File size: 10,759 Bytes
3a4ffcf 1b002e5 3a4ffcf 1b002e5 3a4ffcf 1b002e5 3a4ffcf 1b002e5 3a4ffcf 1b002e5 3a4ffcf 1b002e5 3a4ffcf 1b002e5 3a4ffcf 1b002e5 3a4ffcf 1b002e5 3a4ffcf 1b002e5 3a4ffcf 1b002e5 |
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 |
from __future__ import annotations
import logging
from collections import defaultdict
from dataclasses import dataclass
from datetime import datetime
from typing import Dict, Iterable, List, Tuple
from dateutil.relativedelta import relativedelta
from .schemas import Insight, Transaction
logger = logging.getLogger(__name__)
CURRENCY_SYMBOLS: Dict[str, str] = {
"INR": "₹",
"USD": "$",
"EUR": "€",
"GBP": "£",
}
@dataclass(frozen=True)
class MonthlySummary:
"""Aggregate spending for a single month, category, and currency."""
year: int
month: int
category: str
currency: str
total: float
@property
def iso_month(self) -> str:
return f"{self.year:04d}-{self.month:02d}"
def _bucket_transactions(transactions: Iterable[Transaction]) -> List[MonthlySummary]:
"""Aggregate transactions per month, category, and currency."""
buckets: Dict[Tuple[int, int, str, str], float] = defaultdict(float)
for txn in transactions:
key = (txn.timestamp.year, txn.timestamp.month, txn.category, txn.currency)
buckets[key] += txn.amount
summaries = [
MonthlySummary(year=year, month=month, category=category, currency=currency, total=round(total, 2))
for (year, month, category, currency), total in buckets.items()
]
logger.debug("Created %d monthly summaries", len(summaries))
return summaries
def _format_currency(amount: float, currency: str) -> str:
symbol = CURRENCY_SYMBOLS.get(currency.upper(), "")
formatted_amount = f"{amount:,.2f}"
return f"{symbol}{formatted_amount}" if symbol else f"{formatted_amount} {currency.upper()}"
def _month_key(summary: MonthlySummary) -> datetime:
return datetime(summary.year, summary.month, 1)
def generate_insights(transactions: Iterable[Transaction]) -> Tuple[List[Insight], List[str]]:
"""Create AI-inspired insights from historical spending."""
txns = list(transactions)
if not txns:
logger.info("No transactions provided, returning onboarding insight")
return [Insight(message="Add a few expenses to start seeing personalized insights.")], []
summaries = _bucket_transactions(txns)
if not summaries:
return [Insight(message="No spending data yet. Track expenses to unlock insights.")], []
summaries.sort(key=_month_key, reverse=True)
recent_months = summaries[:12] # guardrail, though we only surface up to 3 months
# Group by category and currency to handle multi-currency scenarios
grouped: Dict[Tuple[str, str], List[MonthlySummary]] = defaultdict(list)
for summary in recent_months:
grouped[(summary.category, summary.currency)].append(summary)
latest_month = max(recent_months, key=_month_key)
latest_month_dt = _month_key(latest_month)
evaluated_months = []
insights: List[Insight] = []
for offset in range(3):
evaluated_months.append((latest_month_dt - relativedelta(months=offset)).strftime("%Y-%m"))
evaluated_months = sorted(set(evaluated_months))
for (category, currency), entries in grouped.items():
entries.sort(key=_month_key, reverse=True)
current = entries[0]
history = entries[1:3]
if not history:
continue
history_avg = sum(e.total for e in history) / len(history)
if history_avg == 0:
continue
change_pct = ((current.total - history_avg) / history_avg) * 100
diff_amount = current.total - history_avg
if abs(change_pct) < 10:
continue
trend = "increased" if change_pct > 0 else "decreased"
insights.append(
Insight(
category=category,
message=(
f"Your {category.lower()} spending {trend} by {abs(change_pct):.0f}% this month "
f"versus your prior average, about {_format_currency(abs(diff_amount), currency)} difference."
),
)
)
# Additional highlight: biggest month-over-month change per currency
# Group monthly totals by currency to avoid mixing currencies
monthly_totals_by_currency: Dict[str, Dict[str, float]] = defaultdict(lambda: defaultdict(float))
for summary in summaries:
monthly_totals_by_currency[summary.currency][summary.iso_month] += summary.total
# Generate insights per currency
for currency, monthly_totals in monthly_totals_by_currency.items():
sorted_months = sorted(monthly_totals.items(), reverse=True)
if len(sorted_months) >= 2:
latest_label, latest_total = sorted_months[0]
prev_label, prev_total = sorted_months[1]
delta = latest_total - prev_total
if abs(delta) >= 1:
descriptor = "more" if delta > 0 else "less"
currency_note = f" (in {currency})" if len(monthly_totals_by_currency) > 1 else ""
insights.append(
Insight(
message=(
f"You spent {_format_currency(abs(delta), currency)} {descriptor} in {latest_label} compared "
f"to {prev_label}{currency_note}. Consider reviewing large outliers."
