fastapi==0.110.0
pydantic==1.10.14
uvicorn==0.29.0
scikit-learn==1.4.2
numpy==1.26.4

pip3 install -r requirements.txt

# train_model.py
import numpy as np
import pickle
from sklearn.linear_model import LinearRegression

# Bộ dữ liệu mẫu: diện tích (foot vuông) và giá nhà tương ứng ($)
X = np.array([[500], [1000], [1500], [2000], [2500]])
y = np.array([100000, 150000, 200000, 250000, 300000])

# Huấn luyện mô hình Linear Regression
model = LinearRegression()
model.fit(X, y)

# Lưu mô hình thành file .pkl để dùng về sau
with open("house_price_model.pkl", "wb") as f:
    pickle.dump(model, f)

print("Model trained and saved as 'house_price_model.pkl'")

# app.py
from fastapi import FastAPI, Request
from pydantic import BaseModel
import pickle
import numpy as np
import logging

# Cấu hình logging
logger = logging.getLogger(__name__)
logging.basicConfig(level=logging.INFO)

app = FastAPI()

# Tải mô hình đã huấn luyện
with open("house_price_model.pkl", "rb") as f:
    model = pickle.load(f)

@app.get("/")
def read_root(request: Request):
    return {"message": "House Price Prediction API is live!"}

# Định nghĩa schema cho request
class HouseFeatures(BaseModel):
    features: list[float]

@app.post("/predict/")
def predict(data: HouseFeatures, request: Request):
    prediction = model.predict(np.array(data.features).reshape(1, -1))
    logger.info(f"Prediction made: {prediction[0]}")
    return {"predicted_price": float(prediction[0])}

uvicorn app:app --reload

curl -i -X POST 'http://127.0.0.1:8000/predict/' -H "Content-Type: application/json" -d '{"features": [1500]}'

{
  "predicted_price": 200000.0
}