def loadProps(path):
props = Properties()
try:
propReader = FileReader(path)
props.load(propReader)
propReader.close()
except:
type, value, traceback = sys.exc_info()
print "Error loading properties from file:" + path + ":" + ` value `
return props
def insert_file_data_to_db_batch():
'''
FUNC FOR DATA INSERTING INTO DATABASE
'''
ins_log("Adding data to DB...", 'Using JDBC from File')
global conn, unarchived_file, lnNum, totalRecords, batch_size
conn.setSchema(s_schema)
truncate_table()
conn.setAutoCommit(False)
#jdbc_insert_sql = 'insert into dim_invalid_passports (pass_serial, pass_no, valid_to_dttm) values (?,?,?)';
jdbc_insert_sql = 'insert into dim_invalid_passports (pass_serial, pass_no, sys_actual_flg, sys_deleted_flg, valid_from_dttm, valid_to_dttm, sys_mod_by) values (?, ?, ?, ?, ?, ?, ? )'
#print(jdbc_insert_sql);
sql_statement = conn.prepareStatement(jdbc_insert_sql)
reader = CSVReader(FileReader(unarchived_file))
#/* Read CSV file in OpenCSV */
nextLine = reader.readNext()
while reader.readNext() != None:
lnNum += 1
sql_statement.setString(1, replace_str(reader.readNext()[0]))
sql_statement.setString(2, replace_str(reader.readNext()[1]))
sql_statement.setInt(3, 1)
sql_statement.setInt(4, 0)
sql_statement.setTimestamp(5, Timestamp(System.currentTimeMillis()))
sql_statement.setString(6, "01.01.2400")
sql_statement.setString(7, "ODI_USER")
sql_statement.addBatch()
if lnNum % batch_size == 0 or reader.readNext() == None:
sql_statement.executeBatch()
#print(sql_statement.executeBatch());
conn.commit()
sql_statement.close()
ins_log('File inserted, ' + str(lnNum) + " rows added;",
str(jdbc_insert_sql) + ' batch_size = ' + str(batch_size))
conn.close()
def LineGroupInstanceAdd(data, fileName, seperator="^\\s*$"):
"""
add some extra data to an instance list.
"""
data.add(
LineGroupIterator(FileReader(File(fileName)),
Pattern.compile(seperator), 1))
def _read_value_from_file(file_path, model_context):
"""
Read a single text value from the first line in the specified file.
:param file_path: the file from which to read the value
:return: the text value
:raises BundleAwareException if an error occurs while reading the value
"""
method_name = '_read_value_from_file'
try:
file_reader = BufferedReader(FileReader(file_path))
line = file_reader.readLine()
file_reader.close()
except IOException, e:
if model_context.get_validation_method() == 'strict':
_logger.severe('WLSDPLY-01733',
file_path,
e.getLocalizedMessage(),
class_name=_class_name,
method_name=method_name)
ex = exception_helper.create_variable_exception(
'WLSDPLY-01733', file_path, e.getLocalizedMessage(), error=e)
_logger.throwing(ex,
class_name=_class_name,
method_name=method_name)
raise ex
else:
_logger.info('WLSDPLY-01733',
file_path,
e.getLocalizedMessage(),
error=e,
class_name=_class_name,
method_name=method_name)
line = ''
def searchFile2(event):
label3.text = "Isi pesan terenkripsi"
label4.text = "Isi pesan asli"
myFileChooser = JFileChooser()
rVal = int(myFileChooser.showOpenDialog(None))
print rVal
if (rVal == JFileChooser.APPROVE_OPTION):
encryptedTextFile.text = myFileChooser.getSelectedFile().getName()
encryptedTextPath.text = myFileChooser.getCurrentDirectory().toString()
try:
myPath = encryptedTextPath.text + "/" + encryptedTextFile.text
fileReaderX = FileReader(myPath)
bufferedReaderX = BufferedReader(fileReaderX)
inputFile = ""
textFieldReadable = bufferedReaderX.readLine()
