def main():
"""Main loop started from command line"""
no_broadcast, current_datetime = parse_args()
if current_datetime is None:
current_datetime = pd.datetime.utcnow()
else:
current_datetime = pd.to_datetime(current_datetime)
data_directory = os.path.join(config.PROJECT_DIRECTORY, 'scraped_data')
model_directoy = os.path.join(config.PROJECT_DIRECTORY, 'trained_models')
log_directory = os.path.join(config.PROJECT_DIRECTORY, 'logs')
configure_logging(log_directory, current_datetime)
logger.info('STARTING main script at {}'.format(current_datetime))
if no_broadcast:
logger.info('Run without broadcasting.')
else:
logger.info('ATTENTION I WILL BROADCAST TO STEEMIT!!!')
time.sleep(2)
steem = MPSteem(nodes=config.NODES, no_broadcast=no_broadcast)
# To post stuff
account = config.ACCOUNT
poster = Poster(account=account, steem=steem)
prediction_frame = tpgd.scrape_hour_data(steem=steem,
current_datetime=current_datetime,
ncores=32,
offset_hours=2)
prediction_frame = tppp.preprocess(prediction_frame, ncores=8)
permalink = 'daily-truffle-picks-2018-03-27'
overview_permalink = 'weekly-truffle-updates-2018-12'
logger.info('Computing the top trending without bidbots')
logger.info('Searching for bid bots and bought votes')
min_datetime = prediction_frame.created.min()
max_datetime = prediction_frame.created.max() + pd.Timedelta(days=1)
upvote_payments, bots = tpad.get_upvote_payments_to_bots(steem=steem,
min_datetime=min_datetime,
max_datetime=max_datetime)
logger.info('Adjusting votes and reward')
sorted_frame = tppp.compute_bidbot_correction(post_frame=prediction_frame,
upvote_payments=upvote_payments)
tt0b.create_trending_post(sorted_frame,
upvote_payments=upvote_payments,
poster=poster,
topN_permalink=permalink,
overview_permalink=overview_permalink,
current_datetime=current_datetime,
bots=bots)
logger.info('DONE at {}'.format(current_datetime))
def test_logging_config(temp_dir):
assert len(os.listdir(temp_dir)) == 0
tfut.configure_logging(temp_dir, pd.datetime.utcnow())
logging.getLogger().info('foobar')
assert len(os.listdir(temp_dir)) == 1
def large_mp_preprocess(log_directory, current_datetime, steem, data_directory,
days, offset_days):
"""Helper function to spawn in child process"""
configure_logging(log_directory, current_datetime)
post_frame = tpgd.load_or_scrape_training_data(steem, data_directory,
current_datetime=current_datetime,
days=days,
offset_days=offset_days,
ncores=32)
return tppp.preprocess(post_frame, ncores=8)
def main():
"""Main loop started from command line"""
no_broadcast, current_datetime = parse_args()
if current_datetime is None:
current_datetime = pd.datetime.utcnow()
else:
current_datetime = pd.to_datetime(current_datetime)
data_directory = os.path.join(config.PROJECT_DIRECTORY, 'scraped_data')
model_directoy = os.path.join(config.PROJECT_DIRECTORY, 'trained_models')
log_directory = os.path.join(config.PROJECT_DIRECTORY, 'logs')
configure_logging(log_directory, current_datetime)
logger.info('STARTING main script at {}'.format(current_datetime))
if no_broadcast:
logger.info('Run without broadcasting.')
else:
logger.info('ATTENTION I WILL BROADCAST TO STEEMIT!!!')
time.sleep(2)
steem = MPSteem(nodes=config.NODES, no_broadcast=no_broadcast)
# To post stuff
account = config.ACCOUNT
poster = Poster(account=account, steem=steem)
tppd.create_wallet(steem,
config.PASSWORD,
posting_key=config.POSTING_KEY,
active_key=config.ACTIVE_KEY)
pipeline = tpmo.load_or_train_pipeline(
None,
model_directoy,
current_datetime,
regressor_kwargs={},
topic_kwargs={},
targets=['adjusted_reward', 'adjusted_votes'])
overview_permalink = tppw.PERMALINK_TEMPLATE.format(
date=current_datetime.strftime('%Y-%V'))
permalink = tppd.PERMALINK_TEMPLATE.format(
date=current_datetime.strftime('%Y-%m-%d'))
logger.info('Done with normal duty, answering manual calls!')
tfod.call_a_pig(poster=poster,
pipeline=pipeline,
topN_permalink=permalink,
current_datetime=current_datetime,
offset_hours=2,
hours=24,
overview_permalink=overview_permalink)
def main():
"""Main loop started from command line"""
no_broadcast, current_datetime = parse_args()
if current_datetime is None:
current_datetime = pd.datetime.utcnow()
else:
current_datetime = pd.to_datetime(current_datetime)
data_directory = os.path.join(config.PROJECT_DIRECTORY, 'scraped_data')
model_directoy = os.path.join(config.PROJECT_DIRECTORY, 'trained_models')
log_directory = os.path.join(config.PROJECT_DIRECTORY, 'logs')
configure_logging(log_directory, current_datetime)
logger.info('STARTING main script at {}'.format(current_datetime))
if no_broadcast:
logger.info('Run without broadcasting.')
