def calculating_features(self, lineofFile, element, qtyofResults, preparedParameter, qtyFeatures , minValueCalculated, maxValueCalculated , dados_saida ):
self.printProgressofEvents(element, qtyofResults, "Calculating features for nodes not liked: ")
item = VariableSelection.getItemFromLine(lineofFile)
resultLinestring = ""
min = minValueCalculated
max = maxValueCalculated
for neighbor_node in item[1]:
self.qtyDataCalculated = self.qtyDataCalculated + 1
item_result = []
#executing the calculation for each features chosen at parameter
for index_features in range(qtyFeatures):
preparedParameter.featuresChoice[index_features][0].parameter = preparedParameter
valueCalculated = preparedParameter.featuresChoice[index_features][0].execute(item[0],neighbor_node) * preparedParameter.featuresChoice[index_features][1]
if valueCalculated < min[index_features]:
min[index_features] = valueCalculated
if valueCalculated > max[index_features]:
max[index_features] = valueCalculated
item_result.append(valueCalculated)
#generating a vetor with the name of the feature and the result of the calculate
for indice in range(qtyFeatures):
resultLinestring = resultLinestring + str({str(preparedParameter.featuresChoice[indice]):item_result[indice]}) + '\t'
resultLinestring = resultLinestring + str(item[0]) + '\t' + str(neighbor_node) + '\n'
finalresult = repr(min) + '|' + repr(max) + '|' + str(self.qtyDataCalculated) + '|' + resultLinestring
dados_saida.put(finalresult)
def step03(paramFile, num_people):
#util = ParameterUtil(parameter_file = 'data/formatado/arxiv/nowell_example_1994_1999.txt')
util = ParameterUtil(parameter_file=paramFile)
myparams = Parameterization(util.keyword_decay, util.lengthVertex, util.t0,
util.t0_, util.t1, util.t1_,
util.FeaturesChoiced, util.graph_file,
util.trainnig_graph_file, util.test_graph_file,
util.decay)
myparams.generating_Training_Graph()
selection = VariableSelection(myparams.trainnigGraph,
util.nodes_notlinked_file, util.min_edges,
False, num_people)
return
def __init__(self, preparedParameter, fileAllNodes):
print "Starting Generating Weights for all Nodes", datetime.today()
self.preparedParameter = preparedParameter
self.filepathAllNodes = Formating.get_abs_file_path(fileAllNodes)
self.preparedParameter.open_connection()
self.preparedParameter.clean_database()
fcontentAllNodes = open(self.filepathAllNodes, 'r')
self.minValueCalculated = list(
99999 for x in self.preparedParameter.WeightsChoiced)
self.maxValueCalculated = list(
0 for x in self.preparedParameter.WeightsChoiced)
qtyFeatures = len(self.preparedParameter.WeightsChoiced)
qtyNodesCalculated = 0
for lineofFile in fcontentAllNodes:
item = VariableSelection.getItemFromLine(lineofFile)
item_result = []
#executing the calculation for each features chosen at parameter
for index_features in range(qtyFeatures):
self.preparedParameter.WeightsChoiced[index_features][
0].parameter = preparedParameter
valueCalculated = self.preparedParameter.WeightsChoiced[
index_features][0].execute(
item[0],
item[1]) * self.preparedParameter.WeightsChoiced[
index_features][1]
if valueCalculated < self.minValueCalculated[index_features]:
self.minValueCalculated[index_features] = valueCalculated
if valueCalculated > self.maxValueCalculated[index_features]:
self.maxValueCalculated[index_features] = valueCalculated
item_result.append(valueCalculated)
self.preparedParameter.add_weight(item[0], item[1], item_result)
self.preparedParameter.add_weight(-1, -1, qtyNodesCalculated)
self.preparedParameter.add_weight(-2, -2,
repr(self.minValueCalculated))
self.preparedParameter.add_weight(-3, -3,
repr(self.maxValueCalculated))
self.preparedParameter.close_connection()
print "Finishinig Generating Weights for all Nodes", datetime.today()
def __init__(self, preparedParameter, fileAllNodes):
