chore: 🔧 More cleaning

config.py

@@ -1,36 +1,6 @@
-import yaml
-import logging
-
 class Config:
-    def __init__(self) -> None:
+    DAT_TOP_FOLDER = "./dat_files"
-        self.IN_TOP_FOLDER = "./dat_files"
+    ASC_TOP_FOLDER = "./asc_files"
-        self.OUT_TOP_FOLDER = "./asc_files"
+    CSV_TOP_FOLDER = "./csv_files"
-        self.CSV_TOP_FOLER = "./csv_files"
+    AREAS_FILE = 'areas.csv'
-        self.AREAS_FILE = 'areas.csv'
-
-    
-
-    def load_areas(self) -> dict:
-        """
-        Load configuration from YAML file.
-
-        Returns:
-            dict: Configuration dictionary containing bounding box information.
-
-        Raises:
-            FileNotFoundError: If the config.yaml file is not found.
-            yaml.YAMLError: If there's an error parsing the YAML file.
-        """
-        try:
-            with open(, "r") as file:
-                config = yaml.safe_load(file)
-                return config.get("bounding_box_info", {})
-        except FileNotFoundError:
-            logging.error(
-                f"Config file {CONFIG_FILE} not found. Using default configuration."
-            )
-            return {}
-        except yaml.YAMLError as e:
-            logging.error(f"Error parsing YAML file: {e}")
-            return {}
 

config.yaml

@@ -1,3 +0,0 @@
-IN_TOP_FOLDER: "./dat_files"
-OUT_TOP_FOLDER: "./asc_files"
-CSV_TOP_FOLER: "./csv_files"

main.py

@@ -1,46 +1,48 @@
 import logging
-import yaml
+import time
+import os
+from pathlib import Path
 
-CONFIG_FILE = "config.yaml"
+from config import Config
+from modules import BatchNimrod, GenerateTimeseries
 
 logging.basicConfig(
     level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s"
 )
 
-def load_config() -> dict:
+if __name__ == "__main__":
-    """
+    os.makedirs(Path(Config.ASC_TOP_FOLDER), exist_ok=True)
-    Load configuration from YAML file.
+    os.makedirs(Path(Config.CSV_TOP_FOLDER), exist_ok=True)
+    dat_file_count = [f for f in os.listdir(Path(Config.DAT_TOP_FOLDER))]
+    asc_file_count = [f for f in os.listdir(Path(Config.ASC_TOP_FOLDER))]
 
-    Returns:
+    locations = [
-        dict: Configuration dictionary containing bounding box information.
+        # loc name, loc id, x loc,   y loc,  resolution
+        ["BRICSC", "TM0816", 608500, 216500, 1000],  
+        ["HEACSC", "TF6842", 568500, 342500, 1000], 
+    ]
 
-    Raises:
+    batch = BatchNimrod(Config)
-        FileNotFoundError: If the config.yaml file is not found.
+    timeseries = GenerateTimeseries(Config)
-        yaml.YAMLError: If there's an error parsing the YAML file.
-    """
-    try:
-        with open(CONFIG_FILE, "r") as file:
-            config = yaml.safe_load(file)
-            return config.get("bounding_box_info", {})
-    except FileNotFoundError:
-        logging.error(
-            f"Config file {CONFIG_FILE} not found. Using default configuration."
-        )
-        return {}
-    except yaml.YAMLError as e:
-        logging.error(f"Error parsing YAML file: {e}")
-        return {}
 
+    start = time.time()
+    logging.info("Starting to process DAT to ASC")
+    if dat_file_count != asc_file_count:
+        batch.process_nimrod_files()
+        batch_checkpoint = time.time()
+        elapsed_time = batch_checkpoint - start
+        logging.info(f"DAT to ASC completed in {elapsed_time:.2f} seconds")
+    else:
+        logging.info("No need to process DAT files, skipping...")
+        time.sleep(1)
 
-os.makedirs(Path(OUT_TOP_FOLDER), exist_ok=True)
+    for place in locations:
-os.makedirs(Path(CSV_TOP_FOLDER), exist_ok=True)
+        logging.info(f'{place[0]} started generating timeseries data.')
+        timeseries.extract_cropped_rain_data(place)
+        place_checkpoint = time.time()
+        since_asc_create = place_checkpoint - batch_checkpoint
+        elapsed_time = place_checkpoint - start
+        logging.info(f"{place[0]} completed in {since_asc_create:.2f} seconds")
+        logging.info(f'total time so far {elapsed_time:.2f} seconds')
     
-
+    logging.info(f'All Complete')
-
-
-# if __name__ == "__main__":
-#     start = time.time()
-#     process_nimrod_files()
-#     end = time.time()
-#     elapsed_time = end - start
-#     logging.info(f"Processing completed in {elapsed_time:.2f} seconds")

modules/__init__.py

@@ -1,2 +1,3 @@
 from .nimrod import Nimrod
-from .batch_nimrod import process_nimrod_files
+from .batch_nimrod import BatchNimrod
+from .generate_timeseries import GenerateTimeseries

modules/batch_nimrod.py

@@ -13,22 +13,22 @@ class BatchNimrod():
         Process all Nimrod files in the input directory, applying bounding box clipping
         and exporting to ASC format.
 
