db.py

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

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

# Function to insert data if the collection is empty.
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")
            collection.insert_many(df.to_dict("records"))
            print("✅ Data Inserted into MongoDB!")
        except Exception as e:
            print(f"❌ Error loading dataset: {e}")

# Function to get dataset summary from MongoDB.
def get_dataset_summary():
    collection = get_mongo_client()
    # Aggregate counts for each sentiment target.
    pipeline = [
        {"$group": {"_id": "$target", "count": {"$sum": 1}}}
    ]
    results = list(collection.aggregate(pipeline))
    # Map the sentiment target values to labels.
    mapping = {"0": "Negative", "2": "Neutral", "4": "Positive"}
    summary_parts = []
    total = 0
    for doc in results:
        target = str(doc["_id"])
        count = doc["count"]
        total += count
        label = mapping.get(target, target)
        summary_parts.append(f"{label}: {count}")
    summary = f"Total tweets: {total}. " + ", ".join(summary_parts) + "."
    return summary