Update app.py

app.py

@@ -4,10 +4,12 @@ Created on Fri Oct 14 10:35:25 2022
 
 @author: mritchey
 """
-from tqdm import tqdm
-from joblib import Parallel, delayed
+# streamlit run "C:\Users\mritchey\.spyder-py3\Python Scripts\streamlit projects\hail\hail h5.py"
+
+import gzip
+import pickle
+import h5py
 import rasterio
-import glob
 from PIL import Image
 import streamlit as st
 import os
@@ -24,10 +26,12 @@ import xarray as xr
 import warnings
 warnings.filterwarnings("ignore")
 
+
 @st.cache_data
 def convert_df(df):
     return df.to_csv(index=0).encode('utf-8')
 
+
 def geocode(address):
     try:
         address2 = address.replace(' ', '+').replace(',', '%2C')
@@ -51,10 +55,14 @@ def map_folium(data, zoom=12):
 
     # folium.GeoJson(gdf['buffer']).add_to(m)
     folium.raster_layers.ImageOverlay(
-        data, opacity=0.8, bounds=[[bottom, left], [top, right]]).add_to(m)
+        data, opacity=0.8, bounds=[[bottom, left], [top, right]],
+        interactive=True
+    ).add_to(m)
     return m
 
-@st.cache_data
+# @st.cache_data
+
+
 def crop_hail_jpg_filter(f, crop_coords, scaling_factor=255):
     date = f[-19:-11]
     image = Image.open(f)
@@ -62,68 +70,80 @@ def crop_hail_jpg_filter(f, crop_coords, scaling_factor=255):
     image = (np.array(cropped_image)/scaling_factor)
     if image.sum() > 0:
         return date, image
-    
-@st.cache_data   
-def get_data(start_date,end_date,crop_coords):
-    files = glob.glob(f'png/**/*.png', recursive=True)
-    
-    files_dates = np.array([int(f[-19:-11]) for f in files])
-    mask = np.where((files_dates >= int(start_date)) & (
-        files_dates <= int(end_date)), True, False)
-    files = np.array(files)[mask]
-    
-    results = Parallel(n_jobs=96, prefer='threads')(
-        delayed(crop_hail_jpg_filter)(i, crop_coords) for i in tqdm(files))
-    results = [i for i in results if i is not None]
-
-    return results
+
+# @st.cache_data
+
+
+def get_data(row, col, radius):
+    files = [
+        "2023_hail.h5",
+        "2022_hail.h5"]
+
+    all_data = []
+    all_dates = []
+    for f in files:
+        with h5py.File(f, 'r') as f:
+            data = f['hail'][:, row-radius:row +
+                             radius+1, col-radius:col+radius+1]
+            dates = f['dates'][:]
+            all_data.append(data)
+            all_dates.append(dates)
+
+    data_mat = np.concatenate(all_data)
+    data_mat = np.where(data_mat < 0, 0, data_mat)*0.0393701
+    dates_mat = np.concatenate(all_dates)
+
+    data_actual = [i[radius, radius] for i in data_mat]
+    data_max = np.max(data_mat, axis=(1, 2))
+    data_max_2 = np.max(data_mat, axis=0)
+
+    df = pd.DataFrame({'Date': dates_mat,
+                       'Actual': data_actual,
+                      'Max': data_max})
+
+    df['Date'] = pd.to_datetime(df['Date'], format='%Y%m%d')
+
+    return df, data_max_2
+
 
 #Set up 2 Columns
 st.set_page_config(layout="wide")
 col1, col2 = st.columns((2))
 
+os.chdir(r'C:\Users\mritchey')
 
 
 #Input Values
 address = st.sidebar.text_input("Address", "123 Main Street, Dallas, TX 75126")
-d = st.sidebar.date_input("Date",  pd.Timestamp(2022, 7, 1))
-days_within = st.sidebar.selectbox('Days Within:', ('30', '90', '180', 'Day Of',))
+start_date = st.sidebar.date_input("Start Date",  pd.Timestamp(2022, 1, 1))
+end_date = st.sidebar.date_input("End Date",  pd.Timestamp(2023, 12, 31))
+
+
 circle_radius = st.sidebar.selectbox('Box Radius (Miles)', (5, 10, 25))
 
 zoom_dic = {5: 12, 10: 11, 25: 10}
 zoom = zoom_dic[circle_radius]
 