)
)
)
if not insights:
insights.append(
Insight(message="Spending is stable across tracked months. Keep up the steady habits!")
)
logger.info("Generated %d insights", len(insights))
return insights, evaluated_months
# from __future__ import annotations
# import logging
# from collections import defaultdict
# from dataclasses import dataclass
# from datetime import datetime
# from typing import Dict, Iterable, List, Tuple
# from dateutil.relativedelta import relativedelta
# from .schemas import Insight, Transaction
# logger = logging.getLogger(__name__)
# CURRENCY_SYMBOLS: Dict[str, str] = {
# "INR": "₹",
# "USD": "$",
# "EUR": "€",
# "GBP": "£",
# }
# @dataclass(frozen=True)
# class MonthlySummary:
# """Aggregate spending for a single month and category."""
# year: int
# month: int
# category: str
# total: float
# @property
# def iso_month(self) -> str:
# return f"{self.year:04d}-{self.month:02d}"
# def _bucket_transactions(transactions: Iterable[Transaction]) -> List[MonthlySummary]:
# """Aggregate transactions per month and category."""
# buckets: Dict[Tuple[int, int, str], float] = defaultdict(float)
# for txn in transactions:
# key = (txn.timestamp.year, txn.timestamp.month, txn.category)
# buckets[key] += txn.amount
# summaries = [
# MonthlySummary(year=year, month=month, category=category, total=round(total, 2))
# for (year, month, category), total in buckets.items()
# ]
# logger.debug("Created %d monthly summaries", len(summaries))
# return summaries
# def _format_currency(amount: float, currency: str) -> str:
# symbol = CURRENCY_SYMBOLS.get(currency.upper(), "")
# formatted_amount = f"{amount:,.2f}"
# return f"{symbol}{formatted_amount}" if symbol else f"{formatted_amount} {currency.upper()}"
# def _month_key(summary: MonthlySummary) -> datetime:
# return datetime(summary.year, summary.month, 1)
# def generate_insights(transactions: Iterable[Transaction]) -> Tuple[List[Insight], List[str]]:
# """Create AI-inspired insights from historical spending."""
# txns = list(transactions)
# if not txns:
# logger.info("No transactions provided, returning onboarding insight")
# return [Insight(message="Add a few expenses to start seeing personalized insights.")], []
# summaries = _bucket_transactions(txns)
# if not summaries:
# return [Insight(message="No spending data yet. Track expenses to unlock insights.")], []
# summaries.sort(key=_month_key, reverse=True)
# recent_months = summaries[:12] # guardrail, though we only surface up to 3 months
# grouped: Dict[str, List[MonthlySummary]] = defaultdict(list)
# for summary in recent_months:
# grouped[summary.category].append(summary)
# latest_month = max(recent_months, key=_month_key)
# latest_month_dt = _month_key(latest_month)
# evaluated_months = []
# insights: List[Insight] = []
# for offset in range(3):
# evaluated_months.append((latest_month_dt - relativedelta(months=offset)).strftime("%Y-%m"))
# evaluated_months = sorted(set(evaluated_months))
# currency = txns[0].currency
# for category, entries in grouped.items():
# entries.sort(key=_month_key, reverse=True)
# current = entries[0]
# history = entries[1:3]
# if not history:
# continue
# history_avg = sum(e.total for e in history) / len(history)
# if history_avg == 0:
# continue
# change_pct = ((current.total - history_avg) / history_avg) * 100
# diff_amount = current.total - history_avg
# if abs(change_pct) < 10:
# continue
# trend = "increased" if change_pct > 0 else "decreased"
# insights.append(
# Insight(
# category=category,
# message=(
# f"Your {category.lower()} spending {trend} by {abs(change_pct):.0f}% this month "
# f"versus your prior average, about {_format_currency(abs(diff_amount), currency)} difference."
# ),
# )
# )
# # Additional highlight: biggest month-over-month change regardless of category
# monthly_totals: Dict[str, float] = defaultdict(float)
# for summary in summaries:
# monthly_totals[summary.iso_month] += summary.total
# sorted_months = sorted(monthly_totals.items(), reverse=True)
# if len(sorted_months) >= 2:
# latest_label, latest_total = sorted_months[0]
# prev_label, prev_total = sorted_months[1]
# delta = latest_total - prev_total
# if abs(delta) >= 1:
# descriptor = "more" if delta > 0 else "less"
# insights.append(
# Insight(
# message=(
# f"You spent {_format_currency(abs(delta), currency)} {descriptor} in {latest_label} compared "
# f"to {prev_label}. Consider reviewing large outliers."
# )
# )
# )
# if not insights:
# insights.append(
# Insight(message="Spending is stable across tracked months. Keep up the steady habits!")
# )
# logger.info("Generated %d insights", len(insights))
# return insights, evaluated_months
|