hawk-sdk 0.0.0__tar.gz

hawk-sdk-0.0.0/PKG-INFO

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

hawk-sdk-0.0.0/README.md

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

hawk-sdk-0.0.0/hawk_sdk/__init__.py

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

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

@@ -0,0 +1,47 @@
+"""
+@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/common/data_object.py

@@ -0,0 +1,39 @@
+import pandas as pd
+
+
+class DataObject:
+    def __init__(self, name, data):
+        self.__name = name
+        self.__data = data
+
+    def to_df(self) -> pd.DataFrame:
+        """Exports data to a pandas DataFrame.
+
+        :return: pd.Dataframe
+        """
+        return self.__data
+
+    def to_csv(self, file_name):
+        """Exports data to an Excel file.
+
+        :param file_name: The name of the output Excel file.
+        :return: None
+        """
+        self.__data.to_csv(file_name, index=False)
+
+    def to_xlsx(self, file_name):
+        """Exports data to an Excel file.
+
+        :param file_name: The name of the output Excel file.
+        :return: None
+        """
+        self.__data.to_excel(file_name, index=False)
+
+    def show(self, n=5):
+        """Print the first n rows of the data.
+
+        :param n: Number of rows to print.
+        :return: None, prints the head of the data.
+        """
+        print(self.__name)
+        print(self.__data.head(n))

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

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

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

@@ -0,0 +1,39 @@
+"""
+@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
+
+
+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)
+        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 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="futures_ohlcvo",
+            data=self.service.get_ohlcvo(start_date, end_date, interval, hawk_ids)
+        )
+

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

@@ -0,0 +1,70 @@
+"""
+@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/futures/service.py

@@ -0,0 +1,40 @@
+"""
+@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
+
+
+class FuturesService:
+    """Service class for Futures business logic."""
+
+    def __init__(self, repository: FuturesRepository) -> None:
+        """Initializes the service with a repository.
+
+        :param repository: An instance of FuturesRepository for data access.
+        """
+        self.repository = repository
+
+    def get_ohlcvo(self, start_date: str, end_date: str, interval: str, hawk_ids: List[int]) -> pd.DataFrame:
+        """Fetches 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_ohlcvo(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-0.0.0/hawk_sdk.egg-info/PKG-INFO

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

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

@@ -0,0 +1,15 @@
+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

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

@@ -0,0 +1 @@
+

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

@@ -0,0 +1,2 @@
+google-cloud-bigquery
+pandas

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

@@ -0,0 +1 @@
+hawk_sdk

hawk-sdk-0.0.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

hawk-sdk-0.0.0/setup.py

@@ -0,0 +1,11 @@
+from setuptools import setup, find_packages
+
+setup(
+    name='hawk-sdk',
+    version='0.0.0',
+    packages=find_packages(),
+    install_requires=[
+        'google-cloud-bigquery',
+        'pandas'
+    ],
+)