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

# Function to establish MongoDB connection and return the collection
def get_mongo_client():
    client = MongoClient("mongodb+srv://groupA:pythongroupA@sentimentcluster.4usfj.mongodb.net/?retryWrites=true&w=majority&appName=SentimentCluster")
    db = client["sentiment_db"]
    return db["tweets"]

# Function to insert the dataset into MongoDB if the collection is empty
def insert_data_if_empty():
    collection = get_mongo_client()

    if collection.count_documents({}) == 0:
        print("🟢 No data found in MongoDB. Inserting dataset...")
        csv_url = "https://huggingface.co/spaces/sharangrav24/SentimentAnalysis/resolve/main/sentiment140.csv"

        try:
            response = requests.get(csv_url)
            response.raise_for_status()  # Ensure the request was successful
            df = pd.read_csv(io.StringIO(response.text), encoding="ISO-8859-1")

            # Insert dataset records into MongoDB
            collection.insert_many(df.to_dict("records"))
            print("✅ Data Inserted into MongoDB!")
        except Exception as e:
            print(f"❌ Error loading dataset: {e}")