#================================================ This script is a simple example of the Knowledge extraction tool ===============================================================#
#The following is the Main script, that calls two Python objects in order to conduct the three main components of the Knowledge extraction tool
#In the following example the operation times of the topology's two machines are given in an Excel document.
#Import_Excel object imports data from the Excel document to the tool and DistFittest object fits the data to a statistical distribution using Kolmogorov-Smirnov test
workbook=xlrd.open_workbook('inputsKEtool.xls')#Using xlrd library opens the Excel document with the input data
worksheets=workbook.sheet_names()
worksheet_OperationTime=worksheets[0]#It creates a variable that holds the first Excel worksheet
X=Import_Excel()#Call the import_Excel object
OperationTimes=X.Input_data(worksheet_OperationTime,workbook)#It defines a Python dictionary, giving as name OpearationTimes and as value the returned dictionary from the import_Excel object
Machine1_OpearationTimes=OperationTimes.get('Machine1',[])#Two lists are defined (Machine1_OpearationTimes, Machine2_OpearationTimes) with the operation times data of each machine
Dict['M1']=B.ks_test(Machine1_OpearationTimes)#It conducts the Kolmogorov-Smirnov test in the list with the operation times data
Dict['M2']=B.ks_test(Machine2_OpearationTimes)
M1=Dict.get('M1')
M2=Dict.get('M2')
#==================================== Output preparation: output the updated values in the CMSD information model of Topology10 ====================================================#
datafile=('CMSD_Topology10.xml')#It defines the name or the directory of the XML file that is manually written the CMSD information model
tree=et.parse(datafile)#This file will be parsed using the XML.ETREE Python library
M1Parameters=[]
M1ParameterValue=[]
forindexinlist(Dict['M1'].keys()):
ifindexisnot'distributionType':
M1Parameters.append(index)
M1ParameterValue.append(Dict['M1'][index])
ifDict['M1']['distributionType']=='Normal':
delM1['min']
delM1['max']
elifDict['M2']['distributionType']=='Normal':
delM2['min']
delM2['max']
M2Parameters=[]
M2ParameterValue=[]
forindexinlist(Dict['M2'].keys()):
ifindexisnot'distributionType':
M2Parameters.append(index)
M2ParameterValue.append(Dict['M2'][index])
root=tree.getroot()
process=tree.findall('./DataSection/ProcessPlan/Process')#It creates a new variable and using the 'findall' order in XML.ETREE library, this new variable holds all the processes defined in the XML file
forprocessinprocess:
process_identifier=process.find('Identifier').text#It creates a new variable that holds the text of the Identifier element in the XML file
ifprocess_identifier=='A020':#It checks using if...elif syntax if the process identifier is 'A020', so the process that uses the first machine
OperationTime=process.get('OpeationTime')#It gets the element attribute OpearationTime inside the Process node
Distribution=process.get('./OperationTime/Distribution')#It gets the element attribute Distribution inside the OpearationTime node
Name=process.find('./OperationTime/Distribution/Name')#It finds the subelement Name inside the Distribution attribute
Name.text=Dict['M1']['distributionType']#It changes the text between the Name element tags, putting the name of the distribution (e.g. in Normal distribution that will be Normal)
Name.text=str(M1Parameters[0])#It changes the text between the Name element tags, putting the name of the distribution's first parameter (e.g. in Normal that will be the mean)
Value.text=str(M1ParameterValue[0])#It changes the text between the Value element tags, putting the value of the distribution's first parameter (e.g. in Normal so for mean value that will be 5.0)
Name.text=str(M1Parameters[1])#It changes the text between the Name element tags, putting the name of the distribution's second parameter (e.g. in Normal that will be the standarddeviation)
Value.text=str(M1ParameterValue[1])#It changes the text between the Value element tags, putting the value of the distribution's second parameter (e.g. in Normal so for standarddeviation value that will be 1.3)
elifprocess_identifier=='A040':#It checks using if...elif syntax if the process identifier is 'A040', so the process that uses the second machine
tree.write('CMSD_Topology10_Output.xml',encoding="utf8")#It writes the element tree to a specified file, using the 'utf8' output encoding
#================================= Output preparation: output the updated values in the JSON file of Topology10 =========================================================#
jsonFile=open('JSON_Topology10.json','r')#It opens the Topology10 JSON file
data=json.load(jsonFile)#It loads the file
jsonFile.close()
nodes=data.get('coreObject',[])#It creates a variable that holds the 'coreObject' list
forelementinnodes:
name=element.get('name')#It creates a variable that gets the element attribute 'name'
processingTime=element.get('processingTime',{})#It creates a variable that gets the element attribute 'processingTime'
ifname=='Machine1':
element['processingTime']=Dict['M1']#It checks using if...elif syntax if the name is 'Machine1', so the first machine in the Topology10
elifname=='Machine2':
element['processingTime']=Dict['M2']
else:
continue
jsonFile=open('JSON_Topology10_Output.json',"w")#It opens the JSON file
jsonFile.write(json.dumps(data,indent=True))#It writes the updated data to the JSON file
jsonFile.close()#It closes the file
#================================ Calling the ExcelOutput object, outputs the outcomes of the statistical analysis in Excel files =============================================#
