His Brother 39-s Wife 1936 Ok.ru Direct

You can drop these directly into a feature‑engineering pipeline (e.g., for a text‑classification, user‑profiling, or recommendation model).

text = "his brother 39-s wife 1936 ok.ru" his brother 39-s wife 1936 ok.ru

def extract_features(txt): feats = {} # 1. relation feats['relation_to_subject'] = re.search(r'\b(brother|sister|father|mother|son|daughter|uncle|aunt)\b', txt).group(0) # 2. gender feats['subject_gender'] = 'male' if 'his' in txt else ('female' if 'her' in txt else 'unknown') # 3‑4. spouse age age_match = re.search(r'(\d+)-s', txt) feats['spouse_age_exact'] = int(age_match.group(1)) if age_match else None # 5‑6. birth year year_match = re.search(r'\b(19|20)\d2\b', txt) feats['spouse_birth_year'] = int(year_match.group(0)) if year_match else None # 7‑8. platform feats['social_media_platform'] = 'ok.ru' if 'ok.ru' in txt else None feats['platform_region'] = 'Russia' if feats['social_media_platform'] else None # 9‑11. numeric tokens numeric_tokens = re.findall(r'\d+', txt) feats['contains_numeric_token'] = bool(numeric_tokens) feats['numeric_token_count'] = len(numeric_tokens) feats['token_length'] = len(txt.split()) # 12‑13. pronoun & language hint feats['has_possessive_pronoun'] = any(p in txt for p in ['his', 'her', 'their']) feats['language_hint'] = 'Russian-orientated' if 'ok.ru' in txt else 'generic' # 14‑15. consistency check if feats['spouse_birth_year']: current_year = 2024 computed_age = current_year - feats['spouse_birth_year'] if feats['spouse_age_exact'] is not None: diff = abs(computed_age - feats['spouse_age_exact']) feats['age_year_consistency'] = 'consistent' if diff <= 5 else 'inconsistent' else: feats['age_year_consistency'] = None else: feats['age_year_consistency'] = None # 16. surname placeholder flag feats['has_surname_placeholder'] = bool(re.search(r'\d+-s', txt)) You can drop these directly into a feature‑engineering

return feats

print(extract_features(text))