def do_test(self, m_class, db, args, i):
self.i = i
# create tokenizer
tzer = u.class_by_name(args.tokenizer)(args.ngram)
# load training & testing tweets from database
exu = None if args.dup_users else set()
(tr_tweets, tr_users) = self.fetch(db, args.srid, 'training', tzer,
args.fields, args.unify_fields, exu)
exu = None if args.dup_users else tr_users
(te_tweets, _) = self.fetch(db, args.srid, 'testing', tzer,
args.fields, args.unify_fields, exu)
if (not args.skip_small_tests or
self.enough_data_p(len(tr_tweets), len(te_tweets))):
self.attempted = True
else:
l.info('insufficient data, skipping test %s ' % (self))
self.attempted = False
self.results = []
return
# tokenize training tweets
tr_tokens = self.group_tokens(tr_tweets,
args.trim_head, args.min_instances)
self.train_tweet_ct = len(tr_tweets)
self.train_token_ct = len(tr_tokens)
# downsample test tweets
if (len(te_tweets) > args.test_tweet_limit):
te_tweets = u.rand.sample(te_tweets, args.test_tweet_limit)
l.info('sampled %d test tweets per --test-tweet-limit'
% (args.test_tweet_limit))
self.test_tweet_ct = len(te_tweets)
# build model
self.model = m_class(tr_tokens, args.srid, tr_tweets)
l.debug('starting model build')
t_start = time.time()
self.model.build()
l.info('built model in %s' % (u.fmt_seconds(time.time() - t_start)))
t_start = time.time()
# test 'em
self.results = multicore.do(test_tweet,
(self.model, args.fields), te_tweets)
l.info('tested tweets in %s' % (u.fmt_seconds(time.time() - t_start)))
def do_test(self, m_class, db, args, i):
self.i = i
# create tokenizer
tzer = u.class_by_name(args.tokenizer)(args.ngram)
# load training & testing tweets from database
exu = None if args.dup_users else set()
(tr_tweets, tr_users) = self.fetch(db, args.srid, 'training', tzer,
args.fields, args.unify_fields, exu)
exu = None if args.dup_users else tr_users
(te_tweets, _) = self.fetch(db, args.srid, 'testing', tzer,
args.fields, args.unify_fields, exu)
if (not args.skip_small_tests
or self.enough_data_p(len(tr_tweets), len(te_tweets))):
self.attempted = True
else:
l.info('insufficient data, skipping test %s ' % (self))
self.attempted = False
self.results = []
return
# tokenize training tweets
tr_tokens = self.group_tokens(tr_tweets, args.trim_head,
args.min_instances)
self.train_tweet_ct = len(tr_tweets)
self.train_token_ct = len(tr_tokens)
# downsample test tweets
if (len(te_tweets) > args.test_tweet_limit):
te_tweets = u.rand.sample(te_tweets, args.test_tweet_limit)
l.info('sampled %d test tweets per --test-tweet-limit' %
(args.test_tweet_limit))
self.test_tweet_ct = len(te_tweets)
# build model
self.model = m_class(tr_tokens, args.srid, tr_tweets)
l.debug('starting model build')
t_start = time.time()
self.model.build()
l.info('built model in %s' % (u.fmt_seconds(time.time() - t_start)))
t_start = time.time()
# test 'em
self.results = multicore.do(test_tweet, (self.model, args.fields),
te_tweets)
l.info('tested tweets in %s' % (u.fmt_seconds(time.time() - t_start)))
def main(self):
u.memory_use_log()
t_start = time.time()
db = db_glue.DB(self.args.database_file)
l.info('opened database %s' % (self.args.database_file))
assert (db.metadata_get('schema_version') == '5')
# normalize start and end times
if (self.args.start is None):
sql = 'SELECT min(created_at) AS "st [timestamp]" FROM tweet'
self.args.start = db.sql(sql)[0]['st']
if (self.args.end is None):
sql = 'SELECT max(created_at) AS "et [timestamp]" FROM tweet'
# add one second because end time is exclusive
self.args.end = db.sql(sql)[0]['et'] + timedelta(seconds=1)
self.args.start = time_.as_utc(self.args.start)
self.args.end = time_.as_utc(self.args.end)
# print test sequence parameters
self.log_parameters()
# set up model parameters
model_class = u.class_by_name(self.args.model)
model_class.parms_init(self.args.model_parms, log_parms=True)
# build schedule
self.schedule_build(self.args.limit)
l.info('scheduled %s tests (%s left over)'
% (len(self.schedule), self.args.end - self.schedule[-1].end))
if (not os.path.exists(self.args.output_dir)):
os.mkdir(self.args.output_dir)
l.info('results in %s' % (self.args.output_dir))
# testing loop
for (i, t) in enumerate(self.schedule):
if (i+1 < self.args.start_test):
l.info('using saved test %d per --start-test' % (i+1))
l.warning('token and tweet counts will be incorrect')
