Create main.py
Browse files
main.py
ADDED
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
from fastapi import FastAPI, HTTPException, Query
|
2 |
+
import pandas as pd
|
3 |
+
import joblib
|
4 |
+
|
5 |
+
|
6 |
+
|
7 |
+
app = FastAPI()
|
8 |
+
|
9 |
+
|
10 |
+
|
11 |
+
# Load the sepsis prediction model
|
12 |
+
model = joblib.load('XGB.joblib')
|
13 |
+
|
14 |
+
|
15 |
+
|
16 |
+
@app.get("/")
|
17 |
+
async def read_root():
|
18 |
+
return {"message": "Sepsis Prediction API using FastAPI"}
|
19 |
+
|
20 |
+
|
21 |
+
|
22 |
+
def classify(prediction):
|
23 |
+
if prediction == 0:
|
24 |
+
return "Patient does not have sepsis"
|
25 |
+
else:
|
26 |
+
return "Patient has sepsis"
|
27 |
+
|
28 |
+
|
29 |
+
|
30 |
+
@app.get("/predict/")
|
31 |
+
async def predict_sepsis(
|
32 |
+
prg: float = Query(..., description="Plasma glucose"),
|
33 |
+
pl: float = Query(..., description="Blood Work Result-1 (mu U/ml)"),
|
34 |
+
pr: float = Query(..., description="Blood Pressure (mm Hg)"),
|
35 |
+
sk: float = Query(..., description="Blood Work Result-2 (mm)"),
|
36 |
+
ts: float = Query(..., description="Blood Work Result-3 (mu U/ml)"),
|
37 |
+
m11: float = Query(..., description="Body mass index (weight in kg/(height in m)^2"),
|
38 |
+
bd2: float = Query(..., description="Blood Work Result-4 (mu U/ml)"),
|
39 |
+
age: int = Query(..., description="Patient's age (years)")
|
40 |
+
):
|
41 |
+
input_data = [prg, pl, pr, sk, ts, m11, bd2, age]
|
42 |
+
|
43 |
+
|
44 |
+
|
45 |
+
input_df = pd.DataFrame([input_data], columns=[
|
46 |
+
"Plasma glucose", "Blood Work Result-1", "Blood Pressure",
|
47 |
+
"Blood Work Result-2", "Blood Work Result-3",
|
48 |
+
"Body mass index", "Blood Work Result-4", "Age"
|
49 |
+
])
|
50 |
+
|
51 |
+
|
52 |
+
|
53 |
+
pred = model.predict(input_df)
|
54 |
+
output = classify(pred[0])
|
55 |
+
|
56 |
+
|
57 |
+
|
58 |
+
response = {
|
59 |
+
"prediction": output
|
60 |
+
}
|
61 |
+
|
62 |
+
|
63 |
+
|
64 |
+
return response
|
65 |
+
|
66 |
+
|
67 |
+
|
68 |
+
# Run the app using Uvicorn
|
69 |
+
if __name__ == "__main__":
|
70 |
+
import uvicorn
|
71 |
+
uvicorn.run(app, host="127.0.0.1", port=7860)
|