg_last['temp_incr']
-        chrg_last['temp_mean']=round(np.mean([df_sts_chrg.loc[0,'temp_mean'],chrg_last['temp_mean']]),1)
-        #chrg_last['temp_end_max']=df_sts_chrg.loc[0,'temp_end_max']
-        #chrg_last['temp_end_min']=df_sts_chrg.loc[0,'temp_end_min']
-        chrg_last['temp_end_mean']=df_sts_chrg.loc[0,'temp_end_mean']
-        chrg_last['difftem_max']=np.max([df_sts_chrg.loc[0,'difftem_max'],chrg_last['difftem_max']])
-        delta_soc=chrg_last['soc_end']-chrg_last['soc_st']
-        if delta_soc >= 3:
-            rate_chrg =round(delta_soc/(100*chrg_last['delta_time']), 2)   #电流的等效倍率
-        else:
-            rate_chrg = 0
-        if rate_chrg > 0.3:
-            stat_flg = 1#快充
-        elif rate_chrg > 0:
-            stat_flg = 2#慢充
-        else:
-            stat_flg = 0
-        if chrg_last['soc_end'] > 98:
-            full_chg_flg = 1#满充
-        else:
-            full_chg_flg = 0
-        chrg_last['meancrnt']= rate_chrg
-        chrg_last['max_meancrnt']=np.max([df_sts_chrg.loc[0,'max_meancrnt'],chrg_last['max_meancrnt']])
-        chrg_last['sts_flg']= stat_flg
-        chrg_last['full_chrg_flg']= full_chg_flg
-        chrg_last['ovchrg_flg']= np.max([df_sts_chrg.loc[0,'ovchrg_flg'],chrg_last['ovchrg_flg']])
-        chrg_last['ovchrg_prop']=df_sts_chrg.loc[0,'ovchrg_prop']+chrg_last['ovchrg_prop']
-        chrg_last['standtime_b']=df_sts_chrg.loc[0,'standtime_b']
-        chrg_last['airtemp_end']=df_sts_chrg.loc[0,'airtemp_end']
-        chrg_last=pd.DataFrame(chrg_last).T
-        df_sts_chrg=df_sts_chrg.drop([0])
-
-    else:
-        chrg_last=pd.DataFrame()
+    if len(chrg_last)>0:
+        time_last=chrg_last['time_end']
+        time_first=df_sts_chrg.loc[0,'time_st']
+        time_last=datetime.datetime.strptime(time_last,'%Y-%m-%d %H:%M:%S')
+        if (chrg_last['status']==df_sts_chrg.loc[0,'status']) & ((time_first-time_last).total_seconds()/60<10) & \
+            (round(chrg_last['gps_lat'],2)==round(df_sts_chrg.loc[0,'gps_lat'],2)) & \
+            (round(chrg_last['gps_lon'],2)==round(df_sts_chrg.loc[0,'gps_lon'],2)) :
+            chrg_last['time_end']=df_sts_chrg.loc[0,'time_end']
+            chrg_last['delta_time']=chrg_last['delta_time']+df_sts_chrg.loc[0,'delta_time']
+            chrg_last['soc_end']=df_sts_chrg.loc[0,'soc_end']
+            chrg_last['volt_end']=df_sts_chrg.loc[0,'volt_end']
+            chrg_last['diffvolt_end']=df_sts_chrg.loc[0,'diffvolt_end']
+            chrg_last['temp_max']=np.max([df_sts_chrg.loc[0,'temp_max'],chrg_last['temp_max']])
+            chrg_last['temp_min']=np.min([df_sts_chrg.loc[0,'temp_min'],chrg_last['temp_min']])
+            chrg_last['temp_incr']=df_sts_chrg.loc[0,'temp_incr']+chrg_last['temp_incr']
+            chrg_last['temp_mean']=round(np.mean([df_sts_chrg.loc[0,'temp_mean'],chrg_last['temp_mean']]),1)
+            #chrg_last['temp_end_max']=df_sts_chrg.loc[0,'temp_end_max']
+            #chrg_last['temp_end_min']=df_sts_chrg.loc[0,'temp_end_min']
+            chrg_last['temp_end_mean']=df_sts_chrg.loc[0,'temp_end_mean']
+            chrg_last['difftem_max']=np.max([df_sts_chrg.loc[0,'difftem_max'],chrg_last['difftem_max']])
+            delta_soc=chrg_last['soc_end']-chrg_last['soc_st']
+            if delta_soc >= 3:
+                rate_chrg =round(delta_soc/(100*chrg_last['delta_time']), 2)   #电流的等效倍率
+            else:
+                rate_chrg = 0
+            if rate_chrg > 0.3:
+                stat_flg = 1#快充
+            elif rate_chrg > 0:
+                stat_flg = 2#慢充
+            else:
+                stat_flg = 0
+            if chrg_last['soc_end'] > 98:
+                full_chg_flg = 1#满充
+            else:
+                full_chg_flg = 0
+            chrg_last['meancrnt']= rate_chrg
+            chrg_last['max_meancrnt']=np.max([df_sts_chrg.loc[0,'max_meancrnt'],chrg_last['max_meancrnt']])
+            chrg_last['sts_flg']= stat_flg
+            chrg_last['full_chrg_flg']= full_chg_flg
+            chrg_last['ovchrg_flg']= np.max([df_sts_chrg.loc[0,'ovchrg_flg'],chrg_last['ovchrg_flg']])
+            chrg_last['ovchrg_prop']=df_sts_chrg.loc[0,'ovchrg_prop']+chrg_last['ovchrg_prop']
+            chrg_last['standtime_b']=df_sts_chrg.loc[0,'standtime_b']
+            chrg_last['airtemp_end']=df_sts_chrg.loc[0,'airtemp_end']
+            chrg_last=pd.DataFrame(chrg_last).T
+            df_sts_chrg=df_sts_chrg.drop([0])
+            
     return df_sts_chrg,chrg_last
 