print "Starting Generating Weights for all Nodes", datetime.today()
self.preparedParameter = preparedParameter
self.filepathAllNodes = Formating.get_abs_file_path(fileAllNodes)
self.preparedParameter.open_connection()
self.preparedParameter.clean_database()
fcontentAllNodes = open(self.filepathAllNodes, 'r')
self.minValueCalculated = list(99999 for x in self.preparedParameter.WeightsChoiced)
self.maxValueCalculated = list(0 for x in self.preparedParameter.WeightsChoiced)
qtyFeatures = len(self.preparedParameter.WeightsChoiced)
qtyNodesCalculated = 0
for lineofFile in fcontentAllNodes:
item = VariableSelection.getItemFromLine(lineofFile)
item_result = []
#executing the calculation for each features chosen at parameter
for index_features in range(qtyFeatures):
self.preparedParameter.WeightsChoiced[index_features][0].parameter = preparedParameter
valueCalculated = self.preparedParameter.WeightsChoiced[index_features][0].execute(item[0],item[1]) * self.preparedParameter.WeightsChoiced[index_features][1]
if valueCalculated < self.minValueCalculated[index_features]:
self.minValueCalculated[index_features] = valueCalculated
if valueCalculated > self.maxValueCalculated[index_features]:
self.maxValueCalculated[index_features] = valueCalculated
item_result.append(valueCalculated)
self.preparedParameter.add_weight(item[0], item[1], item_result)
self.preparedParameter.add_weight(-1,-1, qtyNodesCalculated)
self.preparedParameter.add_weight(-2,-2, repr(self.minValueCalculated))
self.preparedParameter.add_weight(-3,-3, repr(self.maxValueCalculated))
self.preparedParameter.close_connection()
print "Finishinig Generating Weights for all Nodes", datetime.today()
def calculating_features(self, lineofFile, element, qtyofResults,
preparedParameter, qtyFeatures,
minValueCalculated, maxValueCalculated,
dados_saida):
self.printProgressofEvents(
element, qtyofResults,
"Calculating features for nodes not liked: ")
item = VariableSelection.getItemFromLine(lineofFile)
resultLinestring = ""
min = minValueCalculated
max = maxValueCalculated
for neighbor_node in item[1]:
self.qtyDataCalculated = self.qtyDataCalculated + 1
item_result = []
#executing the calculation for each features chosen at parameter
for index_features in range(qtyFeatures):
preparedParameter.featuresChoice[index_features][
0].parameter = preparedParameter
valueCalculated = preparedParameter.featuresChoice[
index_features][0].execute(
item[0], neighbor_node
) * preparedParameter.featuresChoice[index_features][1]
if valueCalculated < min[index_features]:
min[index_features] = valueCalculated
if valueCalculated > max[index_features]:
max[index_features] = valueCalculated
item_result.append(valueCalculated)
#generating a vetor with the name of the feature and the result of the calculate
for indice in range(qtyFeatures):
resultLinestring = resultLinestring + str({
str(preparedParameter.featuresChoice[indice]):
item_result[indice]
}) + '\t'
resultLinestring = resultLinestring + str(
item[0]) + '\t' + str(neighbor_node) + '\n'
finalresult = repr(min) + '|' + repr(max) + '|' + str(
self.qtyDataCalculated) + '|' + resultLinestring
dados_saida.put(finalresult)
def __init__(self, preparedParameter, filepathNodesNotLinked, filepathResult, filePathOrdered, filepathMaxMinCalculated):
print "Starting Calculating Nodes not linked", datetime.today()
self.preparedParameter = preparedParameter
self.filePathOrdered = Formating.get_abs_file_path(filePathOrdered)
self.filepathMaxMinCalculated = Formating.get_abs_file_path(filepathMaxMinCalculated)
self.filepathResult = Formating.get_abs_file_path(filepathResult)
self.filepathNodesNotLinked = Formating.get_abs_file_path(filepathNodesNotLinked)
#for each links that is not linked all the calculates is done.
