def consolidate_features_add(base_graphs, k, Gcollab_delta):
# Get all the k-hop features
features = consolidate_features(base_graphs, Gcollab_delta, k)
Gcollab_base = base_graphs[graphutils.Graph.COLLAB]
feature_graphs = graphutils.split_feat_graphs(base_graphs)
org = len(features)
cnt = 0
# Add positive features for edges that are not k-hop
for edge in Gcollab_delta.Edges():
if cnt < org:
u = edge.GetSrcNId()
v = edge.GetDstNId()
tup = (u, v)
# Not k-hop and not an edge in base graph
if (u, v) not in features and (
v, u) not in features and not Gcollab_base.IsEdge(u, v):
features[tup] = get_all_features(feature_graphs, u, v)
cnt += 1
else:
break
print("Added %d" % (cnt - org))
return features
def consolidate_features(base_graphs, Gcollab_delta, k):
features = {}
Gcollab = base_graphs[graphutils.Graph.COLLAB]
feature_graphs = graphutils.split_feat_graphs(base_graphs)
for node in Gcollab.Nodes():
nodeID = node.GetId()
for neighborID in graphutils.getKHopN(Gcollab, nodeID, k):
if nodeID > neighborID: # swap
nodeID = neighborID + nodeID
neighborID = nodeID - neighborID
nodeID = nodeID - neighborID
if (nodeID, neighborID) in features:
continue
features[(nodeID, neighborID)] = []
for graph in feature_graphs:
features = getFeatures(Gcollab, Gcollab_delta, graph, features)
return features
def consolidate_features(base_graphs, Gcollab_delta, k):
features = {}
Gcollab = base_graphs[graphutils.Graph.COLLAB]
feature_graphs = graphutils.split_feat_graphs(base_graphs)
for node in Gcollab.Nodes():
nodeID= node.GetId()
for neighborID in graphutils.getKHopN(Gcollab, nodeID, k):
if nodeID > neighborID: # swap
nodeID= neighborID + nodeID
neighborID= nodeID - neighborID
nodeID= nodeID - neighborID
if (nodeID, neighborID) in features:
continue
features[(nodeID, neighborID)]= []
for graph in feature_graphs:
features = getFeatures(Gcollab, Gcollab_delta, graph, features)
return features
def consolidate_features_add(base_graphs, k, Gcollab_delta):
# Get all the k-hop features
features = consolidate_features(base_graphs, Gcollab_delta, k)
Gcollab_base = base_graphs[graphutils.Graph.COLLAB]
feature_graphs = graphutils.split_feat_graphs(base_graphs)
org = len(features)
cnt = 0
# Add positive features for edges that are not k-hop
for edge in Gcollab_delta.Edges():
if cnt<org:
u = edge.GetSrcNId()
v = edge.GetDstNId()
tup = (u,v)
# Not k-hop and not an edge in base graph
if (u,v) not in features and (v,u) not in features and not Gcollab_base.IsEdge(u,v):
features[tup] = get_all_features(feature_graphs, u, v)
cnt+=1
else:
break
print("Added %d"%(cnt-org))
return features
feature_graphs = graphutils.get_feat_graphs(db, uid, None, date1)
base_graphs = graphutils.get_base_dict(Gcollab_base, feature_graphs)
# from base graph take a random source node in every iteration
baseG = base_graphs[graphutils.Graph.COLLAB]
featG = graphutils.split_feat_graphs(base_graphs)
'''
followers = reader.followers()
baseG = graphutils.get_db_graph(graphutils.Graph.FOLLOW, uid, followers)
#Gp = snapext.EUNGraph()
#featG = [Gp, Gp, Gp]
featG = graphutils.split_feat_graphs(
graphutils.get_feat_graphs(db, uid, None, date1))
class RequestHandler(SimpleHTTPServer.SimpleHTTPRequestHandler):
def end_headers(self):
self.send_head()
SimpleHTTPServer.SimpleHTTPRequestHandler.end_headers(self)
def send_head(self):
