Update main.py

main.py

@@ -55,72 +55,72 @@ def get_data(address, start_date, end_date, radius_miles, get_max):
     
     # Convert Lat Lon to row & col on Array
     try: 
-        transform = pickle.load(open('apcp_hrrr_api/Data/hrrr_crs.pkl', 'rb'))
+        transform = pickle.load(open('Data/hrrr_crs.pkl', 'rb'))
         row, col = rasterio.transform.rowcol(transform['affine'], lon, lat)
     except:
-        transform =row=col=None
+        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
+    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):
@@ -131,6 +131,6 @@ async def predict(address: str, start_date: str, end_date: str, radius_miles: in
     except:
         results = pd.DataFrame({'Date': ['error'], 'APCP_max': ['error']})
 
-    # return results.to_json()
-    return results
+    return results.to_json()
+    # return results