while (textFieldReadable != None):
inputFile += textFieldReadable
inputFile += "\n"
textFieldReadable = bufferedReaderX.readLine()
pesanAsli.text = inputFile
import myGUI.saveToFile as convertThis
return convertThis.convertBackToInt(inputFile)
except (RuntimeError, TypeError, NameError):
print "eror gan"
def printToTextArea(event):
try:
myPath = plainTextPath.text + "/" + plainTextFile.text
fileReader = FileReader(myPath)
bufferedReader = BufferedReader(fileReader)
inputFile = ""
intToPrint = ""
myString = ""
textFieldReadable = bufferedReader.readLine()
while (textFieldReadable != None):
inputFile += textFieldReadable
inputFile += "\n"
textFieldReadable = bufferedReader.readLine()
pesanAsli.text = inputFile
thisInt = parseMyStringToInt(inputFile)
elGamalPK = [int(alpha.text), int(beta.text), int(genPrima.text)]
encryptedMessage = elGamal.Enkripsi(elGamalPK, thisInt)
#thisInt = thisFoo(inputFile)
for i in range(0, (len(thisInt) - 1)):
intToPrint += encryptedMessage[i][0],
myString += encryptedMessage[i][0]
intToPrint += encryptedMessage[i][1]
myString += encryptedMessage[i][1]
if (i % 5 == 0):
intToPrint += "\n"
print "ini pesan:", intToPrint
pesanTerenkripsi.setText("")
pesanTerenkripsi.text = intToPrint
except (RuntimeError, TypeError, NameError):
print "eror gan"
def __getEc2PrivateIpv4s(self, additionalVariables):
try:
dir = File(self.__basedir)
dir = dir.getParentFile().getParentFile().getParentFile()
fileReader = FileReader(File(dir, "engine-session.properties"))
props = Properties()
props.load(fileReader)
ec2PrivateIpv4s = props.getProperty("ec2PrivateIpv4s")
if ec2PrivateIpv4s:
ipList = ec2PrivateIpv4s.split()
logger.info("Ec2 Private IPv4s:" + list2str(ipList))
engineInstance = getVariableValue("ENGINE_INSTANCE")
engineInstance = int(engineInstance)
if len(ipList) > engineInstance:
self.__dockerHostIp = ipList[engineInstance]
logger.info("Setting DOCKER_HOST_IP:" +
self.__dockerHostIp)
additionalVariables.add(
RuntimeContextVariable(
"DOCKER_HOST_IP", self.__dockerHostIp,
RuntimeContextVariable.STRING_TYPE,
"Docker Host IP", False,
RuntimeContextVariable.NO_INCREMENT))
else:
self.__dockerHostIp = getVariableValue("LISTEN_ADDRESS")
additionalVariables.add(
RuntimeContextVariable(
"DOCKER_HOST_IP", self.__dockerHostIp,
RuntimeContextVariable.STRING_TYPE,
"Docker Host IP", False,
RuntimeContextVariable.NO_INCREMENT))
except:
type, value, traceback = sys.exc_info()
logger.warning("read engine session properties error:" + ` value `)
def _parse_and_rewrite_svg_file(svg_input_path, svg_output_path):
write_str = ""
file_reader = FileReader(svg_input_path)
buffered_reader = BufferedReader(file_reader)
read_line = ""
check = False
while True:
read_line = buffered_reader.readLine()
if read_line is None:
break
if "viewBox" in read_line:
view_box_content = _get_viewbox_content(read_line)
view_box_values = _get_viewbox_values(view_box_content)
if view_box_values[0] != 0:
view_box_values[2] = abs(view_box_values[2]) + abs(
view_box_values[0])
view_box_values[0] = 0
if view_box_values[1] != 0:
view_box_values[3] = abs(view_box_values[3]) + abs(
view_box_values[1])
view_box_values[1] = 0
read_line = re.sub(r"viewBox=\"[\-|0-9| ]+\"", "", read_line, 1)
read_line = re.sub(r"width=\"[0-9]+\"",
"width=\"" + str(view_box_values[2]) + "\"",
read_line, 1)
read_line = re.sub(r"height=\"[0-9]+\"",
"height=\"" + str(view_box_values[3]) + "\"",
read_line, 1)
check = True
