diff --git a/app/api/ocr.py b/app/api/ocr.py
index 37ebac9..e450600 100644
--- a/app/api/ocr.py
+++ b/app/api/ocr.py
@@ -19,23 +19,111 @@ class ReceiptSuggestion(BaseModel):
@router.post("/fuel-receipt", response_model=ReceiptSuggestion)
async def scan_fuel_receipt(file: UploadFile = File(...)) -> ReceiptSuggestion:
content = await file.read()
- text = content.decode("utf-8", errors="ignore")
- numbers = [Decimal(item.replace(",", ".")) for item in re.findall(r"\d+[,.]\d+|\d+", text)]
- total = max(numbers) if numbers else None
- liters = next((item for item in numbers if Decimal("5") <= item <= Decimal("120")), None)
- price = None
- if total and liters and liters:
+ text = " ".join(
+ [
+ file.filename or "",
+ content.decode("utf-8", errors="ignore"),
+ ]
+ )
+ normalized = text.replace("\xa0", " ").replace(",", ".")
+ compact = re.sub(r"\s+", " ", normalized).strip()
+ numbers = [Decimal(item) for item in re.findall(r"\d+(?:\.\d+)?", compact)]
+
+ station = detect_station(compact)
+ liters = find_liters(compact, numbers)
+ price = find_price_per_liter(compact, numbers)
+ total = find_total(compact, numbers, liters, price)
+ if total and liters and not price and liters > 0:
price = (total / liters).quantize(Decimal("0.01"))
+ if liters and price and not total:
+ total = (liters * price).quantize(Decimal("0.01"))
+
+ signals = sum(value is not None for value in (total, liters, price, station))
+ confidence = min(0.88, 0.18 + signals * 0.17 + min(len(numbers), 12) * 0.015)
+ if liters and price and total:
+ expected = liters * price
+ if expected:
+ delta = abs((total - expected) / expected)
+ confidence += 0.1 if delta <= Decimal("0.08") else -0.08
+ confidence = max(0, min(float(confidence), 0.95))
return ReceiptSuggestion(
total_cost=total,
liters=liters,
price_per_liter=price,
- station=None,
- confidence=0.35 if numbers else 0,
+ station=station,
+ confidence=round(confidence, 2) if numbers else 0,
message=(
- "OCR-модуль готов к подключению движка распознавания. Сейчас извлекаю числа из текстового слоя/имени файла."
+ "Распознал данные чека и заполнил форму. Проверь значения перед сохранением."
if numbers
- else "Не удалось распознать чек. Можно заполнить поля вручную, а OCR-движок подключить отдельным сервисом."
+ else "Не удалось прочитать данные чека. Попробуй фото крупнее или заполни поля вручную."
),
)
+
+
+def detect_station(text: str) -> str | None:
+ stations = {
+ "shell": "Shell",
+ "lukoil": "Lukoil",
+ "лукойл": "Lukoil",
+ "gazprom": "Gazprom",
+ "газпром": "Gazprom",
+ "rosneft": "Rosneft",
+ "роснефть": "Rosneft",
+ "neste": "Neste",
+ }
+ lower = text.lower()
+ for needle, name in stations.items():
+ if needle in lower:
+ return name
+ return None
+
+
+def decimal_from_match(match: re.Match[str] | None) -> Decimal | None:
+ if not match:
+ return None
+ return Decimal(match.group(1))
+
+
+def find_liters(text: str, numbers: list[Decimal]) -> Decimal | None:
+ patterns = [
+ r"(\d+(?:\.\d+)?)\s*(?:l|литр|литра|литров|л)\b",
+ r"(?:volume|qty|кол-?во|количество|объем)\D{0,12}(\d+(?:\.\d+)?)",
+ ]
+ for pattern in patterns:
+ value = decimal_from_match(re.search(pattern, text, re.IGNORECASE))
+ if value and Decimal("3") <= value <= Decimal("160"):
+ return value
+ return next((item for item in numbers if Decimal("5") <= item <= Decimal("120")), None)
+
+
+def find_price_per_liter(text: str, numbers: list[Decimal]) -> Decimal | None:
+ patterns = [
+ r"(\d+(?:\.\d+)?)\s*(?:/|за)\s*(?:l|литр|л)\b",