 def sep_chrg_dr(df_merge,sn,gpscity):
@@ -370,21 +386,22 @@ def sep_chrg_dr(df_merge,sn,gpscity):
     celltemp_name = [s for s in list(df_merge) if '温度' in s] 
     df_data=process(df_merge,cellvolt_list,celltemp_name,sn)
     celltype=defcelltype(sn)
-    param=BatParam.BatParam(celltype)       
-    df_data['总电流[A]']=param.PackCrntDec*df_data['总电流[A]']
-    data_new=DataPreProcess.data_split_by_status(df_data,df_data)
-    data_new=DataPreProcess.data_split_by_time(data_new,data_new) 
-    data_new=DataPreProcess.cal_stand_time(data_new,data_new)
-    data_new.reset_index(inplace = True, drop = True)
-    data_sta=city(data_new,gpscity)
-    data_sta=data_sta.reset_index(drop=True)
-    data_sta2=gpstemp_new(data_sta)
-    data_sta2.to_csv('data_sta2.csv')
-    data_split=newsplit(data_sta2)
-    data_split.to_csv('data_split.csv')
-    data_split=chrgst_time(data_split)
-   
-    chrg=chrgdr(data_split)
+    param=BatParam.BatParam(celltype)
+    chrg=pd.DataFrame()
+    data_sta2=pd.DataFrame()
+    if len(df_data)>0:    
+        df_data['总电流[A]']=param.PackCrntDec*df_data['总电流[A]']
+        data_new=DataPreProcess.data_split_by_status(df_data,df_data)
+        data_new=DataPreProcess.data_split_by_time(data_new,data_new) 
+        data_new=DataPreProcess.cal_stand_time(data_new,data_new)
+        data_new.reset_index(inplace = True, drop = True)
+        data_sta=city(data_new,gpscity)
+        data_sta=data_sta.reset_index(drop=True)
+        data_sta2=gpstemp_new(data_sta)
+        data_split=newsplit(data_sta2)
+        data_split=chrgst_time(data_split)
+        if len(data_split)>0:
+            chrg=chrgdr(data_split)
     return chrg,data_sta2,param
 
 def mkdf_chrg(chrg,data_new,param):
@@ -394,7 +411,7 @@ def mkdf_chrg(chrg,data_new,param):
         df_splice_chrg = chrg[chrg['data_split_by_status_time'] == item] 
         df_splice_chrg.reset_index(inplace = True, drop = True)
         df_chrg=makedf_chrgdr(df_splice_chrg,data_new)
-    
+        
         df_sts_chrg_temp=stat_chrg_st(df_chrg,param)
         
