You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
288 lines
14 KiB
288 lines
14 KiB
# -*- coding: utf-8 -*-
|
|
"""
|
|
Created on Sun Feb 28 10:04:26 2016
|
|
PCA source code
|
|
@author: liudiwei
|
|
"""
|
|
|
|
import numpy as np
|
|
import traceback
|
|
import pandas as pd
|
|
#import matplotlib.pyplot as plt
|
|
from scipy.stats import norm
|
|
from scipy.stats import f
|
|
from scipy.stats.distributions import chi2
|
|
import json
|
|
import sys
|
|
import requests
|
|
import datetime
|
|
import jenkspy
|
|
import xlrd
|
|
from smote import smote
|
|
import config
|
|
|
|
|
|
"""
|
|
参数：
|
|
- XMat：传入的是一个numpy的矩阵格式，行表示样本数，列表示特征
|
|
- k：表示取前k个特征值对应的特征向量
|
|
返回值：
|
|
"""
|
|
|
|
|
|
def get_history_value(points,time,interval):
|
|
#url="http://192.168.1.201:8080/openPlant/getMultiplePointHistorys"
|
|
url=f"http://{config._EXA_IP}:9000/exawebapi/exatime/GetSamplingValueArrayFloat"
|
|
headers = {"Content-Type": "application/json;charset=utf-8"}#,"token":get_token()
|
|
point_array = points.split(",")
|
|
time_span = time.split(";")
|
|
value_array = []
|
|
for item in point_array:
|
|
value_group = []
|
|
for time_piece in time_span:
|
|
st = time_piece.split(",")[0]
|
|
et = time_piece.split(",")[1]
|
|
para = {"ItemName": item, "StartingTime": st, "TerminalTime": et, "SamplingPeriod": interval}
|
|
response = requests.get(url, headers=headers, params=para)
|
|
content = response.text.replace('"[','[').replace(']"',']')
|
|
value = json.loads(content)
|
|
for row in value:
|
|
value_group.append(row[1])
|
|
value_array.append(value_group)
|
|
return np.transpose(np.array(value_array))
|
|
|
|
|
|
def pca(XMat,k):
|
|
m = np.array(XMat).shape[1]
|
|
average = np.mean(XMat, axis=0)
|
|
std = np.std(XMat, axis=0)#方差
|
|
m, n = np.shape(XMat)
|
|
avgs = np.tile(average, (m, 1))
|
|
stds = np.tile(std, (m, 1))
|
|
data_adjust = np.divide(XMat - avgs, stds)
|
|
covX = np.cov(data_adjust.T) # 计算协方差矩阵
|
|
# corr=np.corrcoef(data_adjust.T)
|
|
featValue, featVec = np.linalg.eig(covX) # 求解协方差矩阵的特征值和特征向量
|
|
featValue = np.real(featValue)
|
|
featVec = np.real(featVec)
|
|
# ############可能协方差为0（一列数据相同，在训练的时候不要选择一样的数据，就不能除。############################
|
|
index = np.argsort(-featValue) # 按照featValue进行从大到小排序
|
|
featValue=featValue[index]
|
|
featVec = featVec[:,index]
|
|
featValue_sum = np.divide(featValue, np.sum(featValue))
|
|
per = 0 # 特征值百分比
|
|
# k = 0 # 主元个数
|
|
# for precent in featValue_sum:
|
|
# per += precent
|
|
# k = k + 1
|
|
# if per > p:
|
|
# break
|
|
|
|
finalData = []
|
|
if k > n:
|
|
print
|
|
"k must lower than feature number"
|
|
return
|
|
else:
|
|
# 注意特征向量时列向量，而numpy的二维矩阵(数组)a[m][n]中，a[1]表示第1行值
|
|
selectVec = np.matrix(featVec[:, :k]) # 所以这里需要进行转置
|
|
finalData = np.dot(data_adjust, selectVec).dot(selectVec.T)
|
|
reconData = np.add(np.multiply(finalData, stds), avgs) # 重构值
|
|
Train_X_min = np.min(XMat, axis=0) # 训练值最小值
|
|
Train_X_max = np.max(XMat, axis=0) # 训练值最大值
|
|
Train_X_mean = np.mean(XMat, axis=0) # 训练值平均值
|
|
Train_X_std = np.std(XMat, axis=0) # 训练值方差
|
|
Train_X_bais = XMat - reconData # 训练值偏差
|
|
Train_X_bais_max = np.max(np.abs(Train_X_bais), axis=0) # 训练值偏差最大值
|
|
Train_X_bais_min = np.min(np.abs(Train_X_bais), axis=0) # 训练值偏差最小值
|
|
