def calculatingWeights(graph, nodesnotLinked, database, calculatingFile):
pdb = Base(calculatingFile)
pdb.create('node1', 'node2', 'WCNFI','WAAFI')
pdb.create_index('node1', 'node2')
element = 0
qtyofNodesToProcess = len(nodesnotLinked)
for pair in nodesnotLinked:
element = element+1
FormatingDataSets.printProgressofEvents(element, qtyofNodesToProcess, "Calculating features for nodes not liked: ")
neighbors_node1 = all_neighbors(graph, pair[0])
neighbors_node2 = all_neighbors(graph, pair[1])
len_neihbors_node1 = len(neighbors_node1)
len_neihbors_node2 = len(neighbors_node2)
CommonNeigbors = neighbors_node1.intersection(neighbors_node2)
WCNFI = 0;
WAAFI = 0;
for cn in CommonNeigbors:
item = get_partOfWeightCalculating(graph, database, pair, cn)
WCNFI = WCNFI + item['WCN'];
WAAFI = WAAFI + item['WAA'];
pdb.insert(str(pair[0]), str(pair[1]), WCNFI, WAAFI )
pdb.commit()
return pdb;
def __init__(self, preparedParameters, filePathResults, filePathAnalyseResult, topRank):
print "Starting Analysing the results", datetime.today()
absFilePath = filePathResults
absfilePathAnalyseResult = filePathAnalyseResult #FormatingDataSets.get_abs_file_path(filePathAnalyseResult)
fResult = open(absFilePath, 'r')
with open(absfilePathAnalyseResult, 'w') as fnodes:
self.success = 0
element = 0
for line in fResult:
element = element+1
FormatingDataSets.printProgressofEvents(element, topRank, "Analysing the results: ")
cols = line.strip().replace('\n','').split('\t')
if len(list(networkx.common_neighbors(preparedParameters.testGraph, cols[len(cols)-2] , cols[len(cols)-1] ))) != 0:
self.success = self.success + 1
fnodes.write(cols[len(cols)-2] + '\t' + cols[len(cols)-1] + '\t' + 'SUCCESS \r\n')
else:
fnodes.write(cols[len(cols)-2] + '\t' + cols[len(cols)-1] + '\t' + 'FAILED \r\n')
if element == topRank:
break
result = float(self.success) / float(topRank) *100
strResult = 'Final Result: \t' + str(result) + '%'
fnodes.write(strResult)
fnodes.write('\n#\t'+str(self.success))
fnodes.close()
print "Analysing the results finished", datetime.today()
def get_pair_nodes_not_linked(self, graph, file, min_papers):
print "Starting getting pair of nodes that is not liked", datetime.today(
)
results = []
nodesinGraph = set(n for n, d in graph.nodes(data=True)
if d['node_type'] == 'N')
currentNodes = set()
for n in nodesinGraph:
papers = set(networkx.all_neighbors(graph, n))
print papers
if (len(papers) >= min_papers):
currentNodes.add(n)
print 'qty of authors: ', len(currentNodes)
nodesOrdered = sorted(currentNodes)
element = 0
totalnodesOrdered = len(nodesOrdered)
for node1 in nodesOrdered:
element = element + 1
FormatingDataSets.printProgressofEvents(
element, totalnodesOrdered, "Checking Node not liked: ")
others = set(n for n in nodesOrdered if n > node1)
notLinked = set()
for other_node in others:
if len(set(networkx.common_neighbors(graph, node1,
other_node))) == 0:
#notLinked.add(other_node) # como estava antes
# esse if abaixo verifica se estao perto
if networkx.has_path(graph, node1, other_node):
tamanho_caminho = len(