if "g id=\"ID" in read_line and not check:
if "transform=" in read_line:
_log.info(read_line)
read_line = read_line[0:read_line.find("transform")] + ">"
check = True
write_str += read_line + "\n"
buffered_reader.close()
file_reader.close()
file_writer = PrintWriter(svg_output_path)
file_writer.print(write_str)
file_writer.close()
def assign_ids_from_list(tax, filename):
count = 0
if True:
infile = FileReader(filename)
r = CSVReader(infile)
while True:
row = r.readNext()
if row == None: break
[qid, ids] = row
taxon = tax.lookupQid(QualifiedId(qid))
if taxon != None:
for id in ids.split(';'):
z = tax.lookupId(id)
if z == None:
taxon.taxonomy.addId(taxon, id)
count += 1
infile.close()
print '| Assigned %s ids from %s' % (count, filename)
def read_all_gaussian(self, files):
# noinspection PyUnresolvedReferences
from java.io import FileReader
mapped_results = {}
for cur_file in files:
mapped_results[cur_file] = self.loader.load(
cur_file, FileReader(cur_file))
return mapped_results
def assign_ids_from_list(tax, filename):
count = 0
if True:
infile = FileReader(filename)
r = CSVReader(infile)
while True:
row = r.readNext()
if row == None: break
[qid, ids] = row
taxon = tax.lookupQid(QualifiedId(qid))
if taxon != None:
for id in ids.split(';'):
z = tax.lookupId(id)
if z == None:
taxon.taxonomy.addId(taxon, id)
count += 1
infile.close()
print '| Assigned %s ids from %s' % (count, filename)
def registerScript(self, file_name, alias_overrides):
"""
Parses and registers the pig script.
file_name: The Pig script file.
alias_overrides: The list of aliases to override in the Pig script.
"""
grunt = GruntParser(FileReader(File(file_name)), alias_overrides)
grunt.setInteractive(False)
grunt.setParams(self)
grunt.parseStopOnError(True)
def cluster(algorithm, filename, options=''):
reader = BufferedReader(FileReader(filename))
data = Instances(reader)
reader.close()
cl = algorithm()
cl.setOptions(options.split())
cl.buildClusterer(data)
returnData = []
for instance in data.enumerateInstances():
returnData.append(cl.clusterInstance(instance))
print returnData
def _parse_and_rewrite_svg_file(svg_input_path, svg_output_path):
write_str = ""
file_reader = FileReader(svg_input_path)
buffered_reader = BufferedReader(file_reader)
read_line = ""
check = False
while True:
read_line = buffered_reader.readLine()
if read_line is None:
break
if "viewBox" in read_line:
view_box_content = _get_viewbox_content(read_line)
view_box_values = _get_viewbox_values(view_box_content)
if view_box_values[0] != 0:
view_box_values[2] = abs(view_box_values[2]) + abs(view_box_values[0])
view_box_values[0] = 0
if view_box_values[1] != 0:
view_box_values[3] = abs(view_box_values[3]) + abs(view_box_values[1])
view_box_values[1] = 0
read_line = re.sub(r"viewBox=\"[\-|0-9| ]+\"", "", read_line, 1)
read_line = re.sub(r"width=\"[0-9]+\"", "width=\""+ str(view_box_values[2]) + "\"",
read_line, 1)
read_line = re.sub(r"height=\"[0-9]+\"", "height=\""+ str(view_box_values[3]) + "\"",
read_line, 1)
check = True
if "g id=\"ID" in read_line and not check:
if "transform=" in read_line:
_log.info(read_line)
read_line = read_line[0:read_line.find("transform")] + ">"
check = True
write_str += read_line + "\n"
buffered_reader.close()
file_reader.close()
file_writer = PrintWriter(svg_output_path)
file_writer.print(write_str)
file_writer.close()
def getPrivateKey(self, file) :
reader = PemReader(FileReader(File(file)))
pemObject = reader.readPemObject()
