def sp_process_binary(self, trail):
""" Binarily vectorizing the trail
"""
spvec = SparseVector([len(self.namespace), self.veclen])
rveclist = list()
vadd = rveclist.append
kadd = spvec.keys.append
sortkey = lambda x: self.namespace.index(x['poi'])
groupkey = lambda x: x['poi']
sortedtrail = sorted(trail, key=sortkey)
for poi, checkins in itertools.groupby(sortedtrail, key=groupkey):
kadd(self.namespace.index(poi))
ticks = [self.get_timeslot(c['tick']) for c in checkins]
arr = NP.zeros(self.veclen)
arr[ticks] = 1
vadd(arr)
spvec.rvecs = NP.array(rveclist, dtype=NP.float32)
return spvec
def sp_process(self, trail):
""" accumulating gaussian shaped function
"""
spvec = SparseVector([len(self.namespace), self.veclen])
rveclist = list()
vadd = rveclist.append
kadd = spvec.keys.append
sortkey = lambda x: self.namespace.index(x['poi'])
groupkey = lambda x: x['poi']
sortedtrail = sorted(trail, key=sortkey)
for poi, checkins in itertools.groupby(sortedtrail, key=groupkey):
kadd(self.namespace.index(poi))
ticks = [self.get_seconds(c['tick']) for c in checkins]
vadd(kernel_smooth(self.axis,
ticks,
self.params,
aggr=self.aggr,
kernel=self.kernel))
spvec.rvecs = NP.array(rveclist, dtype=NP.float32)
if self.normalized:
NP.add(spvec.rvecs, EPSILON, spvec.rvecs) # insure not divided by zero
unity = NP.sum(spvec.rvecs, axis=0)
NP.divide(spvec.rvecs, unity, spvec.rvecs)
return spvec
