def step08(paramFile):
#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()
myparams.generating_Test_Graph()
print "Trainning Period:", myparams.t0, " - ", myparams.t0_
print "Test Period:", myparams.t1, " - ", myparams.t1_
print "# Papers in Trainning: ", myparams.get_edges(myparams.trainnigGraph)
print "# Authors in Training: ", myparams.get_nodes(myparams.trainnigGraph)
print "# Papers in Test: ", myparams.get_edges(myparams.testGraph)
print "# Authors in Test", myparams.get_nodes(myparams.testGraph)
calc = Calculate(myparams, util.nodes_notlinked_file, util.calculated_file, util.ordered_file, util.maxmincalculated_file)
calc.reading_Max_min_file()
print "# pair of Authors with at least 3 articles Calculated: ", calc.qtyDataCalculated #FormatingDataSets.getTotalLineNumbers(FormatingDataSets.get_abs_file_path(util.calculated_file))
topRank = Analyse.getTopRank(util.analysed_file+ '.random.analised.txt')
print "# pair of Authors with at least 3 articles that is connected in Test Graph in a random way: ", topRank
print "Max values found in calculations: ", str(calc.maxValueCalculated)
print "Min Values found in calculations: ", str(calc.minValueCalculated)
for pathFile in calc.getfilePathOrdered_separeted():
print "File Analised: ", pathFile + '.analised.txt'
number_connected = Analyse.getTopRankABSPathFiles(pathFile + '.analised.txt')
print "# pair of Authors that is connected in Test Graph: ", number_connected
print "%: ", Analyse.getLastInfosofResultsABSPathFiles(pathFile + '.analised.txt', topRank)
print "---------------------------------"
def step08(paramFile):
#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()
myparams.generating_Test_Graph()
print "Trainning Period:", myparams.t0, " - ", myparams.t0_
print "Test Period:", myparams.t1, " - ", myparams.t1_
print "# Papers in Trainning: ", myparams.get_edges(myparams.trainnigGraph)
print "# Authors in Training: ", myparams.get_nodes(myparams.trainnigGraph)
print "# Papers in Test: ", myparams.get_edges(myparams.testGraph)
print "# Authors in Test", myparams.get_nodes(myparams.testGraph)
calc = Calculate(myparams, util.nodes_notlinked_file, util.calculated_file,
util.ordered_file, util.maxmincalculated_file)
calc.reading_Max_min_file()
print "# pair of Authors with at least 3 articles Calculated: ", calc.qtyDataCalculated #FormatingDataSets.getTotalLineNumbers(FormatingDataSets.get_abs_file_path(util.calculated_file))
topRank = Analyse.getTopRank(util.analysed_file + '.random.analised.txt')
print "# pair of Authors with at least 3 articles that is connected in Test Graph in a random way: ", topRank
print "Max values found in calculations: ", str(calc.maxValueCalculated)
print "Min Values found in calculations: ", str(calc.minValueCalculated)
for pathFile in calc.getfilePathOrdered_separeted():
print "File Analised: ", pathFile + '.analised.txt'
number_connected = Analyse.getTopRankABSPathFiles(pathFile +
'.analised.txt')
print "# pair of Authors that is connected in Test Graph: ", number_connected
print "%: ", Analyse.getLastInfosofResultsABSPathFiles(
pathFile + '.analised.txt', topRank)
print "---------------------------------"
def step04(paramFile):
#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()
calc = Calculate(myparams, util.nodes_notlinked_file, util.calculated_file, util.ordered_file, util.maxmincalculated_file)
calc.Separating_calculateFile()
def step07(paramFile):
#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)
calc = Calculate(myparams, util.nodes_notlinked_file, util.calculated_file, util.ordered_file, util.maxmincalculated_file)
myparams.generating_Test_Graph()
topRank = Analyse.getTopRank(util.analysed_file + '.random.analised.txt')
print 'Analising Files with TopRank', str(topRank)
for OrderingFilePath in calc.getfilePathOrdered_separeted():
analise = Analyse(myparams, OrderingFilePath, OrderingFilePath + '.analised.txt', topRank )
