def __init__(self, fileName):
self.fileName = fileName
self.rootDir = self.getRootDir()
self.attrVal1 = attrVal1
self.attrVal2 = attrVal2
self.graphName = self.getGraphName()
self.lblV = snap.TStrV()
self.lblV.Add(attrVal1)
self.lblV.Add(attrVal2)
self.lblNH = snap.TStrIntH() # Node count with attached label
self.lblEH = snap.TIntIntH() # Edge count with attached src dst labels
#self.G = self.getGraph(snap.PUNGraph)
self.G = self.getLblGraph()
self.saveGraph()
ufileName = os.path.abspath(self.rootDir + "/" + self.graphName +
".txt")
self.snapG = snap.LoadEdgeList(snap.PUNGraph, ufileName)
self.nxG = nx.read_edgelist(ufileName)
self.gNAH = self.getNodeIdLabel(self.G)
def getNEStats(self):
lblEH = snap.TIntIntH()
lblNH = snap.TStrIntH()
NI = self.G.BegNI()
cN = 0
while NI < self.G.EndNI():
NId = NI.GetId()
label = self.walkNodeAttributes(NId)
if (label not in lblNH):
lblNH[label] = 0
lblNH[label] += 1
NI.Next()
cN += 1
EI = self.G.BegEI()
ECount = 0
while EI < self.G.EndEI():
srcId = EI.GetSrcNId()
dstId = EI.GetDstNId()
srcLbl = self.walkNodeAttributes(srcId)
dstLbl = self.walkNodeAttributes(dstId)
EdgeLblId = self.getEdgeLbl(srcLbl, dstLbl)
if (EdgeLblId not in lblEH):
lblEH[EdgeLblId] = 0
lblEH[EdgeLblId] += 1
ECount += 1
EI.Next()
return lblNH,lblEH
def __init__(self, filename, mVals, pVal, tau):
self.fileName = fileName
self.mVals = mVals
self.pVal = pVal
self.pVals = []
self.pVals.append(pVal)
self.pVals.append(1 - pVal)
self.tau = tau
self.nLH = snap.TIntStrH()
self.lblNH = snap.TStrIntH() # Node count with attached label
self.lblEH = snap.TIntIntH() # Edge count with attached src dst labels
self.RH = snap.TIntFltPrH()
self.BH = snap.TIntFltPrH()
self.cRV = snap.TIntV()
self.cBV = snap.TIntV()
self.G = self.getGraph(snap.PUNGraph)
self.NG = snap.TNEANet()
self.graphName = self.getGraphName()
self.rootDir = self.getParentDir(self.fileName)
self.absrootDir = os.path.abspath(self.rootDir)
self.cR_count = 0
self.cB_count = 0
self.RH_count = 0
self.BH_count = 0
import snap
print "LoadEdgeListStr 1"
companyEmployeeGraph = snap.LoadEdgeListStr(snap.PUNGraph, "c.txt", 0, 1)
print "LoadEdgeListStr 2"
mapping = snap.TStrIntH()
companyEmployeeGraph = snap.LoadEdgeListStr(snap.PUNGraph, "c.txt", 0, 1,
mapping)
company_name = df_counts.loc[c, 'organization']
#Strip special characters from company_name
company_name = re.sub('[^0-9a-zA-Z]+', '', company_name)
Graph = snap.PUNGraph.New()
#Extract data for company of interest
company_info = df_all[df_all['assignee_id'] == c][[
'patent_id', 'date', 'inventor_id'
]].sort_values(by='patent_id')
#Get date of oldest patent
oldest_patent = max_date.year - min(company_info['date'].tolist()).year
#Get all nodes (inventors)
nodes = company_info['inventor_id'].drop_duplicates().tolist()
#Get all potential edges (patent info)
patents = company_info['patent_id'].drop_duplicates().tolist()
#Hash of inventor_id -> node_id (for easier graph manipulation)
inventor_id_to_index = snap.TStrIntH()
metadata = {}
metadata['number_of_patents'] = len(patents)
metadata['oldest_patent'] = oldest_patent
print metadata
#Add all nodes to graph
for i in range(0, len(nodes)):
Graph.AddNode(i)
inventor_id_to_index[nodes[i]] = i
#Add all edges to graph
for p in patents:
#Get small connected component formed by a patent with multiple authors
mini_cc = company_info[company_info['patent_id'] ==
p]['inventor_id'].tolist()