File size: 44,205 Bytes
9101d7e |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 |
#!/usr/bin/env python3
"""
Advanced Synthetic Data Generator v4.0
======================================
New Features:
1. Markov Chain for realistic message flow
2. Real data calibration from actual samples
3. Multilingual support (Hindi, Tamil, Telugu, Bengali, Kannada)
4. PDF/Image generation for document training
5. Statistical augmentation for rare edge cases
Author: Ranjit Behera
"""
from __future__ import annotations
import json
import random
import hashlib
import argparse
import math
import pickle
from abc import ABC, abstractmethod
from dataclasses import dataclass, field, asdict
from datetime import datetime, timedelta, date
from decimal import Decimal, ROUND_HALF_UP
from enum import Enum, auto
from pathlib import Path
from typing import List, Dict, Optional, Tuple, Set, Any, Iterator
from collections import defaultdict, Counter
import re
# ============================================================================
# MARKOV CHAIN MESSAGE GENERATOR
# ============================================================================
class MarkovChain:
"""
Markov Chain for realistic message structure.
Learns transition probabilities from real data to generate
messages that follow actual patterns.
"""
def __init__(self, order: int = 2):
"""
Args:
order: n-gram order (1 = unigram, 2 = bigram, etc.)
"""
self.order = order
self.transitions: Dict[Tuple, Counter] = defaultdict(Counter)
self.start_states: Counter = Counter()
def train(self, messages: List[str]):
"""Train on real messages."""
for message in messages:
tokens = self._tokenize(message)
if len(tokens) <= self.order:
continue
# Start state
start = tuple(tokens[:self.order])
self.start_states[start] += 1
# Build transitions
for i in range(len(tokens) - self.order):
state = tuple(tokens[i:i + self.order])
next_token = tokens[i + self.order]
self.transitions[state][next_token] += 1
def _tokenize(self, text: str) -> List[str]:
"""Tokenize preserving structure."""
# Split on whitespace but keep special tokens
tokens = []
for word in text.split():
# Keep amounts as single tokens
if re.match(r'^Rs\.?\d', word) or re.match(r'^₹\d', word):
tokens.append(word)
# Keep VPAs together
elif '@' in word:
tokens.append(word)
else:
tokens.append(word)
return tokens
def generate(self, rng: random.Random, max_length: int = 50) -> str:
"""Generate a message using learned transitions."""
if not self.start_states:
return ""
# Sample start state
states = list(self.start_states.keys())
weights = [self.start_states[s] for s in states]
current = list(rng.choices(states, weights=weights)[0])
result = list(current)
for _ in range(max_length - len(current)):
state = tuple(current[-self.order:])
if state not in self.transitions:
break
# Sample next token
next_tokens = list(self.transitions[state].keys())
weights = [self.transitions[state][t] for t in next_tokens]
next_token = rng.choices(next_tokens, weights=weights)[0]
result.append(next_token)
current.append(next_token)
return ' '.join(result)
def save(self, path: Path):
"""Save trained model."""
with open(path, 'wb') as f:
pickle.dump({
'order': self.order,
'transitions': dict(self.transitions),
'start_states': dict(self.start_states),
}, f)
@classmethod
def load(cls, path: Path) -> 'MarkovChain':
"""Load trained model."""
with open(path, 'rb') as f:
data = pickle.load(f)
chain = cls(order=data['order'])
chain.transitions = defaultdict(Counter, {
k: Counter(v) for k, v in data['transitions'].items()
})
chain.start_states = Counter(data['start_states'])
return chain
class HybridGenerator:
"""
Combines Markov Chain with template-based generation.
Uses Markov for structure, templates for entity placement.
"""
def __init__(self, markov: MarkovChain):
self.markov = markov
self.entity_patterns = {
'AMOUNT': r'Rs\.?\s*[\d,]+(?:\.\d{2})?',
'ACCOUNT': r'XX\d{4}',
'DATE': r'\d{1,2}[-/]\d{1,2}[-/]\d{2,4}',
'REF': r'\d{12,16}',
'VPA': r'[a-z0-9]+@[a-z]+',
}
def generate(self, entities: Dict[str, str], rng: random.Random) -> str:
"""
Generate message with specific entities.
