hawk-sdk 0.0.6__tar.gz → 0.0.8__tar.gz

{hawk_sdk-0.0.6 → hawk_sdk-0.0.8}/PKG-INFO

@@ -1,5 +1,5 @@
 Metadata-Version: 2.1
 Name: hawk-sdk
-Version: 0.0.6
+Version: 0.0.8
 Requires-Dist: google-cloud-bigquery
 Requires-Dist: pandas

{hawk_sdk-0.0.6 → hawk_sdk-0.0.8}/hawk_sdk/api/__init__.py

@@ -1,2 +1,3 @@
 from hawk_sdk.api.futures.main import Futures
+from hawk_sdk.api.equities.main import Equities
 from hawk_sdk.api.system.main import System

hawk_sdk-0.0.8/hawk_sdk/api/equities/main.py

@@ -0,0 +1,32 @@
+"""
+@description: Datasource API for Equities data access and export functions.
+@author: Rithwik Babu
+"""
+from typing import List
+
+from hawk_sdk.api.equities.repository import EquitiesRepository
+from hawk_sdk.api.equities.service import EquitiesService
+from hawk_sdk.core.common.data_object import DataObject
+
+
+class Equities:
+    """Datasource API for fetching Futures data."""
+
+    def __init__(self, environment="production") -> None:
+        """Initializes the Equities datasource with required configurations."""
+        self.repository = EquitiesRepository(environment=environment)
+        self.service = EquitiesService(self.repository)
+
+    def get_adjusted_ohlc(self, start_date: str, end_date: str, interval: str, hawk_ids: List[int]) -> DataObject:
+        """Fetch open, high, low, close data for the given date range and hawk_ids.
+
+        :param start_date: The start date for the data query (YYYY-MM-DD).
+        :param end_date: The end date for the data query (YYYY-MM-DD).
+        :param interval: The interval for the data query (e.g., '1d', '1h', '1m').
+        :param hawk_ids: A list of specific hawk_ids to filter by.
+        :return: A hawk DataObject containing the data.
+        """
+        return DataObject(
+            name="adjusted_equities_ohlcv",
+            data=self.service.get_adjusted_ohlc(start_date, end_date, interval, hawk_ids)
+        )

hawk_sdk-0.0.8/hawk_sdk/api/equities/repository.py

@@ -0,0 +1,80 @@
+"""
+@description: Repository layer for fetching Equities data from BigQuery.
+@author: Rithwik Babu
+"""
+import logging
+from typing import Iterator, List
+
+from google.cloud import bigquery
+
+from hawk_sdk.core.common.utils import get_bigquery_client
+
+
+class EquitiesRepository:
+    """Repository for accessing Equities raw data."""
+
+    def __init__(self, environment: str) -> None:
+        """Initializes the repository with a BigQuery client.
+
+        :param environment: The environment to fetch data from (e.g., 'production', 'development').
+        """
+        self.bq_client = get_bigquery_client()
+        self.environment = environment
+
+    def fetch_adjusted_ohlc(self, start_date: str, end_date: str, interval: str, hawk_ids: List[int]) -> Iterator[dict]:
+        """Fetches raw adjusted OHLC data from BigQuery for the given date range and hawk_ids using query parameters."""
+        query = f"""
+        WITH records_data AS (
+          SELECT 
+            r.record_timestamp AS date,
+            hi.value AS ticker,
+            MAX(CASE WHEN f.field_name = @open_field THEN r.double_value END) AS open,
+            MAX(CASE WHEN f.field_name = @high_field THEN r.double_value END) AS high,
+            MAX(CASE WHEN f.field_name = @low_field THEN r.double_value END) AS low,
+            MAX(CASE WHEN f.field_name = @close_field THEN r.double_value END) AS close
+          FROM 
+            `wsb-hc-qasap-ae2e.{self.environment}.records` AS r
+          JOIN 
+            `wsb-hc-qasap-ae2e.{self.environment}.fields` AS f
+            ON r.field_id = f.field_id
+          JOIN 
+            `wsb-hc-qasap-ae2e.{self.environment}.hawk_identifiers` AS hi
+            ON r.hawk_id = hi.hawk_id
+          WHERE 
+            r.hawk_id IN UNNEST(@hawk_ids)
+            AND f.field_name IN (@open_field, @high_field, @low_field, @close_field)
+            AND r.record_timestamp BETWEEN @start_date AND @end_date
+          GROUP BY 
+            date, ticker
+        )
+        SELECT DISTINCT
+          date,
+          ticker,
+          open,
+          high,
+          low,
+          close,
+        FROM 
+          records_data
+        ORDER BY 
+          date;
+        """
+
+        query_params = [
+            bigquery.ArrayQueryParameter("hawk_ids", "INT64", hawk_ids),
+            bigquery.ScalarQueryParameter("start_date", "STRING", start_date),
+            bigquery.ScalarQueryParameter("end_date", "STRING", end_date),
+            bigquery.ScalarQueryParameter("open_field", "STRING", f"adjusted_open_{interval}"),
+            bigquery.ScalarQueryParameter("high_field", "STRING", f"adjusted_high_{interval}"),
+            bigquery.ScalarQueryParameter("low_field", "STRING", f"adjusted_low_{interval}"),
+            bigquery.ScalarQueryParameter("close_field", "STRING", f"adjusted_close_{interval}")
+        ]
+
+        job_config = bigquery.QueryJobConfig(query_parameters=query_params)
+
+        try:
+            query_job = self.bq_client.query(query, job_config=job_config)
+            return query_job.result()
+        except Exception as e:
+            logging.error(f"Failed to fetch OHLC data: {e}")
+            raise

