refactor app

app/models/prediction_models.py

@@ -0,0 +1,12 @@
+from pydantic import BaseModel
+from typing import List
+
+
+class PredictionRequest(BaseModel):
+    invoiceId: List[int]
+    country: str
+
+
+class PredictionResponse(BaseModel):
+    invoiceId: int
+    prediction: float

app/routes/prediction.py

@@ -0,0 +1,25 @@
+from fastapi import APIRouter
+from app.models.prediction_models import PredictionRequest, PredictionResponse
+from typing import List
+from app.utils.data_preparation import load_model_and_data
+from app.utils.validations import check_country_code, check_valid_ids
+
+router = APIRouter()
+
+df, model = load_model_and_data()
+
+
+@router.post("/", response_model=List[PredictionResponse])
+def predict(request: PredictionRequest):
+    check_country_code(request)
+    check_valid_ids(request, df)
+
+    prediction_data = df.loc[request.invoiceId]
+    predictions = model.predict(prediction_data)
+
+    response_data = [
+        {"invoiceId": invoice_id, "prediction": float(prediction)}
+        for invoice_id, prediction in zip(request.invoiceId, predictions)
+    ]
+
+    return response_data

utils.py → app/utils/data_preparation.py

@@ -1,14 +1,23 @@
 import pandas as pd
+import joblib
+
+
+def load_model_and_data():
+    with open("app/data/lightgbm_deuda.pkl", "rb") as file:
+        model = joblib.load(file)
+
+    df = pd.read_csv("app/data/data_finance.csv")
+    df = df.set_index("invoiceId")
+    return df, model
 
 
 def prepare_data(df: pd.DataFrame = None) -> pd.DataFrame:
     """
     Prepare data.
     """
-    # Assuming no additional preprocessing is required for this example
     df = df.drop(["Unnamed: 0", "overdueDays"], axis=1)
     df = df.drop(["businessId", "payerId"], axis=1)
-    df = df.set_index("invoiceId")
+
     df = df[
         [
             "receiptAmount",

app/utils/validations.py

@@ -0,0 +1,20 @@
+from fastapi import HTTPException
+
+
+def check_country_code(request):
+    if request.country not in ["CL", "MX"]:
+        raise HTTPException(
+            status_code=400, detail=f"Invalid country code: {request.country}"
+        )
+    else:
+        return print("correct country code")
+
+
+def check_valid_ids(request, df):
+    invalid_ids = set(request.invoiceId) - set(df.index)
+    if invalid_ids:
+        raise HTTPException(
+            status_code=400, detail=f"Invalid invoiceId(s): {invalid_ids}"
+        )
+    else:
+        return print("invoice ids are valid")

main.py

@@ -1,71 +1,13 @@
-from fastapi import FastAPI, HTTPException
-from pydantic import BaseModel
-from os import getenv
-import pandas as pd
-import joblib
+from fastapi import FastAPI, Depends
+from app.routes import prediction
+from app.models.prediction_models import PredictionRequest, PredictionResponse
 
-# import pickle
-import numpy as np
-from utils import prepare_data
 
 app = FastAPI()
 
-# Cargar el modelo XGBoost desde el archivo .pkl
-# with open("data/lightgbm_deuda.pkl", "rb") as file:
-#    model = pickle.load(file)
-with open("data/lightgbm_deuda.pkl", "rb") as file:
-    # model = joblib.load(file)
-    model = joblib.load(file)
-
-# Cargar el DataFrame desde el archivo CSV
-df = pd.read_csv("data/dataTest.csv")
-# df = df.set_index("invoiceId")
-
-
-df = prepare_data(df)
-
-
-class PredictionRequest(BaseModel):
-    invoiceId: list[int]
-    country: str
-
-
-class PredictionResponse(BaseModel):
-    invoiceId: int
-    prediction: float
-
-
-@app.post("/predict")
-def predict(request: PredictionRequest):
-    # Verificar que los invoiceId enviados estén en el DataFrame
-
-    invalid_ids = set(request.invoiceId) - set(df.index)
-    if invalid_ids:
-        raise HTTPException(
-            status_code=400, detail=f"Invalid invoiceId(s): {invalid_ids}"
-        )
-    if request.country not in ["CL", "MX"]:
-        raise HTTPException(
-            status_code=400, detail=f"Invalid country code: {request.country}"
-        )
-
-    # Filtrar el DataFrame para obtener solo las filas correspondientes a los invoiceId enviados
-    prediction_data = df.loc[request.invoiceId]
-
-    # Realizar la predicción con el modelo
-    predictions = model.predict(prediction_data)
-
-    # Crear la respuesta
-    response_data = [
-        {"invoiceId": invoice_id, "prediction": float(prediction)}
-        for invoice_id, prediction in zip(request.invoiceId, predictions)
-    ]
-
-    return response_data
-
-
-# if __name__ == "__main__":
-#     import uvicorn
-
-#     print("building")
-#     uvicorn.run(app, host="0.0.0.0", reload=True)
+# Include three routers
+app.include_router(
+    prediction.router,
+    prefix="/predict",
+    tags=["prediction"],
+)