MOD: Rename get_shape to get_record_count

Author: cjdsellers

databento/common/bento.py

@@ -1,7 +1,7 @@
 import datetime as dt
 import io
 import os.path
-from typing import TYPE_CHECKING, Any, BinaryIO, Callable, Dict, List, Optional, Tuple
+from typing import TYPE_CHECKING, Any, BinaryIO, Callable, Dict, List, Optional
 
 import numpy as np
 import pandas as pd
@@ -35,7 +35,7 @@ def __init__(self) -> None:
         self._limit: Optional[int] = None
         self._encoding: Optional[Encoding] = None
         self._compression: Optional[Compression] = None
-        self._shape: Optional[Tuple[int, ...]] = None
+        self._record_count: Optional[int] = None
 
     def _check_metadata(self) -> None:
         if not self._metadata:
@@ -340,24 +340,20 @@ def compression(self) -> Compression:
         return self._compression
 
     @property
-    def shape(self) -> Tuple[int, ...]:
+    def record_count(self) -> int:
         """
-        Return the shape of the data.
+        Return the record count.
 
         Returns
         -------
-        Tuple[int, ...]
-            The data shape.
+        int
 
         """
-        if self._shape is None:
+        if self._record_count is None:
             self._check_metadata()
-            self._shape = (
-                self._metadata["record_count"],
-                len(DBZ_STRUCT_MAP[self.schema]),
-            )
+            self._record_count = self._metadata["record_count"]
 
-        return self._shape
+        return self._record_count
 
     @property
     def mappings(self) -> Dict[str, List[Dict[str, Any]]]:

databento/historical/api/metadata.py

@@ -241,7 +241,7 @@ def list_unit_prices(
         )
         return response.json()
 
-    def get_shape(
+    def get_record_count(
         self,
         dataset: Union[Dataset, str],
         start: Union[pd.Timestamp, date, str, int],
@@ -251,11 +251,11 @@ def get_shape(
         encoding: Union[Encoding, str] = "dbz",
         stype_in: Optional[Union[SType, str]] = "native",
         limit: Optional[int] = None,
-    ) -> Tuple[int, ...]:
+    ) -> int:
         """
-        Request the shape of the time series data from Databento.
+        Request the count of data records from Databento.
 
-        Makes a GET `/metadata.get_shape` HTTP request.
+        Makes a GET `/metadata.get_record_count` HTTP request.
 
         Parameters
         ----------
@@ -282,8 +282,8 @@ def get_shape(
 
         Returns
         -------
-        Tuple[int, ...]
-            The shape of the data expressed as size per dimension.
+        int
+            The count of records.
 
         """
         validate_enum(schema, Schema, "schema")
@@ -302,13 +302,12 @@ def get_shape(
             params.append(("limit", str(limit)))
 
         response: Response = self._get(
-            url=self._base_url + ".get_shape",
+            url=self._base_url + ".get_record_count",
             params=params,
             basic_auth=True,
         )
 
-        values: List[int] = response.json()
-        return tuple(values)
+        return response.json()
 
     def get_billable_size(
         self,

examples/historical_metadata_get_shape.py …/historical_metadata_get_record_count.pyexamples/historical_metadata_get_shape.py renamed to examples/historical_metadata_get_record_count.py examples/historical_metadata_get_shape.py renamed to examples/historical_metadata_get_record_count.py

@@ -1,5 +1,3 @@
-from typing import Tuple
-
 import databento as db
 
 
@@ -9,7 +7,7 @@
     key = "YOUR_API_KEY"
     client = db.Historical(key=key)
 
-    shape: Tuple[int, ...] = client.metadata.get_shape(
+    count: int = client.metadata.get_record_count(
         dataset="GLBX.MDP3",
         symbols=["ESM2"],
         schema="mbo",
@@ -18,4 +16,4 @@
         encoding="csv",
     )
 
-    print(shape)
+    print(count)

notebooks/quickstart.ipynb

@@ -446,9 +446,7 @@
     "\n",
     "All time series data requests include a metadata header with the following specifications:\n",
     "- The original query paramaters (these can be used to re-request the data)\n",
-    "- Data shape\n",
     "- Symbology mappings\n",
-    "- Instrument 'mini-definitions'"
    ]
   },
   {
@@ -1737,4 +1735,4 @@
  },
  "nbformat": 4,
  "nbformat_minor": 5
-}
+}

tests/test_historical_bento.py

@@ -126,7 +126,7 @@ def test_bento_given_initial_nbytes_returns_expected_metadata(self) -> None:
         assert data.end == pd.Timestamp("2020-12-29 00:00:00+0000", tz="UTC")
         assert data.limit == 2
         assert data.compression == Compression.ZSTD
-        assert data.shape == (2, 15)
+        assert data.record_count == 2
         assert data.mappings == {
             "ESH1": [
                 {

tests/test_historical_metadata.py

@@ -211,12 +211,14 @@ def test_list_unit_price_sends_expected_request(
         assert isinstance(call["auth"], requests.auth.HTTPBasicAuth)
 
     @pytest.mark.skipif(sys.version_info < (3, 8), reason="incompatible mocking")
-    def test_get_shape_sends_expected_request(self, mocker: MockerFixture) -> None:
+    def test_get_record_count_sends_expected_request(
+        self, mocker: MockerFixture
+    ) -> None:
         # Arrange
         mocked_get = mocker.patch("requests.get")
 
         # Act
-        self.client.metadata.get_shape(
+        self.client.metadata.get_record_count(
             dataset="GLBX.MDP3",
             symbols=["ESH1"],
             schema="mbo",
@@ -229,7 +231,7 @@ def test_get_shape_sends_expected_request(self, mocker: MockerFixture) -> None:
         call = mocked_get.call_args.kwargs
         assert (
             call["url"]
-            == f"https://hist.databento.com/v{db.API_VERSION}/metadata.get_shape"
+            == f"https://hist.databento.com/v{db.API_VERSION}/metadata.get_record_count"
         )
         assert sorted(call["headers"].keys()) == ["accept", "user-agent"]
         assert call["headers"]["accept"] == "application/json"