Pulling monthly total irradiance from the NREL NSRDB API

nrel_nsrdb_monthly.py

import os
import pandas as pd
import itertools

def get_nsrdb_data(
    locations,
    years,
    attributes="ghi",
    leap_day="true",
    interval=60,
    utc="true",
    email="zane.selvans@catalyst.coop",
    api_key=os.environ.get("API_KEY_NREL_NSRDB"),
):
    out_df = pd.DataFrame()
    for (location_id, lat, lon), year in itertools.product(locations, years):
        print(f"Fetching {year} data for location {location_id}.")
        url = (
            "https://developer.nrel.gov/api/solar/nsrdb_psm3_download.csv?"
            f"wkt=POINT({lon}%20{lat})&"
            f"names={year}&"
            f"leap_day={leap_day}&"
            f"interval={interval}&"
            f"email={email}&"
            f"api_key={api_key}&"
            f"attributes={attributes}&"
        )
        # Skip the first two rows to avoid metadata
        df = pd.read_csv(url, skiprows=2)
        df["datetime_utc"] = pd.to_datetime(
            dict(
                year=df["Year"],
                month=df["Month"],
                day=df["Day"],
                hour=df["Hour"],
                minute=df["Minute"],
            )
        )
        df = df.drop(["Year", "Month", "Day", "Hour", "Minute"], axis="columns")
        df = df.set_index("datetime_utc")
        df = df.resample("M").sum()
        df = df.rename_axis(index="month_ending")
        df["GHI"] = df["GHI"] / 1000
        df = df.rename({"GHI": "monthly_sum_ghi_kWh_per_m2"}, axis="columns")
        df["location_id"] = location_id
        df = df[["location_id", "monthly_sum_ghi_kWh_per_m2"]]
        out_df = pd.concat([out_df, df])
        
    return out_df
    
test_locs = [
    ("Boulder", 40.00, -105.30),
    ("Oaxaca de Juarez", 17.10, -96.70),
]

df_out = get_nsrdb_data(
    locations=test_locs,
    years=range(2018, 2020),
    attrs="ghi",
)