VER: Release 0.11.0

cjdsellers · web-flow · commit 825b42c2adc3 · 2023-04-13T11:31:42.000+10:00
See release notes.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -1,5 +1,9 @@
 # Changelog
 
+## 0.11.0 - 2023-04-13
+- Changed `end` and `end_date` to optional to support new forward-fill behaviour
+- Upgraded `zstandard` to 0.20.0
+
 ## 0.10.0 - 2023-04-07
 - Upgraded `databento-dbn` to 0.4.3
 - Renamed `Bento` class to `DBNStore`
@@ -23,7 +27,7 @@
 - Added `from_dbn` convenience alias for loading DBN files
 
 ## 0.8.0 - 2023-03-03
-- Integrated DBN encoding `0.3.2`
+- Integrated DBN encoding 0.3.2
 - Renamed `timeseries.stream` to `timeseries.get_range`
 - Renamed `timeseries.stream_async` to `timeseries.get_range_async`
 - Deprecated `timeseries.stream(...)` method
@@ -39,20 +43,20 @@
 ## 0.7.0 - 2023-01-10
 - Added support for `definition` schema
 - Updated `Flags` enum
-- Upgraded `dbz-python` to `0.2.1`
-- Upgraded `zstandard` to `0.19.0`
+- Upgraded `dbz-python` to 0.2.1
+- Upgraded `zstandard` to 0.19.0
 
 ## 0.6.0 - 2022-12-02
 - Added `metadata.get_dataset_condition` method to `Historical` client
-- Upgraded `dbz-python` to `0.2.0`
+- Upgraded `dbz-python` to 0.2.0
 
 ## 0.5.0 - 2022-11-07
  - Fixed dataframe columns for derived data schemas (dropped `channel_id`)
  - Fixed `batch.submit_job` requests for `dbz` encoding
  - Updated `quickstart.ipynb` jupyter notebook
 
 ## 0.4.0 - 2022-09-14
- - Upgraded `dbz-python` to `0.1.5`
+ - Upgraded `dbz-python` to 0.1.5
  - Added `map_symbols` option for `.to_df()` (experimental)
 
 ## 0.3.0 - 2022-08-30
diff --git a/README.md b/README.md
@@ -35,7 +35,7 @@ The minimum dependencies as found in the `requirements.txt` are also listed belo
 - numpy (>=1.17.0)
 - pandas (>=1.1.3)
 - requests (>=2.24.0)
-- zstandard (>=0.19.0)
+- zstandard (>=0.20.0)
 
 ## Installation
 To install the latest stable version of the package from PyPI:
diff --git a/databento/historical/api/batch.py b/databento/historical/api/batch.py
@@ -55,10 +55,10 @@ def __init__(self, key: str, gateway: str) -> None:
     def submit_job(
         self,
         dataset: Union[Dataset, str],
-        start: Union[pd.Timestamp, date, str, int],
-        end: Union[pd.Timestamp, date, str, int],
         symbols: Optional[Union[List[str], str]],
         schema: Union[Schema, str],
+        start: Union[pd.Timestamp, date, str, int],
+        end: Optional[Union[pd.Timestamp, date, str, int]] = None,
         encoding: Union[Encoding, str] = "dbn",
         compression: Optional[Union[Compression, str]] = "zstd",
         split_duration: Union[SplitDuration, str] = "day",
@@ -78,20 +78,22 @@ def submit_job(
         ----------
         dataset : Dataset or str
             The dataset code (string identifier) for the request.
+        symbols : List[Union[str, int]] or str
+            The product symbols to filter for. Takes up to 2,000 symbols per request.
+            If more than 1 symbol is specified, the data is merged and sorted by time.
+            If 'ALL_SYMBOLS' or `None` then will be for **all** symbols.
+        schema : Schema or str {'mbo', 'mbp-1', 'mbp-10', 'trades', 'tbbo', 'ohlcv-1s', 'ohlcv-1m', 'ohlcv-1h', 'ohlcv-1d', 'definition', 'statistics', 'status'}, default 'trades'  # noqa
+            The data record schema for the request.
         start : pd.Timestamp or date or str or int
             The start datetime of the request time range (inclusive).
             Assumes UTC as timezone unless passed a tz-aware object.
             If an integer is passed, then this represents nanoseconds since the UNIX epoch.
-        end : pd.Timestamp or date or str or int
+        end : pd.Timestamp or date or str or int, optional
             The end datetime of the request time range (exclusive).
             Assumes UTC as timezone unless passed a tz-aware object.
             If an integer is passed, then this represents nanoseconds since the UNIX epoch.
-        symbols : List[Union[str, int]] or str
-            The product symbols to filter for. Takes up to 2,000 symbols per request.
-            If more than 1 symbol is specified, the data is merged and sorted by time.
-            If 'ALL_SYMBOLS' or `None` then will be for **all** symbols.
-        schema : Schema or str {'mbo', 'mbp-1', 'mbp-10', 'trades', 'tbbo', 'ohlcv-1s', 'ohlcv-1m', 'ohlcv-1h', 'ohlcv-1d', 'definition', 'statistics', 'status'}, default 'trades'  # noqa
-            The data record schema for the request.
+            Values are forward filled based on the resolution provided.
+            Defaults to the same value as `start`.
         encoding : Encoding or str {'dbn', 'csv', 'json'}, default 'dbn'
             The data encoding.
         compression : Compression or str {'none', 'zstd'}, default 'zstd'
diff --git a/databento/historical/api/metadata.py b/databento/historical/api/metadata.py
@@ -162,7 +162,7 @@ def list_unit_prices(
         schema: Optional[Union[Schema, str]] = None,
     ) -> Union[float, Dict[str, Any]]:
         """
-        List unit prices for each data schema in dollars per gigabyte.
+        List unit prices for each data schema in US dollars per gigabyte.
 
