hawk-sdk 0.0.0__tar.gz → 0.0.5__tar.gz

hawk_sdk-0.0.5/PKG-INFO

@@ -0,0 +1,5 @@
+Metadata-Version: 2.1
+Name: hawk-sdk
+Version: 0.0.5
+Requires-Dist: google-cloud-bigquery
+Requires-Dist: pandas

hawk_sdk-0.0.5/README.md

@@ -0,0 +1,69 @@
+## Hawk SDK
+
+https://hawk-center.github.io/hawk-sdk/
+
+### Contributing
+
+Please read [CONTRIBUTING.md](.github/CONTRIBUTING.md) for more details.
+
+
+Here’s a sample README section for updating a pip package using `twine`:
+
+---
+
+## Updating the Package on PyPI
+
+Follow these steps to update and publish your package on PyPI using `twine`:
+
+### 1. Update `setup.py`
+Ensure your `setup.py` file reflects the correct metadata and version for the new release. Update the version number in accordance with [Semantic Versioning](https://semver.org/).
+
+```python
+version='X.Y.Z',  # Update this with the new version number
+```
+
+### 2. Install Required Tools
+Make sure you have the necessary tools installed:
+
+```bash
+pip install setuptools wheel twine
+```
+
+### 3. Clean Up Previous Builds (Optional)
+If you have previously built distributions in the `dist/` or `build/` directories, remove them to avoid conflicts:
+
+```bash
+rm -rf dist/ build/
+```
+
+### 4. Build the Package
+Generate the source distribution (`sdist`) and the wheel (`bdist_wheel`) for your package:
+
+```bash
+python setup.py sdist bdist_wheel
+```
+
+This creates distribution files in the `dist/` directory.
+
+### 5. Test the Package Locally (Optional)
+You can test the package locally before uploading it to PyPI:
+
+```bash
+pip install dist/your_package_name-X.Y.Z-py3-none-any.whl
+```
+
+### 6. Upload to PyPI
+Once you’re satisfied with the package, upload it to PyPI. Contact Rithwik for the pypi API key:
+
+```bash
+twine upload dist/*
+```
+
+### 8. Verify the Package
+After uploading, verify the package has been successfully updated on PyPI by visiting your project page: 
+
+[https://pypi.org/project/your-package-name/](https://pypi.org/project/hawk-sd/)
+
+---
+
+Let me know if you'd like any customization to fit your specific workflow!

hawk_sdk-0.0.5/hawk_sdk/api/__init__.py

@@ -0,0 +1,2 @@
+from hawk_sdk.api.futures.main import Futures
+from hawk_sdk.api.system.main import System

hawk_sdk-0.0.5/hawk_sdk/api/futures/__init__.py

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

{hawk-sdk-0.0.0/hawk_sdk → hawk_sdk-0.0.5/hawk_sdk/api}/futures/main.py

@@ -2,31 +2,29 @@
 @description: Datasource API for Hawk Global Futures data access and export functions.
 @author: Rithwik Babu
 """
-
-from hawk_sdk.common.bigquery_connector import BigQueryConnector
-from hawk_sdk.common.data_object import DataObject
-from hawk_sdk.futures.repository import FuturesRepository
-from hawk_sdk.futures.service import FuturesService
 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
+
 
 class Futures:
     """Datasource API for fetching Futures data."""
 
-    def __init__(self, project_id: str, credentials_path: str = None) -> None:
-        """Initializes the Futures datasource with required configurations.
-
-        :param project_id: The GCP project ID.
-        :param credentials_path: Path to the Google Cloud credentials file.
-        """
-        self.connector = BigQueryConnector(project_id, credentials_path)
-        self.repository = FuturesRepository(self.connector)
+    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.service = FuturesService(self.repository)
 
     def get_ohlcvo(self, start_date: str, end_date: str, interval: str, hawk_ids: List[int]) -> DataObject:
         """Fetch open, high, low, close, volume, and open interest data for the given date range and hawk_ids.
 