hawk_sdk-0.0.8/hawk_sdk/api/equities/service.py

@@ -0,0 +1,41 @@
+"""
+@description: Service layer for processing and normalizing Equities data.
+@author: Rithwik Babu
+"""
+from typing import List, Iterator
+
+import pandas as pd
+
+from hawk_sdk.api.equities.repository import EquitiesRepository
+
+
+class EquitiesService:
+    """Service class for Futures business logic."""
+
+    def __init__(self, repository: EquitiesRepository) -> None:
+        """Initializes the service with a repository.
+
+        :param repository: An instance of FuturesRepository for data access.
+        """
+        self.repository = repository
+
+    def get_adjusted_ohlc(self, start_date: str, end_date: str, interval: str, hawk_ids: List[int]) -> pd.DataFrame:
+        """Equities and normalizes data into a pandas DataFrame.
+
+        :param start_date: The start date for the data query (YYYY-MM-DD).
+        :param end_date: The end date for the data query (YYYY-MM-DD).
+        :param interval: The interval for the data query (e.g., '1d', '1h', '1m').
+        :param hawk_ids: A list of specific hawk_ids to filter by.
+        :return: A pandas DataFrame containing the normalized data.
+        """
+        raw_data = self.repository.fetch_adjusted_ohlc(start_date, end_date, interval, hawk_ids)
+        return self._normalize_data(raw_data)
+
+    @staticmethod
+    def _normalize_data(data: Iterator[dict]) -> pd.DataFrame:
+        """Converts raw data into a normalized pandas DataFrame.
+
+        :param data: An iterator over raw data rows.
+        :return: A pandas DataFrame containing normalized data.
+        """
+        return pd.DataFrame([dict(row) for row in data])

hawk_sdk-0.0.8/hawk_sdk/api/futures/__init__.py

@@ -0,0 +1 @@
+from hawk_sdk.api.futures.main import Futures

{hawk_sdk-0.0.6 → hawk_sdk-0.0.8}/hawk_sdk/api/futures/main.py

@@ -4,12 +4,9 @@
 """
 from typing import List
 
-from google.cloud import bigquery
-
-from hawk_sdk.core.common.constants import PROJECT_ID
-from hawk_sdk.core.common.data_object import DataObject
 from hawk_sdk.api.futures.repository import FuturesRepository
 from hawk_sdk.api.futures.service import FuturesService
+from hawk_sdk.core.common.data_object import DataObject
 
 
 class Futures:
@@ -17,8 +14,7 @@ class Futures:
 
     def __init__(self, environment="production") -> None:
         """Initializes the Futures datasource with required configurations."""
-        self.connector = bigquery.Client(project=PROJECT_ID)
-        self.repository = FuturesRepository(self.connector, environment=environment)
+        self.repository = FuturesRepository(environment=environment)
         self.service = FuturesService(self.repository)
 
     def get_ohlcvo(self, start_date: str, end_date: str, interval: str, hawk_ids: List[int]) -> DataObject:
@@ -45,4 +41,4 @@ class Futures:
         return DataObject(
             name="futures_snapshot",
             data=self.service.get_snapshot(timestamp, hawk_ids)
-        )
+        )

{hawk_sdk-0.0.6 → hawk_sdk-0.0.8}/hawk_sdk/api/futures/repository.py

@@ -6,19 +6,19 @@ import logging
 from typing import Iterator, List
 
 from google.cloud import bigquery
-from google.cloud.bigquery import Client
+
+from hawk_sdk.core.common.utils import get_bigquery_client
 
 
 class FuturesRepository:
     """Repository for accessing Futures raw data."""
 
-    def __init__(self, bq_client: Client, environment: str) -> None:
+    def __init__(self, environment: str) -> None:
         """Initializes the repository with a BigQuery client.
 