Train_X_bais_mean = np.mean(np.abs(Train_X_bais), axis=0) # 训练值偏差平均值
|
|
Train_X_bais_std_upperB95 = np.array(np.abs(1.96 * np.std(Train_X_bais, axis=0) + Train_X_bais_mean))[
|
|
0] # 训练值偏差标准差
|
|
Train_X_bais_std_upperB99 = np.array(np.abs(2.58* np.std(Train_X_bais, axis=0) + Train_X_bais_mean))[0]
|
|
Train_X_bais_std_lowerB95 = np.array(np.abs(1.96 * np.std(Train_X_bais, axis=0) - Train_X_bais_mean))[
|
|
0] # 训练值偏差标准差
|
|
Train_X_bais_std_lowerB99 = np.array(np.abs(2.58 * np.std(Train_X_bais, axis=0) - Train_X_bais_mean))[0]
|
|
QCUL_95_line = []#限值
|
|
QCUL_99_line = []
|
|
for index1 in range(len(Train_X_bais_std_upperB95)):
|
|
QCUL_95_line.append(max(Train_X_bais_std_upperB95[index1], Train_X_bais_std_lowerB95[index1]))
|
|
QCUL_99_line.append(max(Train_X_bais_std_upperB99[index1], Train_X_bais_std_lowerB99[index1]))
|
|
QCUL_95_line = np.array(QCUL_95_line)
|
|
QCUL_99_line = np.array(QCUL_99_line)
|
|
#################################################################################
|
|
# 计算阈值----------------QUCL--------------------################################################
|
|
theta1 = np.sum(featValue[k:])
|
|
theta2 = np.sum(np.power(featValue[k:], 2))
|
|
theta3 = np.sum(np.power(featValue[k:], 3))
|
|
h0 = 1 - 2 * theta1 * theta3 / (3 * np.power(theta2, 2))
|
|
ca_95 = norm.ppf(0.95, loc=0, scale=1)
|
|
QCUL_95 = theta1 * np.power(
|
|
h0 * ca_95 * np.sqrt(2 * theta2) / theta1 + 1 + theta2 * h0 * (h0 - 1) / np.power(theta1, 2),
|
|
1 / h0) # 置信域为百分之95
|
|
# QCUL_95_line = Train_X_bais_std*2.58 # +Train_X_mean#反归一化阈值
|
|
ca_99 = norm.ppf(0.99, loc=0, scale=1)
|
|
QCUL_99 = theta1 * np.power(
|
|
(h0 * ca_99 * np.sqrt(2 * theta2) / theta1 + 1 + theta2 * h0 * (h0 - 1) / np.power(theta1, 2)),
|
|
1 / h0) # 置信域为百分之99
|
|
# QCUL_99_line = Train_X_bais_std*1.96 # + Train_X_mean # 反归一化阈值
|
|
|
|
# 计算阈值----------------T2UCL--------------------###########################################
|
|
f_95 = f.ppf(0.95, k, m - k)
|
|
T2CUL_95 = k * (m - 1) * (m + 1) * f_95 / (m * (m - k)) # 置信域为百分之95
|
|
T2CUL_95_line = np.sqrt(T2CUL_95) * Train_X_std / np.sqrt(m) # +Train_X_mean#反归一化阈值
|
|
f_99 = f.ppf(0.99, k, m - k)
|
|
T2CUL_99 = k * (m - 1) * (m + 1) * f_99 / (m * (m - k)) # 置信域为百分之99
|
|
T2CUL_99_line = np.sqrt(T2CUL_99) * Train_X_std / np.sqrt(m) # +Train_X_mean#反归一化阈值
|
|
|
|
# 计算阈值----------------综合--------------------#################################################
|
|
gfi_95 = (k / pow(T2CUL_95, 2) + theta2 / pow(QCUL_95, 2)) / (k / T2CUL_95 + theta1 / QCUL_95)
|
|
hfi_95 = pow((k / T2CUL_95 + theta1 / QCUL_95), 2) / (k / pow(T2CUL_95, 2) + theta2 / pow(QCUL_95, 2))
|
|
Kesi_95 = gfi_95 * chi2.ppf(0.95, hfi_95) # 卡方分布
|
|
Kesi_95_line = np.sqrt(Kesi_95) * Train_X_std / np.sqrt(m) # 反归一化阈值
|
|
|
|
gfi_99 = (k / pow(T2CUL_99, 2) + theta2 / pow(QCUL_99, 2)) / (k / T2CUL_99 + theta1 / QCUL_99)
|
|
hfi_99 = pow((k / T2CUL_99 + theta1 / QCUL_99), 2) / (k / pow(T2CUL_99, 2) + theta2 / pow(QCUL_99, 2))
|
|
Kesi_99 = gfi_99 * chi2.ppf(0.99, hfi_99) # 卡方分布
|
|
Kesi_99_line = np.sqrt(Kesi_99) * Train_X_std / np.sqrt(m) # 反归一化阈值
|
|
|
|
# cos检验值
|
|
# R = per#相关性
|
|
#for index in range(0, reconData.shape[1]):
|
|
#vector1 = XMat[:, index]
|
|
#vector2 = np.array(reconData)[:, index]
|
|
