from fastapi import FastAPI, Query, Request, HTTPException
import pandas as pd
import transformers as pipeline 
from transformers import AutoTokenizer,AutoModelForSequenceClassification
from transformers import AutoModelForSequenceClassification, AutoTokenizer, pipeline

model_name = "Sonny4Sonnix/Movie_Sentiments_Analysis_with_FastAPI"  # Replace with the name of the pre-trained model you want to use
model = AutoModelForSequenceClassification.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)

app = FastAPI()

@app.get("/")
async def read_root():
    return {"message": "Welcome to the Sepsis Prediction using FastAPI"}

def classify(prediction):
    if prediction == 0:
        return "Sentence is positive"
    else:
        return "Sentence is negative"

        
@app.post("/predict/")
async def predict_sepsis(
    request: Request,
    Text: float = Query(..., description="Please type a sentence"),
    # pl: float = Query(..., description="Blood Work Result-1 (mu U/ml)"),
    # pr: float = Query(..., description="Blood Pressure (mm Hg)"),
    # sk: float = Query(..., description="Blood Work Result-2 (mm)"),
    # ts: float = Query(..., description="Blood Work Result-3 (mu U/ml)"),
    # m11: float = Query(..., description="Body mass index (weight in kg/(height in m)^2"),
    # bd2: float = Query(..., description="Blood Work Result-4 (mu U/ml)"),
    # age: int = Query(..., description="Patient's age (years)")
):
    #input_data = [prg, pl, pr, sk, ts, m11, bd2, age]
    input_data = [Text]

    # input_df = pd.DataFrame([input_data], columns=[
    #     "Plasma glucose", "Blood Work Result-1", "Blood Pressure",
    #     "Blood Work Result-2", "Blood Work Result-3",
    #     "Body mass index", "Blood Work Result-4", "Age"

        input_df = pd.DataFrame([input_data], columns=[
        "Text"
    ])

    pred = model.predict(input_df)
    output = classify(pred[0])

    response = {
        "prediction": output
    }

    return response

    # Run the app using Uvicorn
if __name__ == "__main__":
    import uvicorn
    uvicorn.run(app, host="127.0.0.1", port=7860)
sentiment = pipeline("sentiment-analysis", model=model, tokenizer=tokenizer)
    
# def get_sentiment(input_text):
#     result = sentiment(input_text)
#     sentiment_label = result[0]['label']
#     sentiment_score = result[0]['score']
    
#     if sentiment_label == 'LABEL_1':
#         sentiment_label = "positive"
#     elif sentiment_label == 'LABEL_0':
#         sentiment_label = "neutral"
#     else:
#         sentiment_label = "negative"
    
#     return f"Sentiment: {sentiment_label.capitalize()}, Score: {sentiment_score:.2f}"