def truth_load():
truth = dict()
# We could use Pandas' Excel functions instead, to save a dependecy, but
# this seems perhaps clearer? I may be wrong.
book = xlrd.open_workbook(args.truth)
for sheet in book.sheets():
if (args.freq == sheet.name):
headers = sheet.row_values(0)
dates = sheet.col_values(0, start_rowx=1)
date_start = to_date(book, dates[0])
date_end = to_date(book, dates[-1])
index = pd.period_range(date_start,
periods=len(dates),
freq=args.freq)
# If this fails, make sure the dates fall on the week start days you
# expect. For example, 2010-07-04 is a Sunday.
assert (date_start == index[0].to_timestamp(how='start')
and date_end == index[-1].to_timestamp(how='start'))
for (i, context) in enumerate(headers[1:], start=1):
if (len(context) == 0 or context[0] == '_'):
# not a real data series, skip
continue
data = ((j if j != '' else np.nan)
for j in sheet.col_values(i, start_rowx=1))
truth[context] = pd.Series(data, index)
args.ts_start = index[0].to_timestamp(how='start')
args.ts_end = (index[-1].to_timestamp(how='end') +
datetime.timedelta(days=1) -
datetime.timedelta(microseconds=1))
l.info(' periods: %d' % len(index))
l.info(' start: %s (%s)' %
(args.ts_start, args.ts_start.strftime('%A')))
l.info(' end: %s (%s)' %
(args.ts_end, args.ts_end.strftime('%A')))
break
df = pd.DataFrame(truth, index=index)
u.pickle_dump('%s/truth' % args.outdir, df)
return df
def truth_load():
truth = dict()
# We could use Pandas' Excel functions instead, to save a dependecy, but
# this seems perhaps clearer? I may be wrong.
book = xlrd.open_workbook(args.truth)
for sheet in book.sheets():
if (args.freq == sheet.name):
headers = sheet.row_values(0)
dates = sheet.col_values(0, start_rowx=1)
date_start = to_date(book, dates[0])
date_end = to_date(book, dates[-1])
index = pd.period_range(date_start, periods=len(dates), freq=args.freq)
# If this fails, make sure the dates fall on the week start days you
# expect. For example, 2010-07-04 is a Sunday.
assert ( date_start == index[0].to_timestamp(how='start')
and date_end == index[-1].to_timestamp(how='start'))
for (i, context) in enumerate(headers[1:], start=1):
if (len(context) == 0 or context[0] == '_'):
# not a real data series, skip
continue
data = ((j if j != '' else np.nan)
for j in sheet.col_values(i, start_rowx=1))
truth[context] = pd.Series(data, index)
args.ts_start = index[0].to_timestamp(how='start')
args.ts_end = (index[-1].to_timestamp(how='end')
+ datetime.timedelta(days=1)
- datetime.timedelta(microseconds=1))
l.info(' periods: %d' % len(index))
l.info(' start: %s (%s)' % (args.ts_start,
args.ts_start.strftime('%A')))
l.info(' end: %s (%s)' % (args.ts_end,
args.ts_end.strftime('%A')))
break
df = pd.DataFrame(truth, index=index)
u.pickle_dump('%s/truth' % args.outdir, df)
return df
def pickle_dump(name, tag, data):
if (tag is not None):
tag = '.' + tag
else:
tag = ''
u.pickle_dump('%s/%s,%d%s' % (args.out, name, args.distance, tag), data)
def dump(kv):
(name, data) = kv
u.pickle_dump('%s/%s.%s' % (args_b.value.outdir, name, tag), data)
def dump(self, dir_):
u.pickle_dump('%s/model.%d' % (dir_, self.i), self.model)
u.pickle_dump('%s/results.%d' % (dir_, self.i), self.results)
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 pickle_dump(name, tag, data):
if (tag is not None):
tag = '.' + tag
else:
tag = ''
u.pickle_dump('%s/%s,%d%s' % (args.out, name, args.distance, tag), data)
class Test_Sequence(object):
def __init__(self, args):
self.args = args
@property
def first_good_test(self):
# Any attempted test will give us what we need, but an arbitrary
# number of tests might not have been attempted.
return next(itertools.ifilter(lambda t: t.attempted, self.schedule))
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()
# 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 = u.memory_use(True)
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 dump(self, dir_):
u.pickle_dump('%s/model.%d' % (dir_, self.i), self.model)
u.pickle_dump('%s/results.%d' % (dir_, self.i), self.results)
def dump(kv):
(name, data) = kv
u.pickle_dump('%s/%s.%s' % (args_b.value.outdir, name, tag), data)
