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
import pyproj

app = FastAPI()


#Endpoints
#Root endpoints
@app.get("/")
def root():
    return {"API": "ACPC HRRR"}


def lat_lon_to_row_col(lat, lon):
    crs_dic = pickle.load(open('hrrr_crs.pkl', 'rb'))
    lon_hrrr, lat_hrrr = crs_dic['proj_4326'].transform(lon, lat)
    row, col = rasterio.transform.rowcol(crs_dic['affine'], lon_hrrr, lat_hrrr)
    return int(row), int(col)
    
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_data(address, start_date, end_date, radius_miles, get_max):

    start_date = pd.Timestamp(str(start_date)).strftime('%Y%m%d%H')
    end_date = pd.Timestamp(str(end_date)).strftime('%Y%m%d%H')
    date_years = pd.date_range(start=start_date[:-2], end=end_date[:-2], freq='M')
    date_range_days = pd.date_range(start_date[:-2], end_date[:-2], freq='H')
    years = list(set([d.year for d in date_years]))

    if len(years) == 0:
        years = [pd.Timestamp(start_date).year]
    
    # Geocode Address
    try:
        lat, lon= geocode_address(address)
    except:
        lat, lon= None,None

    
    # Convert Lat Lon to row & col on Array
    try:
        row, col = lat_lon_to_row_col(lat, lon)
    except:
        row=col=None
   

    files = [
        # 'Data/APCP_2024_hrrr_v2.h5',
        'Data/APCP_2020_hrrr_v3.h5',
        'Data/APCP_2021_hrrr_3.h5',
        'Data/APCP_2022_hrrr_v2.h5',
        # 'Data/APCP_2023_hrrr_v2c.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['date_time_hr'][:]
    #         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['APCP'][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,
    #                            'APCP_max': data_max})
    # # Get all Data
    # else:
    #     data_all = list(data_mat)
    #     df_data = pd.DataFrame({'Date': dates_all,
    #                            'APCP_all': data_all})

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

    # return df_data
    return lat, lon, row, col

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

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

    # return results.to_json()
    return results