def main(args):
db = args[0]
date1 = args[1]
date2 = args[2]
date3 = args[3]
k = int(args[4])
basename = args[5]
reader = DBReader(db)
print("Getting uid")
uid = reader.uid()
print("Getting all the feature graphs")
feature_graphs = graphutils.get_feat_graphs(db, uid, None, date2)
print("Getting Gcollab_delta graph")
Gcollab_delta = graphutils.get_collab_graph(db, uid, date1, date2)
Gcollab_base = graphutils.get_collab_graph(db, uid, date3, date1)
base_graphs = graphutils.get_base_dict(Gcollab_base, feature_graphs)
graphutils.print_stats(base_graphs)
graphutils.print_graph_stats("Gcollab_delta", Gcollab_delta)
filepath = os.path.join(LEARNING_ROOT, basename + ".mat")
features_matrix_name = "%s_%s" % (basename, FEATURES)
labels_matrix_name = "%s_%s" % (basename, LABELS)
features = consolidateFeatures.consolidate_features_add(
base_graphs, k, Gcollab_delta)
#features = consolidateFeatures.consolidate_features(base_graphs, Gcollab_delta, k)
labels = consolidateFeatures.consolidate_labels(features, Gcollab_delta)
np_train, np_output = interface.matwrapTrain(features, labels)
interface.writeTrain(np_train, np_output, filepath, features_matrix_name,
labels_matrix_name)
# Add learning root to mlab path so that all .m functions are available as mlab attributes
mlab.path(mlab.path(), LEARNING_ROOT)
mlab.training(np_train, np_output)
def main(args):
db = args[0]
date1 = args[1]
date2 = args[2]
date3 = args[3]
k = int(args[4])
basename = args[5]
reader = DBReader(db)
print("Getting uid")
uid = reader.uid()
print("Getting all the feature graphs")
feature_graphs = graphutils.get_feat_graphs(db, uid, None, date2)
print("Getting Gcollab_delta graph")
Gcollab_delta = graphutils.get_collab_graph(db, uid, date1, date2)
Gcollab_base = graphutils.get_collab_graph(db, uid, date3, date1)
base_graphs = graphutils.get_base_dict(Gcollab_base, feature_graphs)
graphutils.print_stats(base_graphs)
graphutils.print_graph_stats("Gcollab_delta", Gcollab_delta)
filepath = os.path.join(LEARNING_ROOT, basename + ".mat")
features_matrix_name = "%s_%s"%(basename, FEATURES)
labels_matrix_name = "%s_%s"%(basename, LABELS)
features = consolidateFeatures.consolidate_features_add(base_graphs, k, Gcollab_delta)
#features = consolidateFeatures.consolidate_features(base_graphs, Gcollab_delta, k)
labels = consolidateFeatures.consolidate_labels(features, Gcollab_delta)
np_train, np_output = interface.matwrapTrain(features, labels)
interface.writeTrain(np_train, np_output, filepath, features_matrix_name, labels_matrix_name)
# Add learning root to mlab path so that all .m functions are available as mlab attributes
mlab.path(mlab.path(), LEARNING_ROOT)
mlab.training(np_train, np_output)
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()
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 db.interface import * from analysis import graphutils import utils db = utils.get_small_db() reader = DBReader(db) uid = reader.uid() rowid = uid.values()[0] print reader.get_users([rowid, rowid]) Gcollab = graphutils.get_collab_graph(db, uid) feature_graphs = graphutils.get_feat_graphs(db, uid) base_graphs = graphutils.get_base_dict(Gcollab, feature_graphs) graphutils.print_stats(base_graphs)