networkx.shortest_path(graph, node1,
other_node)) - 2
#print "%s ate %s: %s" %(node1, other_node,tamanho_caminho)
#print repr(networkx.shortest_path(graph, node1, other_node));
if (tamanho_caminho >
0) and (tamanho_caminho <=
self.MAX_NUMBER_OF_PEOPLE_BETWEEN * 2 +
1): # -2 porque inclui o inicio e fim
print "adicionando %s - %s" % (node1, other_node)
notLinked.add(other_node)
if len(notLinked) > 0:
results.append([node1, notLinked])
if element % 2000 == 0:
for item in results:
file.write(str(item[0]) + '\t' + repr(item[1]) + '\n')
results = []
for item in results:
file.write(str(item[0]) + '\t' + repr(item[1]) + '\n')
results = []
print "getting pair of nodes that is not liked finished", datetime.today(
)
def readingOrginalDataset(self):
print "Starting Reading Original Dataset", datetime.today()
with open(self.OriginalDataSet) as f:
self.OrignalContent = f.readlines()
f.close()
articleid = 0
articles = []
authornames = []
authorofArticles = []
authors = []
article = None
element = 0
for line in self.OrignalContent:
element = element + 1
FormatingDataSets.printProgressofEvents(
element, len(self.OrignalContent), "Reading File Content to Generate Graph: "
)
line = line.strip()
if line.startswith("#*"):
articleid = articleid + 1
article = Article("p_" + str(articleid))
article.articlename = line.replace("#*", "").replace("\r\n", "")
if line.startswith("#t"):
article.time = line.replace("#t", "").replace("\r\n", "")
if line.startswith("#@"):
authorsofArticle = line.replace("#@", "").replace("\r\n", "").split(",")
for author in authorsofArticle:
author = author.strip()
if not author in authornames:
authornames.append(author)
articleauthor = AuthorInArticle(article.articleid, authornames.index(author) + 1)
authorofArticles.append(articleauthor)
if line.startswith("#!"):
articles.append(article)
for index in range(len(authornames)):
author = Author(index + 1, authornames[index])
authors.append(author)
self.Graph = networkx.Graph()
for item_article in articles:
self.Graph.add_node(
item_article.articleid,
{"node_type": "E", "title": item_article.articlename.decode("latin_1"), "time": int(item_article.time)},
)
for item_author in authors:
self.Graph.add_node(
int(item_author.authorid), {"node_type": "N", "name": item_author.name.decode("latin_1")}
)
for item_edge in authorofArticles:
self.Graph.add_edge(item_edge.articleid, int(item_edge.authorid))
print "Reading Original Dataset finished", datetime.today()
def readingOrginalDataset(self):
print "Starting Reading Original Dataset", datetime.today()
con = None
try:
con = psycopg2.connect(database='projetomestrado', user='******', password='******')
curPublicacao = con.cursor()
curPublicacao.execute("select distinct p.idpublicacao, p.titulo, p.ano from projetomestrado.publicacao p inner join projetomestrado.autorpublicacao a on a.idpublicacao = p.idpublicacao where a.idautor in (select idautor from projetomestrado.autor where afiliacao = 'Instituto Militar de Engenharia')")
curPublicacaoData = curPublicacao.fetchall()
element = 0
qty = len(curPublicacaoData)
