main.py

from fastapi import FastAPI, File, UploadFile, HTTPException
from pydantic import BaseModel
from fastapi.staticfiles import StaticFiles
from fastapi.responses import FileResponse
from ml_service import MlProcessing
from ml_service import process_single_comment
from typing import List, Dict, Union
import time
from kafka import KafkaConsumer, KafkaProducer
import asyncio
import json
import pandas as pd
from datetime import datetime

import spacy
from simpletransformers.ner import NERModel
import json
import fasttext
       


app = FastAPI()

labels_file = f"ml_models/labels.json"
ner_model_directory = f"ml_models/ner_model/"
sentiment_model_file = f"ml_models/sentiment_model/model.ft"


# LANGUAGE_MODEL = spacy.load('en_core_web_sm')
# LABELS = ['O', 'B-AMENITIES', 'I-AMENITIES', 'I-CLEANLINESS', 'B-CLEANLINESS', 'I-COMMUNICATION', 'B-COMMUNICATION', 'B-CONDITION', 'I-CONDITION', 'I-CUSTOMER_SERVICE', 'B-CUSTOMER_SERVICE', 'B-EXTERIOR_LIGHTING', 'I-EXTERIOR_LIGHTING', 'B-FINANCIAL', 'I-FINANCIAL', 'B-INTERIOR_LIGHTING', 'I-INTERIOR_LIGHTING', 'B-INTERNET', 'I-INTERNET', 'B-LANDSCAPING_GROUNDS', 'I-LANDSCAPING_GROUNDS', 'B-MAINTENANCE_CLEANLINESS', 'I-MAINTENANCE_CLEANLINESS', 'I-MAINTENANCE_SERVICE', 'B-MAINTENANCE_SERVICE', 'B-MAINTENANCE_TIMELINESS', 'I-MAINTENANCE_TIMELINESS', 'B-MOVE_IN_QUALITY', 'I-MOVE_IN_QUALITY', 'I-NOISE', 'B-NOISE', 'B-PACKAGES_MAIL', 'I-PACKAGES_MAIL', 'B-PARKING', 'I-PARKING', 'I-PESTS', 'B-PESTS', 'B-PET_WASTE', 'I-PET_WASTE', 'I-SECURITY', 'B-SECURITY', 'B-SMOKE', 'I-SMOKE', 'B-TRASH', 'I-TRASH']
# SENTIMENT_MODEL = fasttext.load_model(sentiment_model_file)

class ML_models:
    def __init__(self, sentiment_model_file):
        self.labels = ['O', 'B-AMENITIES', 'I-AMENITIES', 'I-CLEANLINESS', 'B-CLEANLINESS', 'I-COMMUNICATION', 'B-COMMUNICATION', 'B-CONDITION', 'I-CONDITION', 'I-CUSTOMER_SERVICE', 'B-CUSTOMER_SERVICE', 'B-EXTERIOR_LIGHTING', 'I-EXTERIOR_LIGHTING', 'B-FINANCIAL', 'I-FINANCIAL', 'B-INTERIOR_LIGHTING', 'I-INTERIOR_LIGHTING', 'B-INTERNET', 'I-INTERNET', 'B-LANDSCAPING_GROUNDS', 'I-LANDSCAPING_GROUNDS', 'B-MAINTENANCE_CLEANLINESS', 'I-MAINTENANCE_CLEANLINESS', 'I-MAINTENANCE_SERVICE', 'B-MAINTENANCE_SERVICE', 'B-MAINTENANCE_TIMELINESS', 'I-MAINTENANCE_TIMELINESS', 'B-MOVE_IN_QUALITY', 'I-MOVE_IN_QUALITY', 'I-NOISE', 'B-NOISE', 'B-PACKAGES_MAIL', 'I-PACKAGES_MAIL', 'B-PARKING', 'I-PARKING', 'I-PESTS', 'B-PESTS', 'B-PET_WASTE', 'I-PET_WASTE', 'I-SECURITY', 'B-SECURITY', 'B-SMOKE', 'I-SMOKE', 'B-TRASH', 'I-TRASH']
        self.languate_model = spacy.load('en_core_web_sm')
        self.sentiment_model = fasttext.load_model(sentiment_model_file)
        print("Models loaded")

ml_model = ML_models(sentiment_model_file)
LANGUAGE_MODEL = ml_model.languate_model
SENTIMENT_MODEL = ml_model.sentiment_model
LABELS = ml_model.labels
print("Models loading instances created...")