content = pemObject.getContent()
try:
kf = KeyFactory.getInstance("RSA");
keySpec = PKCS8EncodedKeySpec(content);
privateKey = kf.generatePrivate(keySpec);
return privateKey
except:
print "Client registration. Failed to getPrivateKey: %s" %(sys.exc_info()[1])
return False
def _parse_and_rewrite_svg_file(svg_input_path, svg_output_path):
write_str = ""
file_reader = FileReader(svg_input_path)
buffered_reader = BufferedReader(file_reader)
read_line = ""
while True:
read_line = buffered_reader.readLine()
if read_line is None:
break
if "viewBox" in read_line:
view_box_content = _get_viewbox_content(read_line)
view_box_values = _get_viewbox_values(view_box_content)
if view_box_values[0] != 0:
view_box_values[2] += view_box_values[0]
view_box_values[0] = 0
if view_box_values[1] != 0:
view_box_values[3] += view_box_values[1]
view_box_values[1] = 0
new_view_box = str(view_box_values[0]) + " " + str(view_box_values[1]) + " " + \
str(view_box_values[2]) + " " + str(view_box_values[3])
read_line = re.sub(r"viewBox=\"[\-|0-9| ]+\"", "viewBox=\""
+ new_view_box + "\"", read_line, 1)
read_line = re.sub(r"width=\"[0-9]+\"", "width=\""+ str(view_box_values[2]) + "\"",
read_line, 1)
read_line = re.sub(r"height=\"[0-9]+\"", "height=\""+ str(view_box_values[3]) + "\"",
read_line, 1)
write_str += read_line + "\n"
buffered_reader.close()
file_reader.close()
file_writer = PrintWriter(svg_output_path)
file_writer.print(write_str)
file_writer.close()
def LineGroupInstanceList(pipe, fileName, seperator="^\\s*$"):
"""
Takes a pipe and a file name and produces an instance list based on that pipe
and a LineGroupIterator. The optional argument seperator specifies what
seperates instances from eachother. For example, when doing part of speech
tagging an instance is a sentence. Each word in the sentence would have a
seperate line and a line matching the regular expression specified by seperator
would terminate the current sentence.
"""
data = InstanceList(pipe)
data.add(
LineGroupIterator(FileReader(File(fileName)),
Pattern.compile(seperator), 1))
return data
def _read_value_from_file(file_path, model_context):
"""
Read a single text value from the first line in the specified file.
:param file_path: the file from which to read the value
:return: the text value
:raises BundleAwareException if an error occurs while reading the value
"""
method_name = '_read_value_from_file'
try:
file_reader = BufferedReader(FileReader(file_path))
line = file_reader.readLine()
file_reader.close()
except IOException, e:
_report_token_issue('WLSDPLY-01733', method_name, model_context,
file_path, e.getLocalizedMessage())
line = ''
def run():
print
base = raw_input('Base file, eg. config/templates/wl_as_template.properties? ')
env = raw_input('Environment, eg. local? ')
print
new_cfg = 'config/' + env + '/new_config.properties'
input = BufferedReader(FileReader(base))
output = BufferedWriter(FileWriter(new_cfg))
output.write('base=' + base + '\n\n')
line = input.readLine()
while line is not None:
if re.match('.*\?', line):
output.write(line)
output.newLine()
line = input.readLine()
input.close()
output.close()
log.info('new configuration file written to: ' + new_cfg)
def __init__(self, pattern, s3BucketName, debug=False, table=None):
"""
:param debug: When debug = true, AWS credentials will be retrieved from
the user's $AWS_CONFIG_FILE or $HOME/.aws/config file, if
$AWS_CONFIG_FILE is not defined.
