File: Sfmdh_2021_loops_jan-apr.rar ... ✰

import re from datetime import datetime

def extract_features(filename): features = {} # File type features['FileExtension'] = filename.split('.')[-1] # Content type (inferred from extension) if features['FileExtension'] == 'rar': features['ContentType'] = 'CompressedArchive' # Temporal and descriptive features match = re.search(r'(\d{4})', filename) if match: features['Year'] = int(match.group(0)) months = re.search(r'(\w+)-(\w+)', filename) if months: month_map = { 'Jan': 1, 'Feb': 2, 'Mar': 3, 'Apr': 4, 'May': 5, 'Jun': 6, 'Jul': 7, 'Aug': 8, 'Sep': 9, 'Oct': 10, 'Nov': 11, 'Dec': 12 } start_month = month_map[months.group(1)] end_month = month_map[months.group(2)] features['MonthsIncluded'] = list(range(start_month, end_month + 1)) # Probable content if 'Loops' in filename: features['ProbableContent'] = 'MusicLoops' # Naming convention components = filename.replace('.rar', '').split('_') features['Prefix'] = components[0] features['Suffix'] = '_'.join(components[1:]) features['FilenameComponents'] = components return features File: SFMDH_2021_Loops_Jan-Apr.rar ...

# Example usage filename = "SFMDH_2021_Loops_Jan-Apr.rar" features = extract_features(filename) for feature, value in features.items(): print(f"{feature}: {value}") This script defines a function extract_features that takes a filename and attempts to extract various features based on its name and extension. The example usage demonstrates how to use this function with the provided filename. File: SFMDH_2021_Loops_Jan-Apr.rar ...