         if df_splice_chrg.loc[0,'data_status'] =='charge':
@@ -413,11 +430,60 @@ def pro_output(df_merge,sn,gpscity,chrg_last):
     change=pd.DataFrame()
     if len(df_merge)>0:
         chrg,data_new,param=sep_chrg_dr(df_merge,sn,gpscity)
-        chrg.to_csv('chrg.csv')
         if len(chrg)>0:
             data_sta=mkdf_chrg(chrg, data_new,param)
-            data_sta.to_csv('data_sta.csv')
             new=data_sta.copy() 
-            if len(chrg_last)>0:
-                new,change=change_new(data_sta,chrg_last)
+            new,change=change_new(data_sta,chrg_last)
     return new,change
+
+############################ Test ##########################
+def prediction(datatest,kmeans1,kmeans2,kmeans3):
+    if len(datatest)>0:
+        datatest.reset_index(drop=True,inplace=True)
+        #筛选充电数据
+        datatest2=datatest[datatest['status']=='charge']
+        #转化静置时长
+        X00t=datatest2[datatest2['standtime_f']>=10]
+        X00t['standtime_f']=10
+        X01t=datatest2[datatest2['standtime_f']<10]
+        Xt=pd.concat([X00t,X01t])
+        #按温度切分数据
+        Xt1=Xt[Xt['airtemp_st']>=18]
+        Xt2=Xt[Xt['airtemp_st']<18]
+        #温暖天气模型预测
+        if len(Xt1)>0:
+            #KMeans1
+            Xt11=Xt1[['standtime_f','temp_incr']]
+            y_hat = kmeans1.predict(np.array(Xt11))
+            Xt11['cluster_db']=y_hat
+            Xt121=Xt11[(Xt11['cluster_db']==0)|(Xt11['cluster_db']==1)]
+            Xt121['charge_env']='室外'
+            datatest=pd.merge(Xt121['charge_env'],datatest,how='outer',right_index=True,left_index=True)
+            #KMeans2
+            Xt12=Xt11[(Xt11['cluster_db']==2)|(Xt11['cluster_db']==3)]
+            if len(Xt12)>0:
+                Xt13=pd.merge(Xt12['cluster_db'],Xt1,how='left',right_index=True,left_index=True)
+                Xt13['airtemp']=list(Xt13[['airtemp_st','airtemp_end']].mean(axis=1))
+                Xt14=Xt13[['temp_max','airtemp']]
+                y_hat2 = kmeans2.predict(np.array(Xt14))
+                Xt14['cluster_db']=y_hat2
+                Xt151=Xt14[(Xt14['cluster_db']==1)|(Xt14['cluster_db']==2)]
+                for k in list(Xt151.index):
+                    datatest.loc[k,'charge_env']='室外'
+                #KMeans3
+                Xt15=Xt14[(Xt14['cluster_db']==0)|(Xt14['cluster_db']==3)]
+                if len(Xt15)>0:
+                    Xt16=pd.merge(Xt15['cluster_db'],Xt1,how='left',right_index=True,left_index=True)
+                    Xt17=Xt16[['standtime_f','delta_time']]
+                    y_hat3 = kmeans3.predict(np.array(Xt17))
+                    Xt17['cluster_db']=y_hat3
+                    Xt181=Xt17[(Xt17['cluster_db']==0)|(Xt14['cluster_db']==2)]
+                    for k in list(Xt181.index):
+                        datatest.loc[k,'charge_env']='室外'
+                    Xt180=Xt17[Xt17['cluster_db']==3]
+                    for k in list(Xt180.index):
+                        datatest.loc[k,'charge_env']='室内'
+                    Xt182=Xt17[Xt17['cluster_db']==1]
+                    for k in list(Xt182.index):
+                        datatest.loc[k,'charge_env']='疑似室内'
+    return datatest

LIB/MIDDLE/InfoChrgDrive/Charge/main_V0.py

@@ -31,7 +31,7 @@ def diag_cal():
     #读取结果库数据......................................................
     param='sn,time_st,time_end,status,delta_time,soc_st,soc_end,volt_st,volt_end,diffvolt_st,diffvolt_end, \
         temp_max,temp_min,temp_incr,temp_mean,temp_st_mean,temp_end_mean,difftem_max,meancrnt,max_meancrnt, \
-        sts_flg,full_chrg_flg,ovchrg_flg,ovchrg_prop,gps_lon,gps_lat,standtime_f,standtime_b,city,airtemp_st,airtemp_end'
+        sts_flg,full_chrg_flg,ovchrg_flg,ovchrg_prop,gps_lon,gps_lat,standtime_f,standtime_b,city,airtemp_st,airtemp_end,charge_env'
     tablename='algo_charge_info'
     mysql = pymysql.connect (host=host, user=user, password=password, port=port, database=db)
     cursor = mysql.cursor()
@@ -72,7 +72,14 @@ def diag_cal():
                     df_diag_ram_sn=df_diag_ram[df_diag_ram['sn']==sn]
                     if not df_diag_ram_sn.empty:   #该sn相关结果非空
                         df_diag_ram_sn.reset_index(inplace=True,drop=True)
+                        df_diag_ram_sn=df_diag_ram_sn.iloc[-1]
+                        df_diag_ram_sn.reset_index(inplace=True,drop=True)
                 df_diag_new,df_diag_change=pro_output(df_merge,sn,gpscity,df_diag_ram_sn)
+                kmeans1 = joblib.load('kmeans1.pkl')
+                kmeans2 = joblib.load('kmeans2.pkl')
+                kmeans3 = joblib.load('kmeans3.pkl')
+                df_diag_new=prediction(df_diag_new,kmeans1,kmeans2,kmeans3)
+                df_diag_change=prediction(df_diag_change,kmeans1,kmeans2,kmeans3)
                 if not df_diag_change.empty:   #需变更的结果非空
                     cursor.execute("DELETE FROM algo_charge_info WHERE time_end = '0000-00-00 00:00:00' and sn='{}'".format(sn))
                     mysql.commit()