def step06(paramFile):
#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)
calc = Calculate(myparams, util.nodes_notlinked_file, util.calculated_file,
util.ordered_file, util.maxmincalculated_file)
topRank = Analyse.getTopRank(util.analysed_file + '.random.analised.txt')
calc.Ordering_separating_File(topRank)
def step07(paramFile):
#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)
calc = Calculate(myparams, util.nodes_notlinked_file, util.calculated_file,
util.ordered_file, util.maxmincalculated_file)
myparams.generating_Test_Graph()
topRank = Analyse.getTopRank(util.analysed_file + '.random.analised.txt')
print 'Analising Files with TopRank', str(topRank)
for OrderingFilePath in calc.getfilePathOrdered_separeted():
analise = Analyse(myparams, OrderingFilePath,
OrderingFilePath + '.analised.txt', topRank)
def step05(paramFile):
#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)
calc = Calculate(myparams, util.nodes_notlinked_file, util.calculated_file,
util.ordered_file, util.maxmincalculated_file)
myparams.generating_Test_Graph()
analise = Analyse(
myparams, FormatingDataSets.get_abs_file_path(util.calculated_file),
FormatingDataSets.get_abs_file_path(util.analysed_file) +
'.random.analised.txt', calc.qtyDataCalculated)
'''
Created on Aug 22, 2015
@author: cptullio
Analysing the results
'''
from parametering.ParameterUtil import ParameterUtil
from parametering.Parameterization import Parameterization
from calculating.Calculate import Calculate
from analysing.Analyse import Analyse
from calculating.VariableSelection import VariableSelection
from formating.FormatingDataSets import FormatingDataSets
import networkx
if __name__ == '__main__':
util = ParameterUtil(parameter_file = 'data/formatado/arxiv/nowell_example_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()
selection = VariableSelection(myparams.trainnigGraph, util.nodes_notlinked_file,util.min_edges, True)
calc = Calculate(myparams, util.nodes_notlinked_file, util.calculated_file, util.ordered_file, util.maxmincalculated_file)
wg = calc.adding_normalize_values_tograph(myparams.trainnigGraph)
networkx.write_graphml(wg, FormatingDataSets.get_abs_file_path(util.trainnig_graph_file + '.weighted.txt'))
node993 =set(n for n,d in wg.edges(data=True) if n == 993 and d == 994)
print node993
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)
data_result = (dado[1], dado[2].replace('\n',''),str(dado[0]))
cursor.execute(add_result, data_result)
calculatedFile.close()
cnx.commit()
cursor.close()
cnx.close()
'''
Created on Aug 22, 2015
@author: cptullio
Generating TopRank
'''
from parametering.ParameterUtil import ParameterUtil
from parametering.Parameterization import Parameterization
from calculating.Calculate import Calculate
from analysing.Analyse import Analyse
from formating.FormatingDataSets import FormatingDataSets
if __name__ == '__main__':
util = ParameterUtil(
parameter_file='data/formatado/duarte/nowell_duarte_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)
calc = Calculate(myparams, util.nodes_notlinked_file, util.calculated_file,
util.ordered_file, util.maxmincalculated_file)
myparams.generating_Test_Graph()
analise = Analyse(
myparams, FormatingDataSets.get_abs_file_path(util.calculated_file),
FormatingDataSets.get_abs_file_path(util.analysed_file) +
'.random.analised.txt', calc.qtyDataCalculated)
'''
Created on Aug 22, 2015
@author: cptullio
Analysing the results
'''
from parametering.ParameterUtil import ParameterUtil
from parametering.Parameterization import Parameterization
from calculating.Calculate import Calculate
from analysing.Analyse import Analyse
if __name__ == '__main__':
util = ParameterUtil(parameter_file = 'data/formatado/duarte/nowell_duarte_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)
calc = Calculate(myparams, util.nodes_notlinked_file, util.calculated_file, util.ordered_file, util.maxmincalculated_file)
