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 load_pops(start_time, limit = None):
date_str = dt_as_str(start_time)
popfn = '/'.join([_pop_dir, date_str+'.p'])
doc = load_obj(popfn)
if limit is not None:
return doc['new_ancestors'], doc['descendants']
else:
return doc['new_ancestors'][:limit], doc['descendants'][:limit]
def load_pops(start_time, limit=None):
date_str = dt_as_str(start_time)
popfn = '/'.join([_pop_dir, date_str + '.p'])
doc = load_obj(popfn)
if limit is not None:
return doc['new_ancestors'], doc['descendants']
else:
return doc['new_ancestors'][:limit], doc['descendants'][:limit]
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_pops_over_time(db, time_pairs, outdir, limit=None, mark = False):
times = []
popsizes = []
for (time_0, time_1) in time_pairs:
if mark:
ancestors, new_descendants = map(list, get_anc_dec_mark(db, time_0, time_1, limit))
else:
ancestors, new_descendants = map(list, get_anc_dec_noncum(db, time_0, time_1, limit))
precompute_doc = {'start': time_0, 'ancestors': ancestors, 'descendants': new_descendants}
times.append(time_0)
popsizes.append((len(ancestors), len(new_descendants)))
popfn = '/'.join([outdir, dt_as_str(time_0)+'.p'])
print "pickling population for time {} as {}".format(time_0, popfn)
pickle_obj(popfn, precompute_doc)
return times, popsizes
def dump_descendants_over_time(db, time_pairs, outdir, limit = None, debug = True):
# also returns a histogram of pop sizes.
times = []
popsizes = []
for (time_0, time_1) in time_pairs:
new_descendants = list(get_new_descendants(db, time_0, time_1, limit))
precompute_doc = {'start': time_0, 'descendants': new_descendants}
print "number of descendants at time {}: {}".format(time_0, len(new_descendants))
times.append(time_0)
popsizes.append(len(new_descendants))
if debug:
precompute_doc['descendants'] = len(new_descendants)
pprint(precompute_doc)
else:
popfn = '/'.join([outdir, dt_as_str(time_0)+'.p'])
print "pickling population for time {} as {}".format(time_0, popfn)
pickle_obj(popfn, precompute_doc)
return times, popsizes
def load_anc_dec(start_date, indir):
""" Load two lists of patents; ancestral and descendant poulation respectively. """
filename = '/'.join([indir, dt_as_str(start_date)+'.p'])
pop_dict = load_obj(filename)
assert(start_date == pop_dict['start']) # Make sure the date we think we're loading matches the stored date.
return pop_dict['ancestors'], pop_dict['descendants']
def load_pop(start_date):
""" Load a list of patents (dictionaries) occuring in the month following the given start_date."""
filename = '/'.join([_pop_dir, dt_as_str(start_date)+'.p'])
pop_dict = load_obj(filename)
assert(start_date == pop_dict['start']) # Make sure the date we think we're loading matches the stored date.
return pop_dict['descendants']