1. Generate base structure from Markov
2. Replace placeholders with actual entities
"""
base = self.markov.generate(rng)
# Replace detected patterns with actual entities
for entity_type, pattern in self.entity_patterns.items():
if entity_type in entities:
base = re.sub(pattern, entities[entity_type], base, count=1)
return base
# ============================================================================
# REAL DATA CALIBRATION
# ============================================================================
@dataclass
class DistributionFit:
"""Fitted statistical distribution."""
name: str
params: Dict[str, float]
def sample(self, rng: random.Random) -> float:
"""Sample from fitted distribution."""
if self.name == 'normal':
value = rng.gauss(self.params['mean'], self.params['std'])
return max(self.params.get('min', 0),
min(self.params.get('max', float('inf')), value))
elif self.name == 'lognormal':
# Log-normal is better for amounts
log_value = rng.gauss(self.params['mu'], self.params['sigma'])
return math.exp(log_value)
elif self.name == 'exponential':
return rng.expovariate(1 / self.params['lambda'])
elif self.name == 'uniform':
return rng.uniform(self.params['min'], self.params['max'])
elif self.name == 'categorical':
items = list(self.params['categories'].keys())
weights = list(self.params['categories'].values())
return rng.choices(items, weights=weights)[0]
return 0
class DataCalibrator:
"""
Calibrate synthetic distributions to match real data.
Fits statistical distributions to actual transaction data.
"""
def __init__(self):
self.amount_dist: Optional[DistributionFit] = None
self.category_dist: Optional[DistributionFit] = None
self.bank_dist: Optional[DistributionFit] = None
self.hour_dist: Optional[DistributionFit] = None
# Amount by category
self.amount_by_category: Dict[str, DistributionFit] = {}
def fit_from_data(self, data: List[Dict]):
"""Fit distributions from real data."""
if not data:
return
# Extract amounts
amounts = [r['amount'] for r in data if r.get('amount')]
if amounts:
mean_amt = sum(amounts) / len(amounts)
var_amt = sum((x - mean_amt) ** 2 for x in amounts) / len(amounts)
std_amt = math.sqrt(var_amt)
# Use log-normal for amounts (always positive, right-skewed)
log_amounts = [math.log(max(1, a)) for a in amounts]
mu = sum(log_amounts) / len(log_amounts)
sigma_sq = sum((x - mu) ** 2 for x in log_amounts) / len(log_amounts)
self.amount_dist = DistributionFit(
name='lognormal',
params={'mu': mu, 'sigma': math.sqrt(sigma_sq)}
)
# Fit categories
categories = Counter(r.get('category') for r in data if r.get('category'))
if categories:
total = sum(categories.values())
self.category_dist = DistributionFit(
name='categorical',
params={'categories': {k: v/total for k, v in categories.items()}}
)
# Fit banks
banks = Counter(r.get('bank') for r in data if r.get('bank'))
if banks:
total = sum(banks.values())
self.bank_dist = DistributionFit(
name='categorical',
params={'categories': {k: v/total for k, v in banks.items()}}
)
# Fit amounts by category
by_category = defaultdict(list)
for r in data:
if r.get('amount') and r.get('category'):
by_category[r['category']].append(r['amount'])
for cat, amounts in by_category.items():
if len(amounts) >= 10:
log_amounts = [math.log(max(1, a)) for a in amounts]
mu = sum(log_amounts) / len(log_amounts)
sigma_sq = sum((x - mu) ** 2 for x in log_amounts) / len(log_amounts)
self.amount_by_category[cat] = DistributionFit(
name='lognormal',
params={'mu': mu, 'sigma': max(0.1, math.sqrt(sigma_sq))}
)
def sample_amount(self, category: Optional[str], rng: random.Random) -> float:
"""Sample amount, optionally by category."""
if category and category in self.amount_by_category:
return self.amount_by_category[category].sample(rng)
elif self.amount_dist:
return self.amount_dist.sample(rng)
else:
return rng.uniform(100, 10000)
def sample_category(self, rng: random.Random) -> str:
"""Sample category from fitted distribution."""
if self.category_dist:
return self.category_dist.sample(rng)
return 'shopping'
def sample_bank(self, rng: random.Random) -> str:
"""Sample bank from fitted distribution."""
if self.bank_dist:
return self.bank_dist.sample(rng)
return 'HDFC'
def save(self, path: Path):
"""Save calibration."""
with open(path, 'wb') as f:
pickle.dump({
'amount_dist': self.amount_dist,
'category_dist': self.category_dist,
'bank_dist': self.bank_dist,
'amount_by_category': self.amount_by_category,
}, f)
@classmethod
def load(cls, path: Path) -> 'DataCalibrator':
"""Load calibration."""