print qty
for linha in curPublicacaoData:
element = element+1
FormatingDataSets.printProgressofEvents(element, qty, "Adding paper to new graph: ")
idpublicacao = linha[0]
curPublicacaoPalavras = con.cursor()
curPublicacaoPalavras.execute("select k.keyword from projetomestrado.keyword k inner join projetomestrado.publicacaokeyword pk on pk.idkeyword = k.idkeyword where pk.idpublicacao =" + str(idpublicacao))
palavras = []
for palavra in curPublicacaoPalavras.fetchall():
palavras.append(palavra[0].strip())
curAutores = con.cursor()
curAutores.execute("select a.idautor, a.primeironome, a.ultimonome from projetomestrado.autorpublicacao ap inner join projetomestrado.autor a on a.idautor = ap.idautor where ap.idpublicacao = "+ str(idpublicacao))
autores = []
for autor in curAutores.fetchall():
autores.append([autor[0], autor[1] + "," + autor[2]])
self.Publications.append([idpublicacao, linha[1], linha[2], palavras, autores ])
self.Graph = networkx.Graph()
for item_article in self.Publications:
self.Graph.add_node('P_' + str(item_article[0]), {'node_type' : 'E', 'title' : item_article[1].decode("latin_1"), 'time' : int(item_article[2]), 'keywords': str(item_article[3]) })
for item_autor in item_article[4]:
self.Graph.add_node(int(item_autor[0]), {'node_type' : 'N', 'name' : item_autor[1].decode("latin_1") })
self.Graph.add_edge('P_' + str(item_article[0]), int(item_autor[0]) )
print "Reading Original Dataset finished", datetime.today()
except psycopg2.DatabaseError, e:
print 'Error %s' % e
def calculatingInputToFuzzy(graph, nodesnotLinked, params):
result = []
#pdb = Base(calculatingFile)
#pdb.create('node1', 'node2', 'IntensityNode1', 'IntencityNode2' ,'Similarity','AgesNode1', 'AgesNode2')
#pdb.create_index('node1', 'node2')
element = 0
qtyofNodesToProcess = len(nodesnotLinked)
for pair in nodesnotLinked:
element = element+1
FormatingDataSets.printProgressofEvents(element, qtyofNodesToProcess, "Calculating features for nodes not liked: ")
neighbors_node1 = all_neighbors(graph, pair[0])
neighbors_node2 = all_neighbors(graph, pair[1])
len_neihbors_node1 = len(neighbors_node1)
len_neihbors_node2 = len(neighbors_node2)
CommonNeigbors = neighbors_node1.intersection(neighbors_node2)
IntensityNode1 = 0;
IntensityNode2 = 0;
Similarities = 0;
Similarity = 0;
AgesNode1 = 0;
AgesNode2 = 0;
for cn in CommonNeigbors:
infoNode1 = list(edge for n1, n2, edge in graph.edges([ pair[0], cn], data=True) if ((n1 == pair[0] and n2 == cn) or (n1 == cn and n2 == pair[0])) )
infoNode2 = list(edge for n1, n2, edge in graph.edges([pair[1], cn], data=True) if ((n1 == pair[1] and n2 == cn) or (n1 == cn and n2 == pair[1])) )
IntensityNode1 = IntensityNode1 + len(infoNode1)
IntensityNode2 = IntensityNode2 + len(infoNode2)
MaxTimeNode1 = max(info['time'] for info in infoNode1 if 1==1)
MaxTimeNode2 = max(info['time'] for info in infoNode2 if 1==1)
AgesNode1 = max(AgesNode1,MaxTimeNode1)
AgesNode2 = max(AgesNode2,MaxTimeNode1)
bagofWordsNode1 = list(info['keywords'] for info in infoNode1 if 1==1)
