class SubmissionTarget(luigi.target.Target):
"""
Implements a submission target to "output" predictions from luigi tasks on
the numer.ai servers.
"""
def __init__(self, path, public_id, secret):
"""
Creates a new SubmissionTarget.
:param: path (str):
local path to the predictions csv file
:param: public_id (str):
public_id as reported by the numer.ai website when creating API
credentials
:param: secret (str):
secret as reported by the numer.ai website when creating API
credentials
"""
self.path = path
self.fn = os.path.split(path)[1]
self.apc = NumerAPI(public_id, secret)
def exists(self):
"""
Checks if a submission for the file named :py:attr:`path` was uploaded.
NB: the filename as reported by the server is appended by a random
string (before the file extension), and we can just access the file
that was submitted last. This might result in double uploads for the
same file.
"""
qry = "query user { user { latestSubmission { filename } } }"
res = self.apc.raw_query(qry, authorization=True)
data = res['data']['user']['latestSubmission']
for d in data:
if d['filename'].startswith(self.fn.replace('.csv', '')):
return True
return False
def submit(self):
"""
Submits the predictions to the numer.ai servers and tries to report
back the status.
"""
ret = self.apc.upload_predictions(self.path)
print(self.apc.submission_status())
def main():
# set example username and round
example_public_id = "somepublicid"
example_secret_key = "somesecretkey"
# some API calls do not require logging in
napi = NumerAPI(verbosity="info")
# download current dataset
napi.download_current_dataset(unzip=True)
# get competitions
all_competitions = napi.get_competitions()
# get leaderboard for the current round
leaderboard = napi.get_leaderboard()
# leaderboard for a historic round
leaderboard_67 = napi.get_leaderboard(round_num=67)
# provide api tokens
napi = NumerAPI(example_public_id, example_secret_key)
# upload predictions
submission_id = napi.upload_predictions("mypredictions.csv")
# check submission status
napi.submission_status()
def main():
# set example username and round
example_username = "******"
example_round = 51
# set up paths for download of dataset and upload of predictions
now = datetime.now().strftime("%Y%m%d")
dataset_parent_folder = "./dataset"
dataset_name = "numerai_dataset_{0}/example_predictions.csv".format(now)
dataset_path = "{0}/{1}".format(dataset_parent_folder, dataset_name)
# most API calls do not require logging in
napi = NumerAPI(verbosity="info")
# log in
credentials = napi.login()
print(json.dumps(credentials, indent=2))
# download current dataset
dl_succeeded = napi.download_current_dataset(
dest_path=dataset_parent_folder, unzip=True)
print("download succeeded: " + str(dl_succeeded))
# get competitions (returned data is too long to print practically)
# all_competitions = napi.get_all_competitions()
# current_competition = napi.get_competition()
# example_competition = napi.get_competition(round_id=example_round)
# get user earnings per round
user_earnings = napi.get_earnings_per_round()
print("user earnings:")
print(user_earnings)
example_earnings = napi.get_earnings_per_round(username=example_username)
print("example earnings:")
print(example_earnings)
# get scores for user
personal_scores = napi.get_scores_for_user()
print("personal scores:")
print(personal_scores)
other_scores = napi.get_scores_for_user(username=example_username)
print("other scores:")
print(other_scores)
# get user information
current_user = napi.get_user()
print("current user:"******"example user:"******"submission:")
print(json.dumps(submission, indent=2))
# upload predictions
ul_succeeded = napi.upload_predictions(dataset_path)
print("upload succeeded: " + str(ul_succeeded))
class Evaluator(threading.Thread):
def __init__(self):
super(Evaluator, self).__init__()
self.logger = logging.getLogger('evaluator')
self.logger.setLevel(logging.DEBUG)
self.login()
def login(self):
public_id = os.environ['PUBLIC_ID']
private_secret = os.environ['PRIVATE_SECRET']
while True:
try:
self.napi = NumerAPI(public_id, private_secret)
break
except Exception:
self.logger.exception('Login failed')
time.sleep(10)
def upload(self, prediction):
while True:
try:
self.logger.info('Uploading prediction: {}'.format(prediction))
self.napi.upload_predictions(file_path=prediction)
self.logger.info('Uploaded prediction: {}'.format(prediction))
break
except requests.exceptions.HTTPError as error:
if error.response.status_code == 429:
self.logger.info('Backing off')
time.sleep(30 * 60)
else:
self.logger.exception('Network failure')
time.sleep(60)
except Exception as exception:
self.logger.exception('Upload failure')
time.sleep(10)
def check(self, prediction):
while True:
try:
self.logger.info('Checking submission: {}'.format(prediction))
status = self.napi.submission_status()
self.logger.info('Got {}: {}'.format(prediction, str(status)))
logloss_ready = status['validation_logloss'] is not None
concordance_ready = not status['concordance']['pending']
originality_ready = not status['originality']['pending']
if logloss_ready and concordance_ready and originality_ready:
return status
else:
time.sleep(10)
except Exception:
self.logger.exception('Checking submission failed')
time.sleep(10)
def report(self, prediction, status):
result = {
'logloss': status['validation_logloss'],
'consistency': status['consistency'],
'concordance': status['concordance']['value'],
'originality': status['originality']['value']
}
with open(prediction + '.report.json', 'wb') as handle:
handle.write(json.dumps(result).encode('utf-8'))
def submit(self, prediction):
self.upload(prediction)
time.sleep(5)
self.report(prediction, self.check(prediction))
def run(self):
captor = Captor(os.getenv('STORING'), 'predictions*.csv')
while True:
while not captor.empty():
prediction = captor.grab()
if not os.path.isfile(prediction + '.report.json'):
self.submit(prediction)
time.sleep(1)