#R += np.dot(vector1, vector2.T) / (np.sqrt(np.sum(vector1 ** 2)) * np.sqrt(np.sum(vector2 ** 2)))
|
|
#sR /= reconData.shape[1]
|
|
|
|
#####################################################################################################################
|
|
items = [('Train_X_min', np.around(Train_X_min, decimals=3).tolist()),
|
|
('Train_X_max', np.around(Train_X_max, decimals=3).tolist()),
|
|
('Train_X_std', np.around(Train_X_std, decimals=3).tolist()),
|
|
('Train_X_mean',np.around(Train_X_mean, decimals=3).tolist()),
|
|
('Train_X_bais_max',np.around(Train_X_bais_max, decimals=3).tolist()),
|
|
('Train_X_bais_min', np.around(Train_X_bais_min, decimals=3).tolist()),
|
|
('Train_X_bais_mean',np.around(Train_X_bais_mean, decimals=3).tolist()),
|
|
('QCUL_95',QCUL_95.tolist()),
|
|
('QCUL_99', QCUL_99.tolist()),
|
|
('QCUL_95_line',np.around(QCUL_95_line, decimals=3).tolist()),
|
|
('QCUL_99_line',np.around(QCUL_99_line, decimals=3).tolist()),
|
|
('T2CUL_95', np.around(T2CUL_95, decimals=3).tolist()),
|
|
('T2CUL_99', np.around(T2CUL_99, decimals=3).tolist()),
|
|
('T2CUL_95_line', np.around(T2CUL_95_line, decimals=3).tolist()),
|
|
('T2CUL_99_line', np.around(T2CUL_99_line, decimals=3).tolist()),
|
|
('Kesi_95', np.around(Kesi_95, decimals=3).tolist()),
|
|
('Kesi_99', np.around(Kesi_99, decimals=3).tolist()),
|
|
('Kesi_95_line', np.around(Kesi_95_line, decimals=3).tolist()),
|
|
('Kesi_99_line', np.around(Kesi_99_line, decimals=3).tolist()),
|
|
('COV', np.around(covX, decimals=3).tolist()),
|
|
('K', k),
|
|
("featValue",np.around(featValue, decimals=3).tolist()),
|
|
("featVec", np.around(featVec, decimals=3).tolist()),
|
|
("selectVec", np.around(selectVec, decimals=3).tolist())]
|
|
# model_info=json.dumps(dict(items))
|
|
# res_items = [('Model_info', dict(items)), ('Model_type', 'PCA')]
|
|
result = dict(items) # json.dumps(result)
|
|
return result
|
|
|
|
|
|
def main(info):
|
|
Train_Data = info["Train_Data"]
|
|
points = Train_Data["points"]
|
|
time = Train_Data["time"]
|
|
interval = Train_Data["interval"]
|
|
Hyper_para = info["Hyper_para"]
|
|
percent = Hyper_para["percent"]
|
|
XMat = get_history_value(points, time, interval)
|
|
result = pca(XMat, percent) # 训练数据，主元百分比
|
|
result = result.replace("NaN", "-1") # 防止出现非数 解析不出来
|
|
return result
|
|
|
|
def isnumber(limits):
|
|
flag=True
|
|
for item in limits:
|
|
item=item.replace("-","")
|
|
if(item.isdigit()==False):
|
|
flag=False
|
|
break
|
|
return flag
|
|
|
|
|
|
def clearmain(info):
|
|
try:
|
|
Train_Data = info["Train_Data"]
|
|
condition=info["conditon"].replace("=","==").replace(">=",">").replace("<=","<")
|
|
times = Train_Data["time"].split(';')
|
|
points = Train_Data["points"].split(',')
|
|
interval = Train_Data["interval"]
|
|
if interval == 10000:
|
|
DCount = 60
|
|
elif interval == 100000:
|
|
DCount = 6
|
|
elif interval == 300000:
|
|
DCount = 5
|
|
else:
|
|
DCount = 4
|
|
dead = Train_Data["dead"].split(',')
|
|
limit = Train_Data["limit"].split(',')
|
|
uplower = Train_Data["uplow"].split(';')
|
|
percent = info["Hyper_para"]["percent"]
|
|
count=0
|
|
ItemsInfo, SamplingTimePeriods = [], []
|
|
Constraint = ""
|
|
for i in range(len(points)):
|
|
iteminfo = {}
|
|
iteminfo["ItemName"] = points[i] # 加点
|
|
if (dead[i] == "1"): # 判断是否参与死区清洗
|
|