:param table: Usually for testing, this will perform operations only on
the specified table.
:return: void
"""
if debug:
from org.ini4j import Ini
from os import environ
from java.io import FileReader
profile = 'profile dev'
if environ.has_key('AWS_CONFIG_FILE'):
configfile = environ['AWS_CONFIG_FILE']
else:
configfile = '%s/.aws/config' % environ['HOME']
ini = Ini(FileReader(configfile))
access_key = ini.get(profile).fetch('aws_access_key_id')
secret_key = ini.get(profile).fetch('aws_secret_access_key')
session_token = ini.get(profile).fetch('aws_session_token')
creds = BasicSessionCredentials(access_key, secret_key,
session_token)
self.creds = creds
self.dynamoDb = AmazonDynamoDBClient(self.creds)
else:
self.creds = None
self.dynamoDb = AmazonDynamoDBClient()
# S3 path is created from today's date
now = datetime.now()
self.date = now.date().isoformat()
self.s3path = "Backups/%s" % self.date
self.s3BucketName = s3BucketName
self.tables = []
self.tableData = {}
self.__getTableList__(pattern, table)
self.throughput = 15.0
def buildImagesCSVTable(fileName, logger):
# Initialize the table
csvTable = LinkedHashMap()
# Header
isHeader = True
# Read the CSV file
br = BufferedReader(FileReader(fileName))
# Read the first line from the text file
line = br.readLine()
# loop until all lines are read
while line is not None:
if isHeader:
# We are past the header
isHeader = False
# Read next line
line = br.readLine()
continue
# Get all values for current row
row = line.split(";")
# Remove '"' and '\' characters if needed
for i in range(len(row)):
row[i] = row[i].replace("\"", "")
row[i] = row[i].replace("\\\\", "\\")
row[i] = row[i].replace("\\", "/")
# Add the row with the file name as key
csvTable.put(row[6], row)
# Read next line
line = br.readLine()
return csvTable
def searchFile(event):
myFileChooser = JFileChooser()
rVal = int(myFileChooser.showOpenDialog(None))
print rVal
if (rVal == JFileChooser.APPROVE_OPTION):
plainTextFile.text = myFileChooser.getSelectedFile().getName()
plainTextPath.text = myFileChooser.getCurrentDirectory().toString()
try:
myPath = plainTextPath.text + "/" + plainTextFile.text
fileReader = FileReader(myPath)
bufferedReader = BufferedReader(fileReader)
inputFile = ""
textFieldReadable = bufferedReader.readLine()
while (textFieldReadable != None):
inputFile += textFieldReadable
inputFile += "\n"
textFieldReadable = bufferedReader.readLine()
pesanAsli.text = inputFile
except (RuntimeError, TypeError, NameError):
print "eror gan"
def returnObject(self,
objectStructure,
objectType,
objectParams=False,
noSkip=True):
reader = FileReader(self.filePath)
jsonParser = JSONParser()
jsonObject = jsonParser.parse(reader)
try:
structure = jsonObject.get(objectStructure)
if not structure:
raise Exception
except:
self.CMUConfigParserLogger.infoMessage(
'returnObject',
"Unable to find structure: %s in JSON file." % objectStructure)
System.exit(1)
try:
returnObject = structure.get(objectType)
except:
self.CMUConfigParserLogger.infoMessage(
'returnObject', "Unable to find value %s in structure %s" %
(objectStructure, objectType))
else:
if objectParams:
try:
returnObjectParam = returnObject.get(objectParams)
except:
self.CMUConfigParserLogger.infoMessage(
'returnObject',
"Unable to find param %s in value %s in structure %s" %
