Now deleting existing combined csv files after confirmation at start.

* feat: ✨ added the extraction process into the main multi threaded loop
Also added a warning when the app finds existing CSV files in the combined folder

* fix: 🐛 Fixed time calculations for ETA & Completion

README.MD

@@ -15,7 +15,7 @@ The project consists of a main pipeline workflow that processes multiple modules
 
 ### main.py
 
-- **Startup Safety Check**: Scans the `COMBINED_FOLDER` at startup and warns the user if existing files are found, offering a chance to abort to prevent accidental data mixing.
+- **Startup Safety Check**: Scans the `COMBINED_FOLDER` at startup and warns the user if existing files are found, Deleting existing files if continue is accepted.
 - **Batch Processing**: Processes input tar files in configurable batches to manage resource usage.
 - **End-to-End Processing**: Extracts GZ files, processes DAT/ASC, and appends to CSV in a single thread per file.
 - **Concurrency**: Uses multi-threading to process individual GZ files within a batch concurrently.

main.py

@@ -92,13 +92,16 @@ if __name__ == "__main__":
             f"Found {len(existing_combined)} files in {Config.COMBINED_FOLDER}"
         )
         logging.warning(
-            "You may want to remove these before continuing to avoid duplicates or messy data."
+            "If you continue these WILL BE DELETED, Please make sure you have them saved."
         )
         logging.warning("!" * 80)
         response = input("Continue? (Y/N): ").strip().lower()
         if response != "y":
             logging.info("Aborting...")
             exit(0)
+        else:
+            shutil.rmtree(Path(Config.COMBINED_FOLDER))  # Delete everything including the directory
+            Path(Config.COMBINED_FOLDER).mkdir()
 
     extraction = Extract(Config)
     batch = BatchNimrod(Config)
@@ -130,12 +133,6 @@ if __name__ == "__main__":
         # 1. Extract batch (TAR -> GZ)
         logging.info("Extracting tar files for batch")
         extraction.extract_tar_batch(batch_files)
-        # Note: We do NOT run extract_gz_batch anymore. We will find GZ files and process them.
-
-        # Get list of GZ files (recursively or flat?)
-        # extract_tar_batch puts them in GZ_TOP_FOLDER/tar_name_without_ext
-        # So we need to look there.
-        # Ideally we know where we put them.
 
         gz_files_to_process = []
         for tar_file in batch_files:
@@ -167,13 +164,13 @@ if __name__ == "__main__":
 
                     completed_count += 1
                     if completed_count % 100 == 0:
-                        elapsed_time = time.time() - start
-                        rate_per_second = completed_count / elapsed_time
-
                         files_processed_previous = i * files_per_tar
                         files_processed_so_far = (
                             files_processed_previous + completed_count
                         )
+                        
+                        elapsed_time = time.time() - start
+                        rate_per_second = files_processed_so_far / elapsed_time
 
                         remaining_files = estimated_total_files - files_processed_so_far
 
@@ -213,4 +210,11 @@ if __name__ == "__main__":
     end = time.time()
     elapsed_time = end - start
 
-    logging.info(f"All Complete total time {elapsed_time:.2f} seconds")
+    if elapsed_time < 60:
+        elapsed_time_str = f"{int(elapsed_time)}s"
+    elif elapsed_time < 3600:
+        elapsed_time_str = f"{int(elapsed_time // 60)}m {int(elapsed_time % 60)}s"
+    else:
+        elapsed_time_str = f"{int(elapsed_time // 3600)}h {int((elapsed_time % 3600) // 60)}m"
+
+    logging.info(f"All Complete total time {elapsed_time_str}")

pyproject.toml

@@ -1,7 +1,7 @@
 [project]
 name = "met-office"
-version = "1.3.0"
+version = "1.3.2"
-description = "Convert .dat nimrod files to .asc files"
+description = "Convert nimrod files to .csv timeseries"
 readme = "README.md"
 requires-python = ">=3.14"
 dependencies = [

uv.lock

@@ -4,7 +4,7 @@ requires-python = ">=3.14"
 
 [[package]]
 name = "met-office"
-version = "1.3.0"
+version = "1.3.2"
 source = { virtual = "." }
 dependencies = [
     { name = "numpy" },