with open(path, 'rb') as f:
data = pickle.load(f)
calibrator = cls()
calibrator.amount_dist = data.get('amount_dist')
calibrator.category_dist = data.get('category_dist')
calibrator.bank_dist = data.get('bank_dist')
calibrator.amount_by_category = data.get('amount_by_category', {})
return calibrator
# ============================================================================
# MULTILINGUAL SUPPORT
# ============================================================================
class Language(Enum):
ENGLISH = "en"
HINDI = "hi"
TAMIL = "ta"
TELUGU = "te"
BENGALI = "bn"
KANNADA = "kn"
MARATHI = "mr"
GUJARATI = "gu"
@dataclass
class MultilingualTemplate:
"""Template with translations."""
english: str
translations: Dict[Language, str]
def get(self, lang: Language) -> str:
"""Get template in specified language."""
if lang == Language.ENGLISH:
return self.english
return self.translations.get(lang, self.english)
class MultilingualBank:
"""
Bank SMS templates in multiple Indian languages.
Based on actual bank SMS formats in different languages.
"""
TEMPLATES = {
'debit': MultilingualTemplate(
english="{bank}: Rs.{amount} debited from A/c XX{account} on {date}. {vpa}. Ref: {ref}",
translations={
Language.HINDI: "{bank}: आपके खाते XX{account} से Rs.{amount} डेबिट हुआ। दिनांक {date}। {vpa}। संदर्भ: {ref}",
Language.TAMIL: "{bank}: உங்கள் கணக்கு XX{account} இல் இருந்து Rs.{amount} டெபிட் செய்யப்பட்டது. தேதி {date}. Ref: {ref}",
Language.TELUGU: "{bank}: మీ ఖాతా XX{account} నుండి Rs.{amount} డెబిట్ చేయబడింది. తేదీ {date}. {vpa}. Ref: {ref}",
Language.BENGALI: "{bank}: আপনার অ্যাকাউন্ট XX{account} থেকে Rs.{amount} ডেবিট হয়েছে। তারিখ {date}। Ref: {ref}",
Language.KANNADA: "{bank}: ನಿಮ್ಮ ಖಾತೆ XX{account} ನಿಂದ Rs.{amount} ಡೆಬಿಟ್ ಆಗಿದೆ. ದಿನಾಂಕ {date}. Ref: {ref}",
Language.MARATHI: "{bank}: तुमच्या खात्यातून XX{account} Rs.{amount} डेबिट झाले. तारीख {date}. Ref: {ref}",
Language.GUJARATI: "{bank}: તમારા ખાતા XX{account} માંથી Rs.{amount} ડેબિટ થયું. તારીખ {date}. Ref: {ref}",
}
),
'credit': MultilingualTemplate(
english="{bank}: Rs.{amount} credited to A/c XX{account} on {date}. {sender}. Ref: {ref}",
translations={
Language.HINDI: "{bank}: आपके खाते XX{account} में Rs.{amount} क्रेडिट हुआ। दिनांक {date}। {sender}। संदर्भ: {ref}",
Language.TAMIL: "{bank}: உங்கள் கணக்கு XX{account} க்கு Rs.{amount} கிரெடிட் செய்யப்பட்டது. தேதி {date}. Ref: {ref}",
Language.TELUGU: "{bank}: మీ ఖాతా XX{account} కు Rs.{amount} క్రెడిట్ చేయబడింది. తేదీ {date}. Ref: {ref}",
Language.BENGALI: "{bank}: আপনার অ্যাকাউন্ট XX{account} এ Rs.{amount} ক্রেডিট হয়েছে। তারিখ {date}। Ref: {ref}",
Language.KANNADA: "{bank}: ನಿಮ್ಮ ಖಾತೆ XX{account} ಗೆ Rs.{amount} ಕ್ರೆಡಿಟ್ ಆಗಿದೆ. ದಿನಾಂಕ {date}. Ref: {ref}",
Language.MARATHI: "{bank}: तुमच्या खात्यात XX{account} Rs.{amount} क्रेडिट झाले. तारीख {date}. Ref: {ref}",
Language.GUJARATI: "{bank}: તમારા ખાતા XX{account} માં Rs.{amount} ક્રેડિટ થયું. તારીખ {date}. Ref: {ref}",
}
),
'otp': MultilingualTemplate(
english="{bank}: Your OTP is {otp}. Valid for 10 mins. Do not share with anyone.",
translations={
Language.HINDI: "{bank}: आपका OTP {otp} है। 10 मिनट के लिए मान्य। किसी के साथ साझा न करें।",
