Spaces:
Runtime error
Runtime error
Upload 2 files
Browse files- app.py +36 -0
- requirements.txt +9 -0
app.py
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import numpy as np
|
2 |
+
from fastapi import FastAPI, HTTPException
|
3 |
+
from pydantic import BaseModel
|
4 |
+
from typing import List
|
5 |
+
from tensorflow.keras.models import model_from_json
|
6 |
+
from sklearn.preprocessing import StandardScaler
|
7 |
+
|
8 |
+
class InputData(BaseModel):
|
9 |
+
data: List[float] # Lista de características numéricas (flotantes)
|
10 |
+
|
11 |
+
app = FastAPI()
|
12 |
+
|
13 |
+
# Cargar el modelo desde JSON
|
14 |
+
with open("model.json", "r") as json_file:
|
15 |
+
model_json = json_file.read()
|
16 |
+
model = model_from_json(model_json)
|
17 |
+
|
18 |
+
# Cargar los pesos en el modelo
|
19 |
+
model.load_weights("model_weights.h5")
|
20 |
+
|
21 |
+
# Ruta de predicción
|
22 |
+
@app.post("/predict/")
|
23 |
+
async def predict(data: InputData):
|
24 |
+
try:
|
25 |
+
# Convertir la lista de entrada a un array de NumPy para la predicción
|
26 |
+
input_data = np.array(data.data).reshape(1, -1)
|
27 |
+
|
28 |
+
# Escalar los datos (asegúrate de que el escalador ha sido entrenado y guardado adecuadamente)
|
29 |
+
scaler = StandardScaler()
|
30 |
+
input_data = scaler.fit_transform(input_data)
|
31 |
+
|
32 |
+
# Realizar la predicción
|
33 |
+
prediction = model.predict(input_data).round()
|
34 |
+
return {"prediction": prediction.tolist()}
|
35 |
+
except Exception as e:
|
36 |
+
raise HTTPException(status_code=500, detail=str(e))
|
requirements.txt
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
fastapi
|
2 |
+
pydantic
|
3 |
+
numpy
|
4 |
+
pandas
|
5 |
+
matplotlib
|
6 |
+
seaborn
|
7 |
+
scikit-learn
|
8 |
+
tensorflow
|
9 |
+
uvicorn
|