(objectParams, objectStructure, objectType), noSkip)
else:
return returnObjectParam
else:
return returnObject
def readLocations(self):
self.locations = {}
self.order = []
if Environment.getExternalStorageState() != Environment.MEDIA_MOUNTED:
return
storageDir = Environment.getExternalStoragePublicDirectory(
Environment.DIRECTORY_DOWNLOADS)
subdir = File(storageDir, "WeatherForecast")
if subdir.exists():
f = File(subdir, "locations.txt")
try:
stream = BufferedReader(FileReader(f))
while True:
line = stream.readLine()
if line == None:
break
spec = line.trim()
pieces = spec.split("/")
if len(pieces) < 3:
continue
place = pieces[len(pieces) - 1]
self.locations[place] = spec
self.order.add(place)
stream.close()
except FileNotFoundException:
pass
def _get_openssl_key_manager(cert_file, key_file=None):
paths = [key_file] if key_file else []
paths.append(cert_file)
private_key = None
certs = []
for path in paths:
with closing(FileReader(path)) as reader:
br = BufferedReader(reader)
while True:
obj = PEMReader(br).readObject()
if obj is None:
break
if isinstance(obj, KeyPair):
private_key = obj.getPrivate()
elif isinstance(obj, X509Certificate):
certs.append(obj)
key_store = KeyStore.getInstance(KeyStore.getDefaultType())
key_store.load(None, None)
key_store.setKeyEntry(str(uuid.uuid4()), private_key, [], certs)
kmf = KeyManagerFactory.getInstance(KeyManagerFactory.getDefaultAlgorithm())
kmf.init(key_store, [])
return kmf
def fileBrowser():
myFileChooser = JFileChooser()
rVal = int(myFileChooser.showOpenDialog(None))
print rVal
if (rVal == JFileChooser.APPROVE_OPTION):
theName = myFileChooser.getSelectedFile().getName()
thePath = myFileChooser.getCurrentDirectory().toString()
try:
myPath = theName + "/" + thePath
fileReader = FileReader(myPath)
bufferedReader = BufferedReader(fileReader)
inputFile = ""
textFieldReadable = bufferedReader.readLine()
while (textFieldReadable != None):
inputFile += textFieldReadable
inputFile += "\n"
# textFieldReadable = bufferedReader.readLine()
#pesanAsli.text = inputFile
return inputFile
except (RuntimeError, TypeError, NameError):
print "eror gan"
def readModules():
mapCategoryToAppComponent = HashMap()
try:
builder = SAXBuilder(0)
separator = CollectorsParameters.FILE_SEPARATOR
fileLocation = CollectorsParameters.BASE_PROBE_MGR_DIR + separator + 'discoveryResources' + separator + 'sap-application-components.xml'
doc = builder.build(FileReader(File(fileLocation)))
root = doc.getRootElement()
categories = root.getChildren('category')
if categories != None:
itCat = categories.iterator()
while itCat.hasNext():
categoryElem = itCat.next()
category = categoryElem.getAttributeValue('name')
applicationComponents = categoryElem.getChildren(
'application-component')
itComp = applicationComponents.iterator()
while itComp.hasNext():
component = itComp.next().getAttributeValue('name')
mapCategoryToAppComponent.put(component, category)
except:
logger.errorException('Failed to read modules')
return mapCategoryToAppComponent
def call(self):
#CountdownLatch
latch = CountDownLatch(1)
#Read History.txt into TextArea
br = BufferedReader(FileReader(self.hist_file))
#Runnable Inner Class
class HistoryTaskRunnable (Runnable):
def __init__(self, textArea, br):
self.textArea = textArea
self.br = br
self.sbf = StringBuffer()
#@Override
