def main_both():
""" Runs the GPE calculation for the whole population, for each docvec trait."""
db = MongoClient().patents
oneweek = timedelta(days=7)
mindate = list(
db.traits.find({
'isd': {
'$exists': True
}
}).sort('isd', 1).limit(1))[0]['isd']
maxdate = list(
db.traits.find({
'isd': {
'$exists': True
}
}).sort('isd', -1).limit(1))[0]['isd']
old_ancestors = []
gpes_tfidf = {}
gpes_docvec = {}
for (t1, _, _) in step_through_time(mindate, maxdate, oneweek):
logging.info(
"computing gpe for time {}, both tf-idf and w2v".format(t1))
gpe_dict_w2v, new_ancestors = gpe_multi_threaded(
t1, 'w2v', _docvec_traits, None, old_ancestors)
gpe_dict_tfidf, _ = gpe_multi(
t1, 'tf-idf', _tfidf_traits, None,
old_ancestors) # multithreading Not worth overhead for tfidf.
gpes_docvec[t1] = gpe_dict_w2v[t1]
gpes_tfidf[t1] = gpe_dict_tfidf[t1]
old_ancestors = old_ancestors + new_ancestors
return gpes_tfidf, gpes_docvec
def main_docvec():
""" Runs the GPE calculation for the whole population, for each docvec trait."""
db = MongoClient().patents
oneweek = timedelta(days=7)
mindate = list(
db.traits.find({
'isd': {
'$exists': True
}
}).sort('isd', 1).limit(1))[0]['isd']
maxdate = list(
db.traits.find({
'isd': {
'$exists': True
}
}).sort('isd', -1).limit(1))[0]['isd']
trait_type = 'w2v'
traits = _docvec_traits
old_ancestors = []
gpes = {}
for (t1, _, _) in step_through_time(mindate, maxdate, oneweek):
logging.info("computing gpe for time {}".format(t1))
gpe_dict, new_ancestors = gpe_multi(t1, trait_type, traits, None,
old_ancestors)
gpes[t1] = gpe_dict[t1]
old_ancestors = old_ancestors + new_ancestors
return gpes
def test_docvec(time_limit=20, pop_limit=50000):
""" Runs the GPE calculation on a subset of each population in the time window 1976-2014, for the tf-idf trait 'dna'. """
db = MongoClient().patents
oneweek = timedelta(days=7)
mindate = list(
db.traits.find({
'isd': {
'$exists': True
}
}).sort('isd', 1).limit(1))[0]['isd']
maxdate = list(
db.traits.find({
'isd': {
'$exists': True
}
}).sort('isd', -1).limit(1))[0]['isd']
trait_type = 'w2v'
traits = _docvec_traits
old_ancestors = []
gpes = {}
for (t1, _, _) in step_through_time(mindate, maxdate,
oneweek)[:time_limit]:
logging.info("computing gpe for time {}".format(t1))
gpe_dict, new_ancestors = gpe_multi(t1, trait_type, traits, pop_limit,
old_ancestors)
gpes[t1] = gpe_dict[t1]
old_ancestors = old_ancestors + new_ancestors
return gpes
def tester_mp():
db = MongoClient().patents
oneweek = timedelta(days=7)
mindate = list(
db.traits.find({
'isd': {
'$exists': True
}
}).sort('isd', 1).limit(1))[0]['isd']
maxdate = list(
db.traits.find({
'isd': {
'$exists': True
}
}).sort('isd', -1).limit(1))[0]['isd']
trait_type = 'w2v'
traits = list(set(_docvec_traits))
old_ancestors = []
gpes = {}
for (t1, _, _) in step_through_time(mindate, maxdate, oneweek)[:10]:
logging.info("computing gpe for time {}".format(t1))
gpe_dict, new_ancestors = gpe_multi_threaded(t1, trait_type, traits,
None, old_ancestors)
gpes[t1] = gpe_dict[t1]
old_ancestors = old_ancestors + new_ancestors
return gpes
def dump_populations(db,
start,
end,
outdir,
delta=timedelta(days=7),
lim=100,
debug=True):
""" Step through time, maintaining the known ancestral population at each time step. Save each
set of populations as a pickled dictionary."""
for (tm1, t, tp1) in step_through_time(start, end):
new_ancestors, descendants = get_populations(db, tm1, t, tp1, lim)
precompute_doc = {
'_id': tm1,
'new_ancestors': list(new_ancestors),
'descendants': list(descendants)
}
if debug:
precompute_doc['new_ancestors'] = len(
precompute_doc['new_ancestors'])
precompute_doc['descendants'] = len(precompute_doc['descendants'])
pprint(precompute_doc)
else:
popfn = '/'.join([outdir, dt_as_str(tm1) + '.p'])
print "pickling population for time {} as {}".format(tm1, popfn)
print "#new ancestors: {}, #descendants:{}".format(
len(precompute_doc['new_ancestors']),
len(precompute_doc['descendants']))
pickle_obj(popfn, precompute_doc)
def dump_populations(db, start, end, outdir, delta=timedelta(days=7),lim=100, debug=True):
""" Step through time, maintaining the known ancestral population at each time step. Save each
set of populations as a pickled dictionary."""