element = 0
qtyofResults = FormatingDataSets.getTotalLineNumbers(self.filepathNodesNotLinked)
fcontentNodesNotLinked = open(self.filepathNodesNotLinked, 'r')
if os.path.exists(self.filepathResult):
print "Calculate already done for this file, please delete if you want a new one.", datetime.today()
self.reading_Max_min_file()
return
fcontentCalcResult = open(self.filepathResult, 'w')
self.minValueCalculated = list(99999 for x in self.preparedParameter.featuresChoice)
self.maxValueCalculated = list(0 for x in self.preparedParameter.featuresChoice)
qtyFeatures = len(self.preparedParameter.featuresChoice)
qtyNodesCalculated = 0
partialResults = []
for lineofFile in fcontentNodesNotLinked:
element = element+1
item = VariableSelection.getItemFromLine(lineofFile)
qtyothernodenotlinked = len(item[1])
newelement = 0
for neighbor_node in item[1]:
newelement = newelement +1
qtyNodesCalculated = qtyNodesCalculated + 1
self.printProgressofEvents(element, qtyofResults, "Calculating features for nodes not liked: ")
self.printProgressofEventsWihoutPercent(newelement, qtyothernodenotlinked, "Calculating nodes: " + str(item[0]) + ":" + str(neighbor_node) )
item_result = []
#executing the calculation for each features chosen at parameter
for index_features in range(qtyFeatures):
self.preparedParameter.featuresChoice[index_features][0].parameter = preparedParameter
valueCalculated = self.preparedParameter.featuresChoice[index_features][0].execute(item[0],neighbor_node) * self.preparedParameter.featuresChoice[index_features][1]
if valueCalculated < self.minValueCalculated[index_features]:
self.minValueCalculated[index_features] = valueCalculated
if valueCalculated > self.maxValueCalculated[index_features]:
self.maxValueCalculated[index_features] = valueCalculated
item_result.append(valueCalculated)
lineContent = []
#generating a vetor with the name of the feature and the result of the calculate
for indice in range(qtyFeatures):
lineContent.append(str({str(self.preparedParameter.featuresChoice[indice]):item_result[indice]}) )
partialResults.append([lineContent, item[0], neighbor_node])
if element % 10 == 0:
for item in partialResults:
for calc in item[0]:
fcontentCalcResult.write(calc + '\t')
fcontentCalcResult.write(str(item[1]) + '\t' + str(item[2]) + '\n' )
partialResults = []
for item in partialResults:
for calc in item[0]:
fcontentCalcResult.write(calc + '\t')
fcontentCalcResult.write(str(item[1]) + '\t' + str(item[2]) + '\n' )
fcontentCalcResult.flush()
fcontentCalcResult.close()
fcontentNodesNotLinked.close()
fcontentMaxMin = open(self.filepathMaxMinCalculated, 'w')
fcontentMaxMin.write(str(qtyNodesCalculated) + '\t' + repr(self.minValueCalculated) + '\t' + repr(self.maxValueCalculated) )
fcontentMaxMin.close()
print "Calculating Nodes not linked finished", datetime.today()
from calculating.CalculateInMemory import CalculateInMemory
if __name__ == '__main__':
#plt.show()
#util = ParameterUtil(parameter_file = 'data/formatado/arxiv/nowell_astroph_1994_1999/AllExecutionScores/config.txt')
util = ParameterUtil(parameter_file = 'data/formatado/arxiv/exemplomenor/config/config.txt')
myparams = Parameterization(t0 = util.t0, t0_ = util.t0_, t1 = util.t1, t1_ = util.t1_, linear_combination=util.linear_combination,
