def test_create_and_update(self):
delete_all_datasets_by_name(self.api, self.dataset_name)
filters = {"rp_entity_id": {"$in": ['AAAAAA']}}
dataset = Dataset(
name=self.dataset_name,
filters=filters, # a dataset with a filter
)
dataset = self.api.create_dataset(dataset)
assert dataset.id is not None
dataset_id = dataset.id
# change the dataset
new_filters = {"rp_entity_id": {"$in": ['BBBBBB']}}
dataset.filters = new_filters
dataset.save()
# get the dataset again
dataset = self.api.get_dataset(dataset_id)
assert dataset.filters == new_filters
new_filters = {"rp_entity_id": {"$in": ['CCCCCC']}}
dataset.filters = new_filters
dataset.save()
dataset.delete()
assert delete_all_datasets_by_name(self.api, self.dataset_name) == 0
def create_dataset(self, dataset):
# be sure to create a copy
new_dataset_data = dataset.as_dict()
new_dataset = Dataset(api=self, **new_dataset_data)
if 'uuid' in new_dataset_data:
del new_dataset['uuid']
new_dataset.save()
dataset_id = new_dataset.id
logger.info("Created dataset %s" % dataset_id)
return new_dataset
def test_dataset_copy_updated(self):
source_dataset = Dataset(api=self.api, id='us30')
new_dataset = Dataset(
api=self.api,
name="copy of the us30 dataset",
filters=source_dataset.filters,
fields=['timestamp_utc', 'rp_entity_id', 'avg_sentiment'],
custom_fields=[{
"avg_sentiment": {
"avg": {
"field": "EVENT_SENTIMENT_SCORE",
}
}
}],
frequency='daily',
tags=['copy', 'test'])
new_dataset.save()
new_dataset.delete()
"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')
dataset_id = None # put here a dataset_id if you have it already
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
# You can then add functions (https://app.ravenpack.com/api-documentation/#indicator-syntax)
# Alternatively you can also create the dataset via the query builder and just use the dataset_uuid
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