for (tm1, t, tp1) in step_through_time(start, end):
new_ancestors, descendants = get_populations(db, tm1, t, tp1, lim)
precompute_doc = {'_id': tm1, 'new_ancestors': list(new_ancestors), 'descendants': list(descendants)}
if debug:
precompute_doc['new_ancestors'] = len(precompute_doc['new_ancestors'])
precompute_doc['descendants'] = len(precompute_doc['descendants'])
pprint(precompute_doc)
else:
popfn = '/'.join([outdir, dt_as_str(tm1)+'.p'])
print "pickling population for time {} as {}".format(tm1, popfn)
print "#new ancestors: {}, #descendants:{}".format(len(precompute_doc['new_ancestors']), len(precompute_doc['descendants']))
pickle_obj(popfn, precompute_doc)
def tester_mp():
db = MongoClient().patents
oneweek = timedelta(days=7)
mindate = list(db.traits.find({'isd': {'$exists': True}}).sort('isd', 1).limit(1))[0]['isd']
maxdate = list(db.traits.find({'isd': {'$exists': True}}).sort('isd', -1).limit(1))[0]['isd']
trait_type = 'w2v'
traits = list(set(_docvec_traits))
old_ancestors = []
gpes = {}
for (t1,_,_) in step_through_time(mindate,maxdate,oneweek)[:10]:
logging.info("computing gpe for time {}".format(t1))
gpe_dict, new_ancestors = gpe_multi_threaded(t1, trait_type, traits, None, old_ancestors)
gpes[t1] = gpe_dict[t1]
old_ancestors = old_ancestors + new_ancestors
return gpes
def main_docvec():
""" Runs the GPE calculation for the whole population, for each docvec trait."""
db = MongoClient().patents
oneweek = timedelta(days=7)
mindate = list(db.traits.find({'isd': {'$exists': True}}).sort('isd', 1).limit(1))[0]['isd']
maxdate = list(db.traits.find({'isd': {'$exists': True}}).sort('isd', -1).limit(1))[0]['isd']
trait_type = 'w2v'
traits = _docvec_traits
old_ancestors = []
gpes = {}
for (t1,_,_) in step_through_time(mindate,maxdate,oneweek):
logging.info("computing gpe for time {}".format(t1))
gpe_dict, new_ancestors = gpe_multi(t1, trait_type, traits, None, old_ancestors)
gpes[t1] = gpe_dict[t1]
old_ancestors = old_ancestors + new_ancestors
return gpes
def test_docvec(time_limit=20, pop_limit = 50000):
""" Runs the GPE calculation on a subset of each population in the time window 1976-2014, for the tf-idf trait 'dna'. """
db = MongoClient().patents
oneweek = timedelta(days=7)
mindate = list(db.traits.find({'isd': {'$exists': True}}).sort('isd', 1).limit(1))[0]['isd']
maxdate = list(db.traits.find({'isd': {'$exists': True}}).sort('isd', -1).limit(1))[0]['isd']
trait_type = 'w2v'
traits = _docvec_traits
old_ancestors = []
gpes = {}
for (t1,_,_) in step_through_time(mindate,maxdate,oneweek)[:time_limit]:
logging.info("computing gpe for time {}".format(t1))
gpe_dict, new_ancestors = gpe_multi(t1, trait_type, traits, pop_limit, old_ancestors)
gpes[t1] = gpe_dict[t1]
old_ancestors = old_ancestors + new_ancestors
return gpes
def main_both():
""" Runs the GPE calculation for the whole population, for each docvec trait."""
db = MongoClient().patents
oneweek = timedelta(days=7)
mindate = list(db.traits.find({'isd': {'$exists': True}}).sort('isd', 1).limit(1))[0]['isd']
maxdate = list(db.traits.find({'isd': {'$exists': True}}).sort('isd', -1).limit(1))[0]['isd']
old_ancestors = []
gpes_tfidf = {}
gpes_docvec = {}
for (t1,_,_) in step_through_time(mindate,maxdate,oneweek):
logging.info("computing gpe for time {}, both tf-idf and w2v".format(t1))
gpe_dict_w2v, new_ancestors = gpe_multi_threaded(t1, 'w2v', _docvec_traits, None, old_ancestors)
gpe_dict_tfidf, _ = gpe_multi(t1, 'tf-idf', _tfidf_traits, None, old_ancestors) # multithreading Not worth overhead for tfidf.
gpes_docvec[t1] = gpe_dict_w2v[t1]
gpes_tfidf[t1] = gpe_dict_tfidf[t1]
old_ancestors = old_ancestors + new_ancestors
return gpes_tfidf, gpes_docvec