# FIXME: hack.....
try:
t.model = u.Deleted_To_Save_Memory()
t.results = u.Deleted_To_Save_Memory()
t.i = i
t.train_tweet_ct = -1e6
t.train_token_ct = -1e6
t.test_tweet_ct = -1e6
t.unshrink_from_disk(self.args.output_dir, results=True)
t.attempted = True
except IOError, x:
if (x.errno != 2):
raise
t.attempted = False
else:
l.info('starting test %d of %d: %s' % (i+1, len(self.schedule), t))
t.do_test(model_class, db, self.args, i)
t.summarize()
if (t.attempted):
if (self.args.profile_memory):
# We dump a memory profile here because it's the high water
# mark; we're about to reduce usage significantly.
import meliae.scanner as ms
filename = 'memory.%d.json' % (i)
l.info('dumping memory profile %s' % (filename))
ms.dump_all_objects('%s/%s' % (self.args.output_dir, filename))
t.shrink_to_disk(self.args.output_dir)
l.debug('result: %s' % (t.summary))
u.memory_use_log()
def main(self):
u.memory_use_log()
t_start = time.time()
# Replaced with self.cur in __init__
# db = db_glue.DB(self.args.database_file)
# assert (db.metadata_get('schema_version') == '5')
# normalize start and end times
if (self.args.start is None):
sql = 'SELECT min(created_at) AS st FROM {0};'.format(self.table)
self.cur.execute(sql)
self.args.start = self.cur.fetchone()[0]
if (self.args.end is None):
sql = 'SELECT max(created_at) AS et FROM {0};'.format(self.table)
self.cur.execute(sql)
# add one second because end time is exclusive
self.args.end = self.cur.fetchone()[0] + timedelta(seconds=1)
self.args.start = time_.as_utc(self.args.start)
self.args.end = time_.as_utc(self.args.end)
# print test sequence parameters
self.log_parameters()
# set up model parameters
model_class = u.class_by_name(self.args.model)
model_class.parms_init(self.args.model_parms, log_parms=True)
# build schedule
self.schedule_build(self.args.limit)
l.info('scheduled %s tests (%s left over)'
% (len(self.schedule), self.args.end - self.schedule[-1].end))
if (not os.path.exists(self.args.output_dir)):
os.mkdir(self.args.output_dir)
l.info('results in %s' % (self.args.output_dir))
# testing loop
for (i, t) in enumerate(self.schedule):
if (i+1 < self.args.start_test):
l.info('using saved test %d per --start-test' % (i+1))
l.warning('token and tweet counts will be incorrect')
