39 lines
1.3 KiB
Python
39 lines
1.3 KiB
Python
|
import joblib
|
||
|
|
import pandas as pd
|
||
|
|
# Импортируем наши классы, чтобы joblib мог их десериализовать
|
||
|
|
from train import TextExtractor, NumberExtractor
|
||
|
|
|
||
|
|
# 1. Загружаем модель
|
||
|
|
model = joblib.load('solution/model/mcc_model.pkl')
|
||
|
|
|
||
|
|
# 2. Подготавливаем тестовые данные (как они придут в API)
|
||
|
|
test_json = {
|
||
|
|
"transaction_id": "TX00001116",
|
||
|
|
"terminal_name": "STORE001",
|
||
|
|
"terminal_description": "common common common thing",
|
||
|
|
"city": "NYC",
|
||
|
|
"amount": 272.80,
|
||
|
|
"items": [
|
||
|
|
{"name": "basic loyalty", "price": 58.20},
|
||
|
|
{"name": "Bringiong item lifes", "price": 28.99}
|
||
|
|
]
|
||
|
|
}
|
||
|
|
|
||
|
|
|
||
|
|
# 3. Преобразуем в формат, который понимает пайплайн (как в main.py)
|
||
|
|
items_str = " ".join([i['name'] for i in test_json['items']])
|
||
|
|
full_text = f"{test_json['terminal_name']} {test_json['terminal_description']} {items_str}".lower()
|
||
|
|
|
||
|
|
input_df = pd.DataFrame([{
|
||
|
|
'full_text': full_text,
|
||
|
|
'amount': test_json['amount']
|
||
|
|
}])
|
||
|
|
|
||
|
|
# 4. Делаем предсказание
|
||
|
|
prediction = model.predict(input_df)[0]
|
||
|
|
confidence = model.predict_proba(input_df).max()
|
||
|
|
|
||
|
|
print(f"Transaction ID: {test_json['transaction_id']}")
|
||
|
|
print(f"Predicted MCC: {prediction}")
|
||
|
|
print(f"Confidence: {confidence:.4f}")
|