Currently, the graph has node attribute:
- vid
- ckn (insofar, checkin number)
- sts (start timestamp)
- ets (end timestamp)
- lat
- lng
- category
- pcategor
And edge attribute:
- trsn_cnt
- duration
'''
venue_g = GH.load_graph(graph_path, graph_name)
category_list = VH.get_category_list(venue_path, category_name)
pcategory_list = VH.get_category_list(venue_path, pcategory_name)
#GH.print_node_attr_names(venue_g)
#GH.print_edge_attr_names(venue_g)
#print category_list
GH.print_nids(venue_g)
# create snapshop of the graph - node accurate, but edge aren't
center = (37.76010, -122.44779)
radius = 0.095
print venue_g.GetNodes()
print venue_g.GetEdges()
i = 0
for edge in venue_g.Edges():
i += 1
c_lat = center[0]
c_lng = center[1]
# print lat, c_lat, lng, c_lng
# print abs(lat-c_lat), abs(lng-c_lng)
if abs(lat-c_lat) <= radius and abs(lng-c_lng) <= radius:
return True
else:
print "catch a false"
return False
data_path = '../DataSet/'
graph_path = '../DataSet/GraphData/'
venue_path = '../DataSet/VenueData/'
trsn_list = VH.load_pickle_file(data_path, 'sf_trsn')
time_list = VH.load_pickle_file(data_path, 'sf_time')
full_venue_dict = VH.GetFullVenueDict(venue_path, 'venues-CA-new.json')
category_dict = VH.load_json(venue_path, 'category_map.json')
pcategory_dict = VH.load_json(venue_path, 'pcategory_map.json')
lng_list = [GH.get_lat_lng(full_venue_dict, trsn[1]) for trsn in trsn_list]
lng_list.sort(key=lambda t:t[1], reverse=True)
print lng_list[0]
'''
vid_map = create_vid_map(trsn_list)
venue_g = snap.TNEANet.New()
lngs = []
for trsn_idx, trsn in enumerate(trsn_list):
# only need check one vid
def within_ts_range(sts, curr_ts):
curr_ts = int(curr_ts)
ets = sts + 3600 * 24 * 30 # hardcode 30 days
if curr_ts >= sts and curr_ts < ets:
return True
else:
return False
data_path = "../DataSet/Transition/"
graph_path = "../DataSet/GraphData/"
venue_path = "../DataSet/VenueData/"
trsn_list = VH.load_pickle_file(data_path, "sf_trsn_small_new")
time_list = VH.load_pickle_file(data_path, "sf_time_small_new")
full_venue_dict = VH.GetFullVenueDict(venue_path, "venues-CA-new.json")
category_dict = VH.load_json(venue_path, "category_map.json")
pcategory_dict = VH.load_json(venue_path, "pcategory_map.json")
vid_map = create_vid_map(trsn_list)
ts_list = TH.gen_ts_list("201201010000", "201301010000", 30)
venue_g = snap.TNEANet.New()
for ts_idx, ts in enumerate(ts_list):
for trsn_idx, trsn in enumerate(trsn_list):
src_ts = time_list[trsn_idx][0] # only need check one ts
dst_ts = time_list[trsn_idx][1]
if within_ts_range(ts, src_ts):
src_nid = vid_map[trsn[0]]
venue_dict[data['id']] = data
fin.close()
return venue_dict
# add attributes for graph nodes
def AddNodeAttr(graph, full_venue_dict):
''' for each node in the graph, add two attributes
1. two float values: latitude, longitute
2. category
3. parent-category
'''
for NI in graph.Nodes():
vid = graph.GetStrAttrDatN(NI.GetId(), 'vid')
if vid in full_venue_dict:
graph.AddFltAttrDatN(NI.GetId(), float(full_venue_dict[vid]['lat']), 'lat')
graph.AddFltAttrDatN(NI.GetId(), float(full_venue_dict[vid]['lng']), 'lng')
graph.AddStrAttrDatN(NI.GetId(), full_venue_dict[vid]['category'], 'category')
graph.AddStrAttrDatN(NI.GetId(), full_venue_dict[vid]['parentcategory'], 'pcategory')
#GH.save_graph(graph, result_path, result_filename)
#return None
trsn_g = GH.load_graph(graph_data_path, graph_filename)
full_venue_dict = VH.GetFullVenueDict(venue_graph_data_path, venue_filename)
category_dict = VH.load_json(venue_graph_data_path, 'category_map.json')
pcategory_dict = VH.load_json(venue_graph_data_path, 'pcategory_map.json')
GH.add_category(trsn_g, full_venue_dict, category_dict, pcategory_dict)
GH.save_graph(trsn_g, graph_data_path, 'sf_venue_graph')
print 'successfully build venue_graph!'