def f(*args):
(_, node, cargs) = args
log = Logger().log
log.info('{0}: setup +'.format(node))
with DatabaseConnection() as conn:
source = nd.Node(node, conn)
neighbors = [ nd.Node(x, conn) for x in source.neighbors ]
log.info('{0}: setup -'.format(node))
classes = [ WindowInfluence ] # [ MinuteInfluence, WindowInfluence ]
return [ i(source, neighbors, cargs).run() for i in classes ]
def __init__(self, nid, level, cluster, lag=0, db_conn=None, seen=None):
self.lag = lag
self.children = set()
close = not db_conn
if close:
db_conn = db.DatabaseConnection().resource
self.node = nd.Node(nid, db_conn)
if not seen:
seen = set()
seen.add(nid)
self.__build(level, cluster, db_conn, seen)
if close:
db_conn.close()
def f(*args):
(index, nid, (window, classify, freq)) = args
log.info('{0} create'.format(nid))
node = nd.Node(nid)
stats = []
for _ in range(window.prediction):
stats.append([0 for _ in range(window.target)])
for i in loop(window):
args = [i, classify]
df = pd.rolling_apply(node.readings.speed, len(i), rapply, args=args)
log.info('{0} {1} {2} {3}'.format(nid, i, df.sum(), df.count()))
stats[i.prediction][i.target] = df.resample(freq, how=sum)
return stats
def f(*args):
(index, nid, (window, oneday, threshold, agg)) = args
log.info('{0} create'.format(nid))
node = nd.Node(nid)
winlen = nd.winsum(window)
log.info('{0} apply'.format(nid))
#
# determine which windows constitute a traffic event
#
df = pd.rolling_apply(node.readings.speed,
winlen,
g,
min_periods=winlen,
args=[window, threshold])
df.dropna(inplace=True)
#
# aggregate the results
#
log.info('{0} aggregate'.format(nid))
if df.empty:
log.error('{0}: No observations'.format(nid))
return []
# items = zip(range(oneday), [ [] ] * oneday)
totals = OrderedDict()
for i in range(oneday):
totals[i] = [0]
for i in df.index:
key = cp.bucket(i)
totals[key].append(df.ix[i])
vals = [agg(x) for x in totals.values()]
vals.append(nid) # this is important
return vals
unpaired = []
paired = set()
symmetric = (len(ref_seqs) == 2) and (ref_seqs[0] == ref_seqs[1])
for inter in filter(lambda x: x.wc, interactions):
pairing.append(pair.Pair(inter.id1, inter.id2, pair.Pair.PTYPE_MUST))
paired.add(inter.id1)
paired.add(inter.id2)
for (chain, ref_seq) in enumerate(ref_seqs):
for (ndx, c) in enumerate(ref_seq):
id = len(nodes)
conds = map(lambda x: x.id1,
filter(lambda x: x.id2 == id, interactions))
nodes.append(node.Node(id, chain, ndx, conds))
if (id not in paired):
unpaired.append(id)
# save a definition file and set the definition input to that file
model = model.Model(name,
version,
ref_seqs,
data_sources,
nodes,
None,
pairing,
unpaired,
None,
sep_min=4,