Version 1.0.25: don't buffer RT requests to avoid waiting for chunks

* Updated README and examples

Author: Dario Varotto

README.md

@@ -28,6 +28,24 @@ from ravenpackapi import RPApi
 api = RPApi(api_key="YOUR_API_KEY")
 ```
 
+### Creating a new dataset
+
+To create a dataset you can call the `create_dataset` method of the API with a Dataset instance.
+
+```python
+ds = api.create_dataset(
+    Dataset(
+        name="New Dataset",
+        filters={
+            "relevance": {
+                "$gte": 90
+            }
+        },
+    )
+)
+print("Dataset created", ds)
+```
+
 ### Getting data from the datasets
 
 In the API wrapper, there are several models that maybe used for interacting with data.

README.rst

@@ -39,6 +39,26 @@ environment variable or set it in your code:
 
     api = RPApi(api_key="YOUR_API_KEY")
 
+Creating a new dataset
+~~~~~~~~~~~~~~~~~~~~~~
+
+To create a dataset you can call the ``create_dataset`` method of the
+API with a Dataset instance.
+
+.. code:: python
+
+    ds = api.create_dataset(
+        Dataset(
+            name="New Dataset",
+            filters={
+                "relevance": {
+                    "$gte": 90
+                }
+            },
+        )
+    )
+    print("Dataset created", ds)
+
 Getting data from the datasets
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 

ravenpackapi/core.py

@@ -14,7 +14,7 @@
 from ravenpackapi.utils.constants import JSON_AVAILABLE_FIELDS, ENTITY_TYPES
 
 _VALID_METHODS = ('get', 'post', 'put', 'delete')
-VERSION = '1.0.24'
+VERSION = '1.0.25'
 
 logger = logging.getLogger("ravenpack.core")
 

ravenpackapi/examples/create_dataset.py

@@ -0,0 +1,50 @@
+from ravenpackapi import RPApi, Dataset
+
+api = RPApi()
+
+ds = api.create_dataset(
+    Dataset(
+        **{
+            "product": "rpa",
+            "product_version": "1.0",
+            "name": "Events in UK - example",
+            "fields": [
+                "timestamp_utc",
+                "rp_story_id",
+                "rp_entity_id",
+                "entity_type",
+                "entity_name",
+                "country_code",
+                "relevance",
+                "event_sentiment_score",
+                "topic",
+                "group",
+                "headline"
+            ],
+            "filters": {
+                "$and": [
+                    {
+                        "relevance": {
+                            "$gte": 90
+                        }
+                    },
+                    {
+                        "country_code": {
+                            "$in": [
+                                "GB"
+                            ]
+                        }
+                    },
+                    {
+                        "event_sentiment_score": {
+                            "$nbetween": [-0.5, 0.5]
+                        }
+                    }
+                ]
+            },
+            "frequency": "granular",
+        }
+    )
+)
+
+print("Dataset created", ds)

ravenpackapi/examples/query_entity_mapping.py

@@ -1,25 +1,13 @@
 from ravenpackapi import RPApi
 
-
-class TestEntityMapping(object):
+if __name__ == '__main__':
+    entities = [{'ticker': 'AAPL', 'name': 'Apple Inc.'},
+                {'ticker': 'JPM'},
+                {'listing': 'XNYS:DVN'}]
     api = RPApi()
 
-    def test_matching_entity_mapping(self):
-        entities = [{'ticker': 'AAPL', 'name': 'Apple Inc.'},
-                    {'ticker': 'JPM'},
-                    {'listing': 'XNYS:DVN'}]
-        api = self.api
-        mapping = api.get_entity_mapping(entities)
-        assert not mapping.errors
-        assert len(mapping.matched) == len(mapping.submitted) == 3
-
-        # let's get the first mapped entities
-        rp_entity_ids = [match.id for match in mapping.matched]
-        assert rp_entity_ids == ['D8442A', '619882', '14BA06']
+    mapping = api.get_entity_mapping(entities)
 
-    def test_mismatch_mapping(self):
-        entities = ["unknown!"]
-        api = self.api
-        mapping = api.get_entity_mapping(entities)
-        rp_entity_ids = [match.id for match in mapping.matched]
-        assert rp_entity_ids == []
+    # show the matched entities
+    for match in mapping.matched:
+        print(match.id, match.name, match.type, match.request)

ravenpackapi/models/dataset.py

@@ -3,9 +3,9 @@
 import requests
 
 from ravenpackapi.exceptions import api_method, APIException
+from ravenpackapi.util import to_curl
 from ravenpackapi.utils.constants import JSON_AVAILABLE_FIELDS
 from ravenpackapi.utils.date_formats import as_datetime_str
-from ravenpackapi.util import to_curl
 from .job import Job
 from .results import Results, Result
 
@@ -240,5 +240,5 @@ def request_realtime(self):
                 ), response=response)
         response.encoding = 'utf-8'
 
-        for line in response.iter_lines(decode_unicode=True):
+        for line in response.iter_lines(decode_unicode=True, chunk_size=1):
             yield Result(line)

ravenpackapi/tests/query_entity_mapping.py

@@ -27,7 +27,7 @@ def test_mapping_example(self):
         universe = [
             "RavenPack",
             {'ticker': 'AAPL'},
-            'California USA',
+            'California, U.S.',
             {  # Amazon, specifying various fields
                 "client_id": "12345-A",
                 "date": "2017-01-01",
@@ -50,3 +50,12 @@ def test_mapping_example(self):
         ]
         assert len(mapping.errors) == 1
         assert mapping.errors[0].request == invalid_entity_request
+
+    def test_matching_by_cusip(self):
+        entities = [{'cusip': '037833100', },
+                    {'cusip': '48127A161'},
+                    {'cusip': '25179M103'}]
+        api = self.api
+        mapping = api.get_entity_mapping(entities)
+        assert not mapping.errors
+        assert len(mapping.matched) == len(mapping.submitted) == 3

ravenpackapi/tests/test_dataset_update.py

@@ -9,7 +9,7 @@ class TestDatasetUpdate(object):
 
     def test_create_and_update(self):
         delete_all_datasets_by_name(self.api, self.dataset_name)
-        filters = {"rp_entity_id": {"$in": ['AAAAA']}}
+        filters = {"rp_entity_id": {"$in": ['AAAAAA']}}
         dataset = Dataset(
             name=self.dataset_name,
             filters=filters,  # a dataset with a filter
@@ -20,14 +20,14 @@ def test_create_and_update(self):
         dataset_id = dataset.id
 
         # change the dataset
-        new_filters = {"rp_entity_id": {"$in": ['BBBBB']}}
+        new_filters = {"rp_entity_id": {"$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": {"$in": ['CCCCC']}}
+        new_filters = {"rp_entity_id": {"$in": ['CCCCCC']}}
         dataset.filters = new_filters
         dataset.save()
 

setup.py

@@ -1,6 +1,6 @@
 from setuptools import setup, find_packages
 
-VERSION = '1.0.24'
+VERSION = '1.0.25'
 
 with open('README.rst') as readme_file:
     readme = readme_file.read()