-        :param start_date: The start date for the data query (YYYY-MM-DD).
+        :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.
@@ -36,4 +34,3 @@ class Futures:
             name="futures_ohlcvo",
             data=self.service.get_ohlcvo(start_date, end_date, interval, hawk_ids)
         )
-

hawk_sdk-0.0.5/hawk_sdk/api/futures/repository.py

@@ -0,0 +1,87 @@
+"""
+@description: Repository layer for fetching Futures data from BigQuery.
+@author: Rithwik Babu
+"""
+import logging
+from typing import Iterator, List
+
+from google.cloud import bigquery
+from google.cloud.bigquery import Client
+
+
+class FuturesRepository:
+    """Repository for accessing Futures raw data."""
+
+    def __init__(self, bq_client: Client, 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.environment = environment
+
+    def fetch_ohlcvo(self, start_date: str, end_date: str, interval: str, hawk_ids: List[int]) -> Iterator[dict]:
+        """Fetches raw 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,
+            MAX(CASE WHEN f.field_name = @volume_field THEN r.int_value END) AS volume,
+            MAX(CASE WHEN f.field_name = @open_interest_field THEN r.int_value END) AS open_interest
+          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, @volume_field, @open_interest_field)
+            AND r.record_timestamp BETWEEN @start_date AND @end_date
+          GROUP BY 
+            date, ticker
+        )
+        SELECT DISTINCT
+          date,
+          ticker,
+          open,
+          high,
+          low,
+          close,
+          volume,
+          open_interest
+        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"open_{interval}"),
+            bigquery.ScalarQueryParameter("high_field", "STRING", f"high_{interval}"),
+            bigquery.ScalarQueryParameter("low_field", "STRING", f"low_{interval}"),
+            bigquery.ScalarQueryParameter("close_field", "STRING", f"close_{interval}"),
+            bigquery.ScalarQueryParameter("volume_field", "STRING", f"volume_{interval}"),
+            bigquery.ScalarQueryParameter("open_interest_field", "STRING", f"open_interest_{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 OHLCVO data: {e}")
+            raise

{hawk-sdk-0.0.0/hawk_sdk → hawk_sdk-0.0.5/hawk_sdk/api}/futures/service.py

@@ -2,11 +2,12 @@
 @description: Service layer for processing and normalizing Futures data.
 @author: Rithwik Babu
 """
-
-from hawk_sdk.futures.repository import FuturesRepository
 from typing import List, Iterator
+
 import pandas as pd
 
+from hawk_sdk.api.futures.repository import FuturesRepository
+
 
 class FuturesService:
     """Service class for Futures business logic."""

hawk_sdk-0.0.5/hawk_sdk/api/system/__init__.py

@@ -0,0 +1 @@
+from hawk_sdk.api.system.main import System

hawk_sdk-0.0.5/hawk_sdk/api/system/main.py

@@ -0,0 +1,33 @@
+"""
+@description: Datasource API for Hawk System data access and export functions.
+@author: Rithwik Babu
+"""
+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
+
+
+class System:
+    """Datasource API for fetching System data."""
+
+    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.service = SystemService(self.repository)
+
+    def get_hawk_ids(self, tickers: List[str]) -> DataObject:
+        """Fetch hawk_ids for the given list of tickers.
+
+        :param tickers: A list of specific tickers to filter by.
+        :return: A hawk DataObject containing the hawk ID data.
+        """
+        return DataObject(
+            name="system_hawk_id_mappings",
+            data=self.service.get_hawk_ids(tickers)
+        )

hawk_sdk-0.0.5/hawk_sdk/api/system/repository.py

@@ -0,0 +1,52 @@
+"""
+@description: Repository layer for fetching System data from BigQuery.
+@author: Rithwik Babu
+"""
+import logging
+from typing import Iterator, List
+
+from google.cloud import bigquery
+from google.cloud.bigquery import Client
+
+
+class SystemRepository:
+    """Repository for accessing System data."""
+
+    def __init__(self, bq_client: Client, 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.environment = environment
+
+    def fetch_hawk_ids(self, tickers: List[str]) -> Iterator[dict]:
+        """Fetches hawk_ids for the given list of tickers from BigQuery.
+
+        :param tickers: A list of ticker strings to filter by.
+        :return: An iterator over raw data rows.
+        """
+        query = f"""
+        SELECT 
+            value AS ticker, 
+            hawk_id
+        FROM 
+            `wsb-hc-qasap-ae2e.{self.environment}.hawk_identifiers`
+        WHERE 
+            id_type = 'TICKER'
+            AND value IN UNNEST(@ticker_list)
+        """
+
+        query_params = [
+            bigquery.ArrayQueryParameter("ticker_list", "STRING", tickers),
+        ]
+
+        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 hawk_ids: {e}")
+            raise