bagofWordsNode2 = list(info['keywords'] for info in infoNode2 if 1==1)
Similarities = Similarities + get_jacard_domain(bagofWordsNode1, bagofWordsNode2)
AgesNode1 = abs(params.t0_ - AgesNode1)
AgesNode2 = abs(params.t0_ - AgesNode2)
if len(CommonNeigbors) > 0:
Similarity = (Similarities / len(CommonNeigbors)) *100
result.append({ 'no1': str(pair[0]), 'no2' :str(pair[1]), 'intensityno1' : IntensityNode1,'intensityno2' : IntensityNode2, 'similarity' : Similarity, 'ageno1' : AgesNode1, 'ageno2' :AgesNode2 })
return result
def calculatingWeights(graph, nodesnotLinked, database, calculatingFile):
pdb = Base(calculatingFile)
pdb.create('node1', 'node2', 'cnWTS02', 'cnWTS05', 'cnWTS08', 'aaWTS02',
'aaWTS05', 'aaWTS08')
pdb.create_index('node1', 'node2')
element = 0
qtyofNodesToProcess = len(nodesnotLinked)
for pair in nodesnotLinked:
element = element + 1
FormatingDataSets.printProgressofEvents(
element, qtyofNodesToProcess,
"Calculating features for nodes not liked: ")
neighbors_node1 = all_neighbors(graph, pair[0])
neighbors_node2 = all_neighbors(graph, pair[1])
len_neihbors_node1 = len(neighbors_node1)
len_neihbors_node2 = len(neighbors_node2)
CommonNeigbors = neighbors_node1.intersection(neighbors_node2)
CNWts02Feature = 0
CNWts05Feature = 0
CNWts08Feature = 0
AAWts02Feature = 0
AAWts05Feature = 0
AAWts08Feature = 0
CNWJCFeature = 0
AAWJCFeature = 0
for cn in CommonNeigbors:
item = get_partOfWeightCalculating(graph, database, pair, cn)
CNWts02Feature = CNWts02Feature + item['cnWts02']
CNWts05Feature = CNWts05Feature + item['cnWts05']
CNWts08Feature = CNWts08Feature + item['cnWts08']
AAWts02Feature = AAWts02Feature + item['aaWts02']
AAWts05Feature = AAWts05Feature + item['aaWts05']
AAWts08Feature = AAWts08Feature + item['aaWts08']
#CNWJCFeature = CNWJCFeature + item['cnWJC'];
#AAWJCFeature = AAWJCFeature + item['aaWJC'];
pdb.insert(str(pair[0]), str(pair[1]), CNWts02Feature, CNWts05Feature,
CNWts08Feature, AAWts02Feature, AAWts05Feature,
AAWts08Feature)
pdb.commit()
return pdb
def calculatingWeights(graph, nodesnotLinked, database, calculatingFile):
pdb = Base(calculatingFile)
pdb.create('node1', 'node2', 'cnWTS02','cnWTS05','cnWTS08', 'aaWTS02', 'aaWTS05', 'aaWTS08')
pdb.create_index('node1', 'node2')
element = 0
qtyofNodesToProcess = len(nodesnotLinked)
for pair in nodesnotLinked:
element = element+1
FormatingDataSets.printProgressofEvents(element, qtyofNodesToProcess, "Calculating features for nodes not liked: ")
neighbors_node1 = all_neighbors(graph, pair[0])
neighbors_node2 = all_neighbors(graph, pair[1])
len_neihbors_node1 = len(neighbors_node1)
len_neihbors_node2 = len(neighbors_node2)
CommonNeigbors = neighbors_node1.intersection(neighbors_node2)
CNWts02Feature = 0;
CNWts05Feature = 0;
CNWts08Feature = 0;
AAWts02Feature = 0;
AAWts05Feature = 0;
AAWts08Feature = 0;
CNWJCFeature = 0;
AAWJCFeature = 0;
for cn in CommonNeigbors:
item = get_partOfWeightCalculating(graph, database, pair, cn)
CNWts02Feature = CNWts02Feature + item['cnWts02'];
CNWts05Feature = CNWts05Feature + item['cnWts05'];
CNWts08Feature = CNWts08Feature + item['cnWts08'];
