Spaces:
Sleeping
Sleeping
File size: 4,227 Bytes
89faf7b bccf49f 89faf7b 809b57b 89faf7b 9bb134e 809b57b 89faf7b b52bc3a 809b57b 89faf7b b52bc3a 471dfc4 b52bc3a 471dfc4 b52bc3a 89faf7b 471dfc4 89faf7b b6f337f 89faf7b 809b57b 89faf7b 809b57b 89faf7b 471dfc4 89faf7b |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 |
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": "ACPC HRRR"}
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:
transform = pickle.load(open('Data/hrrr_crs.pkl', 'rb'))
row, col = rasterio.transform.rowcol(transform['affine'], lon, lat)
except:
row=col=1000
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, transform, 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
|