Language.TAMIL: "{bank}: உங்கள் OTP {otp}. 10 நிமிடங்களுக்கு செல்லுபடியாகும். யாருடனும் பகிர வேண்டாம்.",
Language.TELUGU: "{bank}: మీ OTP {otp}. 10 నిమిషాలు చెల్లుబాటు. ఎవరితోనూ షేర్ చేయకండి.",
Language.BENGALI: "{bank}: আপনার OTP হল {otp}। 10 মিনিটের জন্য বৈধ। কারো সাথে শেয়ার করবেন না।",
}
),
'balance': MultilingualTemplate(
english="{bank}: Your A/c XX{account} balance is Rs.{balance}.",
translations={
Language.HINDI: "{bank}: आपके खाते XX{account} में शेष राशि Rs.{balance} है।",
Language.TAMIL: "{bank}: உங்கள் கணக்கு XX{account} இருப்பு Rs.{balance}.",
Language.TELUGU: "{bank}: మీ ఖాతా XX{account} బ్యాలెన్స్ Rs.{balance}.",
Language.BENGALI: "{bank}: আপনার অ্যাকাউন্ট XX{account} ব্যালেন্স Rs.{balance}।",
}
),
}
# Numbers in Indian languages
NUMBERS = {
Language.HINDI: {
'0': '०', '1': '१', '2': '२', '3': '३', '4': '४',
'5': '५', '6': '६', '7': '७', '8': '८', '9': '९',
},
Language.BENGALI: {
'0': '০', '1': '১', '2': '২', '3': '৩', '4': '৪',
'5': '৫', '6': '৬', '7': '৭', '8': '৮', '9': '৯',
},
Language.TAMIL: {
'0': '௦', '1': '௧', '2': '௨', '3': '௩', '4': '௪',
'5': '௫', '6': '௬', '7': '௭', '8': '௮', '9': '௯',
},
Language.KANNADA: {
'0': '೦', '1': '೧', '2': '೨', '3': '೩', '4': '೪',
'5': '೫', '6': '೬', '7': '೭', '8': '೮', '9': '೯',
},
}
@classmethod
def generate(
cls,
template_type: str,
language: Language,
params: Dict[str, str],
use_native_numbers: bool = False,
rng: random.Random = None
) -> str:
"""Generate message in specified language."""
template = cls.TEMPLATES.get(template_type)
if not template:
return ""
text = template.get(language)
message = text.format(**params)
# Optionally convert numbers to native script
if use_native_numbers and language in cls.NUMBERS:
for eng, native in cls.NUMBERS[language].items():
message = message.replace(eng, native)
return message
class MultilingualNameGenerator:
"""Generate names in multiple Indian languages."""
NAMES = {
Language.HINDI: [
"राहुल शर्मा", "प्रिया सिंह", "अमित कुमार", "नेहा गुप्ता",
"विजय पटेल", "दीपक वर्मा", "अंजलि मेहता", "राजेश नायर",
"सुनीता अय्यर", "अरुण जोशी", "पूजा रेड्डी", "संजय मिश्रा",
],
Language.TAMIL: [
"முருகன் செல்வம்", "லக்ஷ்மி நாராயணன்", "கார்த்திக் சுப்பிரமணியம்",
"மீனா குமார்", "அருண் பிரகாஷ்", "சரிதா வேணுகோபால்",
],
Language.TELUGU: [
"రవి కుమార్", "లక్ష్మీ దేవి", "సురేష్ రెడ్డి", "వెంకట రావు",
"ప్రసాద్ నాయుడు", "కమల శర్మ", "రాజేష్ గుప్తా",
],
Language.BENGALI: [
"রাহুল ব্যানার্জী", "প্রিয়া দাস", "অমিত চক্রবর্তী",
"সুমিতা সেন", "রাজেশ মুখার্জী", "কবিতা বসু",
],
Language.KANNADA: [
"ರಾಜೇಶ್ ಗೌಡ", "ಲಕ್ಷ್ಮೀ ನಾರಾಯಣ", "ಸುರೇಶ್ ಕುಮಾರ್",
"ಮೀನಾ ಹೆಗ್ಡೆ", "ಪ್ರಕಾಶ್ ರಾವ್", "ನೇತ್ರಾ ಶೆಟ್ಟಿ",
],
}
@classmethod
def get_name(cls, language: Language, rng: random.Random) -> str:
"""Get a random name in specified language."""
names = cls.NAMES.get(language, cls.NAMES[Language.HINDI])
return rng.choice(names)
# ============================================================================
# DATA AUGMENTATION
# ============================================================================
class DataAugmenter:
"""
Advanced data augmentation techniques.
