for ct in crime_types:
print "Started %s, getting data..." % ct
data, t0, cid = cad.get_crimes_from_dump('monsuru_cad_%s' % ct)
cid = np.array(cid)
# filter by end date
idx = np.where(data[:, 0] < (MAX_DAY_NUMBER + 1))[0]
data = data[idx]
cid = cid[idx]
cids[ct] = cid
jiggled = cad.jiggle_all_points_on_grid(data[:, 1], data[:, 2])
b_jiggled = [np.all(a != b) for a, b in zip(data[:, 1:], jiggled)]
snapped, fail = NetworkData.from_cartesian(net,
jiggled,
return_failure_idx=True)
keep_idx = [k for k in range(len(cid)) if k not in fail]
cid = cid[keep_idx]
times = data[keep_idx, 0]
failed[ct] = fail
print "Done. writing data to a file."
fields = [
'my_idx', 'original_idx', 'days_since_1_mar_2011', 'x', 'y',
'jiggled?'
]
xy = snapped.to_cartesian()
out_data = []
for k in range(cid.size):
out_data.append(
from data.models import CartesianData, DataArray, NetworkData
from matplotlib import pyplot as plt
itn_net = load_test_network()
nodes = np.array([t['loc'] for t in itn_net.g.node.values()])
xmin, ymin, xmax, ymax = itn_net.extent
targets, n_per_edge = utils.network_walker_uniform_sample_points(
itn_net, 10)
# lay down some random points within that box
num_pts = 100
x_pts = np.random.rand(num_pts) * (xmax - xmin) + xmin
y_pts = np.random.rand(num_pts) * (ymax - ymin) + ymin
xy = CartesianData.from_args(x_pts, y_pts)
sources = NetworkData.from_cartesian(
itn_net, xy, grid_size=50) # grid_size defaults to 50
# not all points necessarily snap successfully
num_pts = sources.ndata
radius = 200.
nw = utils.NetworkWalker(itn_net,
targets,
max_distance=radius,
max_split=1e4)
k = NetworkKernelEqualSplitLinear(sources.getone(0), 200.)
k.set_walker(nw)
z = k.pdf()
zn = z / max(z)
# plt.figure()
# itn_net.plot_network()
def create_network_with_crime_counts(
start_date=datetime.date(2011, 3, 1), domain_name='South'):
# load network, count crimes in 6mo and 12mo window, output shapefile
domains = chicago.get_chicago_side_polys()
domain = domains[domain_name]
end_date = start_date + datetime.timedelta(days=365)
crime_types = (
'THEFT',
'BURGLARY',
'HOMICIDE',
'BATTERY',
'ARSON',
'MOTOR VEHICLE THEFT',
'ASSAULT',
'ROBBERY',
)
time_window_filters = {
'6mo': lambda t: t <= 183,
'12mo': lambda t: t <= 365,
}
# get crime data
data, t0, cid = chicago.get_crimes_by_type(crime_type=crime_types,
start_date=start_date,
end_date=end_date,
domain=domain)
# get network
osm_file = os.path.join(
DATA_DIR, 'osm_chicago',
'%s_clipped.net' % consts.FILE_FRIENDLY_REGIONS[domain_name])
net = osm.OSMStreetNet.from_pickle(osm_file)
# snap crime data to network with maximum distance cutoff
netdata, failed = NetworkData.from_cartesian(net,
data[:, 1:],
radius=50,
return_failure_idx=True)
# get non-failed times
idx = sorted(set(range(data.shape[0])) - set(failed))
netdata = DataArray(data[idx, 0]).adddim(netdata,
type=NetworkSpaceTimeData)
# run over edges, count crimes in the two time windows
filters = {}
for filt_name, filt_func in time_window_filters.items():
filters[filt_name] = filt_func(netdata.toarray(0)).astype(int)
# add count attributes to all edges
for e in net.edges():
e.attrs['crimes_6mo'] = 0
e.attrs['crimes_12mo'] = 0
edge_counts = {}
for i, t in enumerate(netdata.space.toarray()):
t.edge.attrs['crimes_6mo'] += filters['6mo'][i]
t.edge.attrs['crimes_12mo'] += filters['12mo'][i]
net.save(consts.FILE_FRIENDLY_REGIONS[domain_name] +
'_network_crime_counts',
fmt='shp')