         Makes a `GET /metadata.list_unit_prices` HTTP request.
 
@@ -273,7 +273,7 @@ def get_record_count(
         self,
         dataset: Union[Dataset, str],
         start: Union[pd.Timestamp, date, str, int],
-        end: Union[pd.Timestamp, date, str, int],
+        end: Optional[Union[pd.Timestamp, date, str, int]] = None,
         symbols: Optional[Union[List[str], str]] = None,
         schema: Union[Schema, str] = "trades",
         stype_in: Optional[Union[SType, str]] = "native",
@@ -289,11 +289,15 @@ def get_record_count(
         dataset : Dataset or str
             The dataset code for the request.
         start : pd.Timestamp or date or str or int
-            The start datetime for the request range. Assumes UTC as timezone unless otherwise specified.
+            The start datetime for the request range (inclusive).
+            Assumes UTC as timezone unless otherwise specified.
             If an integer is passed, then this represents nanoseconds since the UNIX epoch.
-        end : pd.Timestamp or date or str or int
-            The end datetime for the request range. Assumes UTC as timezone unless otherwise specified.
+        end : pd.Timestamp or date or str or int, optional
+            The end datetime for the request range (exclusive).
+            Assumes UTC as timezone unless otherwise specified.
             If an integer is passed, then this represents nanoseconds since the UNIX epoch.
+            Values are forward filled based on the resolution provided.
+            Defaults to the same value as `start`.
         symbols : List[Union[str, int]] or str, optional
             The product symbols to filter for. Takes up to 2,000 symbols per request.
             If 'ALL_SYMBOLS' or `None` then will be for **all** symbols.
@@ -337,7 +341,7 @@ def get_billable_size(
         self,
         dataset: Union[Dataset, str],
         start: Union[pd.Timestamp, date, str, int],
-        end: Union[pd.Timestamp, date, str, int],
+        end: Optional[Union[pd.Timestamp, date, str, int]] = None,
         symbols: Optional[Union[List[str], str]] = None,
         schema: Union[Schema, str] = "trades",
         stype_in: Optional[Union[SType, str]] = "native",
@@ -353,12 +357,16 @@ def get_billable_size(
         ----------
         dataset : Dataset or str
             The dataset code for the request.
-        start : pd.Timestamp or date or str or int, optional
-            The start datetime for the request range. Assumes UTC as timezone unless otherwise specified.
+        start : pd.Timestamp or date or str or int
+            The start datetime for the request range (inclusive).
+            Assumes UTC as timezone unless otherwise specified.
             If an integer is passed, then this represents nanoseconds since the UNIX epoch.
         end : pd.Timestamp or date or str or int, optional
-            The end datetime for the request range. Assumes UTC as timezone unless otherwise specified.
+            The end datetime for the request range (exclusive).
+            Assumes UTC as timezone unless otherwise specified.
             If an integer is passed, then this represents nanoseconds since the UNIX epoch.
+            Values are forward filled based on the resolution provided.
+            Defaults to the same value as `start`.
         symbols : List[Union[str, int]] or str, optional
             The product symbols to filter for. Takes up to 2,000 symbols per request.
             If 'ALL_SYMBOLS' or `None` then will be for **all** symbols.
@@ -380,7 +388,7 @@ def get_billable_size(
         params: List[Tuple[str, Optional[str]]] = [
             ("dataset", validate_semantic_string(dataset, "dataset")),
             ("start", datetime_to_string(start)),
-            ("end", datetime_to_string(end)),
+            ("end", optional_datetime_to_string(end)),
             ("symbols", symbols_list),
             ("schema", str(validate_enum(schema, Schema, "schema"))),
             ("stype_in", str(stype_in_valid)),
@@ -402,15 +410,15 @@ def get_cost(
         self,
         dataset: Union[Dataset, str],
         start: Union[pd.Timestamp, date, str, int],
-        end: Union[pd.Timestamp, date, str, int],
+        end: Optional[Union[pd.Timestamp, date, str, int]] = None,
         mode: Union[FeedMode, str] = "historical-streaming",
         symbols: Optional[Union[List[str], str]] = None,
         schema: Union[Schema, str] = "trades",
         stype_in: Optional[Union[SType, str]] = "native",
         limit: Optional[int] = None,
     ) -> float:
         """
-        Request the cost in US Dollars for historical streaming or batched files
+        Request the cost in US dollars for historical streaming or batched files
         from Databento.
 