Techniques:
1. Back-translation (via templates)
2. Synonym replacement
3. Random insertion/deletion
4. Noise injection
5. Entity swapping
"""
SYNONYMS = {
'debited': ['withdrawn', 'deducted', 'paid', 'transferred', 'sent'],
'credited': ['received', 'deposited', 'added', 'transferred'],
'transaction': ['payment', 'transfer', 'txn'],
'account': ['A/c', 'Acc', 'Acct', 'a/c'],
'reference': ['Ref', 'UTR', 'Txn ID'],
'available': ['Avl', 'remaining', 'left'],
'balance': ['Bal', 'amt'],
}
def __init__(self, seed: int = 42):
self.rng = random.Random(seed)
def augment(
self,
text: str,
ground_truth: Dict,
techniques: List[str] = None
) -> List[Tuple[str, Dict]]:
"""
Generate augmented versions of a sample.
Returns list of (augmented_text, ground_truth) tuples.
"""
if techniques is None:
techniques = ['synonym', 'noise', 'case']
augmented = []
if 'synonym' in techniques:
aug = self._synonym_replace(text)
augmented.append((aug, ground_truth))
if 'noise' in techniques:
aug = self._add_noise(text)
augmented.append((aug, ground_truth))
if 'case' in techniques:
aug = self._vary_case(text)
augmented.append((aug, ground_truth))
if 'truncate' in techniques:
aug = self._truncate(text)
augmented.append((aug, ground_truth))
if 'reorder' in techniques:
aug = self._reorder_phrases(text)
augmented.append((aug, ground_truth))
return augmented
def _synonym_replace(self, text: str) -> str:
"""Replace words with synonyms."""
words = text.split()
for i, word in enumerate(words):
word_lower = word.lower().strip('.,;:')
if word_lower in self.SYNONYMS and self.rng.random() < 0.3:
synonym = self.rng.choice(self.SYNONYMS[word_lower])
# Preserve case
if word[0].isupper():
synonym = synonym.capitalize()
words[i] = synonym
return ' '.join(words)
def _add_noise(self, text: str) -> str:
"""Add realistic noise."""
# Random spacing
if self.rng.random() < 0.3:
text = text.replace('. ', '.')
if self.rng.random() < 0.3:
text = text.replace(': ', ':')
# Abbreviations
text = text.replace('Reference', 'Ref' if self.rng.random() < 0.5 else 'Reference')
text = text.replace('Account', 'A/c' if self.rng.random() < 0.5 else 'Account')
return text
def _vary_case(self, text: str) -> str:
"""Vary text case."""
r = self.rng.random()
if r < 0.2:
return text.upper()
elif r < 0.4:
return text.lower()
return text
def _truncate(self, text: str) -> str:
"""Truncate to SMS limit."""
if len(text) > 160:
return text[:157] + '...'
return text
def _reorder_phrases(self, text: str) -> str:
"""Reorder independent phrases."""
# Split by common delimiters
phrases = re.split(r'[.;]', text)
phrases = [p.strip() for p in phrases if p.strip()]
if len(phrases) <= 2:
return text
# Keep first phrase, shuffle middle, keep last
first = phrases[0]
last = phrases[-1]
middle = phrases[1:-1]
self.rng.shuffle(middle)
return '. '.join([first] + middle + [last])
def augment_batch(
self,
data: List[Dict],
augmentation_factor: int = 3
) -> List[Dict]:
"""Augment entire dataset."""
augmented_data = []
for record in data:
text = record.get('text') or record.get('input', '')
gt = record.get('ground_truth', record.get('output', {}))
if isinstance(gt, str):
gt = json.loads(gt)
# Original
augmented_data.append(record)
# Augmented versions
for aug_text, aug_gt in self.augment(text, gt)[:augmentation_factor-1]:
augmented_data.append({
'text': aug_text,
'ground_truth': aug_gt,
'augmented': True,
})
return augmented_data
# ============================================================================
# RARE EDGE CASE OVERSAMPLING
# ============================================================================
class RareEdgeCaseSampler:
"""
Oversample rare edge cases to improve model robustness.
Uses importance sampling to increase representation of:
- Failed transactions
- Large amounts
- Unusual formats
- Rare banks
- Unicode text
"""
def __init__(self, seed: int = 42):
self.rng = random.Random(seed)
# Define edge case conditions
self.edge_cases = {
'failed_txn': lambda r: r.get('status') == 'failed',
'pending_txn': lambda r: r.get('status') == 'pending',
'large_amount': lambda r: (r.get('amount') or 0) > 100000,
'small_amount': lambda r: (r.get('amount') or float('inf')) < 10,
'unicode': lambda r: any(ord(c) > 127 for c in str(r.get('text', ''))),
'credit': lambda r: r.get('type') == 'credit',
}
# Oversampling weights (higher = more samples)
self.oversample_weights = {
'failed_txn': 5.0,
'pending_txn': 3.0,
'large_amount': 2.0,
'small_amount': 2.0,
'unicode': 4.0,
'credit': 1.5,
}
def identify_edge_cases(self, record: Dict) -> List[str]:
"""Identify which edge cases a record matches."""