-        :param bq_client: An instance of BigQuery Client.
         :param environment: The environment to fetch data from (e.g., 'production', 'development').
         """
-        self.bq_client = bq_client
+        self.bq_client = get_bigquery_client()
         self.environment = environment
 
     def fetch_ohlcvo(self, start_date: str, end_date: str, interval: str, hawk_ids: List[int]) -> Iterator[dict]:

{hawk_sdk-0.0.6 → hawk_sdk-0.0.8}/hawk_sdk/api/system/main.py

@@ -4,12 +4,9 @@
 """
 from typing import List
 
-from google.cloud import bigquery
-
-from hawk_sdk.core.common.constants import PROJECT_ID
-from hawk_sdk.core.common.data_object import DataObject
 from hawk_sdk.api.system.repository import SystemRepository
 from hawk_sdk.api.system.service import SystemService
+from hawk_sdk.core.common.data_object import DataObject
 
 
 class System:
@@ -17,8 +14,7 @@ class System:
 
     def __init__(self, environment="production") -> None:
         """Initializes the System datasource with required configurations."""
-        self.connector = bigquery.Client(project=PROJECT_ID)
-        self.repository = SystemRepository(self.connector, environment=environment)
+        self.repository = SystemRepository(environment=environment)
         self.service = SystemService(self.repository)
 
     def get_hawk_ids(self, tickers: List[str]) -> DataObject:

{hawk_sdk-0.0.6 → hawk_sdk-0.0.8}/hawk_sdk/api/system/repository.py

@@ -6,19 +6,20 @@ import logging
 from typing import Iterator, List
 
 from google.cloud import bigquery
-from google.cloud.bigquery import Client
+
+from hawk_sdk.core.common.utils import get_bigquery_client
 
 
 class SystemRepository:
     """Repository for accessing System data."""
 
-    def __init__(self, bq_client: Client, environment: str) -> None:
+    def __init__(self, environment: str) -> None:
         """Initializes the repository with a BigQuery client.
 
         :param bq_client: An instance of BigQuery Client.
         :param environment: The environment to fetch data from (e.g., 'production', 'development').
         """
-        self.bq_client = bq_client
+        self.bq_client = get_bigquery_client()
         self.environment = environment
 
     def fetch_hawk_ids(self, tickers: List[str]) -> Iterator[dict]:

hawk_sdk-0.0.8/hawk_sdk/core/common/utils.py

@@ -0,0 +1,21 @@
+import json
+import os
+
+from google.cloud import bigquery
+from google.oauth2 import service_account
+
+from hawk_sdk.core.common.constants import PROJECT_ID
+
+
+def get_bigquery_client() -> bigquery.Client:
+    if 'GOOGLE_APPLICATION_CREDENTIALS' in os.environ:
+        # Initialize the client using the json file in the environment variable
+        return bigquery.Client(project=PROJECT_ID)
+
+    else:
+        # Load the service account credentials from the JSON string
+        service_account_json = os.environ.get('SERVICE_ACCOUNT_JSON')
+        credentials = service_account.Credentials.from_service_account_info(
+            json.loads(service_account_json)
+        )
+        return bigquery.Client(project=PROJECT_ID, credentials=credentials)

{hawk_sdk-0.0.6 → hawk_sdk-0.0.8}/hawk_sdk.egg-info/PKG-INFO

@@ -1,5 +1,5 @@
 Metadata-Version: 2.1
 Name: hawk-sdk
-Version: 0.0.6
+Version: 0.0.8
 Requires-Dist: google-cloud-bigquery
 Requires-Dist: pandas

{hawk_sdk-0.0.6 → hawk_sdk-0.0.8}/hawk_sdk.egg-info/SOURCES.txt

@@ -7,6 +7,10 @@ hawk_sdk.egg-info/dependency_links.txt
 hawk_sdk.egg-info/requires.txt
 hawk_sdk.egg-info/top_level.txt
 hawk_sdk/api/__init__.py
+hawk_sdk/api/equities/__init__.py
+hawk_sdk/api/equities/main.py
+hawk_sdk/api/equities/repository.py
+hawk_sdk/api/equities/service.py
 hawk_sdk/api/futures/__init__.py
 hawk_sdk/api/futures/main.py
 hawk_sdk/api/futures/repository.py
@@ -19,4 +23,5 @@ hawk_sdk/core/__init__.py
 hawk_sdk/core/common/__init__.py
 hawk_sdk/core/common/base_enum.py
 hawk_sdk/core/common/constants.py
-hawk_sdk/core/common/data_object.py
+hawk_sdk/core/common/data_object.py
+hawk_sdk/core/common/utils.py

{hawk_sdk-0.0.6 → hawk_sdk-0.0.8}/setup.py

@@ -2,7 +2,7 @@ from setuptools import setup, find_packages
 
 setup(
     name='hawk-sdk',
-    version='0.0.6',
+    version='0.0.8',
     packages=find_packages(),
     install_requires=[
         'google-cloud-bigquery',