main.py

from fastapi import FastAPI
import uvicorn

import pandas as pd
import numpy as np
import pickle
import rasterio
import h5py
from skimage.morphology import disk
from geopy.extra.rate_limiter import RateLimiter
from geopy.geocoders import Nominatim

app = FastAPI()


#Endpoints
#Root endpoints
@app.get("/")
def root():
    return {"API": "Hail Docker Data"}
    
def geocode_address(address):

    try:
        address2 = address.replace(' ', '+').replace(',', '%2C')
        df = pd.read_json(
            f'https://geocoding.geo.census.gov/geocoder/locations/onelineaddress?address={address2}&benchmark=2020&format=json')
        results = df.iloc[:1, 0][0][0]['coordinates']
        lat, lon = results['y'], results['x']
    except:
        geolocator = Nominatim(user_agent='GTA Lookup')
        geocode = RateLimiter(geolocator.geocode, min_delay_seconds=2)
        location = geolocator.geocode(address)
        lat, lon = location.latitude, location.longitude
        
    return lat, lon

def get_hail_data(address, start_date, end_date, radius_miles, get_max):

    resolution=1 # mrms 1 and hrrr is 3
    radius = int(np.ceil(radius_miles*1.6/resolution))

    
    start_date = pd.Timestamp(str(start_date)).strftime('%Y%m%d')
    end_date = pd.Timestamp(str(end_date)).strftime('%Y%m%d')
    date_years = pd.date_range(start=start_date, end=end_date, freq='M')
    date_range_days = pd.date_range(start_date, end_date)
    years = list(set([d.year for d in date_years]))

    if len(years) == 0:
        years = [pd.Timestamp(start_date).year]
        
    # Geocode Address
    lat, lon= geocode_address(address)

    # Convert Lat Lon to row & col on Array
  
    transform = pickle.load(open('Data/transform_mrms.pkl', 'rb'))
    
    row, col = rasterio.transform.rowcol(transform, lon, lat)

   

    files = [
        'Data/2023_hail.h5',
        'Data/2022_hail.h5',
        'Data/2021_hail.h5',
        'Data/2020_hail.h5'
    ]

    files_choosen = [i for i in files if any(i for j in years if str(j) in i)]

    # Query and Collect H5 Data
    all_data = []
    all_dates = []
    for file in files_choosen:
        with h5py.File(file, 'r') as f:
            # Get Dates from H5
            dates = f['dates'][:]
            date_idx = np.where((dates >= int(start_date))
                                & (dates <= int(end_date)))[0]

            # Select Data by Date and Radius
            dates = dates[date_idx]
            data = f['hail'][date_idx, row-radius_miles:row +
                             radius_miles+1, col-radius_miles:col+radius_miles+1]

            all_data.append(data)
            all_dates.append(dates)

    data_all = np.vstack(all_data)
    dates_all = np.concatenate(all_dates)

    # Convert to Inches
    data_mat = np.where(data_all < 0, 0, data_all)*0.0393701

    # Get Radius of Data
    disk_mask = np.where(disk(radius_miles) == 1, True, False)
    data_mat = np.where(disk_mask, data_mat, -1).round(3)

    # Process to DataFrame
    # Find Max of Data
    if get_max == True:
        data_max = np.max(data_mat, axis=(1, 2))
        df_data = pd.DataFrame({'Date': dates_all,
                               'Hail_max': data_max})
    # Get all Data
    else:
        data_all = list(data_mat)
        df_data = pd.DataFrame({'Date': dates_all,
                               'Hail_all': data_all})

    df_data['Date'] = pd.to_datetime(df_data['Date'], format='%Y%m%d')
    df_data = df_data.set_index('Date')

    df_data = df_data.reindex(date_range_days, fill_value=0).reset_index().rename(
        columns={'index': 'Date'})
    df_data['Date'] = df_data['Date'].dt.strftime('%Y-%m-%d')

    return df_data
   

@app.get('/Hail_Docker_Data')
async def predict(address: str, start_date: str, end_date: str, radius_miles: int, get_max: bool):

    try:
        results = get_hail_data(address, start_date,
                                end_date, radius_miles, get_max)
    except:
        results = pd.DataFrame({'Date': ['error'], 'Hail_max': ['error']})

    return results.to_json()