self.send_header("Content-type", "application/json")
self.send_header("Access-Control-Allow-Origin", "*")
def do_GET(self):
try:
userid = self.path.lstrip("/")
def main(args):
db = args[0]
date1 = args[1]
date2 = args[2]
date3 = args[3]
k = int(args[4])
OUTFILE=args[5]
if len(args)>=7:
beta = float(args[6])
bstart = beta
bfinish = beta
else:
bstart = 0
bfinish = 20
reader = DBReader(db)
print("Getting uid")
uid = reader.uid()
print("Getting all the base graphs")
feature_graphs = graphutils.get_feat_graphs(db, uid, None, date1)
Gcollab_base = graphutils.get_collab_graph(db, uid, date3, date1)
base_graphs = graphutils.get_base_dict(Gcollab_base, feature_graphs)
print("Getting Gcollab_delta graph")
Gcollab_delta = graphutils.get_collab_graph(db, uid, date1, date2)
# from base graph take a random source node in every iteration
baseG = base_graphs[graphutils.Graph.COLLAB]
featG = graphutils.split_feat_graphs(base_graphs)
deltaNIDs = [node.GetId() for node in Gcollab_delta.Nodes()]
baseNIDs = [node.GetId() for node in baseG.Nodes()]
common_nodes = list(set(deltaNIDs).intersection(baseNIDs))
ktop = 20
subGraphK= 10
f = open(OUTFILE,"w")
print_and_log("# Beta\tRecall\tAvg. Rank\tPrec 20\n", f)
n_iterations = 10
it = 0
sources = []
while it < n_iterations:
src = random.choice(common_nodes)
subBaseG= graphutils.getSubGraph(baseG, src, subGraphK)
#print 'subgraph: ', subBaseG.GetNodes(), subBaseG.GetEdges()
actual = evaluate.getYList(subBaseG, Gcollab_delta, src)
#actual = evaluate.getYList(baseG, Gcollab_delta, src)
# Consider source node if it forms at least one edge in delta graph
if len(actual)>0:
sources.append(src)
common_nodes.remove(src)
it += 1
else:
print("Warning. Ignoring node with 0 new edges")
print 'number of nodes and edges in graph:', baseG.GetNodes(), baseG.GetEdges()
for beta in frange(bstart, bfinish, 4):
total_recall = 0
total_avg_rank= 0
total_preck = 0
for src in sources:
subBaseG= graphutils.getSubGraph(baseG, src, subGraphK)
print 'sub graph nodes:', subBaseG.GetNodes()
print 'sub graph edges:', subBaseG.GetEdges()
topIDs = runrw.runrw(subBaseG, featG, src, beta)
#topIDs = runrw.runrw(baseG, featG, Gcollab_delta, src, beta)
# compare topIDs with list of labels already formed
actual = evaluate.getYList(subBaseG, Gcollab_delta, src)
#actual = evaluate.getYList(baseG, Gcollab_delta, src)
# ignore if the node did not form an edge in the delta
recall, preck, average_rank = evaluate.getAccuracy(topIDs, actual, ktop)
print recall, preck, average_rank
total_recall+=recall
total_avg_rank += average_rank
total_preck += len(preck)
num = float(n_iterations)
print_and_log("%f\t%f\t%f\t%f\n"%(beta, total_recall/num, total_avg_rank/num, total_preck/num), f)
f.close()
feature_graphs = graphutils.get_feat_graphs(db, uid, None, date1)
base_graphs = graphutils.get_base_dict(Gcollab_base, feature_graphs)
# from base graph take a random source node in every iteration
baseG = base_graphs[graphutils.Graph.COLLAB]
featG = graphutils.split_feat_graphs(base_graphs)
'''
followers = reader.followers()
baseG = graphutils.get_db_graph(graphutils.Graph.FOLLOW, uid, followers)
#Gp = snapext.EUNGraph()
#featG = [Gp, Gp, Gp]
featG = graphutils.split_feat_graphs(graphutils.get_feat_graphs(db, uid, None, date1))
class RequestHandler(SimpleHTTPServer.SimpleHTTPRequestHandler):