myparams.generating_Test_Graph()
topRank = Analyse.getTopRank(util.analysed_file + '.random.analised.txt')
print 'Analising Files with TopRank', str(topRank)
for OrderingFilePath in calc.getfilePathOrdered_separeted():
analise = Analyse(myparams, OrderingFilePath, OrderingFilePath + '.analised.txt', topRank )
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_
print "# Papers in Trainning: ", myparams.get_edges(myparams.trainnigGraph)
result = line
break
elif textov2 in line:
result = line
break
calculatedFile.seek(0)
return result
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(
if __name__ == '__main__':
util = ParameterUtil(parameter_file = 'data/formatado/arxiv/exemplomenor/config/configuration_weights.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()
print "Trainning Period:", myparams.t0, " - ", myparams.t0_
print "Test Period:", myparams.t1, " - ", myparams.t1_
print "# Papers in Trainning: ", myparams.get_edges(myparams.trainnigGraph)
print "# Authors in Training: ", myparams.get_nodes(myparams.trainnigGraph)
print "# Papers in Test: ", myparams.get_edges(myparams.testGraph)
print "# Authors in Test", myparams.get_nodes(myparams.testGraph)
calc = Calculate(myparams, util.nodes_notlinked_file, util.calculated_file, util.ordered_file, util.maxmincalculated_file)
calc.reading_Max_min_file()
print "# pair of Authors with at least 3 articles Calculated: ", calc.qtyDataCalculated #FormatingDataSets.getTotalLineNumbers(FormatingDataSets.get_abs_file_path(util.calculated_file))
topRank = Analyse.getTopRank(util.analysed_file+ '.random.analised.txt')
print "# pair of Authors with at least 3 articles that is connected in Test Graph in a random way: ", topRank
print "Max values found in calculations: ", str(calc.maxValueCalculated)
print "Min Values found in calculations: ", str(calc.minValueCalculated)
for pathFile in calc.getfilePathOrdered_separeted():
print "File Analised: ", pathFile + '.analised.txt'
number_connected = Analyse.getTopRankABSPathFiles(pathFile + '.analised.txt')
print "# pair of Authors that is connected in Test Graph: ", number_connected
print "%: ", Analyse.getLastInfosofResultsABSPathFiles(pathFile + '.analised.txt', topRank)
print "---------------------------------"
'''
Created on Aug 22, 2015
@author: cptullio
Ordering Calculation
'''
from parametering.ParameterUtil import ParameterUtil
from parametering.Parameterization import Parameterization
from calculating.Calculate import Calculate
from analysing.Analyse import Analyse
if __name__ == '__main__':
util = ParameterUtil(
parameter_file='data/formatado/duarte/nowell_duarte_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)
calc = Calculate(myparams, util.nodes_notlinked_file, util.calculated_file,
util.ordered_file, util.maxmincalculated_file)
topRank = Analyse.getTopRank(util.analysed_file + '.random.analised.txt')
calc.Ordering_separating_File(topRank)
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)
data_result = (dado[1], dado[2].replace('\n', ''), str(dado[0]))
cursor.execute(add_result, data_result)
from matplotlib import pyplot
if __name__ == '__main__':
#util = ParameterUtil(parameter_file = 'data/formatado/arxiv/exemplomenor/config/configuration_weights.txt')
util = ParameterUtil(
parameter_file=
'data/formatado/duarte/1994_1999/config/configuration.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()
calc = Calculate(myparams, util.nodes_notlinked_file, util.calculated_file,
util.ordered_file, util.maxmincalculated_file)
calc.Separating_calculateFile()
#networkx.networkx.draw_networkx(myparams.trainnigGraph) # networkx draw()
#pyplot.draw() # pyplot draw()
#pyplot.show()
for line in calculatedFile:
if texto in line:
result = line
break
elif textov2 in line:
result = line
break
calculatedFile.seek(0)
return result
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)