# FIXME: hack.....
try:
t.model = u.Deleted_To_Save_Memory()
t.results = u.Deleted_To_Save_Memory()
t.i = i
t.train_tweet_ct = -1e6
t.train_token_ct = -1e6
t.test_tweet_ct = -1e6
t.unshrink_from_disk(self.args.output_dir, results=True)
t.attempted = True
except (IOError, x):
if (x.errno != 2):
raise
t.attempted = False
else:
l.info('starting test %d of %d: %s' % (i+1, len(self.schedule), t))
t.do_test(model_class, self.cur, self.args, i)
t.summarize()
if (t.attempted):
if (self.args.profile_memory):
# We dump a memory profile here because it's the high water
# mark; we're about to reduce usage significantly.
import meliae.scanner as ms
filename = 'memory.%d.json' % (i)
l.info('dumping memory profile %s' % (filename))
ms.dump_all_objects('%s/%s' % (self.args.output_dir, filename))
t.shrink_to_disk(self.args.output_dir)
l.debug('result: %s' % (t.summary))
u.memory_use_log()
# done!
l.debug('computing summary')
self.summarize()
l.debug('summary: %s' % (self.summary))
l.debug('saving TSV results')
test_indices = u.sl_union_fromtext(len(self.schedule), ':')
self.tsv_save_tests('%s/%s' % (self.args.output_dir, 'tests.tsv'),
test_indices)
l.debug('saving pickled summary')
self.memory_use = u.memory_use()
self.memory_use_peak = "Not implemented"
self.time_use = time.time() - t_start
u.pickle_dump('%s/%s' % (self.args.output_dir, 'summary'), self)
u.memory_use_log()
l.info('done in %s' % (u.fmt_seconds(self.time_use)))
def main(self):
u.memory_use_log()
t_start = time.time()
db = db_glue.DB(self.args.database_file)
l.info('opened database %s' % (self.args.database_file))
assert (db.metadata_get('schema_version') == '5')
# normalize start and end times
if (self.args.start is None):
sql = 'SELECT min(created_at) AS "st [timestamp]" FROM tweet'
self.args.start = db.sql(sql)[0]['st']
if (self.args.end is None):
sql = 'SELECT max(created_at) AS "et [timestamp]" FROM tweet'
# add one second because end time is exclusive
self.args.end = db.sql(sql)[0]['et'] + timedelta(seconds=1)
self.args.start = time_.as_utc(self.args.start)
self.args.end = time_.as_utc(self.args.end)
# print test sequence parameters
self.log_parameters()
# set up model parameters
model_class = u.class_by_name(self.args.model)
model_class.parms_init(self.args.model_parms, log_parms=True)
# build schedule
self.schedule_build(self.args.limit)
l.info('scheduled %s tests (%s left over)' %
(len(self.schedule), self.args.end - self.schedule[-1].end))
if (not os.path.exists(self.args.output_dir)):
os.mkdir(self.args.output_dir)
l.info('results in %s' % (self.args.output_dir))
# testing loop
for (i, t) in enumerate(self.schedule):
if (i + 1 < self.args.start_test):
l.info('using saved test %d per --start-test' % (i + 1))
l.warning('token and tweet counts will be incorrect')
# FIXME: hack.....
try:
t.model = u.Deleted_To_Save_Memory()
t.results = u.Deleted_To_Save_Memory()
t.i = i
t.train_tweet_ct = -1e6
t.train_token_ct = -1e6
t.test_tweet_ct = -1e6
t.unshrink_from_disk(self.args.output_dir, results=True)
t.attempted = True
except IOError, x:
if (x.errno != 2):
raise
t.attempted = False
else:
l.info('starting test %d of %d: %s' %
(i + 1, len(self.schedule), t))
t.do_test(model_class, db, self.args, i)
t.summarize()
if (t.attempted):
if (self.args.profile_memory):
# We dump a memory profile here because it's the high water
# mark; we're about to reduce usage significantly.
import meliae.scanner as ms
filename = 'memory.%d.json' % (i)
l.info('dumping memory profile %s' % (filename))
ms.dump_all_objects('%s/%s' %
(self.args.output_dir, filename))
t.shrink_to_disk(self.args.output_dir)
l.debug('result: %s' % (t.summary))
u.memory_use_log()