else:
logger.info('ATTENTION I WILL BROADCAST TO STEEMIT!!!')
time.sleep(2)
steem = MPSteem(nodes=config.NODES, no_broadcast=no_broadcast)
# hack to allow for payments, because of https://github.com/steemit/steem-python/issues/191
noapisteem = MPSteem(nodes=config.NODES[1:], no_broadcast=no_broadcast)
# To post stuff
account = config.ACCOUNT
poster = Poster(account=account, steem=noapisteem)
tppd.create_wallet(steem,
config.PASSWORD,
posting_key=config.POSTING_KEY,
active_key=config.ACTIVE_KEY)
logger.info('Paying out investors')
tpde.pay_delegates(
account=account,
steem=noapisteem, # use a steem instance without api.steem!
current_datetime=current_datetime)
if not tpmo.model_exists(current_datetime, model_directoy):
post_frame = load_and_preprocess_2_frames(
log_directory=log_directory,
current_datetime=current_datetime,
steem=steem,
noapisteem=noapisteem,
data_directory=data_directory)
logger.info('Garbage collecting')
gc.collect()
else:
post_frame = None
regressor_kwargs = dict(n_estimators=256,
max_leaf_nodes=5000,
max_features=0.2,
n_jobs=-1,
verbose=1,
random_state=42)
topic_kwargs = dict(num_topics=128,
no_below=7,
no_above=0.1,
ngrams=(1, 2),
keep_n=333000)
if post_frame is not None and len(post_frame) > MAX_DOCUMENTS:
logger.info('Frame has {} Documents, too many, '
'reducing to {}'.format(len(post_frame), MAX_DOCUMENTS))
post_frame.sort_values('created', inplace=True, ascending=False)
train_frame = post_frame.iloc[:MAX_DOCUMENTS, :]
else:
train_frame = post_frame
pipeline = tpmo.load_or_train_pipeline(
train_frame,
model_directoy,
current_datetime,
regressor_kwargs=regressor_kwargs,
topic_kwargs=topic_kwargs,
targets=['adjusted_reward', 'adjusted_votes'])
tpmo.log_pipeline_info(pipeline=pipeline)
overview_permalink = tppw.return_overview_permalink_if_exists(
account=account, current_datetime=current_datetime, steem=steem)
if not overview_permalink:
if post_frame is None:
logger.info('Need to reaload data for weekly overview')
post_frame = load_and_preprocess_2_frames(
log_directory=log_directory,
current_datetime=current_datetime,
steem=steem,
noapisteem=noapisteem,
data_directory=data_directory)
logger.info('I want to post my weekly overview')
overview_permalink = tppw.post_weakly_update(
pipeline=pipeline,
post_frame=post_frame,
poster=poster,
current_datetime=current_datetime)
logger.info('Garbage collecting')
del post_frame
gc.collect()
prediction_frame = tpgd.scrape_hour_data(steem=steem,
current_datetime=current_datetime,
ncores=32,
offset_hours=2)
prediction_frame = tppp.preprocess(prediction_frame, ncores=8)
sorted_frame = tpmo.find_truffles(prediction_frame,
pipeline,
account=account)
permalink = tppd.post_topN_list(sorted_frame,
poster=poster,
current_datetime=current_datetime,
overview_permalink=overview_permalink)
tppd.comment_on_own_top_list(sorted_frame,
poster=poster,
topN_permalink=permalink)
tppd.vote_and_comment_on_topK(sorted_frame,
poster=poster,
topN_permalink=permalink,
overview_permalink=overview_permalink)
logger.info('Computing the top trending without bidbots')
logger.info('Searching for bid bots and bought votes')
min_datetime = sorted_frame.created.min()
max_datetime = sorted_frame.created.max() + pd.Timedelta(days=1)
upvote_payments, bots = tpad.get_upvote_payments_to_bots(
steem=noapisteem, min_datetime=min_datetime, max_datetime=max_datetime)
logger.info('Adjusting votes and reward')
sorted_frame = tppp.compute_bidbot_correction(
post_frame=sorted_frame, upvote_payments=upvote_payments)
tt0b.create_trending_post(sorted_frame,
upvote_payments=upvote_payments,
poster=poster,
topN_permalink=permalink,
overview_permalink=overview_permalink,
current_datetime=current_datetime,
bots=bots)
logger.info('Done with normal duty, answering manual calls!')
tfod.call_a_pig(poster=poster,
pipeline=pipeline,
topN_permalink=permalink,
current_datetime=current_datetime,
offset_hours=2,
hours=24,
overview_permalink=overview_permalink)
logger.info('Cleaning up after myself')
tfut.clean_up_directory(model_directoy, keep_last=3)
tfut.clean_up_directory(data_directory, keep_last=25)
tfut.clean_up_directory(log_directory, keep_last=14)
logger.info('Preloading -8 days for later training')
tpgd.load_or_scrape_training_data(steem,
data_directory,
current_datetime=current_datetime,
days=1,
offset_days=8,
ncores=32)
logger.info('DONE at {}'.format(current_datetime))