old

analysis/generate.py

@@ -0,0 +1,76 @@
+import importlib
+import logging
+import pkgutil
+import shutil
+from pathlib import Path
+
+# The final destination for all generated outputs
+DIST_DIR = Path("dist")
+
+# Configure logging
+logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
+
+def create_all_outputs(processed_df):
+    """
+    Dynamically discovers, imports, and runs all output generators.
+
+    This function iterates through all modules in the 'analysis.generators'
+    package. For each module, it assumes there is a 'generate(data)' function,
+    which it calls with the provided preprocessed DataFrame.
+
+    The generator function is expected to save its output to a temporary file
+    and return the path to that file. This function then moves the output
+
+    to the 'dist/' directory.
+
+    Args:
+        processed_df (pd.DataFrame): The fully preprocessed data to be used
+                                     by the generator functions.
+    """
+    logging.info("Starting output generation...")
+    DIST_DIR.mkdir(exist_ok=True)
+    logging.info(f"Output directory is '{DIST_DIR.resolve()}'")
+
+    # Path to the generators package
+    from . import generators as generators_package
+    generators_path = generators_package.__path__
+    generators_prefix = generators_package.__name__ + "."
+
+    generated_files_count = 0
+
+    # Discover and run all modules in the generators package
+    for _, module_name, _ in pkgutil.iter_modules(generators_path, prefix=generators_prefix):
+        try:
+            logging.info(f"--- Running generator: {module_name} ---")
+
+            # Import the generator module
+            generator_module = importlib.import_module(module_name)
+
+            # Check if the module has the required 'generate' function
+            if not hasattr(generator_module, 'generate'):
+                logging.warning(f"Generator module {module_name} does not have a 'generate' function. Skipping.")
+                continue
+
+            # Call the generator function, passing in the preprocessed data
+            generator_func = getattr(generator_module, 'generate')
+            temp_output_path = generator_func(processed_df)
+
+            # If the generator returned a path, move the file to the dist directory
+            if temp_output_path and isinstance(temp_output_path, Path) and temp_output_path.exists():
+                # Sanitize the module name to create a valid filename
+                base_filename = module_name.split('.')[-1]
+                # Keep the original extension from the temp file
+                final_filename = base_filename + temp_output_path.suffix
+                final_output_path = DIST_DIR / final_filename
+
+                shutil.move(temp_output_path, final_output_path)
+                logging.info(f"Successfully generated '{final_output_path.name}'")
+                generated_files_count += 1
+            else:
+                logging.warning(f"Generator {module_name} did not return a valid output file path. Nothing was saved.")
+
+        except Exception as e:
+            logging.error(f"Failed to run generator {module_name}. Error: {e}", exc_info=True)
+            # Continue to the next generator
+
+    logging.info(f"--- Output generation complete. Total files generated: {generated_files_count} ---")