def run(self):
while True:
line = self.br.readLine()
if line != None:
self.sbf.append(line + "\n")
# self.textArea.appendText(line + "\n") - Very slow
else:
break
#Add Text to TextArea
self.textArea.setText(self.sbf.toString())
self.textArea.appendText("") #Used to trigger event handler
#Close Buffered Reader
br.close()
#Run Later
Platform.runLater(HistoryTaskRunnable(self.textArea, br))
#Set Starting positions
textArea.setScrollLeft(Double.MAX_VALUE)
textArea.setScrollTop(Double.MAX_VALUE)
#Make the Application Thread wait
latch.await()
def fileBrowser(event):
myFileChooserX = JFileChooser()
rValX = int(myFileChooserX.showOpenDialog(None))
print "rVal =", rValX
if (rValX == JFileChooser.APPROVE_OPTION):
namaFile.text = myFileChooserX.getSelectedFile().getName()
alamatFile.text = myFileChooserX.getCurrentDirectory().toString()
try:
myPath = alamatFile.text + "/" + namaFile.text
fileReader = FileReader(myPath)
print "mypath =", myPath
bufferedReader = BufferedReader(fileReader)
inputFile = ""
textFieldReadable = bufferedReader.readLine()
while (textFieldReadable != None):
inputFile += textFieldReadable
inputFile += "\n"
textFieldReadable = bufferedReader.readLine()
print textFieldReadable
# textFieldReadable = bufferedReader.readLine()
plainText.text = inputFile
return inputFile
except (): #RuntimeError, TypeError, NameError):
print "gagal mengembalikan pesan"
def __init__(self, fn): '''Initialize the Lexer @fn: file name''' lexer.Lexer.__init__(self, PushbackReader(BufferedReader(FileReader(fn)), 1024)) self.m_file_name = fn
## Creating percentiles
percentiles=[]
for i in range(0,100,step_size):
index = int (n*i/100)
percentiles.append(thread_array[index]) # 0-99 percentile
percentiles.append(thread_array[n-1]) # 100th percentile
f = open(''.join([directory , 'percentiles.txt']), 'w')
f.write(str(percentiles))
f.close()
#print str(percentiles)
## Data Distribution testing/Training
data = FileReader(data_file)
data = Instances(data)
data = Instances(data , 0 , n - (n % folds) )
n = n- (n % folds)
print data.numInstances()
len_fold = int(math.floor(n/folds))
folds_test = []
folds_train = []
for i in range(0,n+1,len_fold)[:-1]:
folds_test.append(Instances(data,i,len_fold))
f = open(''.join([directory , ''.join(['fold_test_' , str(i/len_fold) , '.arff'])]) , "w")
f.write(str(folds_test[-1]));
f.close()
temp = Instances(data, 0 , n)
for j in range(i,i+len_fold,1):
temp.delete(i)
def retain_ids_from_list(tax, filename):
count = 0
change_count = 0
infile = FileReader(filename)
r = CSVReader(infile)
while True:
row = r.readNext()
if row == None: break
[qid_string, ids] = row
tracep = (qid_string == 'ncbi:33543' or qid_string == 'gbif:2433391'
or qid_string == 'gbif:2467506'
or qid_string == 'ncbi:28376')
if tracep:
print '# Tracing %s %s' % (qid_string, ids)
qid = QualifiedId(qid_string)
taxon = tax.lookupQid(qid)
if taxon != None:
id_list = ids.split(';')
qid_id = id_list[0]
if tracep == False:
tracep = (qid_id == '565578' or qid_id == '5541322')
if tracep:
print '# qid %s, id_list %s' % (qid, id_list)
# Look for collision
tenant = tax.lookupId(qid_id)
if tenant != None:
# qid_id is unavailable
# Happens 7700 or so times; most cases ought to be homonymized,
# but not all
if tracep:
print '# %s (for %s) is in use by %s' % (qid_id, taxon,
tenant)