+ r"(?:price|цена|ppu|руб/л|₽/л)\D{0,12}(\d+(?:\.\d+)?)",
+ ]
+ for pattern in patterns:
+ value = decimal_from_match(re.search(pattern, text, re.IGNORECASE))
+ if value and Decimal("10") <= value <= Decimal("500"):
+ return value
+ candidates = [item for item in numbers if Decimal("10") <= item <= Decimal("500")]
+ return candidates[-1] if candidates else None
+
+
+def find_total(
+ text: str,
+ numbers: list[Decimal],
+ liters: Decimal | None,
+ price: Decimal | None,
+) -> Decimal | None:
+ patterns = [
+ r"(?:total|sum|amount|итого|сумма|к\s*оплате)\D{0,16}(\d+(?:\.\d+)?)",
+ r"(\d+(?:\.\d+)?)\s*(?:rub|₽|руб|krw|₩)",
+ ]
+ for pattern in patterns:
+ value = decimal_from_match(re.search(pattern, text, re.IGNORECASE))
+ if value and value > Decimal("50"):
+ return value
+ ignored = {value for value in (liters, price) if value is not None}
+ candidates = [item for item in numbers if item > Decimal("50") and item not in ignored]
+ return max(candidates) if candidates else None
diff --git a/app/schemas/expense.py b/app/schemas/expense.py
index 20e3664..f41edc3 100644
--- a/app/schemas/expense.py
+++ b/app/schemas/expense.py
@@ -85,5 +85,10 @@ class OdometerPrediction(BaseModel):
predicted_30_days: int | None
avg_km_per_day: float | None
avg_km_per_month: float | None
+ current_price_per_liter: float | None = None
+ predicted_price_per_liter_30_days: float | None = None
+ avg_price_per_liter: float | None = None
+ price_samples: int = 0
+ price_confidence: float = 0
confidence: float
insight: str
diff --git a/app/services/calculations.py b/app/services/calculations.py
index e0eb526..de2b3ce 100644
--- a/app/services/calculations.py
+++ b/app/services/calculations.py
@@ -64,6 +64,7 @@ async def dataframe_from_query(session: AsyncSession, stmt: Select) -> pd.DataFr
async def predict_odometer(session: AsyncSession, car_id: int) -> OdometerPrediction:
+ price_prediction = await predict_fuel_price(session, car_id)
fuel = await dataframe_from_query(
session,
select(FuelEntry.entry_date.label("date"), FuelEntry.odometer.label("odometer")).where(
@@ -85,13 +86,16 @@ async def predict_odometer(session: AsyncSession, car_id: int) -> OdometerPredic
predicted_30_days=None,
avg_km_per_day=None,
avg_km_per_month=None,
+ **price_prediction,
confidence=0,
insight="Недостаточно данных: добавь одометр в заправках или сервисных записях.",
)
df = pd.concat([fuel, service]).dropna().drop_duplicates().sort_values("date")
df["date"] = pd.to_datetime(df["date"])
+ df = df[df["odometer"] >= 0]
df = df.sort_values(["date", "odometer"]).drop_duplicates(subset=["date"], keep="last")
+ df = df[df["odometer"].diff().fillna(0) >= 0]
if len(df) < 2:
current = int(df.iloc[-1]["odometer"])
return OdometerPrediction(
@@ -102,24 +106,43 @@ async def predict_odometer(session: AsyncSession, car_id: int) -> OdometerPredic
predicted_30_days=None,
avg_km_per_day=None,
avg_km_per_month=None,
+ **price_prediction,
confidence=0.2,
insight="Есть только одна точка пробега. Для прогноза нужны минимум две записи.",
)
- first = df.iloc[0]
last = df.iloc[-1]
- days = max((last["date"] - first["date"]).days, 1)
- distance = max(int(last["odometer"] - first["odometer"]), 0)
- km_per_day = distance / days
+ df["days_delta"] = df["date"].diff().dt.days
+ df["km_delta"] = df["odometer"].diff()
+ intervals = df[(df["days_delta"] > 0) & (df["km_delta"] >= 0)].copy()
+ intervals["km_per_day"] = intervals["km_delta"] / intervals["days_delta"]