         Makes a `GET /metadata.get_cost` HTTP request.
@@ -420,11 +428,15 @@ def get_cost(
         dataset : Dataset or str
             The dataset code for the request.
         start : pd.Timestamp or date or str or int
-            The start datetime for the request range. Assumes UTC as timezone unless otherwise specified.
+            The start datetime for the request range (inclusive).
+            Assumes UTC as timezone unless otherwise specified.
             If an integer is passed, then this represents nanoseconds since the UNIX epoch.
-        end : pd.Timestamp or date or str or int
-            The end datetime for the request range. Assumes UTC as timezone unless otherwise specified.
+        end : pd.Timestamp or date or str or int, optional
+            The end datetime for the request range (exclusive).
+            Assumes UTC as timezone unless otherwise specified.
             If an integer is passed, then this represents nanoseconds since the UNIX epoch.
+            Values are forward filled based on the resolution provided.
+            Defaults to the same value as `start`.
         mode : FeedMode or str {'live', 'historical-streaming', 'historical'}, default 'historical-streaming'
             The data feed mode for the request.
         symbols : List[Union[str, int]] or str, optional
@@ -440,15 +452,15 @@ def get_cost(
         Returns
         -------
         float
-            The cost in US Dollars.
+            The cost in US dollars.
 
         """
         stype_in_valid = validate_enum(stype_in, SType, "stype_in")
         symbols_list = optional_symbols_list_to_string(symbols, stype_in_valid)
-        params: List[Tuple[str, str]] = [
+        params: List[Tuple[str, Optional[str]]] = [
             ("dataset", validate_semantic_string(dataset, "dataset")),
             ("start", datetime_to_string(start)),
-            ("end", datetime_to_string(end)),
+            ("end", optional_datetime_to_string(end)),
             ("symbols", symbols_list),
             ("schema", str(validate_enum(schema, Schema, "schema"))),
             ("stype_in", str(stype_in_valid)),
diff --git a/databento/historical/api/symbology.py b/databento/historical/api/symbology.py
@@ -4,6 +4,7 @@
 from databento.common.enums import SType
 from databento.common.parsing import (
     datetime_to_date_string,
+    optional_date_to_string,
     optional_symbols_list_to_string,
 )
 from databento.common.validation import validate_enum, validate_semantic_string
@@ -28,7 +29,7 @@ def resolve(
         stype_in: Union[SType, str],
         stype_out: Union[SType, str],
         start_date: Union[date, str],
-        end_date: Union[date, str],
+        end_date: Optional[Union[date, str]] = None,
         default_value: Optional[str] = "",
     ) -> Dict[str, Any]:
         """
@@ -48,7 +49,7 @@ def resolve(
             The output symbology type to resolve to.
         start_date : date or str
             The start date (UTC) of the request time range (inclusive).
-        end_date : date or str
+        end_date : date or str, optional
             The end date (UTC) of the request time range (exclusive).
         default_value : str, default '' (empty string)
             The default value to return if a symbol cannot be resolved.
@@ -68,7 +69,7 @@ def resolve(
             ("stype_in", str(stype_in_valid)),
             ("stype_out", str(validate_enum(stype_out, SType, "stype_out"))),
             ("start_date", datetime_to_date_string(start_date)),
-            ("end_date", datetime_to_date_string(end_date)),
+            ("end_date", optional_date_to_string(end_date)),
             ("default_value", default_value),
         ]
 