AAWts02Feature = AAWts02Feature + item['aaWts02'];
AAWts05Feature = AAWts05Feature + item['aaWts05'];
AAWts08Feature = AAWts08Feature + item['aaWts08'];
#CNWJCFeature = CNWJCFeature + item['cnWJC'];
#AAWJCFeature = AAWJCFeature + item['aaWJC'];
pdb.insert(str(pair[0]), str(pair[1]), CNWts02Feature, CNWts05Feature, CNWts08Feature, AAWts02Feature, AAWts05Feature, AAWts08Feature )
pdb.commit()
return pdb;
def __init__(self, preparedParameters, filePathResults,
filePathAnalyseResult, topRank):
print "Starting Analysing the results", datetime.today()
absFilePath = filePathResults
absfilePathAnalyseResult = filePathAnalyseResult #FormatingDataSets.get_abs_file_path(filePathAnalyseResult)
fResult = open(absFilePath, 'r')
with open(absfilePathAnalyseResult, 'w') as fnodes:
self.success = 0
element = 0
for line in fResult:
element = element + 1
FormatingDataSets.printProgressofEvents(
element, topRank, "Analysing the results: ")
cols = line.strip().replace('\n', '').split('\t')
if len(
list(
networkx.common_neighbors(
preparedParameters.testGraph,
cols[len(cols) - 2],
cols[len(cols) - 1]))) != 0:
self.success = self.success + 1
fnodes.write(cols[len(cols) - 2] + '\t' +
cols[len(cols) - 1] + '\t' + 'SUCCESS \r\n')
else:
fnodes.write(cols[len(cols) - 2] + '\t' +
cols[len(cols) - 1] + '\t' + 'FAILED \r\n')
if element == topRank:
break
result = float(self.success) / float(topRank) * 100
strResult = 'Final Result: \t' + str(result) + '%'
fnodes.write(strResult)
fnodes.write('\n#\t' + str(self.success))
fnodes.close()
print "Analysing the results finished", datetime.today()
def get_pair_nodes_not_linked(self):
print "Starting getting pair of nodes that is not liked", datetime.today()
results = []
nodesinGraph =self.graph.nodes()
nodesOrdered = sorted(nodesinGraph)
totalnodesOrdered = len(nodesOrdered)
element = 0
for node in nodesOrdered:
element = element+1
FormatingDataSets.printProgressofEvents(element, totalnodesOrdered, "Checking Node not liked: ")
publicacoes = self.graph.edges(node,data=False)
qtdepublicacoes = len(publicacoes)
#print "O autor e seus papers ",node,qtdepublicacoes ,publicacoes
if (qtdepublicacoes >= self.min_papers):
others = set(n for n in nodesOrdered if n > node)
for otherNode in others:
other_publicacoes = self.graph.edges(otherNode,data=False)
other_qtdepublicacoes = len(other_publicacoes)
if (other_qtdepublicacoes >= self.min_papers):
if (not self.graph.has_edge(node, otherNode)):
if self.USE_MAX_NUMBER_OF_PEOPLE_BETWEEN == True:
if networkx.has_path(self.graph, node, otherNode):
shortestPathResult = networkx.shortest_path(self.graph, node, otherNode)
#print shortestPathResult
tamanho_caminho = len(shortestPathResult) - 1
#print "%s ate %s: %s" %(node1, other_node,tamanho_caminho)
#print repr(networkx.shortest_path(graph, node1, other_node));
if ( tamanho_caminho > 0 ) and (tamanho_caminho <= self.MAX_NUMBER_OF_PEOPLE_BETWEEN ): # -2 porque inclui o inicio e fim
#print "adicionando %s - %s" %(node, otherNode)
results.append([node, otherNode])
else:
