Data Pipelining With Polygon

    """
    Fetch full historical data for a given product from Polygon API.

    Parameters:
    -----------
    client
        Polygon API client instance.
    ticker : str
        Ticker symbol to download.
    timespan : str
        Time span for the data (e.g., "minute", "hour", "day", "week", "month", "quarter", "year").
    multiplier : int
        Multiplier for the time span (e.g., 1 for daily data).
    adjusted : bool
        If True, return adjusted data; if False, return raw data.
    full_history_df : pd.DataFrame
        DataFrame containing the data.
    current_start : datetime
        Date for which to start pulling data in datetime format.
    free_tier : bool
        If True, then pause to avoid API limits.
    verbose : bool
        If True, print detailed information about the data being processed.

    Returns:
    --------
    full_history_df : pd.DataFrame
        DataFrame containing the data.
    """

from load_api_keys import load_api_keys
from polygon import RESTClient

# Load API keys from the environment
api_keys = load_api_keys()

# Get the environment variable for where data is stored
DATA_DIR = config("DATA_DIR")

# Open client connection
client = RESTClient(api_key=api_keys["POLYGON_KEY"])

# Create an empty DataFrame
df = pd.DataFrame({
    'Date': pd.Series(dtype="datetime64[ns]"),
    'open': pd.Series(dtype="float64"),
    'high': pd.Series(dtype="float64"),
    'low': pd.Series(dtype="float64"),
    'close': pd.Series(dtype="float64"),
    'volume': pd.Series(dtype="float64"),
    'vwap': pd.Series(dtype="float64"),
    'transactions': pd.Series(dtype="int64"),
    'otc': pd.Series(dtype="object")
})

# Example usage - minute
df = polygon_fetch_full_history(
    client=client,
    ticker="AMZN",
    timespan="day",
    multiplier=1,
    adjusted=True,
    full_history_df=df,
    current_start=datetime(2025, 1, 1),
    free_tier=True,
    verbose=True,
)

    """
    Read existing data file, download price data from Polygon, and export data.

    Parameters:
    -----------
    base_directory : any
        Root path to store downloaded data.
    ticker : str
        Ticker symbol to download.
    source : str
        Name of the data source (e.g., 'Polygon').
    asset_class : str
        Asset class name (e.g., 'Equities').
    start_date : datetime
        Start date for the data in datetime format.
    timespan : str
        Time span for the data (e.g., "minute", "hour", "day", "week", "month", "quarter", "year").
    multiplier : int
        Multiplier for the time span (e.g., 1 for daily data).
    adjusted : bool
        If True, return adjusted data; if False, return raw data.
    force_existing_check : bool
        If True, force a complete check of the existing data file to verify that there are not any gaps in the data.
    free_tier : bool
        If True, then pause to avoid API limits.
    verbose : bool
        If True, print detailed information about the data being processed.
    excel_export : bool
        If True, export data to Excel format.
    pickle_export : bool
        If True, export data to Pickle format.
    output_confirmation : bool
        If True, print confirmation message.

    Returns:
    --------
    None
    """

current_year = datetime.now().year
current_month = datetime.now().month
current_day = datetime.now().day

# Example usage - daily
df = polygon_pull_data(
    base_directory=DATA_DIR,
    ticker="AMZN",
    source="Polygon",
    asset_class="Equities",
    start_date=datetime(current_year - 2, current_month, current_day),
    timespan="day",
    multiplier=1,
    adjusted=True,
    force_existing_check=True,
    free_tier=True,
    verbose=True,
    excel_export=True,
    pickle_export=True,
    output_confirmation=True,
)