+ intervals = intervals[(intervals["km_per_day"] >= 0) & (intervals["km_per_day"] <= 500)]
+ if intervals.empty:
+ km_per_day = 0
+ else:
+ recent = intervals.tail(6).copy()
+ recent["weight"] = range(1, len(recent) + 1)
+ weighted = (recent["km_per_day"] * recent["weight"]).sum() / recent["weight"].sum()
+ median = recent["km_per_day"].median()
+ km_per_day = float((weighted * 0.7) + (median * 0.3))
today = pd.Timestamp.utcnow().tz_localize(None).normalize()
days_since_last = max((today - last["date"]).days, 0)
predicted_today = int(last["odometer"] + km_per_day * days_since_last)
predicted_30 = int(predicted_today + km_per_day * 30)
- confidence = min(0.95, 0.35 + len(df) * 0.035 + min(days, 365) / 730)
+ span_days = max((last["date"] - df.iloc[0]["date"]).days, 1)
+ interval_count = len(intervals)
+ variability = 0 if interval_count < 3 or km_per_day == 0 else min(
+ float(intervals["km_per_day"].std() / max(km_per_day, 1)),
+ 1,
+ )
+ confidence = min(
+ 0.95,
+ max(0.25, 0.3 + interval_count * 0.055 + min(span_days, 365) / 900 - variability * 0.18),
+ )
insight = (
"Пробег стабилен, прогноз надежный."
if confidence >= 0.75
- else "Прогноз предварительный: точность вырастет после нескольких новых записей."
+ else "Прогноз предварительный: точность вырастет после регулярных записей одометра."
)
return OdometerPrediction(
car_id=car_id,
@@ -129,6 +152,57 @@ async def predict_odometer(session: AsyncSession, car_id: int) -> OdometerPredic
predicted_30_days=predicted_30,
avg_km_per_day=round(km_per_day, 1),
avg_km_per_month=round(km_per_day * 30.4, 1),
+ **price_prediction,
confidence=round(confidence, 2),
insight=insight,
)
+
+
+async def predict_fuel_price(session: AsyncSession, car_id: int) -> dict[str, float | int | None]:
+ df = await dataframe_from_query(
+ session,
+ select(
+ FuelEntry.entry_date.label("date"),
+ FuelEntry.price_per_liter.label("price"),
+ ).where(FuelEntry.car_id == car_id),
+ )
+ empty = {
+ "current_price_per_liter": None,
+ "predicted_price_per_liter_30_days": None,
+ "avg_price_per_liter": None,
+ "price_samples": 0,
+ "price_confidence": 0,
+ }
+ if df.empty:
+ return empty
+
+ df = df.dropna().copy()
+ if df.empty:
+ return empty
+ df["date"] = pd.to_datetime(df["date"])
+ df["price"] = pd.to_numeric(df["price"], errors="coerce")
+ df = df[(df["price"] > 0) & (df["price"] < 10000)].sort_values("date")
+ if df.empty:
+ return empty
+
+ recent = df.tail(8).copy()
+ current = float(recent.iloc[-1]["price"])
+ avg = float(recent["price"].mean())
+ predicted = current
+ confidence = min(0.72, 0.22 + len(recent) * 0.055)
+
+ if len(recent) >= 2:
+ span_days = max((recent.iloc[-1]["date"] - recent.iloc[0]["date"]).days, 1)
+ change_per_day = float((recent.iloc[-1]["price"] - recent.iloc[0]["price"]) / span_days)
+ predicted = current + change_per_day * 30
+ predicted = (predicted * 0.65) + (avg * 0.35)
+ volatility = float(recent["price"].std() / max(avg, 1)) if len(recent) >= 3 else 0
+ confidence = min(0.9, max(0.3, confidence + min(span_days, 180) / 600 - volatility))
+
+ return {
+ "current_price_per_liter": round(current, 2),
+ "predicted_price_per_liter_30_days": round(max(predicted, 0), 2),
+ "avg_price_per_liter": round(avg, 2),
+ "price_samples": int(len(df)),
+ "price_confidence": round(confidence, 2),
+ }
diff --git a/web/index.html b/web/index.html
index 93bea95..a6d873e 100644
--- a/web/index.html
+++ b/web/index.html
@@ -60,6 +60,7 @@
Добавь авто и первую запись, чтобы видеть точные отчеты
+ Готов к работе