def daily_download(dataset_id):
end_date = datetime.datetime.utcnow().replace(hour=0,
minute=0,
second=0,
microsecond=0)
start_date = end_date - datetime.timedelta(days=1)
print("Date range: %s-%s" % (start_date, end_date))
dataset = Dataset(api=api, id=dataset_id)
job = dataset.request_datafile(start_date, end_date)
print("Waiting for the job to complete")
job.wait_for_completion()
output_filename = "dailydata-%s.csv" % start_date.strftime("%Y-%m-%d")
job.save_to_file(output_filename)
print("Daily download saved on:", output_filename)
"count": {
"field": "RP_ENTITY_ID"
}
}
}, {
"average_news_count_90d": {
"avg": {
"field": "news_count_1d",
"lookback": 90
}
}
}]
custom_dataset = Dataset(api=api,
name="Us30 indicators",
filters=new_filters,
fields=new_fields,
frequency='daily')
custom_dataset.save()
print(custom_dataset)
# query the datafile and save it to file
job = custom_dataset.request_datafile(
start_date='2017-01-01 19:30',
end_date='2017-01-02 19:30',
compressed=True,
time_zone='Europe/London',
)
job.save_to_file('output.csv')
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)
dataset = Dataset(api,
name='My Indicator dataset',
filters={"relevance": {"$gt": 90}},
frequency='daily',
fields=[{"avg_1d": {"avg": {"field": "EVENT_SENTIMENT_SCORE", "lookback": 1,
"mode": "granular"}}},
{"avg_7d": {
"avg": {"field": "avg_1d", "lookback": 1, "mode": "granular"}}},
{"buzz_365d": {"buzz": {"field": "RP_ENTITY_ID", "lookback": 365}}},
{"newsvolume_1d": {"count": {"field": "RP_ENTITY_ID", "lookback": 1}}},
{"newsvolume_365d": {"avg": {"field": "newsvolume_1d", "lookback": 365,
"mode": "granular"}}}]
)
dataset.save()
# you can also change the fields, (remember to save afterward)
dataset.fields = [
{"avg": {"avg": {"field": "EVENT_SENTIMENT_SCORE", "lookback": 365}}},
]
dataset.save()
# Following this, you can then generate a datafile (for your desired date range)
job = dataset.request_datafile(
start_date='2018-04-10', end_date='2018-04-11',
output_format='csv'
)
job.save_to_file('output.csv') # This will poll until the file is ready for download
# a convenience function to delete all the dataset given a name
# delete_all_datasets_by_name(api, 'My Indicator dataset')