def end_headers(self):
self.send_head()
SimpleHTTPServer.SimpleHTTPRequestHandler.end_headers(self)
def send_head(self):
self.send_header("Content-type", "application/json")
self.send_header("Access-Control-Allow-Origin", "*")
def do_GET(self):
try:
userid = self.path.lstrip("/")
def main(args):
db = args[0]
date1 = args[1]
date2 = args[2]
date3 = args[3]
k = int(args[4])
OUTFILE = args[5]
if len(args) >= 7:
beta = float(args[6])
bstart = beta
bfinish = beta
else:
bstart = 0
bfinish = 20
reader = DBReader(db)
print("Getting uid")
uid = reader.uid()
print("Getting all the base graphs")
feature_graphs = graphutils.get_feat_graphs(db, uid, None, date1)
Gcollab_base = graphutils.get_collab_graph(db, uid, date3, date1)
base_graphs = graphutils.get_base_dict(Gcollab_base, feature_graphs)
print("Getting Gcollab_delta graph")
Gcollab_delta = graphutils.get_collab_graph(db, uid, date1, date2)
# from base graph take a random source node in every iteration
baseG = base_graphs[graphutils.Graph.COLLAB]
featG = graphutils.split_feat_graphs(base_graphs)
deltaNIDs = [node.GetId() for node in Gcollab_delta.Nodes()]
baseNIDs = [node.GetId() for node in baseG.Nodes()]
common_nodes = list(set(deltaNIDs).intersection(baseNIDs))
ktop = 20
subGraphK = 10
f = open(OUTFILE, "w")
print_and_log("# Beta\tRecall\tAvg. Rank\tPrec 20\n", f)
n_iterations = 10
it = 0
sources = []
while it < n_iterations:
src = random.choice(common_nodes)
subBaseG = graphutils.getSubGraph(baseG, src, subGraphK)
#print 'subgraph: ', subBaseG.GetNodes(), subBaseG.GetEdges()
actual = evaluate.getYList(subBaseG, Gcollab_delta, src)
#actual = evaluate.getYList(baseG, Gcollab_delta, src)
# Consider source node if it forms at least one edge in delta graph
if len(actual) > 0:
sources.append(src)
common_nodes.remove(src)
it += 1
else:
print("Warning. Ignoring node with 0 new edges")
print 'number of nodes and edges in graph:', baseG.GetNodes(
), baseG.GetEdges()
for beta in frange(bstart, bfinish, 4):
total_recall = 0
total_avg_rank = 0
total_preck = 0
for src in sources:
subBaseG = graphutils.getSubGraph(baseG, src, subGraphK)
print 'sub graph nodes:', subBaseG.GetNodes()
print 'sub graph edges:', subBaseG.GetEdges()
topIDs = runrw.runrw(subBaseG, featG, src, beta)
#topIDs = runrw.runrw(baseG, featG, Gcollab_delta, src, beta)
# compare topIDs with list of labels already formed
actual = evaluate.getYList(subBaseG, Gcollab_delta, src)
#actual = evaluate.getYList(baseG, Gcollab_delta, src)
# ignore if the node did not form an edge in the delta
recall, preck, average_rank = evaluate.getAccuracy(
topIDs, actual, ktop)
print recall, preck, average_rank
total_recall += recall
total_avg_rank += average_rank
total_preck += len(preck)
num = float(n_iterations)
print_and_log(
"%f\t%f\t%f\t%f\n" % (beta, total_recall / num,
total_avg_rank / num, total_preck / num), f)
f.close()
import path from learning import getFeatures from db.interface import * from analysis import graphutils db = '../db/github.2013_1_20.2013_2_20.db' reader = DBReader(db) uid = reader.uid() base_graphs = graphutils.get_db_graphs(db, uid) Gcollab = base_graphs["Gcollab"] feature_graphs = graphutils.split_feat_graphs(base_graphs) reader.close() start = Gcollab.GetRndNId() walk_features = getFeatures.get_walk_features(Gcollab, feature_graphs, start) print(walk_features)