filePathGraph = util.graph_file, filePathTrainingGraph = util.trainnig_graph_file, filePathTestGraph = util.test_graph_file, decay = util.decay, domain_decay = util.domain_decay, min_edges = util.min_edges, scoreChoiced = util.ScoresChoiced, weightsChoiced = util.WeightsChoiced, weightedScoresChoiced = util.WeightedScoresChoiced, FullGraph = None, result_random_file=util.result_random_file)
myparams.generating_Training_Graph()
#myparams.generating_Test_Graph()
selection = VariableSelection(myparams.trainnigGraph, util.min_edges)
nodesNotLinked = selection.get_pair_nodes_not_linked()
selection.saveResults(util.nodes_notlinked_file, nodesNotLinked)
#dado = selection.readingResultsFile(util.nodes_notlinked_file)
#print dado[1]
#calc = CalculateInMemory(myparams, nodesNotLinked)
#resultsCalculate = calc.executingCalculate()
#resultados = []
#orderDataMetrica0 = sorted(resultsCalculate, key=lambda value: value[0][0], reverse=True)
#orderDataMetrica1 = sorted(resultsCalculate, key=lambda value: value[0][5], reverse=True)
#for result in orderDataMetrica1:
# metricas = result[0]
# no1 = result[1]
t1=util.t1,
t1_=util.t1_,
filePathGraph=util.graph_file,
filePathTrainingGraph=util.trainnig_graph_file,
filePathTestGraph=util.test_graph_file,
decay=util.decay,
domain_decay=util.domain_decay,
min_edges=util.min_edges,
scoreChoiced=util.ScoresChoiced,
weightsChoiced=util.WeightsChoiced,
weightedScoresChoiced=util.WeightedScoresChoiced,
FullGraph=None)
myparams.generating_Training_Graph()
myparams.generating_Test_Graph()
selection = VariableSelection(myparams.trainnigGraph,
util.nodes_notlinked_file, util.min_edges)
calc = Calculate(myparams, util.nodes_notlinked_file, util.calculated_file,
util.ordered_file, util.maxmincalculated_file)
calc.Separating_calculateFile()
analise = Analyse(
myparams, FormatingDataSets.get_abs_file_path(util.calculated_file),
FormatingDataSets.get_abs_file_path(util.analysed_file) +
'.random.analised.txt', calc.qtyDataCalculated)
topRank = Analyse.getTopRank(util.analysed_file + '.random.analised.txt')
calc.Ordering_separating_File(topRank)
for OrderingFilePath in calc.getfilePathOrdered_separeted():
analise = Analyse(myparams, OrderingFilePath,
OrderingFilePath + '.analised.txt', topRank)
print "Trainning Period:", myparams.t0, " - ", myparams.t0_
print "Test Period:", myparams.t1, " - ", myparams.t1_
t1=util.t1,
t1_=util.t1_,
linear_combination=util.linear_combination,
filePathGraph=util.graph_file,
filePathTrainingGraph=util.trainnig_graph_file,
filePathTestGraph=util.test_graph_file,
decay=util.decay,
domain_decay=util.domain_decay,
min_edges=util.min_edges,
scoreChoiced=util.ScoresChoiced,
weightsChoiced=util.WeightsChoiced,
weightedScoresChoiced=util.WeightedScoresChoiced,
FullGraph=None,
result_random_file=util.result_random_file)
myparams.generating_Training_Graph()
selection = VariableSelection(myparams.trainnigGraph, util.min_edges)
nodesNotLinked = selection.readingResultsFile(util.nodes_notlinked_file)
calc = CalculateInMemory(myparams, nodesNotLinked)
resultsofCalculation = calc.executingCalculate()
#print resultsofCalculation
calc.saving_calculateResult(util.calculated_file, resultsofCalculation)
calc.saving_calculateResult_normalized(
util.calculated_file + '_normalizated.csv', resultsofCalculation)
result2 = calc.reading_calculateResult_normalized(util.calculated_file)