results.append([node, otherNode])
print "getting pair of nodes that is not liked finished", datetime.today()
return results
def get_pair_nodes_not_linked(self, graph, file, min_papers):
print "Starting getting pair of nodes that is not liked", datetime.today()
results = []
nodesinGraph =set(n for n,d in graph.nodes(data=True) if d['node_type'] == 'N')
currentNodes = set()
for n in nodesinGraph:
papers = set(networkx.all_neighbors(graph, n))
print papers
if (len(papers) >= min_papers):
currentNodes.add(n)
print 'qty of authors: ', len(currentNodes)
nodesOrdered = sorted(currentNodes)
element = 0
totalnodesOrdered = len(nodesOrdered)
for node1 in nodesOrdered:
element = element+1
FormatingDataSets.printProgressofEvents(element, totalnodesOrdered, "Checking Node not liked: ")
others = set(n for n in nodesOrdered if n > node1)
notLinked = set()
for other_node in others:
if len(set(networkx.common_neighbors(graph, node1, other_node))) == 0:
notLinked.add(other_node)
results.append([node1, notLinked])
if element % 2000 == 0:
for item in results:
file.write(str(item[0]) + '\t' + repr(item[1]) + '\n')
results = []
for item in results:
file.write(str(item[0]) + '\t' + repr(item[1]) + '\n')
results = []
print "getting pair of nodes that is not liked finished", datetime.today()
def readingOrginalDataset(self):
print "Starting Reading Original Dataset", datetime.today()
con = None
try:
con = psycopg2.connect(database='projetomestrado',
user='******',
password='******')
curPublicacao = con.cursor()
curPublicacao.execute(
"select idpublicacao, titulo, ano from projetomestrado.publicacao where ano >= 1993 and ano <= 2000"
)
curPublicacaoData = curPublicacao.fetchall()
element = 0
for linha in curPublicacaoData:
element = element + 1
FormatingDataSets.printProgressofEvents(
element, len(curPublicacaoData),
"Adding paper to new graph: ")
idpublicacao = linha[0]
curPublicacaoPalavras = con.cursor()
curPublicacaoPalavras.execute(
"select k.keyword from projetomestrado.keyword k inner join projetomestrado.publicacaokeyword pk on pk.idkeyword = k.idkeyword where pk.idpublicacao ="
+ str(idpublicacao))
palavras = []
for palavra in curPublicacaoPalavras.fetchall():
palavras.append(palavra[0].strip())
curAutores = con.cursor()
curAutores.execute(
"select a.idautor, a.primeironome, a.ultimonome from projetomestrado.autorpublicacao ap inner join projetomestrado.autor a on a.idautor = ap.idautor where ap.idpublicacao = "
+ str(idpublicacao))
autores = []
for autor in curAutores.fetchall():
autores.append([autor[0], autor[1] + "," + autor[2]])
self.Publications.append(
[idpublicacao, linha[1], linha[2], palavras, autores])
self.Graph = networkx.Graph()
for item_article in self.Publications:
self.Graph.add_node(
'P_' + str(item_article[0]), {
'node_type': 'E',
'title': item_article[1].decode("latin_1"),
'time': int(item_article[2]),
'keywords': str(item_article[3])
})
for item_autor in item_article[4]:
self.Graph.add_node(int(item_autor[0]), {
'node_type': 'N',
'name': item_autor[1].decode("latin_1")
})
self.Graph.add_edge('P_' + str(item_article[0]),