diff --git a/databento/historical/api/timeseries.py b/databento/historical/api/timeseries.py
@@ -11,7 +11,11 @@
 from databento.common.deprecated import deprecated
 from databento.common.enums import Compression, Dataset, Encoding, Schema, SType
 from databento.common.error import BentoWarning
-from databento.common.parsing import datetime_to_string, optional_symbols_list_to_string
+from databento.common.parsing import (
+    datetime_to_string,
+    optional_datetime_to_string,
+    optional_symbols_list_to_string,
+)
 from databento.common.validation import validate_enum, validate_semantic_string
 from databento.historical.api import API_VERSION
 from databento.historical.http import BentoHttpAPI
@@ -31,7 +35,7 @@ def stream(
         self,
         dataset: Union[Dataset, str],
         start: Union[pd.Timestamp, date, str, int],
-        end: Union[pd.Timestamp, date, str, int],
+        end: Optional[Union[pd.Timestamp, date, str, int]] = None,
         symbols: Optional[Union[List[str], str]] = None,
         schema: Union[Schema, str] = "trades",
         stype_in: Union[SType, str] = "native",
@@ -59,7 +63,7 @@ def get_range(
         self,
         dataset: Union[Dataset, str],
         start: Union[pd.Timestamp, date, str, int],
-        end: Union[pd.Timestamp, date, str, int],
+        end: Optional[Union[pd.Timestamp, date, str, int]] = None,
         symbols: Optional[Union[List[str], str]] = None,
         schema: Union[Schema, str] = "trades",
         stype_in: Union[SType, str] = "native",
@@ -83,11 +87,15 @@ def get_range(
         dataset : Dataset or str
             The dataset code (string identifier) for the request.
         start : pd.Timestamp or date or str or int
-            The start datetime (UTC) of the request time range (inclusive).
+            The start datetime of the request time range (inclusive).
+            Assumes UTC as timezone unless passed a tz-aware object.
             If an integer is passed, then this represents nanoseconds since the UNIX epoch.
-        end : pd.Timestamp or date or str or int
-            The end datetime (UTC) of the request time range (exclusive).
+        end : pd.Timestamp or date or str or int, optional
+            The end datetime of the request time range (exclusive).
+            Assumes UTC as timezone unless passed a tz-aware object.
             If an integer is passed, then this represents nanoseconds since the UNIX epoch.
+            Values are forward filled based on the resolution provided.
+            Defaults to the same value as `start`.
         symbols : List[Union[str, int]] or str, optional
             The product symbols to filter for. Takes up to 2,000 symbols per request.
             If more than 1 symbol is specified, the data is merged and sorted by time.
@@ -122,7 +130,7 @@ def get_range(
         params: List[Tuple[str, Optional[str]]] = [
             ("dataset", validate_semantic_string(dataset, "dataset")),
             ("start", datetime_to_string(start)),
-            ("end", datetime_to_string(end)),
+            ("end", optional_datetime_to_string(end)),
             ("symbols", symbols_list),
             ("schema", str(schema_valid)),
             ("stype_in", str(stype_in_valid)),
@@ -166,7 +174,7 @@ async def stream_async(
         self,
         dataset: Union[Dataset, str],
         start: Union[pd.Timestamp, date, str, int],
-        end: Union[pd.Timestamp, date, str, int],
+        end: Optional[Union[pd.Timestamp, date, str, int]] = None,
         symbols: Optional[Union[List[str], str]] = None,
         schema: Union[Schema, str] = "trades",
         stype_in: Union[SType, str] = "native",
@@ -195,7 +203,7 @@ async def get_range_async(
         self,