return [
name for name, condition in self.edge_cases.items()
if condition(record)
]
def calculate_sample_weight(self, record: Dict) -> float:
"""Calculate importance weight for a record."""
weight = 1.0
for edge_case in self.identify_edge_cases(record):
weight *= self.oversample_weights.get(edge_case, 1.0)
return weight
def oversample(
self,
data: List[Dict],
target_size: Optional[int] = None
) -> List[Dict]:
"""
Oversample data with edge case weighting.
Returns dataset with increased representation of rare cases.
"""
if target_size is None:
target_size = len(data)
# Calculate weights
weights = [self.calculate_sample_weight(r) for r in data]
total_weight = sum(weights)
probs = [w / total_weight for w in weights]
# Sample with replacement
indices = self.rng.choices(range(len(data)), weights=probs, k=target_size)
oversampled = []
for i in indices:
record = data[i].copy()
record['oversampled'] = True
oversampled.append(record)
return oversampled
def generate_targeted_edge_cases(
self,
generator,
edge_case_type: str,
count: int
) -> List[Dict]:
"""Generate specific edge case samples."""
samples = []
if edge_case_type == 'failed_txn':
from scripts.data_pipeline.generate_synthetic import TransactionStatus
for _ in range(count):
sample = generator.generate_transaction(
status=TransactionStatus.FAILED
)
samples.append(sample)
elif edge_case_type == 'large_amount':
for _ in range(count):
sample = generator.generate_transaction()
# Force large amount
sample['ground_truth']['amount'] = self.rng.uniform(100000, 1000000)
samples.append(sample)
elif edge_case_type == 'unicode':
for _ in range(count):
sample = generator.generate_transaction()
# Use Hindi name
sample['ground_truth']['beneficiary'] = self.rng.choice([
"राहुल शर्मा", "प्रिया सिंह", "అమిత్ కుమార్"
])
samples.append(sample)
return samples
# ============================================================================
# DOCUMENT/PDF GENERATION (Placeholder - needs external libs)
# ============================================================================
class DocumentGenerator:
"""
Generate synthetic bank statements and documents.
Note: Full implementation requires:
- reportlab for PDF generation
- PIL for image processing
- wkhtmltopdf for HTML to PDF
"""
STATEMENT_TEMPLATE = """
============================================
{bank} BANK
ACCOUNT STATEMENT
============================================
Account Holder: {name}
Account Number: XXXXXXXX{account}
Statement Period: {start_date} to {end_date}
Opening Balance: Rs. {opening_balance}
--------------------------------------------
Date Description Debit Credit Balance
--------------------------------------------
{transactions}
--------------------------------------------
Closing Balance: Rs. {closing_balance}
This is a computer-generated statement.
"""
@classmethod
def generate_text_statement(
cls,
transactions: List[Dict],
bank: str,
account: str,
name: str,
rng: random.Random
) -> str:
"""Generate a text-based bank statement."""
if not transactions:
return ""
# Sort by date
sorted_txns = sorted(
transactions,
key=lambda x: x.get('date', '2025-01-01')
)
# Calculate running balance
opening = rng.randint(10000, 100000)
balance = opening
lines = []
for txn in sorted_txns:
amount = txn.get('amount', 0)
txn_type = txn.get('type', 'debit')
if txn_type == 'debit':
balance -= amount
debit = f"{amount:,.2f}"
credit = ""
else:
balance += amount
debit = ""
credit = f"{amount:,.2f}"
desc = txn.get('merchant') or txn.get('beneficiary') or 'Transaction'
date_str = txn.get('date', '2025-01-01')
line = f"{date_str} {desc[:20]:<20} {debit:>10} {credit:>10} {balance:>12,.2f}"
lines.append(line)
start_date = sorted_txns[0].get('date', '2025-01-01')
end_date = sorted_txns[-1].get('date', '2025-01-31')
return cls.STATEMENT_TEMPLATE.format(
bank=bank,
name=name,
account=account[-4:],
start_date=start_date,
end_date=end_date,
opening_balance=f"{opening:,.2f}",
closing_balance=f"{balance:,.2f}",
transactions='\n '.join(lines)
)
@classmethod
def generate_statement_image_data(
cls,
transactions: List[Dict],
bank: str,
rng: random.Random
) -> Dict:
"""
Generate data for statement image (actual rendering needs PIL).
