RICHARDMENSAH/Sepsis-Prediction-APP-using-FASTAPI-and-Machine-Learning

1import pandas as pd2import joblib3from fastapi import FastAPI4import uvicorn5import numpy as np6import os7 8app = FastAPI()9#app.mount("/static", StaticFiles(directory="static"), name="static")10#templates = Jinja2Templates(directory="templates")11 12def load_model():13    cwd = os.getcwd()14    destination = os.path.join(cwd, "Assets")15 16    imputer_filepath = os.path.join(destination, "numerical_imputer.joblib")17    scaler_filepath = os.path.join(destination, "scaler.joblib")18    model_filepath = os.path.join(destination, "lr_model.joblib")19 20    num_imputer = joblib.load(imputer_filepath)21    scaler = joblib.load(scaler_filepath)22    model = joblib.load(model_filepath)23 24    return num_imputer, scaler, model25 26 27def preprocess_input_data(input_data, num_imputer, scaler):28    input_data_df = pd.DataFrame([input_data])29    num_columns = [col for col in input_data_df.columns if input_data_df[col].dtype != 'object']30    input_data_imputed_num = num_imputer.transform(input_data_df[num_columns])31    input_scaled_df = pd.DataFrame(scaler.transform(input_data_imputed_num), columns=num_columns)32    return input_scaled_df33 34@app.get("/")35def read_root():36    return "Sepsis Prediction App"37 38@app.get("/sepsis/predict")39def predict_sepsis_endpoint(PRG: float, PL: float, PR: float, SK: float, TS: float,40                            M11: float, BD2: float, Age: float, Insurance: int):41    num_imputer, scaler, model = load_model()42 43    input_data = {44        'PRG': [PRG],45        'PL': [PL],46        'PR': [PR],47        'SK': [SK],48        'TS': [TS],49        'M11': [M11],50        'BD2': [BD2],51        'Age': [Age],52        'Insurance': [Insurance]53    }54 55    input_scaled_df = preprocess_input_data(input_data, num_imputer, scaler)56 57    probabilities = model.predict_proba(input_scaled_df)[0]58    prediction = np.argmax(probabilities)59 60    sepsis_status = "Positive" if prediction == 1 else "Negative"61    62    probability = probabilities[1] if prediction == 1 else probabilities[0]63 64    #statement = f"The patient is {sepsis_status}. There is a {'high' if prediction == 1 else 'low'} probability ({probability:.2f}) that the patient is susceptible to developing sepsis."65 66    if prediction == 1:67        status_icon = "✔"  # Red 'X' icon for positive sepsis prediction68        sepsis_explanation = "Sepsis is a life-threatening condition caused by an infection. A positive prediction suggests that the patient might be exhibiting sepsis symptoms and requires immediate medical attention."69    else:70        status_icon = "✘"  # Green checkmark icon for negative sepsis prediction71        sepsis_explanation = "Sepsis is a life-threatening condition caused by an infection. A negative prediction suggests that the patient is not currently exhibiting sepsis symptoms."72 73    statement = f"The patient's sepsis status is {sepsis_status} {status_icon} with a probability of {probability:.2f}. {sepsis_explanation}"74 75    user_input_statement = "Please note this is the user-inputted data: "76 77    output_df = pd.DataFrame([input_data])78 79    result = {'predicted_sepsis': sepsis_status, 'statement': statement, 'user_input_statement': user_input_statement, 'input_data_df': output_df.to_dict('records')}80 81    return result82 83if __name__ == "__main__":84    uvicorn.run(app, host="0.0.0.0", port=7860, reload=True)