         dataset: Union[Dataset, str],
         start: Union[pd.Timestamp, date, str, int],
-        end: Union[pd.Timestamp, date, str, int],
+        end: Optional[Union[pd.Timestamp, date, str, int]] = None,
         symbols: Optional[Union[List[str], str]] = None,
         schema: Union[Schema, str] = "trades",
         stype_in: Union[SType, str] = "native",
@@ -219,11 +227,15 @@ async def get_range_async(
         dataset : Dataset or str
             The dataset code (string identifier) for the request.
         start : pd.Timestamp or date or str or int
-            The start datetime (UTC) of the request time range (inclusive).
+            The start datetime of the request time range (inclusive).
+            Assumes UTC as timezone unless passed a tz-aware object.
             If an integer is passed, then this represents nanoseconds since the UNIX epoch.
-        end : pd.Timestamp or date or str or int
-            The end datetime (UTC) of the request time range (exclusive).
+        end : pd.Timestamp or date or str or int, optional
+            The end datetime of the request time range (exclusive).
+            Assumes UTC as timezone unless passed a tz-aware object.
             If an integer is passed, then this represents nanoseconds since the UNIX epoch.
+            Values are forward filled based on the resolution provided.
+            Defaults to the same value as `start`.
         symbols : List[Union[str, int]] or str, optional
             The product symbols to filter for. Takes up to 2,000 symbols per request.
             If more than 1 symbol is specified, the data is merged and sorted by time.
@@ -258,7 +270,7 @@ async def get_range_async(
         params: List[Tuple[str, Optional[str]]] = [
             ("dataset", validate_semantic_string(dataset, "dataset")),
             ("start", datetime_to_string(start)),
-            ("end", datetime_to_string(end)),
+            ("end", optional_datetime_to_string(end)),
             ("symbols", symbols_list),
             ("schema", str(schema_valid)),
             ("stype_in", str(stype_in_valid)),
diff --git a/databento/version.py b/databento/version.py
@@ -1 +1 @@
-__version__ = "0.10.0"
+__version__ = "0.11.0"
diff --git a/notebooks/quickstart.ipynb b/notebooks/quickstart.ipynb
@@ -308,7 +308,7 @@
    },
    "source": [
     "### Data cost\n",
-    "Before making a request for data, you can query the expected price in USD. The price is determined from the following formula: `unit_cost` * `uncompressed_size_GB`."
+    "Before making a request for data, you can query the expected price in US dollars. The price is determined from the following formula: `unit_cost` * `uncompressed_size_GB`."
    ]
   },
   {
diff --git a/requirements.txt b/requirements.txt
@@ -3,4 +3,4 @@ databento-dbn==0.4.3
 numpy>=1.17.0
 pandas>=1.1.3
 requests>=2.24.0
-zstandard>=0.19.0
+zstandard>=0.20.0
diff --git a/requirements_dev.txt b/requirements_dev.txt
@@ -1,4 +1,4 @@
-mypy==1.1.1
-pytest>=7.2.2
+mypy==1.2.0
+pytest>=7.3.0
 pytest-mock>=3.10.0
 types-requests

Original file line number	Diff line number	Diff line change
`@@ -1 +1 @@`
`1`		`-__version__ = "0.10.0"`
	`1`	`+__version__ = "0.11.0"`
Original file line number	Diff line number	Diff line change
`@@ -308,7 +308,7 @@`
`308`	`308`	`},`
`309`	`309`	`"source": [`
`310`	`310`	`"### Data cost\n",`
`311`		- "Before making a request for data, you can query the expected price in USD. The price is determined from the following formula: `unit_cost` * `uncompressed_size_GB`."
	`311`	+ "Before making a request for data, you can query the expected price in US dollars. The price is determined from the following formula: `unit_cost` * `uncompressed_size_GB`."
`312`	`312`	`]`
`313`	`313`	`},`
`314`	`314`	`{`