Timezone support for the datafile

Example to copy, modify and save

Author: Dario Varotto

ravenpackapi/core.py

@@ -13,7 +13,7 @@
 from ravenpackapi.utils.constants import JSON_AVAILABLE_FIELDS
 
 _VALID_METHODS = ('get', 'post', 'put', 'delete')
-VERSION = '1.0.13'
+VERSION = '1.0.14'
 
 logger = logging.getLogger("ravenpack.core")
 

ravenpackapi/examples/copy_dataset.py

@@ -0,0 +1,83 @@
+from ravenpackapi import RPApi, Dataset
+import logging
+
+logging.basicConfig(level=logging.INFO)
+# initialize the API (here we use the RP_API_KEY in os.environ)
+api = RPApi()
+
+# get the us30 dataset (its filters contain the top 30 US companies)
+us30 = Dataset(api=api, id='us30')
+
+print(us30.filters)
+
+new_filters = {"$and": [
+    us30.filters,
+    {"relevance": {
+        "$gte": 90
+    }
+    },
+    {
+        "event_similarity_days": {
+            "$gte": 1
+        }
+    }
+]}
+new_fields = [
+    {
+        "daily_average_ess_1d": {
+            "avg": {
+                "field": "EVENT_SENTIMENT_SCORE",
+                "lookback": 1,
+                "mode": "daily"
+            }
+        }
+    },
+    {
+        "daily_average_ess_90d": {
+            "avg": {
+                "field": "EVENT_SENTIMENT_SCORE",
+                "lookback": 90,
+                "mode": "daily"
+            }
+        }
+    },
+    {
+        "buzz": {
+            "buzz": {
+                "field": "RP_ENTITY_ID",
+                "lookback": 2
+            }
+        }
+    },
+    {
+        "news_count_1d": {
+            "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=us30.filters,
+                         fields=new_fields,
+                         frequency='daily'
+                         )
+custom_dataset.save()
+print(custom_dataset)
+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')

ravenpackapi/models/dataset.py

@@ -22,6 +22,8 @@ def __init__(self, api=None, **kwargs):
         :type api: RPApi
         """
         super(Dataset, self).__init__()
+        if 'id' in kwargs:
+            kwargs['uuid'] = kwargs.pop('id')
         self._data = kwargs
         self.api = api
         # the dataset can be initialized with just the uuid
@@ -44,16 +46,20 @@ def __setattr__(self, field, value):
         if field in Dataset._VALID_FIELDS:
             self._data[field] = value
         else:
-            return super(Dataset, self).__setattr__(field, value)
+            object.__setattr__(self, field, value)
 
     @property
     def id(self):  # an alias for the dataset unique id
         return self.uuid
 
     def __getattr__(self, field):
         if field in Dataset._VALID_FIELDS:
-            if field not in self._data:
+            if field not in self._data and 'uuid' in self._data:
+                # get the missing fields
                 self.get_from_server()
+            if field == 'uuid' and field not in self._data:
+                # we can't get the uuid of a new dataset
+                return None
             return self._data[field]
         else:
             return self.__getattribute__(field)
@@ -148,7 +154,9 @@ def request_datafile(self, start_date, end_date,
                          compressed=False,
                          tags=None,
                          notify=False,
-                         allow_empty=True):
+                         allow_empty=True,
+                         time_zone='UTC'
+                         ):
         """ Request a datafile with data in the requested date
             This is asyncronous: it returns a job that you can wait for
             if allow_empty is True, it may return None meaning that the job will have no data
@@ -160,6 +168,7 @@ def request_datafile(self, start_date, end_date,
             "format": output_format,
             "compressed": compressed,
             "notify": notify,
+            "time_zone": time_zone,
         }
         if tags:
             data['tags'] = tags

setup.py

@@ -1,6 +1,6 @@
 from setuptools import setup, find_packages
 
-VERSION = '1.0.13'
+VERSION = '1.0.14'
 
 with open('README.rst') as readme_file:
     readme = readme_file.read()