USGS Data Loading#

Import the libraries and USGS TEEHR module.#

from datetime import datetime
from pathlib import Path

from teehr.loading.usgs.usgs import usgs_to_parquet

Define the input parameters.#

OUTPUT_ROOT = Path(Path().home(), "temp")
OUTPUT_DIR = Path(OUTPUT_ROOT, "usgs")

START_DATE = datetime(2023, 2, 20)
END_DATE = datetime(2023, 3, 25)
CHUNK_BY = "month"
OVERWRITE = True

SITES = [
        "02449838",
        "02450825"
]

Fetch and load the data.#

usgs_to_parquet(
    sites=SITES,
    start_date=START_DATE,
    end_date=END_DATE,
    output_parquet_dir=OUTPUT_DIR,
    chunk_by=CHUNK_BY,
    overwrite_output=OVERWRITE
)