Returns structured data that can be used with image generation.
"""
return {
'type': 'bank_statement',
'bank': bank,
'transactions': transactions,
'format': 'image_data',
'note': 'Use PIL/reportlab to render actual image'
}
# ============================================================================
# UNIFIED ADVANCED GENERATOR
# ============================================================================
class AdvancedSyntheticGenerator:
"""
Unified generator combining all advanced features.
Features:
1. Markov chain learning from real data
2. Statistical calibration
3. Multilingual support
4. Data augmentation
5. Edge case oversampling
"""
def __init__(self, seed: int = 42):
self.seed = seed
self.rng = random.Random(seed)
# Components
self.markov: Optional[MarkovChain] = None
self.calibrator: Optional[DataCalibrator] = None
self.augmenter = DataAugmenter(seed)
self.edge_sampler = RareEdgeCaseSampler(seed)
def train_on_real_data(self, real_data: List[Dict]):
"""Train/calibrate on real data."""
print("Training on real data...")
# Train Markov chain
texts = [r.get('text') or r.get('input', '') for r in real_data]
self.markov = MarkovChain(order=2)
self.markov.train(texts)
print(f" Markov chain trained on {len(texts)} samples")
# Calibrate distributions
self.calibrator = DataCalibrator()
parsed_data = []
for r in real_data:
gt = r.get('ground_truth') or r.get('output', {})
if isinstance(gt, str):
gt = json.loads(gt)
parsed_data.append(gt)
self.calibrator.fit_from_data(parsed_data)
print(" Distributions calibrated")
def generate(
self,
count: int,
languages: List[Language] = None,
include_documents: bool = False,
augmentation_factor: int = 1,
edge_case_ratio: float = 0.1,
) -> List[Dict]:
"""
Generate synthetic data with all advanced features.
Args:
count: Number of records
languages: Languages to include (None = English only)
include_documents: Include bank statement format
augmentation_factor: How many augmented versions per sample
edge_case_ratio: Proportion of edge cases to include
"""
if languages is None:
languages = [Language.ENGLISH]
records = []
base_count = int(count / augmentation_factor)
edge_count = int(base_count * edge_case_ratio)
normal_count = base_count - edge_count
print(f"Generating {count:,} records...")
print(f" Base: {base_count:,}, Edges: {edge_count:,}, Augmented: {count - base_count:,}")
# Generate normal transactions
for i in range(normal_count):
lang = self.rng.choice(languages)
# Sample from calibrated distributions if available
if self.calibrator:
category = self.calibrator.sample_category(self.rng)
bank = self.calibrator.sample_bank(self.rng)
amount = self.calibrator.sample_amount(category, self.rng)
else:
category = self.rng.choice(['shopping', 'food', 'transfer', 'bills'])
bank = self.rng.choice(['HDFC', 'ICICI', 'SBI', 'Axis'])
amount = self.rng.uniform(100, 10000)
# Generate message
is_debit = self.rng.random() < 0.7
template_type = 'debit' if is_debit else 'credit'
params = {
'bank': bank,
'amount': f"{amount:,.2f}",
'account': str(self.rng.randint(1000, 9999)),
'date': (date.today() - timedelta(days=self.rng.randint(0, 365))).strftime('%d-%m-%Y'),
'vpa': f"{self.rng.choice(['swiggy', 'amazon', 'paytm'])}@ybl",
'sender': 'PhonePe',
'ref': ''.join(self.rng.choices('0123456789', k=12)),
}
text = MultilingualBank.generate(template_type, lang, params)
records.append({
'text': text,
'ground_truth': {
'amount': round(amount, 2),
'type': 'debit' if is_debit else 'credit',
'bank': bank,
'category': category,
'language': lang.value,
},
'language': lang.value,
})
if (i + 1) % 5000 == 0:
print(f" Generated {i+1:,}/{base_count:,}")
# Generate edge cases
for i in range(edge_count):
lang = self.rng.choice(languages)
edge_type = self.rng.choice(['unicode', 'large_amount', 'small_amount'])
if edge_type == 'unicode' and lang == Language.ENGLISH:
lang = Language.HINDI
amount = (
self.rng.uniform(100000, 1000000) if edge_type == 'large_amount'
else self.rng.uniform(0.5, 10) if edge_type == 'small_amount'
else self.rng.uniform(100, 10000)
)
params = {
'bank': self.rng.choice(['HDFC', 'ICICI', 'SBI']),
'amount': f"{amount:,.2f}",
'account': str(self.rng.randint(1000, 9999)),
'date': date.today().strftime('%d-%m-%Y'),
'vpa': 'merchant@ybl',
'sender': MultilingualNameGenerator.get_name(lang, self.rng) if edge_type == 'unicode' else 'User',
'ref': ''.join(self.rng.choices('0123456789', k=12)),
}
text = MultilingualBank.generate('debit', lang, params, use_native_numbers=(edge_type == 'unicode'))
records.append({
'text': text,
'ground_truth': {
'amount': round(amount, 2),
'type': 'debit',
'language': lang.value,
},
'edge_case': edge_type,
'language': lang.value,
})
# Augment if factor > 1
if augmentation_factor > 1:
print(f" Augmenting {len(records):,} records...")
