Upload 2 files

app.py

@@ -0,0 +1,157 @@
+# -*- coding: utf-8 -*-
+"""
+Created on Thu Jun  8 03:39:02 2023
+
+@author: mritchey
+"""
+# streamlit run "C:\Users\mritchey\.spyder-py3\Python Scripts\streamlit projects\hail\hail all.py"
+
+import pandas as pd
+import numpy as np
+import streamlit as st
+from geopy.extra.rate_limiter import RateLimiter
+from geopy.geocoders import Nominatim
+import folium
+from streamlit_folium import st_folium
+from vincenty import vincenty
+import duckdb
+
+st.set_page_config(layout="wide")
+
+
+@st.cache_data
+def convert_df(df):
+    return df.to_csv(index=0).encode('utf-8')
+
+
+def duck_sql(sql_code):
+    con = duckdb.connect()
+    con.execute("PRAGMA threads=2")
+    con.execute("PRAGMA enable_object_cache")
+    return con.execute(sql_code).df()
+
+
+def get_data(lat, lon, date_str):
+    code = f"""
+        select "#ZTIME" as "Date_utc", LON, LAT, MAXSIZE 
+          from 
+          'data/*.parquet'
+                 where LAT<={lat}+1 and LAT>={lat}-1
+                 and LON<={lon}+1 and LON>={lon}-1
+                 and "#ZTIME"<={date_str}
+    
+    """
+    duck_sql(code)
+    return duck_sql(code)
+
+
+def map_perimeters(address, lat, lon):
+
+    m = folium.Map(location=[lat, lon],
+
+                   zoom_start=6,
+                   height=400)
+    folium.Marker(
+        location=[lat, lon],
+        tooltip=f'Address: {address}',
+    ).add_to(m)
+
+    return m
+
+
+def distance(x):
+    left_coords = (x[0], x[1])
+    right_coords = (x[2], x[3])
+    return vincenty(left_coords, right_coords, miles=True)
+
+
+def geocode(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=1)
+        location = geolocator.geocode(address)
+        lat, lon = location.latitude, location.longitude
+    return lat, lon
+
+
+#Side Bar
+address = st.sidebar.text_input(
+    "Address", "Dallas, TX")
+date = st.sidebar.date_input(
+    "Loss Date",  pd.Timestamp(2023, 7, 14), key='date')
+date_str = date.strftime("%Y%m%d")
+
+#Geocode Addreses
+lat, lon = geocode(address)
+
+#Filter Data
+df_hail_cut = get_data(lat, lon, date_str)
+
+
+df_hail_cut["Lat_address"] = lat
+df_hail_cut["Lon_address"] = lon
+df_hail_cut['Miles to Hail'] = [
+    distance(i) for i in df_hail_cut[['LAT', 'LON', 'Lat_address', 'Lon_address']].values]
+df_hail_cut['MAXSIZE'] = df_hail_cut['MAXSIZE'].round(1)
+
+df_hail_cut = df_hail_cut.query("`Miles to Hail`<10")
+df_hail_cut['Category'] = np.where(df_hail_cut['Miles to Hail'] < .25, "At Location",
+                                   np.where(df_hail_cut['Miles to Hail'] < 1, "Within 1 Mile",
+                                            np.where(df_hail_cut['Miles to Hail'] < 3, "Within 3 Miles",
+                                                     np.where(df_hail_cut['Miles to Hail'] < 10, "Within 10 Miles", 'Other'))))
+
+df_hail_cut_group = pd.pivot_table(df_hail_cut, index='Date_utc',
+                                   columns='Category',
+                                   values='MAXSIZE',
+                                   aggfunc='max')
+
+cols = df_hail_cut_group.columns
+cols_focus = ['At Location', "Within 1 Mile",
+              "Within 3 Miles", "Within 10 Miles"]
+
+missing_cols = set(cols_focus)-set(cols)
+for c in missing_cols:
+    df_hail_cut_group[c] = np.nan
+
+df_hail_cut_group2 = df_hail_cut_group[cols_focus].query(
+    "`Within 3 Miles`==`Within 3 Miles`")
+
+for i in range(3):
+    df_hail_cut_group2[cols_focus[i+1]] = np.where(df_hail_cut_group2[cols_focus[i+1]].fillna(0) <
+                                                   df_hail_cut_group2[cols_focus[i]].fillna(
+                                                       0),
+                                                   df_hail_cut_group2[cols_focus[i]],
+                                                   df_hail_cut_group2[cols_focus[i+1]])
+
+
+df_hail_cut_group2 = df_hail_cut_group2.sort_index(ascending=False)
+
+df_hail_cut_group2.index = pd.to_datetime(
+    df_hail_cut_group2.index, format='%Y%m%d').strftime("%Y-%m-%d")
+
+
+#Map Data
+m = map_perimeters(address, lat, lon)
+
+#Display
+col1, col2 = st.columns((3, 2))
+
+with col1:
+    st.header('Estimated Maximum Hail Size')
+    st.write('Data from 2010 to 2023-09-24')
+    df_hail_cut_group2
+    csv2 = convert_df(df_hail_cut_group2.reset_index())
+    st.download_button(
+        label="Download data as CSV",
+        data=csv2,
+        file_name=f'{address}_{date_str}.csv',
+        mime='text/csv')
+with col2:
+    st.header('Map')
+    st_folium(m, height=400)

requirements.txt

@@ -0,0 +1,8 @@
+folium
+geopy
+numpy
+pandas
+streamlit
+streamlit_folium
+vincenty
+duckdb