db.py

import pandas as pd
import requests
import io
from pymongo import MongoClient

def get_mongo_client():
    client = MongoClient("mongodb+srv://groupA:[email protected]/?retryWrites=true&w=majority&appName=SentimentCluster")
    db = client["sentiment_db"]
    return db["tweets"]

def insert_data_if_empty():
    collection = get_mongo_client()
    if collection.count_documents({}) == 0:
        print("🟢 No data found. Inserting dataset...")
        csv_url = "https://huggingface.co/spaces/sharangrav24/SentimentAnalysis/resolve/main/sentiment140.csv"
        try:
            response = requests.get(csv_url)
            response.raise_for_status()
            df = pd.read_csv(io.StringIO(response.text), encoding="ISO-8859-1")
            # Add default fields if not present.
            if "user" not in df.columns:
                df["user"] = "Unknown"
            if "date" not in df.columns:
                df["date"] = "Unknown"
            collection.insert_many(df.to_dict("records"))
            print("✅ Data Inserted into MongoDB!")
        except Exception as e:
            print(f"❌ Error loading dataset: {e}")

def get_entry_by_index(index=0):
    collection = get_mongo_client()
    # Fetch the document by skipping "index" entries.
    doc_cursor = collection.find({}, {"_id": 0}).skip(index).limit(1)
    docs = list(doc_cursor)
    if docs:
        return docs[0]
    return None