int(item_autor[0]))
print "Reading Original Dataset finished", datetime.today()
except psycopg2.DatabaseError, e:
print 'Error %s' % e
def calculatingWeights(graph, nodesnotLinked, database, calculatingFile):
pdb = Base(calculatingFile)
pdb.create('node1', 'node2', 'WCNFTI01','WCNFTI02', 'WCNFTI03','WCNFTI04','WCNFTI05','WCNFTI06','WCNFTI07','WCNFTI08','WCNFTI09','WAAFTI01','WAAFTI02', 'WAAFTI03','WAAFTI04','WAAFTI05','WAAFTI06','WAAFTI07','WAAFTI08','WAAFTI09')
pdb.create_index('node1', 'node2')
element = 0
qtyofNodesToProcess = len(nodesnotLinked)
for pair in nodesnotLinked:
element = element+1
FormatingDataSets.printProgressofEvents(element, qtyofNodesToProcess, "Calculating features for nodes not liked: ")
neighbors_node1 = all_neighbors(graph, pair[0])
neighbors_node2 = all_neighbors(graph, pair[1])
len_neihbors_node1 = len(neighbors_node1)
len_neihbors_node2 = len(neighbors_node2)
CommonNeigbors = neighbors_node1.intersection(neighbors_node2)
WCNFTI01 = 0;
WCNFTI02 = 0;
WCNFTI03 = 0;
WCNFTI04 = 0;
WCNFTI05 = 0;
WCNFTI06 = 0;
WCNFTI07 = 0;
WCNFTI08 = 0;
WCNFTI09 = 0;
WAAFTI01 = 0;
WAAFTI02 = 0;
WAAFTI03 = 0;
WAAFTI04 = 0;
WAAFTI05 = 0;
WAAFTI06 = 0;
WAAFTI07 = 0;
WAAFTI08 = 0;
WAAFTI09 = 0;
for cn in CommonNeigbors:
item = get_partOfWeightCalculating(graph, database, pair, cn)
WCNFTI01 = WCNFTI01 + item['WCN'][0];
WCNFTI02 = WCNFTI02 + item['WCN'][1];
WCNFTI03 = WCNFTI03 + item['WCN'][2];
WCNFTI04 = WCNFTI04 + item['WCN'][3];
WCNFTI05 = WCNFTI05 + item['WCN'][4];
WCNFTI06 = WCNFTI06 + item['WCN'][5];
WCNFTI07 = WCNFTI07 + item['WCN'][6];
WCNFTI08 = WCNFTI08 + item['WCN'][7];
WCNFTI09 = WCNFTI09 + item['WCN'][8];
WAAFTI01 = WAAFTI01 + item['WAA'][0];
WAAFTI02 = WAAFTI02 + item['WAA'][1];
WAAFTI03 = WAAFTI03 + item['WAA'][2];
WAAFTI04 = WAAFTI04 + item['WAA'][3];
WAAFTI05 = WAAFTI05 + item['WAA'][4];
WAAFTI06 = WAAFTI06 + item['WAA'][5];
WAAFTI07 = WAAFTI07 + item['WAA'][6];
WAAFTI08 = WAAFTI08 + item['WAA'][7];
WAAFTI09 = WAAFTI09 + item['WAA'][8];
pdb.insert(str(pair[0]), str(pair[1]), WCNFTI01, WCNFTI02, WCNFTI02,
WCNFTI03,WCNFTI04,WCNFTI05,WCNFTI06,WCNFTI07,WCNFTI08,WCNFTI09,
WAAFTI01, WAAFTI02, WAAFTI02,
WAAFTI03,WAAFTI04,WAAFTI05,WAAFTI06,WAAFTI07,WAAFTI08,WAAFTI09,
)
pdb.commit()
return pdb;
def readingOrginalDataset(self):
print "Starting Reading Original Dataset", datetime.today()
with open(self.OriginalDataSet) as f:
self.OrignalContent = f.readlines()
f.close()
articleid = 0
articles = []
authornames = []
authorofArticles = []
authors = []
article = None
element = 0
for line in self.OrignalContent:
element = element + 1
FormatingDataSets.printProgressofEvents(
element, len(self.OrignalContent),
"Reading File Content to Generate Graph: ")
line = line.strip()
if line.startswith('#*'):
articleid = articleid + 1
article = Article('p_' + str(articleid))
article.articlename = line.replace('#*',
'').replace('\r\n', '')
if line.startswith('#t'):
article.time = line.replace('#t', '').replace('\r\n', '')
if line.startswith('#@'):
authorsofArticle = line.replace('#@',