-        This function reads all files from IN_TOP_FOLDER, applies the appropriate bounding
+        This function reads all files from DAT_TOP_FOLDER, applies the appropriate bounding
         box for each area, and exports clipped raster data to OUT_TOP_FOLDER.
         """
         # Read all file names in the folder
-        files_to_process = [f for f in os.listdir(Path(self.config.IN_TOP_FOLDER))]
+        files_to_process = [f for f in os.listdir(Path(self.config.DAT_TOP_FOLDER))]
 
         logging.info(f"Processing {len(files_to_process)} files...")
 
-        for in_file in os.listdir(Path(self.config.IN_TOP_FOLDER)):
+        for in_file in os.listdir(Path(self.config.DAT_TOP_FOLDER)):
-            in_file_full = Path(self.config.IN_TOP_FOLDER, in_file)
+            in_file_full = Path(self.config.DAT_TOP_FOLDER, in_file)
 
             try:
                 image = Nimrod(open(in_file_full, "rb"))
 
                 out_file_name = f"{image.get_validity_time()}.asc"
-                out_file_path = Path(self.config.OUT_TOP_FOLDER, out_file_name)
+                out_file_path = Path(self.config.ASC_TOP_FOLDER, out_file_name)
 
                 with open(out_file_path, "w") as outfile:
                     image.extract_asc(outfile)

modules/generate_timeseries.py

@@ -4,12 +4,12 @@ import glob
 import pandas as pd
 from datetime import datetime
 
-# Configuration
-asc_path = "asc_files/"
-asc_wildcard_file = "*.asc"
-asc_mult_source = asc_path + asc_wildcard_file
 
-def read_ascii_header(ascii_raster_file: str) -> list:
+class GenerateTimeseries:
+    def __init__(self, config):
+        self.config = config
+
+    def _read_ascii_header(self, ascii_raster_file: str) -> list:
         """Reads header information from an ASCII DEM
 
         Args:
@@ -23,7 +23,7 @@ def read_ascii_header(ascii_raster_file: str) -> list:
         return header_data
 
 
-def calculate_crop_coords(basin_header: list, radar_header: list) -> tuple:
+    def _calculate_crop_coords(self, basin_header: list, radar_header: list) -> tuple:
         """Calculate crop coordinates based on header data
 
         Args:
@@ -41,8 +41,8 @@ def calculate_crop_coords(basin_header: list, radar_header: list) -> tuple:
 
         nrows_radar = radar_header[1]
 
-    nrows_basin = 2  # hardcoded, we always expect 2 rows
+        nrows_basin = 2  # hardcoded, likely to change?
-    ncols_basin = 2  # hardcoded, we always expect 2 columns
+        ncols_basin = 2  # hardcoded, likely to change?
 
         cellres_radar = radar_header[4]
         cellres_basin = basin_header[4]
@@ -63,21 +63,19 @@ def calculate_crop_coords(basin_header: list, radar_header: list) -> tuple:
         return int(start_col), int(start_row), int(end_col), int(end_row)
 
 
-def extract_cropped_rain_data(location):
+    def extract_cropped_rain_data(self, location):
         """Extract cropped rain data and create rainfall timeseries
 
         Returns:
             None
         """
         rainfile = []
-
-    # Create datetime list
         datetime_list = []
-    print(location)
+
-    for f in glob.iglob(asc_mult_source):
+        for f in glob.iglob(f'{self.config.ASC_TOP_FOLDER}/*.asc'):
             # print(f)
-        radar_header = read_ascii_header(f)
+            radar_header = self._read_ascii_header(f)
-        start_col, start_row, end_col, end_row = calculate_crop_coords(
+            start_col, start_row, end_col, end_row = self._calculate_crop_coords(
                 location, radar_header
             )
 
@@ -93,11 +91,10 @@ def extract_cropped_rain_data(location):
             cur_croppedrain = cur_rawgrid[start_row:end_row, start_col:end_col]
             # Flatten the cropped rain data into a 1D array
             cur_rainrow = cur_croppedrain.flatten()
-        rainfile.append(cur_rainrow)
+            rainfile.append(cur_rainrow[2]/32)
 
             # Extract datetime from filename
             filename = f.split("/")[-1]  # Get just the filename
-        # 20240929 0015
             date_str = filename[:8]  # YYYYMMDD
             time_str = filename[8:12]  # HHMM
 
@@ -112,16 +109,8 @@ def extract_cropped_rain_data(location):
         # sort the dataframe into date order 
         sorted_df = df.sort_index()
         # add headers 
-    header_row = ['rainfall_1', 'rainfall_2', 'rainfall_3', 'rainfall_4']
+        header_row = [location[1]]
         file_name = f"csv_files/{location[0]}_timeseries_data.csv"
         sorted_df.to_csv(file_name, sep=",", float_format="%1.4f", header=header_row, index_label='datetime')
 
 
-if __name__ == "__main__":
-    locations = [
-        # loc name, loc id, x loc,   y loc,  resolution
-        ["BRICSC", "TM0816", 608500, 216500, 1000],  
-        ["HEACSC", "TF6842", 568500, 342500, 1000], 
-    ]
-    for place in locations:
-        extract_cropped_rain_data(place)