def process_fcn(g): print "now processing" input_stats = geo_stats(g) geo_check_for_isolated(g) geo_filter_nones(g) geo_check_for_isolated(g) filtered_stats = geo_stats(g) node_map = geo_cluster(g, cities=[], restrict=False) #r = nx.DiGraph() g = geo_reduce(g, node_map) node_map = geo_cluster(g, cities=city_list, restrict=False) first_pass_stats = geo_stats(g) if self.options.filter_cities: g = geo_reduce(g, node_map) output_stats = geo_stats(g) elif self.options.geo_filter: print "Geo filtering..." g = geo_box_reduce(g, GEO_FILTERS[self.options.geo_filter]) output_stats = geo_stats(g) print "input stats: \n" + input_stats print "filtered stats: \n" + filtered_stats print "first pass (no city filtering): \n" + first_pass_stats if self.options.filter_cities or self.options.geo_filter: print "output stats (after city filter): \n" + output_stats return g
def __init__(self, post_fcn = None): self.parse_args() options = self.options input = options.input # Input graph input_path = os.path.join(input, input + '.gpk') self.g = nx.read_gpickle(input_path) if not self.g: raise Exception("null input file for input path %s" % input_path) # Output (reduced) graph. # Nodes: (lat, long) tuples w/ list of associated users & location strings # Edges: weight: number of links in this direction self.r = nx.DiGraph() conn = Connection() self.input_db = conn[self.options.input_db] self.input_coll = self.input_db[self.options.input_coll] print "now processing" self.reduce() print geo_stats(self.r) if options.write: geo_path = os.path.join(input, input + '.grg') nx.write_gpickle(self.r, geo_path)
def process_fcn(g): print "now processing" input_stats = geo_stats(g) geo_check_for_isolated(g) geo_filter_nones(g) geo_check_for_isolated(g) filtered_stats = geo_stats(g) node_map = geo_cluster(g, cities = [], restrict = False) #r = nx.DiGraph() g = geo_reduce(g, node_map) node_map = geo_cluster(g, cities = city_list, restrict = False) first_pass_stats = geo_stats(g) if self.options.filter_cities: g = geo_reduce(g, node_map) output_stats = geo_stats(g) elif self.options.geo_filter: print "Geo filtering..." g = geo_box_reduce(g, GEO_FILTERS[self.options.geo_filter]) output_stats = geo_stats(g) print "input stats: \n" + input_stats print "filtered stats: \n" + filtered_stats print "first pass (no city filtering): \n"+ first_pass_stats if self.options.filter_cities or self.options.geo_filter: print "output stats (after city filter): \n" + output_stats return g
def __init__(self, post_fcn=None): self.parse_args() options = self.options input = options.input # Input graph input_path = os.path.join(input, input + '.gpk') self.g = nx.read_gpickle(input_path) if not self.g: raise Exception("null input file for input path %s" % input_path) # Output (reduced) graph. # Nodes: (lat, long) tuples w/ list of associated users & location strings # Edges: weight: number of links in this direction self.r = nx.DiGraph() conn = Connection() self.input_db = conn[self.options.input_db] self.input_coll = self.input_db[self.options.input_coll] print "now processing" self.reduce() print geo_stats(self.r) if options.write: geo_path = os.path.join(input, input + '.grg') nx.write_gpickle(self.r, geo_path)