class TextRatingRequest(BaseModel):
    text: str
    rating: int

class AllTextRatingRequest(BaseModel):
    reviews : List[Dict[str, Union[str, dict, int]]]

@app.post("/predict")
def predict_single_review(text_rating: TextRatingRequest):
    text = text_rating.text
    rating = text_rating.rating
    skip = False
    raw_data = {"text": text, "star_rating": rating, "skip": skip}
    start_time = time.time()
    # ml = MlProcessing(comment_dict=raw_data)
    # processed_data = ml.main()
    # spans = processed_data.get('spans', list())
    # has_sentiments = True
    # if not any(spans):
    #     spans = [{'label': text, 'color': '', 'value': '', 'sentiment': '', 'score': ''}]
    #     has_sentiments = False
    # processed_data['spans'] = spans
    try:
        processed_data, has_sentiments = process_single_comment(raw_data, LANGUAGE_MODEL, SENTIMENT_MODEL, LABELS )
    except Exception as e:
        print("error during prediction: ", e)
        return {"error":e}
    end_time = time.time()
    print(f"Time taken to process the data : {end_time - start_time} seconds")
    return {"processed_data": processed_data, "has_sentiments":has_sentiments}

@app.post("/predict_all")
def predict_all_reviews(reviews: AllTextRatingRequest):
    reviews = reviews.reviews
    skip = False
    processed_data_list = list()
    start_time = time.time()
    for review in reviews:
        raw_data = {"text":review.get('text', str()), "star_rating":review.get('rating', 5), "skip":skip}
        try:
            processed_data, has_sentiments = process_single_comment(raw_data, LANGUAGE_MODEL, SENTIMENT_MODEL, LABELS )
        except Exception as e:
            print("error during prediction: ", e)
            return {"error":e}
        processed_data_list.append({"processed_data":processed_data, "has_sentiments":has_sentiments})
    end_time = time.time()
    print(f"Time taken to process the data : {end_time - start_time} seconds")
    return processed_data_list

@app.post("/predict_file")
def predict_file_responses(file: UploadFile = File(...)):
    if not file.filename.endswith(".csv"):
        raise HTTPException(status_code=400, detail="Only CSV files are allowed")
    try:
        df = pd.read_csv(file.file)
        df = df.fillna('')
    except Exception as e:
        raise HTTPException(status_code=400, detail=f"Error processing CSV file: {e}")
    processed_data_list = list()
    start_time = time.time()
    for index, row in df.iterrows():
        try:
            text = row['ACTUAL REVIEW']
            star_rating = row['STAR RATING']
            review_id = row['REVIEWID']
            raw_data = {"text":text, "star_rating":star_rating, "skip":False}
            try:
                processed_data, has_sentiments = process_single_comment(raw_data,LANGUAGE_MODEL, SENTIMENT_MODEL, LABELS ) 
            except Exception as e:
                print("error during prediction: ", e)
                return {"error":e}
            now = datetime.now()
            print(f"Processed review with index {index} at time {now.time()}")
            processed_data_list.append({"processed_data":processed_data, "has_sentiments":has_sentiments, "review_id":review_id})
        finally:
            pass
    end_time = time.time()
    print(f">>>>>>>>>>>>>>>>>>>>>>>> Processing time : {end_time - start_time} seconds >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>")
    return processed_data_list

app.mount("/", StaticFiles(directory="static", html=True), name="static")

@app.get("/")
def index() -> FileResponse:
    return FileResponse(path="/static/index.html", media_type="text/html")