calc.save_Max_min_file(util.maxmincalculated_file, calc.qtyDataCalculated,
calc.minValueCalculated, calc.maxValueCalculated)
print resultsofCalculation
print result2
for linha in calculatedFile:
x.append(Calculate.reading_calculateLine(linha))
calculatedFile.close()
myparams = Parameterization(util.keyword_decay, util.lengthVertex, util.t0, util.t0_, util.t1, util.t1_, util.FeaturesChoiced, util.graph_file, util.trainnig_graph_file, util.test_graph_file, util.decay)
myparams.generating_Training_Graph()
Nodes_notLinked = VariableSelection(myparams.trainnigGraph, util.nodes_notlinked_file,util.min_edges)
nodes_notlinkedFile = open(FormatingDataSets.get_abs_file_path(util.nodes_notlinked_file), 'r')
qtyLine = 0
qtyCalculated = 0
f = open(FormatingDataSets.get_abs_file_path(util.calculated_file )+ '.weight.txt', 'w')
minValueCalculated = list(99999 for x in myparams.featuresChoice)
maxValueCalculated = list(0 for x in myparams.featuresChoice)
qtyFeatures = len(myparams.featuresChoice)
for line in nodes_notlinkedFile:
qtyLine = qtyLine + 1
item = VariableSelection.getItemFromLine(line)
qtyofnodesnotLinked = len(item[1])
print 'Qtde of not linked itens', qtyofnodesnotLinked, ' in line ', qtyLine
for neighbor_node in item[1]:
qtyCalculated = qtyCalculated + 1
node1 = item[0]
node2 = neighbor_node
cn = util.FeaturesChoiced[0][0].get_common_neighbors(node1,node2)
total = 0
for c in cn:
total = total + ( Calculate.reading_calculateLine(getPairNodes(node1, c, calculatedFile))[0][0] + Calculate.reading_calculateLine(getPairNodes(node2, c, calculatedFile))[0][0])
for index_features in range(qtyFeatures):
if total < minValueCalculated[index_features]:
minValueCalculated[index_features] = total
from parametering.ParameterUtil import ParameterUtil
from parametering.Parameterization import Parameterization
from calculating.CalculateInMemory import CalculateInMemory
from calculating.VariableSelection import VariableSelection
if __name__ == '__main__':
util = ParameterUtil(parameter_file = 'data/formatado/arxiv/exemplomenor/config/config.txt')
#util = ParameterUtil(parameter_file = 'data/formatado/arxiv/nowell_astroph_1994_1999/config/configuration_forAG.txt')
myparams = Parameterization(t0 = util.t0, t0_ = util.t0_, t1 = util.t1, t1_ = util.t1_, linear_combination=util.linear_combination,
filePathGraph = util.graph_file, filePathTrainingGraph = util.trainnig_graph_file, filePathTestGraph = util.test_graph_file, decay = util.decay, domain_decay = util.domain_decay, min_edges = util.min_edges, scoreChoiced = util.ScoresChoiced, weightsChoiced = util.WeightsChoiced, weightedScoresChoiced = util.WeightedScoresChoiced, FullGraph = None, result_random_file=util.result_random_file)
myparams.generating_Training_Graph()
selection = VariableSelection(myparams.trainnigGraph, util.min_edges)
nodesNotLinked = selection.readingResultsFile(util.nodes_notlinked_file)
calc = CalculateInMemory(myparams,nodesNotLinked)
resultsofCalculation = calc.executingCalculate()
#print resultsofCalculation
calc.saving_calculateResult(util.calculated_file, resultsofCalculation)
calc.saving_calculateResult_normalized(util.calculated_file + '_normalizated.csv', resultsofCalculation)
result2 = calc.reading_calculateResult_normalized(util.calculated_file)