iteminfo["ClearDeadZone"] = "true"
|
|
else:
|
|
iteminfo["ClearDeadZone"] = "false"
|
|
if (limit[i] == "1"): # 参与上下限清洗
|
|
limits = uplower[i].split(',')
|
|
if (isnumber(limits) == True): # 输入上下限正确
|
|
count += 1
|
|
Constraint += "[" + points[i] + "]>" + limits[0] + " and " + "[" + points[i] + "]<" + limits[1] + " and "
|
|
ItemsInfo.append(iteminfo)
|
|
if(count!=0):
|
|
Constraint = Constraint[:len(Constraint) - 4:]
|
|
else:
|
|
Constraint="1==1"#没有上下限清洗
|
|
Constraint+=" and ("+condition+")"
|
|
for i in range(len(times)):
|
|
Eachsampletime = {}
|
|
timess = times[i].split(',')
|
|
Eachsampletime["StartingTime"] = timess[0]
|
|
Eachsampletime["TerminalTime"] = timess[1]
|
|
SamplingTimePeriods.append(Eachsampletime)
|
|
Constraint = Constraint.replace("\n", " ")
|
|
url = f"http://{config._CLEAN_IP}/exawebapi/exatime/GetCleaningData?ItemsInfo=%s&SamplingTimePeriods=%s&Constraint=%s&SamplingPeriod=%s&DCount=%d" % (
|
|
ItemsInfo, SamplingTimePeriods, Constraint, interval, DCount)
|
|
response = requests.get(url)
|
|
content = json.loads(response.text)
|
|
data = np.array([item for item in content["ClearData"]]).T
|
|
try:
|
|
smote_data = info["smote"]
|
|
except KeyError:
|
|
smote_data = False
|
|
if smote_data:
|
|
smote_index = [points.index(item["smote_point"]) for item in info["smote_config"]]
|
|
smote_num = [item["break_point_num"] for item in info["smote_config"]]
|
|
data = smote(data, smote_index, smote_num)
|
|
result = pca(data, percent)
|
|
result = result.replace("NaN", "-1")
|
|
result=json.loads(result)
|
|
result["BeforeCleanSamNum"]=content["BeforeCleanSamNum"]
|
|
result["AfterCleanSamNum"]=content["AfterCleanSamNum"]
|
|
result["CleanOrNot"] = True
|
|
return json.dumps(result)
|
|
except Exception as e:
|
|
result = [{"CleanOrNot": False}]
|
|
return json.dumps(result)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
worksheet = pd.read_excel("train_data_1.xlsx", sheet_name="Sheet1")
|
|
data = [item for _, item in worksheet.iterrows()]
|
|
pca(data, 3)
|
|
# info_str = '{"Train_Data":{"time":"2020-01-12 19:35:34,2020-01-13 04:29:48;2020-01-13 05:46:07,2020-01-13 13:18:00","points":"JL_D1_10DAS05B:MAD10CY102A,JL_D1_10DAS05B:MAD10CY103A,JL_D1_10DAS05B:MAD20CY102A,JL_D1_10DAS05B:MAD20CY103A,JL_D1_10DAS05B:MAD30CY102A,JL_D1_10DAS05B:MAD30CY103A,JL_D1_10DAS05B:MAD40CY102A,JL_D1_10DAS05B:MAD40CY103A,JL_D1_10DAS05B:MAD50CY102A,JL_D1_10DAS05B:MAD50CY103A,JL_D1_10DAS05B:MAD60CY102A,JL_D1_10DAS05B:MAD60CY103A,JL_D1_10DAS05B:MAD70CY102A,JL_D1_10DAS05B:MAD70CY103A,JL_D1_10DAS05B:MAD80CY102A,JL_D1_10DAS05B:MAD80CY103A,JL_D1_10DAS05B:MAD90CY102A,JL_D1_10DAS05B:MAD90CY103A,JL_D1_10MCS07A:MAV15CT301,JL_D1_10DAS09A:MAV15CP101.PNT,JL_D1_10DAS25B:10MKA01CE001.PNT","interval":300000,"dead":"1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1","limit":"0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0","uplow":"0,500;0,500;0,500;0,500;0,500;0,500;0,500;0,500;0,500;0,500;0,500;0,500;0,500;0,500;0,500;0,500;0,500;0,500;0,100;0,0.4;0,866"},"Hyper_para":{"percent":0.85},"type":"PCA","conditon":"[JL_D1_10DAS25B:10MKA01CE001.PNT]>0 and [JL_D1_1OA_IO:GV13PZCHAR]<5 and [JL_D1_1OA_IO:GV24PZCHAR]<5"}'
|
|
# info = json.loads(info_str)
|
|
# res = json.loads(clearmain(info))
|
|
# print("aaa")
|
|
|