from ravenpackapi import RPApi
import logging
logging.basicConfig(level=logging.DEBUG)
# initialize the API (here we use the RP_API_KEY in os.environ)
api = RPApi()
# query the json endpoint for a dataset ***
# use the public dataset with id 'us30'
ds = api.get_dataset(dataset_id='us30')
# query the dataset analytics with the json endpoint
print(ds)
data = ds.json(
start_date='2018-01-05 18:00:00',
end_date='2018-01-05 18:01:00',
)
for record in data:
print(record)
# query the ad-hoc json endpoint ***
adhoc_data = api.json(
start_date='2018-01-05 18:00:00',
end_date='2018-01-05 18:01:00',
fields=ds.fields,
filters=ds.filters,
)
print(adhoc_data)
for record in adhoc_data:
print(record)
# New video tutorials are available at https://www.microprediction.com/python-1 to help you
# get started creating streams (see the 4th module in particular)
# This might be broken
from ravenpackapi import RPApi, ApiConnectionError
logging.basicConfig(level=logging.DEBUG)
logger = logging.getLogger(__name__)
# initialize the API (here we use the RP_API_KEY in os.environ)
api = RPApi(api_key=COVID_API)
# query the realtime feed
ds = api.get_dataset(dataset_id=COVID_UUID)
def wait_between_attempts():
""" Incremental backoff between connection attempts """
wait_time = 19.3 # time is in seconds
while True:
yield wait_time
wait_time = min(wait_time * 1.5, 30)
wait_time *= (100 + random.randint(0, 50)) / 100
wait_time = wait_between_attempts()
def get_live_data_keyword_count(keywords):
"""
Download all data from the chosen dataset in a time range
Download files are compressed, and chunked per year
"""
import os
from ravenpackapi import RPApi
from ravenpackapi.util import time_intervals, SPLIT_WEEKLY
api = RPApi(api_key='YOUR_API_KEY')
ds = api.get_dataset('YOUR_DATASET_ID')
start_date = '2018-01-01'
end_date = '2018-01-10'
GET_COMPRESSED = True
output_folder = './output'
os.makedirs(output_folder, exist_ok=True) # create folder for output
for range_start, range_end in time_intervals(
start_date,
end_date,
split=SPLIT_WEEKLY,
# available splits:
# SPLIT_YEARLY, SPLIT_WEEKLY, SPLIT_DAILY
# or SPLIT_MONTHLY (the default)
):
job = ds.request_datafile(
if dataset_id is None:
dataset = Dataset(api=api,
filters={},
name='Average sentiment',
frequency='daily',
fields=[{
'average_ess': {
'avg': {
'field': 'EVENT_SENTIMENT_SCORE'
}
}
}])
dataset_id = dataset.save()
else:
dataset = api.get_dataset(dataset_id)
# job = Job(api=api,
# token='xxx') # if you already have a job you can use this
# ... or request a new one
job = dataset.request_datafile(
start_date='2018-01-01 00:00:00',
end_date='2018-01-02 00:00:00',
)
# write only the ROLLUP rows
for line in job.iterate_results():
timestamp, entity_id, entity_name, avg_sentiment = line
if entity_id == 'ROLLUP':
print(line)
import logging
import random
import time
from ravenpackapi import RPApi, ApiConnectionError
logging.basicConfig(level=logging.DEBUG)
logger = logging.getLogger(__name__)
# initialize the API (here we use the RP_API_KEY in os.environ)
api = RPApi()
# query the realtime feed
ds = api.get_dataset(dataset_id='us500')
def wait_between_attempts():
""" Incremental backoff between connection attempts """
wait_time = 0.3 # time is in seconds
while True:
yield wait_time
wait_time = min(wait_time * 1.5, 30)
wait_time *= (100 + random.randint(0, 50)) / 100
wait_time = wait_between_attempts()
while True:
try:
for record in ds.request_realtime():
print(record)
print(record.timestamp_utc, record.entity_name,
def check_realtime():
print("Realtime ...")
for record in ds.request_realtime():
assert isinstance(record, Result)
break
print('Realtime - OK')
results['realtime'] = True
if __name__ == '__main__':
args = parser.parse_args()
api = RPApi(args.key)
ds = api.get_dataset('all-granular-data')
date_end = datetime.datetime.utcnow() - datetime.timedelta(minutes=60)
date_start = date_end - datetime.timedelta(minutes=3) # 3 minutes of data
if not api.api_key:
print("Please provide an APIKEY: with the --key parameter or setting the RP_API_KEY environment variable")
exit(1)
print("Checking connection with APIKEY: %s" % api.api_key)
checks = [
threading.Thread(target=check_datafile),
threading.Thread(target=check_json),
threading.Thread(target=check_realtime),
]
results = dict(
datafile=False,