calc.save_Max_min_file(util.maxmincalculated_file, calc.qtyDataCalculated, calc.minValueCalculated, calc.maxValueCalculated)
print resultsofCalculation
print result2
if __name__ == '__main__':
util = ParameterUtil(
parameter_file='data/formatado/arxiv/nowell_astroph_1994_1999.txt')
calculatedFile = open(
FormatingDataSets.get_abs_file_path(util.calculated_file), 'r')
for linha in calculatedFile:
x.append(Calculate.reading_calculateLine(linha))
calculatedFile.close()
myparams = Parameterization(util.keyword_decay, util.lengthVertex, util.t0,
util.t0_, util.t1, util.t1_,
util.FeaturesChoiced, util.graph_file,
util.trainnig_graph_file, util.test_graph_file,
util.decay)
myparams.generating_Training_Graph()
Nodes_notLinked = VariableSelection(myparams.trainnigGraph,
util.nodes_notlinked_file,
util.min_edges)
nodes_notlinkedFile = open(
FormatingDataSets.get_abs_file_path(util.nodes_notlinked_file), 'r')
qtyLine = 0
qtyCalculated = 0
f = open(
FormatingDataSets.get_abs_file_path(util.calculated_file) +
'.weight.txt', 'w')
minValueCalculated = list(99999 for x in myparams.featuresChoice)
maxValueCalculated = list(0 for x in myparams.featuresChoice)
qtyFeatures = len(myparams.featuresChoice)
for line in nodes_notlinkedFile:
qtyLine = qtyLine + 1
item = VariableSelection.getItemFromLine(line)
from analysing.Analyse import Analyse
from calculating.VariableSelection import VariableSelection
from formating.FormatingDataSets import FormatingDataSets
import networkx
import mysql.connector
if __name__ == '__main__':
util = ParameterUtil(
parameter_file='data/formatado/arxiv/nowell_astroph_1994_1999.txt')
myparams = Parameterization(util.keyword_decay, util.lengthVertex, util.t0,
util.t0_, util.t1, util.t1_,
util.FeaturesChoiced, util.graph_file,
util.trainnig_graph_file, util.test_graph_file,
util.decay)
myparams.generating_Training_Graph()
AllNodes = VariableSelection(myparams.trainnigGraph, util.nodes_file,
util.min_edges, True)
calc = Calculate(myparams, util.nodes_file, util.calculated_file,
util.ordered_file, util.maxmincalculated_file)
print 'armazenando resultados'
cnx = mysql.connector.connect(user='******',
password='******',
host='127.0.0.1',
database='calculos')
add_result = ("INSERT INTO resultadopesos "
"(no1, no2, resultados) "
"VALUES (%s, %s, %s)")
cursor = cnx.cursor()
calculatedFile = open(
FormatingDataSets.get_abs_file_path(util.calculated_file), 'r')
for linha in calculatedFile:
dado = Calculate.reading_calculateLine(linha)
'''
from parametering.ParameterUtil import ParameterUtil
from parametering.Parameterization import Parameterization
from analysing.Analyse import Analyse
from calculating.CalculateInMemory import CalculateInMemory
from calculating.VariableSelection import VariableSelection
if __name__ == '__main__':
util = ParameterUtil(parameter_file = 'data/formatado/arxiv/exemplomenor/config/config.txt')
myparams = Parameterization(t0 = util.t0, t0_ = util.t0_, t1 = util.t1, t1_ = util.t1_, linear_combination=util.linear_combination,
filePathGraph = util.graph_file, filePathTrainingGraph = util.trainnig_graph_file, filePathTestGraph = util.test_graph_file, decay = util.decay, domain_decay = util.domain_decay, min_edges = util.min_edges, scoreChoiced = util.ScoresChoiced, weightsChoiced = util.WeightsChoiced, weightedScoresChoiced = util.WeightedScoresChoiced, FullGraph = None, result_random_file=util.result_random_file)