-try:
-    days_within = int(days_within)
-    start_date, end_date = d - \
-        pd.Timedelta(days=days_within), d+pd.Timedelta(days=days_within+1)
-    start_date, end_date = start_date.strftime(
-        '%Y%m%d'), end_date.strftime('%Y%m%d')
-except:
-    days_within = 0
-    start_date = end_date=d -pd.Timedelta(days=days_within)
-    start_date = end_date=start_date.strftime('%Y%m%d')
 #Geocode and get Data
 result = geocode(address)
 lat, lon = result.values[0]
 
-ds_stage = xr.open_rasterio('hail_stage.grib2')
-transform = ds_stage.rio.transform()
 
+#Raster Data
+extracted_file = 'hail_stage.grib2'
+ds_stage = xr.open_dataarray(extracted_file,engine='rasterio')
+transform = ds_stage.rio.transform()
 row, col = rasterio.transform.rowcol(transform, lon, lat)
 
-# center=row,col
-radius = int(np.ceil(circle_radius*1.6))  
+
+radius = int(np.ceil(circle_radius*1.6))
 crop_coords = col-radius, row-radius, col+radius+1, row+radius+1
 
 # Get Data
-results=get_data(start_date,end_date,crop_coords)
-    
+df_data, max_values = get_data(row, col, radius)
+
+df_data=df_data.query(f"'{start_date}'<=Date<='{end_date}'")
 
-try:
-    max_values = np.max(np.array([i[1] for i in results]), axis=0)*0.0393701
-except:
-    max_values=np.zeros(shape=(2*radius+1,2*radius+1))
 
 # Bin Data
 bin_edges = [0, 0.1, 0.2, 0.4, 0.8, 1.2, 1.6, 2, 3, 4, np.inf]
@@ -133,38 +153,26 @@ colors_values = ['#ffffff', '#ffff00', '#d1ab00', '#ff9b00', '#fe0000', '#cd0000
                  '#ff30cd', '#9a009b', '#4a4d4c']
 color_discrete_map = dict(zip(bin_names, colors_values))
 
-all_data = []
-for date, mat in results:
-    mat = mat*0.0393701
-    hist_values, _ = np.histogram(mat, bins=bin_edges)
-    df = pd.DataFrame({'bin_edges': bin_edges[:-1],
-                       'Bin': bin_names,
-                       'Values': hist_values},
-                      )
-    df['Date'] = pd.to_datetime(date)
-    all_data.append(df)
-
-try:
-    final = pd.concat(all_data)
-    final = final.query('bin_edges!=0')
-    fig = px.bar(final, x="Date", y="Values", color="Bin",
-                 barmode="stack",
-                 color_discrete_map=color_discrete_map)
-except:
-    pass
 
+fig = px.bar(df_data, x="Date", y="Actual", color="Actual",
+             # barmode="stack",
+             # color='red',
+             # color_discrete_map=color_discrete_map,
+
+             )
 
 # Crop the raster using the bounds
 cropped_data = ds_stage[0][row-radius:row+radius+1, col-radius:col+radius+1]
 cropped_data.values = max_values
 
-# Max Values Bin for RGB
 
+# Max Values Bin for RGB
 def hex_to_rgb(hex_code):
     hex_code = hex_code.lstrip('#')  # Remove the '#' character if present
     rgb = tuple(int(hex_code[i:i+2], 16) for i in (0, 2, 4))
     return rgb
 
+
 def hex_to_rgba(hex_code, alpha=.8):
     if hex_code == '#ffffff':
         alpha = 0.0
@@ -182,10 +190,10 @@ max_values_rgb = np.array([hex_to_rgba(i) for i in bin_colors.flatten()]).reshap
     max_values.shape[0], max_values.shape[0], 4)
 
 
-
 #Mapping
 img = max_values_rgb.astype('uint8')
 
+
 boundary = cropped_data.rio.bounds()
 left, bottom, right, top = boundary
 
@@ -197,10 +205,10 @@ clon = (left + right)/2
 vmin = np.floor(np.nanmin(img))
 vmax = np.ceil(np.nanmax(img))
 
-# colormap = cm.StepColormap(colors=list(color_discrete_map.values()),
-#                            index=bin_edges,
-#                            # vmin=vmin, vmax=vmax
-#                            )
+colormap = cm.StepColormap(colors=list(color_discrete_map.values()),
+                           index=bin_edges,
+                           # vmin=vmin, vmax=vmax
+                           )
 
 
 m = map_folium(img, zoom)
@@ -215,7 +223,7 @@ with col2:
     st.title(f'Hail')
     try:
         st.plotly_chart(fig)
-        csv = convert_df(final)
+        csv = convert_df(df_data)
         st.download_button(
             label="Download data as CSV",
             data=csv,