records = self.augmenter.augment_batch(records, augmentation_factor)
# Add statements if requested
if include_documents:
print(" Generating document samples...")
for _ in range(min(100, count // 100)):
bank = self.rng.choice(['HDFC', 'ICICI', 'SBI'])
account = str(self.rng.randint(10000000, 99999999))
name = self.rng.choice(['Rahul Sharma', 'Priya Singh', 'Amit Kumar'])
# Use recent records for statement
txns = [r['ground_truth'] for r in self.rng.sample(records, min(10, len(records)))]
statement = DocumentGenerator.generate_text_statement(
txns, bank, account, name, self.rng
)
records.append({
'text': statement,
'ground_truth': {'document_type': 'bank_statement', 'bank': bank},
'document': True,
})
self.rng.shuffle(records)
# Add IDs
for i, r in enumerate(records):
r['id'] = i + 1
print(f"✅ Generated {len(records):,} total records")
return records
def save_training_data(self, records: List[Dict], output_path: Path):
"""Save in training format."""
output_path.parent.mkdir(parents=True, exist_ok=True)
with open(output_path, 'w', encoding='utf-8') as f:
for r in records:
line = {
'input': r['text'],
'output': json.dumps(r['ground_truth'], ensure_ascii=False),
'id': r.get('id'),
'language': r.get('language', 'en'),
}
if r.get('edge_case'):
line['edge_case'] = r['edge_case']
f.write(json.dumps(line, ensure_ascii=False) + '\n')
print(f"✅ Saved to: {output_path}")
# ============================================================================
# CLI
# ============================================================================
def main():
parser = argparse.ArgumentParser(description="Advanced Synthetic Data Generator v4.0")
parser.add_argument("-n", "--count", type=int, default=10000, help="Number of records")
parser.add_argument("-o", "--output", default="data/synthetic/advanced_synthetic.jsonl")
parser.add_argument("--seed", type=int, default=42, help="Random seed")
parser.add_argument("--languages", nargs='+', default=['en'],
help="Languages: en, hi, ta, te, bn, kn, mr, gu")
parser.add_argument("--augment", type=int, default=1, help="Augmentation factor")
parser.add_argument("--edge-ratio", type=float, default=0.1, help="Edge case ratio")
parser.add_argument("--real-data", help="Path to real data for calibration")
parser.add_argument("--documents", action="store_true", help="Include document samples")
args = parser.parse_args()
# Parse languages
lang_map = {
'en': Language.ENGLISH, 'hi': Language.HINDI, 'ta': Language.TAMIL,
'te': Language.TELUGU, 'bn': Language.BENGALI, 'kn': Language.KANNADA,
'mr': Language.MARATHI, 'gu': Language.GUJARATI,
}
languages = [lang_map.get(l, Language.ENGLISH) for l in args.languages]
# Initialize generator
generator = AdvancedSyntheticGenerator(seed=args.seed)
# Train on real data if provided
if args.real_data:
real_path = Path(args.real_data)
if real_path.exists():
with open(real_path) as f:
real_data = [json.loads(line) for line in f]
generator.train_on_real_data(real_data)
# Generate
records = generator.generate(
count=args.count,
languages=languages,
include_documents=args.documents,
augmentation_factor=args.augment,
edge_case_ratio=args.edge_ratio,
)
# Save
output_path = Path(args.output)
generator.save_training_data(records, output_path)
# Summary
print("\n📊 Summary:")
lang_counts = Counter(r.get('language', 'en') for r in records)
for lang, count in lang_counts.most_common():
print(f" {lang}: {count:,}")
edge_counts = Counter(r.get('edge_case') for r in records if r.get('edge_case'))
if edge_counts:
print("\n📋 Edge Cases:")
for edge, count in edge_counts.most_common():
print(f" {edge}: {count:,}")
if __name__ == "__main__":
main()
|