myparams.generating_Training_Graph()
myparams.generating_Test_Graph()
selecao = VariableSelection(myparams.trainnigGraph)
nodesNotLinked = selecao.readingResultsFile(util.nodes_notlinked_file)
calc = CalculateInMemory(myparams, myparams.trainnigGraph)
resultsNormalized = calc.reading_calculateResult_normalized(util.calculated_file)
AnalyseNodesnotLinkedInFuture = Analyse.reading_analyseResult(util.result_random_file)
topRank = Analyse.get_topRank(AnalyseNodesnotLinkedInFuture)
orderResult = []
if myparams.linear_combination:
resultCombination = calc.combinate_linear(resultsNormalized)
orderResult = calc.ordering_combinate_linear(topRank, resultCombination)
else:
orderResult = calc.ordering(topRank, resultsNormalized)
FinalResult = []
for featureOrderResult in orderResult:
final = Analyse.AnalyseNodesInFuture(featureOrderResult, myparams.testGraph)
from parametering.Parameterization import Parameterization
from analysing.Analyse import Analyse
from calculating.VariableSelection import VariableSelection
from formating.FormatingDataSets import FormatingDataSets
import networkx
from calculating.CalculateInMemory import CalculateInMemory
if __name__ == '__main__':
util = ParameterUtil(parameter_file = 'data/formatado/exemplomenor/config/config.txt')
myparams = Parameterization(t0 = util.t0, t0_ = util.t0_, t1 = util.t1, t1_ = util.t1_,
filePathGraph = util.graph_file, filePathTrainingGraph = util.trainnig_graph_file, filePathTestGraph = util.test_graph_file, decay = util.decay, domain_decay = util.domain_decay, min_edges = util.min_edges, scoreChoiced = util.ScoresChoiced, weightsChoiced = util.WeightsChoiced, weightedScoresChoiced = util.WeightedScoresChoiced, FullGraph = None)
myparams.generating_Training_Graph()
myparams.generating_Test_Graph()
selection = VariableSelection(myparams.trainnigGraph, util.min_edges)
nodesNotLinked = selection.get_pair_nodes_not_linked()
calc = CalculateInMemory(myparams, nodesNotLinked)
resultsCalculate = calc.executingCalculate()
calc.Separating_calculateFile()
analise = Analyse(myparams, FormatingDataSets.get_abs_file_path(util.calculated_file), FormatingDataSets.get_abs_file_path(util.analysed_file) + '.random.analised.txt', calc.qtyDataCalculated)
topRank = Analyse.getTopRank(util.analysed_file + '.random.analised.txt')
calc.Ordering_separating_File(topRank)
for OrderingFilePath in calc.getfilePathOrdered_separeted():
analise = Analyse(myparams, OrderingFilePath, OrderingFilePath + '.analised.txt', topRank )
print "Trainning Period:", myparams.t0, " - ", myparams.t0_
print "Test Period:", myparams.t1, " - ", myparams.t1_
def __init__(self, preparedParameter, filepathNodesNotLinked,
filepathResult, filePathOrdered, filepathMaxMinCalculated):
print "Starting Calculating Nodes not linked", datetime.today()
self.preparedParameter = preparedParameter
self.filePathOrdered = Formating.get_abs_file_path(filePathOrdered)
self.filepathMaxMinCalculated = Formating.get_abs_file_path(
filepathMaxMinCalculated)
self.filepathResult = Formating.get_abs_file_path(filepathResult)
self.filepathNodesNotLinked = Formating.get_abs_file_path(
filepathNodesNotLinked)
#for each links that is not linked all the calculates is done.