False
# Qid from list is one of the taxon's qids.
# Use the proposed id if the qid's node has no id
elif taxon.id == None:
# Happens 87854 for OTT 3.0
if tracep: print '# Setting %s as id of %s' % (qid_id, taxon)
taxon.setId(qid_id)
# Deal with aliases
for id in id_list[1:]:
if tax.lookupId(id) == None:
if tracep:
print '# adding %s as id for %s' % (id, taxon)
tax.addId(taxon, id)
else:
if tracep:
print '# alias %s (for %s) is in use by %s' % (
id, taxon, tax.lookupId(id))
count += 1
# If it has an id, but qid is not the primary qid, skip it
elif taxon.sourceIds != None and taxon.sourceIds[0] != qid:
if tracep: print '# %s is minor for %s' % (qid_id, taxon)
False
# Use the id in the id_list if it's smaller than the one in taxon
elif int(qid_id) < int(taxon.id):
if tracep:
print '# %s is replacing %s as the id of %s' % (
qid_id, taxon.id, taxon)
taxon.setId(qid_id)
for id in id_list[1:]:
if tax.lookupId(id) == None:
tax.addId(taxon, id)
change_count += 1
else:
if tracep: print '# %s has id %s < %s' % (qid, qid_id, taxon)
else:
if tracep: print '# no taxon with qid %s; ids %s' % (qid, ids)
infile.close()
print '| Assigned %s ids, changed %s ids from %s' % (count, change_count,
filename)
---------------------------------------------------------------------------------------------
"""
import java.io.FileReader;
import java.util.Iterator;
import org.json.simple.JSONArray;
import org.json.simple.JSONObject;
import org.json.simple.parser.JSONParser;
public class emp{
public static void main(String[] args) {
JSONParser parser = new JSONParser();
try {
Object obj = parser.parse(new FileReader("/home/unix/emp.txt"));
JSONObject jsonObject = (JSONObject) obj;
JSONArray emplist = (JSONArray) jsonObject.get("Employee List");
System.out.println("\nEmployee List:");
Iterator<String> iterator= emplist.iterator();
while (iterator.hasNext()) {
System.out.println(iterator.next());
} }catch (Exception e) {
e.printStackTrace();
}
}
}
"""
first parameter must be the ARFF file one wants to process with J48
Note: needs Weka 3.7.x to run (due to changes in the
weka.classifiers.Evaluation class)
"""
# check commandline parameters
if (not (len(sys.argv) == 2)):
print "Usage: UsingJ48Ext.py <ARFF-file>"
sys.exit()
# load data file
print "Loading data..."
file = FileReader(sys.argv[1])
data = Instances(file)
# set the class Index - the index of the dependent variable
data.setClassIndex(data.numAttributes() - 1)
# create the model
evaluation = Evaluation(data)
output = PlainText() # plain text output for predictions
output.setHeader(data)
buffer = StringBuffer() # buffer to use
output.setBuffer(buffer)
attRange = Range() # no additional attributes output
outputDistribution = Boolean(False) # we don't want distribution
j48 = J48()
j48.buildClassifier(data) # only a trained classifier can be evaluated
eqPos = line.find('=')
if line[:eqPos] == 'url': url = line[eqPos+1:].strip()
if line[:eqPos] == 'user': user = line[eqPos+1:].strip()
if line[:eqPos] == 'passwd': passwd = line[eqPos+1:].strip()
if line[:eqPos] == 'fromQuery': fromQuery = line[eqPos+1:].strip()
if line[:eqPos] == 'toQuery': toQuery = re.sub(r'\/\w+?\/', r'%s', line[eqPos+1:]).strip()
file.close()
else:
inform('configuration file (config.ini) is missing')
sys.exit()
inform('getting database connection')
dbHandler = MySQLAccess(url, user, passwd, toQuery)
db = dbHandler.connect()
arffFile = FileReader(TrainData)
data = Instances(arffFile)
data.setClassIndex(data.numAttributes() - 1)
arffFile.close()
arffFileNum = FileReader(TrainDataNum)
dataNum = Instances(arffFileNum)
dataNum.setClassIndex(dataNum.numAttributes() - 1)
arffFileNum.close()
if not Path.isfile(model):
inform('training J48')
j48 = J48()
j48.setOptions('-R -N 3 -Q 1 -M 2'.split()) # reduced error pruning, use j48.setOptions('-C 0.1 -M 2'.split()) for confidence interval pruning
j48.buildClassifier(data)
serialize.write(model, j48)
