def user_important_rank_test(date, window_size):
date_time = datetime2ts(date)
uid_active = {}
if window_size == 1:
db_name = get_leveldb('important', date_time)
daily_user_active_bucket = leveldb.LevelDB(os.path.join(LEVELDBPATH, db_name),
block_cache_size=8 * (2 << 25), write_buffer_size=8 * (2 << 25))
for uid, active in daily_user_active_bucket.RangeIter():
uid = int(uid)
active = float(active)
uid_active[uid] = active
else:
for i in range(window_size):
db_name = get_leveldb('active', date_time - i*24*60*60)
daily_user_active_bucket = leveldb.LevelDB(os.path.join(LEVELDBPATH, db_name),
block_cache_size=8 * (2 << 25), write_buffer_size=8 * (2 << 25))
for uid, active in daily_user_active_bucket.RangeIter():
uid = int(uid)
active = float(active)
if uid not in uid_active:
uid_active[uid] = 0
uid_active[uid] += active
sorted_uids = user_rank(uid_active, 'important', 500, date, window_size)
for uid in sorted_uids[:5]:
print uid
def burst_important_task(top_n, date, window_size):
date_time = datetime2ts(date)
uid_important = {}
db_name = get_leveldb('important', date_time)
previous_db_name = get_leveldb('important', date_time-window2time(window_size))
daily_user_important_bucket = leveldb.LevelDB(os.path.join(LEVELDBPATH, db_name),
block_cache_size=8 * (2 << 25), write_buffer_size=8 * (2 << 25))
previous_daily_user_important_bucket = leveldb.LevelDB(os.path.join(LEVELDBPATH, previous_db_name),
block_cache_size=8 * (2 << 25), write_buffer_size=8 * (2 << 25))
for uid, important in daily_user_important_bucket.RangeIter():
uid = int(uid)
important = float(important)
try:
previous_important = float(previous_daily_user_important_bucket.Get(str(uid)))
except:
previous_important = 0
uid_important[uid] = math.fabs(important - previous_important)
if len(uid_important) < 100000000:
sorted_uid_important = sorted(uid_important.iteritems(), key=operator.itemgetter(1), reverse=True)
sorted_uids = []
count = 0
for uid, value in sorted_uid_important:
if count >= top_n:
break
sorted_uids.append(uid)
count += 1
else:
sorted_uids = user_rank(uid_important, 'whole_active', top_n, date, window_size)
return sorted_uids
def important_rank(top_n, date, window_size):
date_time = datetime2ts(date)
uid_important = {}
if window_size == 1:
db_name = get_leveldb('important', date_time)
daily_user_important_bucket = leveldb.LevelDB(os.path.join(LEVELDBPATH, db_name),
block_cache_size=8 * (2 << 25), write_buffer_size=8 * (2 << 25))
count = 0
for uid, important in daily_user_important_bucket.RangeIter():
count = count + 1
print count
uid = int(uid)
important = float(important)
uid_important[uid] = important
else:
for i in range(window_size):
db_name = get_leveldb('important', date_time - i*24*60*60)
daily_user_important_bucket = leveldb.LevelDB(os.path.join(LEVELDBPATH, db_name),
block_cache_size=8 * (2 << 25), write_buffer_size=8 * (2 << 25))
for uid, important in daily_user_important_bucket.RangeIter():
uid = int(uid)
important = float(important)
if uid not in uid_important:
uid_important[uid] = 0
uid_important[uid] += important
if len(uid_important) < 100000000:
sorted_uid_important = sorted(uid_important.iteritems(), key=operator.itemgetter(1), reverse=True)
sorted_uids = []
count = 0
for uid, value in sorted_uid_important:
if is_in_trash_list(uid):
continue
if count >= top_n:
break
sorted_uids.append(uid)
count += 1
else:
sorted_uids = user_rank(uid_important, 'whole_active', top_n, date, window_size)
return sorted_uids
def whole_active_task(top_n, date, window_size):
date_time = datetime2ts(date)
uid_active = {}
if window_size == 1:
db_name = get_leveldb('active', date_time)
daily_user_active_bucket = leveldb.LevelDB(os.path.join(LEVELDBPATH, db_name),
block_cache_size=8 * (2 << 25), write_buffer_size=8 * (2 << 25))
for uid, active in daily_user_active_bucket.RangeIter():
uid = int(uid)
active = float(active)
uid_active[uid] = active
else:
for i in range(window_size):
db_name = get_leveldb('active', date_time - i*24*60*60)
daily_user_active_bucket = leveldb.LevelDB(os.path.join(LEVELDBPATH, db_name),
block_cache_size=8 * (2 << 25), write_buffer_size=8 * (2 << 25))
for uid, active in daily_user_active_bucket.RangeIter():
uid = int(uid)
active = float(active)
if uid not in uid_active:
uid_active[uid] = 0
uid_active[uid] += active
if len(uid_active) < 100000000:
sorted_uid_active = sorted(uid_active.iteritems(), key=operator.itemgetter(1), reverse=True)
sorted_uids = []
count = 0
for uid, value in sorted_uid_active:
if count >= top_n:
break
sorted_uids.append(uid)
count += 1
else:
sorted_uids = user_rank(uid_active, 'whole_active', top_n, date, window_size)
return sorted_uids
def rank_simulation(uid_value):
date = '2012-12-22'
window_size = 1
sorted_uids = user_rank(uid_value, 'test', 500, date, window_size)