'').replace('\r\n',
'').split(',')
for author in authorsofArticle:
author = author.strip()
if not author in authornames:
authornames.append(author)
articleauthor = AuthorInArticle(
article.articleid,
authornames.index(author) + 1)
authorofArticles.append(articleauthor)
if line.startswith('#!'):
articles.append(article)
for index in range(len(authornames)):
author = Author(index + 1, authornames[index])
authors.append(author)
self.Graph = networkx.Graph()
for item_article in articles:
self.Graph.add_node(
item_article.articleid, {
'node_type': 'E',
'title': item_article.articlename.decode("latin_1"),
'time': int(item_article.time)
})
for item_author in authors:
self.Graph.add_node(int(item_author.authorid), {
'node_type': 'N',
'name': item_author.name.decode("latin_1")
})
for item_edge in authorofArticles:
self.Graph.add_edge(item_edge.articleid, int(item_edge.authorid))
print "Reading Original Dataset finished", datetime.today()
def calculatingWeights(graph, nodesnotLinked, database, calculatingFile):
pdb = Base(calculatingFile)
pdb.create('node1', 'node2', 'WCNFTI01', 'WCNFTI02', 'WCNFTI03',
'WCNFTI04', 'WCNFTI05', 'WCNFTI06', 'WCNFTI07', 'WCNFTI08',
'WCNFTI09', 'WAAFTI01', 'WAAFTI02', 'WAAFTI03', 'WAAFTI04',
'WAAFTI05', 'WAAFTI06', 'WAAFTI07', 'WAAFTI08', 'WAAFTI09')
pdb.create_index('node1', 'node2')
element = 0
qtyofNodesToProcess = len(nodesnotLinked)
for pair in nodesnotLinked:
element = element + 1
FormatingDataSets.printProgressofEvents(
element, qtyofNodesToProcess,
"Calculating features for nodes not liked: ")
neighbors_node1 = all_neighbors(graph, pair[0])
neighbors_node2 = all_neighbors(graph, pair[1])
len_neihbors_node1 = len(neighbors_node1)
len_neihbors_node2 = len(neighbors_node2)
CommonNeigbors = neighbors_node1.intersection(neighbors_node2)
WCNFTI01 = 0
WCNFTI02 = 0
WCNFTI03 = 0
WCNFTI04 = 0
WCNFTI05 = 0
WCNFTI06 = 0
WCNFTI07 = 0
WCNFTI08 = 0
WCNFTI09 = 0
WAAFTI01 = 0
WAAFTI02 = 0
WAAFTI03 = 0
WAAFTI04 = 0
WAAFTI05 = 0
WAAFTI06 = 0
WAAFTI07 = 0
WAAFTI08 = 0
WAAFTI09 = 0
for cn in CommonNeigbors:
item = get_partOfWeightCalculating(graph, database, pair, cn)
WCNFTI01 = WCNFTI01 + item['WCN'][0]
WCNFTI02 = WCNFTI02 + item['WCN'][1]
WCNFTI03 = WCNFTI03 + item['WCN'][2]
WCNFTI04 = WCNFTI04 + item['WCN'][3]
WCNFTI05 = WCNFTI05 + item['WCN'][4]
WCNFTI06 = WCNFTI06 + item['WCN'][5]
WCNFTI07 = WCNFTI07 + item['WCN'][6]
WCNFTI08 = WCNFTI08 + item['WCN'][7]
WCNFTI09 = WCNFTI09 + item['WCN'][8]
WAAFTI01 = WAAFTI01 + item['WAA'][0]
WAAFTI02 = WAAFTI02 + item['WAA'][1]
WAAFTI03 = WAAFTI03 + item['WAA'][2]
WAAFTI04 = WAAFTI04 + item['WAA'][3]
WAAFTI05 = WAAFTI05 + item['WAA'][4]
WAAFTI06 = WAAFTI06 + item['WAA'][5]
WAAFTI07 = WAAFTI07 + item['WAA'][6]
WAAFTI08 = WAAFTI08 + item['WAA'][7]
WAAFTI09 = WAAFTI09 + item['WAA'][8]
pdb.insert(
str(pair[0]),
str(pair[1]),
WCNFTI01,
WCNFTI02,
WCNFTI02,
WCNFTI03,
WCNFTI04,
WCNFTI05,
WCNFTI06,
WCNFTI07,
WCNFTI08,
WCNFTI09,
WAAFTI01,
WAAFTI02,
WAAFTI02,
WAAFTI03,
WAAFTI04,
WAAFTI05,
WAAFTI06,
WAAFTI07,
WAAFTI08,
WAAFTI09,
)
pdb.commit()
return pdb