element = 0
qtyofResults = FormatingDataSets.getTotalLineNumbers(
self.filepathNodesNotLinked)
fcontentNodesNotLinked = open(self.filepathNodesNotLinked, 'r')
if os.path.exists(self.filepathResult):
print "Calculate already done for this file, please delete if you want a new one.", datetime.today(
)
self.reading_Max_min_file()
return
fcontentCalcResult = open(self.filepathResult, 'w')
self.minValueCalculated = list(
99999 for x in self.preparedParameter.featuresChoice)
self.maxValueCalculated = list(
0 for x in self.preparedParameter.featuresChoice)
qtyFeatures = len(self.preparedParameter.featuresChoice)
qtyNodesCalculated = 0
partialResults = []
for lineofFile in fcontentNodesNotLinked:
element = element + 1
item = VariableSelection.getItemFromLine(lineofFile)
qtyothernodenotlinked = len(item[1])
newelement = 0
for neighbor_node in item[1]:
newelement = newelement + 1
qtyNodesCalculated = qtyNodesCalculated + 1
self.printProgressofEvents(
element, qtyofResults,
"Calculating features for nodes not liked: ")
self.printProgressofEventsWihoutPercent(
newelement, qtyothernodenotlinked, "Calculating nodes: " +
str(item[0]) + ":" + str(neighbor_node))
item_result = []
#executing the calculation for each features chosen at parameter
for index_features in range(qtyFeatures):
self.preparedParameter.featuresChoice[index_features][
0].parameter = preparedParameter
valueCalculated = self.preparedParameter.featuresChoice[
index_features][0].execute(
item[0], neighbor_node
) * self.preparedParameter.featuresChoice[
index_features][1]
if valueCalculated < self.minValueCalculated[
index_features]:
self.minValueCalculated[
index_features] = valueCalculated
if valueCalculated > self.maxValueCalculated[
index_features]:
self.maxValueCalculated[
index_features] = valueCalculated
item_result.append(valueCalculated)
lineContent = []
#generating a vetor with the name of the feature and the result of the calculate
for indice in range(qtyFeatures):
lineContent.append(
str({
str(self.preparedParameter.featuresChoice[indice]):
item_result[indice]
}))
partialResults.append([lineContent, item[0], neighbor_node])
if element % 10 == 0:
for item in partialResults:
for calc in item[0]:
fcontentCalcResult.write(calc + '\t')
fcontentCalcResult.write(
str(item[1]) + '\t' + str(item[2]) + '\n')
partialResults = []
for item in partialResults:
for calc in item[0]:
fcontentCalcResult.write(calc + '\t')
fcontentCalcResult.write(str(item[1]) + '\t' + str(item[2]) + '\n')
fcontentCalcResult.flush()
fcontentCalcResult.close()
fcontentNodesNotLinked.close()
fcontentMaxMin = open(self.filepathMaxMinCalculated, 'w')
fcontentMaxMin.write(
str(qtyNodesCalculated) + '\t' + repr(self.minValueCalculated) +
'\t' + repr(self.maxValueCalculated))
fcontentMaxMin.close()
print "Calculating Nodes not linked finished", datetime.today()
filePathGraph=util.graph_file,
filePathTrainingGraph=util.trainnig_graph_file,
filePathTestGraph=util.test_graph_file,
decay=util.decay,
domain_decay=util.domain_decay,
min_edges=util.min_edges,
scoreChoiced=util.ScoresChoiced,
weightsChoiced=util.WeightsChoiced,
weightedScoresChoiced=util.WeightedScoresChoiced,
FullGraph=None,
result_random_file=util.result_random_file)
myparams.generating_Training_Graph()
#myparams.generating_Test_Graph()
selection = VariableSelection(myparams.trainnigGraph, util.min_edges)
nodesNotLinked = selection.get_pair_nodes_not_linked()
selection.saveResults(util.nodes_notlinked_file, nodesNotLinked)
#dado = selection.readingResultsFile(util.nodes_notlinked_file)
#print dado[1]
#calc = CalculateInMemory(myparams, nodesNotLinked)
#resultsCalculate = calc.executingCalculate()
#resultados = []
#orderDataMetrica0 = sorted(resultsCalculate, key=lambda value: value[0][0], reverse=True)
#orderDataMetrica1 = sorted(resultsCalculate, key=lambda value: value[0][5], reverse=True)
#for result in orderDataMetrica1:
# metricas = result[0]
# no1 = result[1]
