approach_api/utils/comparative_analysis.py

import json
from collections import Counter

def comparative_sentiment_analysis(company, articles, max_comparisons=10, chunk_size=5):
    """
    Perform a comparative sentiment analysis on multiple articles.
    """
    overall_sentiment_counts = Counter()
    overall_coverage_differences = []
    all_topics = []

    if not articles:
        print("No articles found for analysis.")
        return {
            "Company": company,
            "Articles": [],
            "Comparative Sentiment Score": {
                "Sentiment Distribution": {},
                "Coverage Differences": [],
                "Topic Overlap": {"Common Topics": [], "Unique Topics Per Article": []}
            },
            "Final Sentiment Analysis": "No data available."
        }

    # Process articles in chunks
    for start in range(0, len(articles), chunk_size):
        chunk = articles[start:start + chunk_size]

        # Count sentiment distribution
        sentiment_counts = Counter(article["Sentiment"] for article in chunk)
        overall_sentiment_counts.update(sentiment_counts)

        # Identify coverage differences
        for i in range(len(chunk) - 1):
            for j in range(i + 1, len(chunk)):
                if len(overall_coverage_differences) >= max_comparisons:
                    break
                article1, article2 = chunk[i], chunk[j]
                comparison = {
                    "Comparison": f"'{article1.get('Title', 'Article 1')}' vs '{article2.get('Title', 'Article 2')}'",
                    "Impact": f"{article1.get('Topics', [])} vs {article2.get('Topics', [])}"
                }
                overall_coverage_differences.append(comparison)

        # Extract topics ensuring valid lists
        topics = [set(article.get("Topics", [])) for article in chunk if isinstance(article.get("Topics", list), list) and article.get("Topics", [])]
        all_topics.extend(topics)

    # Debugging Output
    print("All Topics Extracted:", all_topics)

    # Determine common and unique topics
    if len(all_topics) == 0:
        common_topics = set()  # No topics found
    elif len(all_topics) == 1:
        common_topics = all_topics[0]  # Only one article, take its topics as common
    else:
        common_topics = set.intersection(*all_topics)  # Find intersection normally

    unique_topics = [{"Article": i + 1, "Unique Topics": list(topics - common_topics)}
                     for i, topics in enumerate(all_topics)]

    # Convert to list for JSON output
    common_topics = list(common_topics)

    print("Common Topics:", common_topics)

    # Final sentiment summary
    final_analysis = "The news coverage is mostly "
    if overall_sentiment_counts["Positive"] > overall_sentiment_counts["Negative"]:
        final_analysis += "positive, indicating potential growth."
    elif overall_sentiment_counts["Negative"] > overall_sentiment_counts["Positive"]:
        final_analysis += "negative, suggesting challenges ahead."
    else:
        final_analysis += "balanced, with mixed reactions."

    # Final JSON structure
    return {
        "Comparative Sentiment Score": {
            "Sentiment Distribution": dict(overall_sentiment_counts),
            "Coverage Differences": overall_coverage_differences,
            "Topic Overlap": {
                "Common Topics": common_topics,
                "Unique Topics Per Article": unique_topics
            }
        },
        "Final Sentiment Analysis": final_analysis
    }

# if __name__ == "__main__":
#     articles = [
#         {
#             "Title": "Agentic AI startup AMT aims to be 'Google Adwords for influencers,' raises seed round",
#             "Summary": "Agentic Marketing Technologies (AMT) has raised $3.5 million in a seed funding round led by San Francisco-based VC NFX .<n>AMT works by getting its AI agent, dubbed Lyra, to talk to influencers using natural language .<n>The company claims Lyra can also autonomously find influencers that match a campaign’s goals .",
#             "Sentiment": "neutral",
#             "Topics": [
#                 "influencer",
#                 "marketing"
#             ]
#         },
#         {
#             "Title": "Google Seals $32 Billion Deal for Cyber Start-Up Wiz",
#             "Summary": "Google agreed to buy Wiz, a fast-growing cybersecurity start-up, for $32 billion .<n>The all-cash deal would be Google's largest, easily surpassing its $12.5 billion purchase of Motorola Mobility in 2012 .<n>In July, Wiz rejected Google’s $23 billion takeover offer, saying it wanted to pursue an initial public offering .",
#             "Sentiment": "neutral",
#             "Topics": [
#                 "wiz",
#                 "google"
#             ]
#         },
#         {
#             "Title": "Google's new Severance Easter egg is one only innies will understand",
#             "Summary": "Just search for Severance and Google will pepper your screen with blue balloons .<n>Severance producer and frequent director Ben Stiller shared his show’s new Easter egg on X last night .<n>Severance’s season two finale airs this Friday on Apple TV Plus .",
#             "Sentiment": "positive",
#             "Topics": [
#                 "severance"
#             ]
#         }
#     ]
# result = comparative_sentiment_analysis(articles)
# print(json.dumps(result, indent=4))