hawk_sdk-0.0.5/hawk_sdk/api/system/service.py

@@ -0,0 +1,39 @@
+"""
+@description: Service layer for processing and normalizing System data.
+@author: Rithwik Babu
+"""
+
+from typing import List, Iterator
+
+import pandas as pd
+
+from hawk_sdk.api.system.repository import SystemRepository
+
+
+class SystemService:
+    """Service class for System business logic."""
+
+    def __init__(self, repository: SystemRepository) -> None:
+        """Initializes the service with a repository.
+
+        :param repository: An instance of SystemRepository for data access.
+        """
+        self.repository = repository
+
+    def get_hawk_ids(self, tickers: List[str]) -> pd.DataFrame:
+        """Fetches and normalizes hawk IDs into a pandas DataFrame.
+
+        :param tickers: A list of specific tickers to filter by.
+        :return: A pandas DataFrame containing the normalized hawk ID data.
+        """
+        raw_data = self.repository.fetch_hawk_ids(tickers)
+        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-0.0.5/hawk_sdk/core/common/base_enum.py

@@ -0,0 +1,16 @@
+"""
+@description: Base enum class.
+@author: Rithwik Babu
+"""
+
+from enum import Enum
+
+
+class BaseEnum(str, Enum):
+    """
+    Base enum class used by all enum classes.
+
+    Note: Inheriting from str is necessary to correctly serialize output of enum
+    """
+
+    pass

hawk_sdk-0.0.5/hawk_sdk/core/common/constants.py

@@ -0,0 +1 @@
+PROJECT_ID = 'wsb-hc-qasap-ae2e'

{hawk-sdk-0.0.0/hawk_sdk → hawk_sdk-0.0.5/hawk_sdk/core}/common/data_object.py

@@ -1,3 +1,7 @@
+"""
+@description: Data Object class to handle output transformations.
+@author: Rithwik Babu
+"""
 import pandas as pd
 
 

hawk_sdk-0.0.5/hawk_sdk.egg-info/PKG-INFO

@@ -0,0 +1,5 @@
+Metadata-Version: 2.1
+Name: hawk-sdk
+Version: 0.0.5
+Requires-Dist: google-cloud-bigquery
+Requires-Dist: pandas

hawk_sdk-0.0.5/hawk_sdk.egg-info/SOURCES.txt

@@ -0,0 +1,22 @@
+README.md
+setup.py
+hawk_sdk/__init__.py
+hawk_sdk.egg-info/PKG-INFO
+hawk_sdk.egg-info/SOURCES.txt
+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/futures/__init__.py
+hawk_sdk/api/futures/main.py
+hawk_sdk/api/futures/repository.py
+hawk_sdk/api/futures/service.py
+hawk_sdk/api/system/__init__.py
+hawk_sdk/api/system/main.py
+hawk_sdk/api/system/repository.py
+hawk_sdk/api/system/service.py
+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-0.0.0 → hawk_sdk-0.0.5}/setup.py

@@ -2,7 +2,7 @@ from setuptools import setup, find_packages
 
 setup(
     name='hawk-sdk',
-    version='0.0.0',
+    version='0.0.5',
     packages=find_packages(),
     install_requires=[
         'google-cloud-bigquery',

hawk-sdk-0.0.0/PKG-INFO

@@ -1,3 +0,0 @@
-Metadata-Version: 2.1
-Name: hawk-sdk
-Version: 0.0.0

hawk-sdk-0.0.0/README.md

@@ -1 +0,0 @@
-# hawk-sdk

hawk-sdk-0.0.0/hawk_sdk/__init__.py

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

hawk-sdk-0.0.0/hawk_sdk/common/bigquery_connector.py

@@ -1,47 +0,0 @@
-"""
-@description: Handles the connection and interaction with Google BigQuery.
-@author: Rithwik Babu
-"""
-
-import os
-from typing import Iterator
-
-from google.cloud import bigquery
-
-
-class BigQueryConnector:
-    """Handles authentication and querying BigQuery."""
-
-    def __init__(self, project_id: str, credentials_path: str = None) -> None:
-        """Initializes BigQuery client and sets up authentication.
-
-        :param project_id: The GCP project ID.
-        :param credentials_path: Path to the Google Cloud credentials file.
-        """
-        if credentials_path:
-            os.environ["GOOGLE_APPLICATION_CREDENTIALS"] = credentials_path
-
-        if not self._validate_credentials_exists():
-            raise ValueError("Credentials not found. Set GOOGLE_APPLICATION_CREDENTIALS environment variable.")
-
-        self.client = bigquery.Client(project=project_id)
-
-    def run_query(self, query: str) -> Iterator[bigquery.Row]:
-        """Runs a SQL query on BigQuery and returns an iterator over rows.
-
-        :param query: The SQL query to execute.
-        :return: An iterator over the result rows.
-        """
-        query_job = self.client.query(query)
-        return query_job.result()
-
-    def _validate_credentials_exists(self) -> bool:
-        """Validates if the GOOGLE_APPLICATION_CREDENTIALS environment variable is set.
-
-        :return: True if the environment variable is set, False otherwise.
-        """
-        if "GOOGLE_APPLICATION_CREDENTIALS" in os.environ:
-            return True
-        else:
-            print("Environment variable for credentials is not set.")
-            return False

hawk-sdk-0.0.0/hawk_sdk/futures/__init__.py

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

hawk-sdk-0.0.0/hawk_sdk/futures/repository.py

@@ -1,70 +0,0 @@
-"""
-@description: Repository layer for fetching Futures data from BigQuery.
-@author: Rithwik Babu
-"""
-
-from hawk_sdk.common.bigquery_connector import BigQueryConnector
-from typing import Iterator, List
-
-
-class FuturesRepository:
-    """Repository for accessing Futures raw data."""
-
-    def __init__(self, connector: BigQueryConnector) -> None:
-        """Initializes the repository with a BigQuery connector.
-
-        :param connector: An instance of BigQueryConnector.
-        """
-        self.connector = connector
-
-    def fetch_ohlcvo(self, start_date: str, end_date: str, interval: str, hawk_ids: List[int]) -> Iterator[dict]:
-        """Fetches raw data from BigQuery 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: An iterator over raw data rows.
-        """
-        hawk_ids_str = ', '.join(map(str, hawk_ids))
-        query = f"""
-        WITH records_data AS (
-          SELECT 
-            r.record_timestamp AS date,
-            hi.value AS ticker,
-            MAX(CASE WHEN f.field_name = 'open_{interval}' THEN r.double_value END) AS open,
-            MAX(CASE WHEN f.field_name = 'high_{interval}' THEN r.double_value END) AS high,
-            MAX(CASE WHEN f.field_name = 'low_{interval}' THEN r.double_value END) AS low,
-            MAX(CASE WHEN f.field_name = 'close_{interval}' THEN r.double_value END) AS close,
-            MAX(CASE WHEN f.field_name = 'volume_{interval}' THEN r.int_value END) AS volume,
-            MAX(CASE WHEN f.field_name = 'open_interest_{interval}' THEN r.double_value END) AS open_interest
-          FROM 
-            `wsb-hc-qasap-ae2e.development.records` AS r
-          JOIN 
-            `wsb-hc-qasap-ae2e.development.fields` AS f
-            ON r.field_id = f.field_id
-          JOIN 
-            `wsb-hc-qasap-ae2e.development.hawk_identifiers` AS hi
-            ON r.hawk_id = hi.hawk_id
-          WHERE 
-            r.hawk_id IN ({hawk_ids_str})
-            AND f.field_name IN ('open_1d', 'high_1d', 'low_1d', 'close_1d', 'volume_1d', 'open_interest_1d')
-            AND r.record_timestamp BETWEEN '{start_date}' AND '{end_date}'
-          GROUP BY 
-            date, ticker
-        )
-        SELECT 
-          date,
-          ticker,
-          open,
-          high,
-          low,
-          close,
-          volume,
-          open_interest
-        FROM 
-          records_data
-        ORDER BY 
-          date;
-        """
-        return self.connector.run_query(query)

hawk-sdk-0.0.0/hawk_sdk.egg-info/PKG-INFO

@@ -1,3 +0,0 @@
-Metadata-Version: 2.1
-Name: hawk-sdk
-Version: 0.0.0

hawk-sdk-0.0.0/hawk_sdk.egg-info/SOURCES.txt

@@ -1,15 +0,0 @@
-README.md
-setup.py
-hawk_sdk/__init__.py
-hawk_sdk.egg-info/PKG-INFO
-hawk_sdk.egg-info/SOURCES.txt
-hawk_sdk.egg-info/dependency_links.txt
-hawk_sdk.egg-info/requires.txt
-hawk_sdk.egg-info/top_level.txt
-hawk_sdk/common/__init__.py
-hawk_sdk/common/bigquery_connector.py
-hawk_sdk/common/data_object.py
-hawk_sdk/futures/__init__.py
-hawk_sdk/futures/main.py
-hawk_sdk/futures/repository.py
-hawk_sdk/futures/service.py