esg_statistics.py

import plotly.graph_objects as go


def compute_esg_keyword_distribution(text):
    text = text.lower()

    environmental_keywords = ["emission", "carbon", "climate", "energy", "waste"]
    social_keywords = ["diversity", "employee", "community", "health", "safety"]
    governance_keywords = ["board", "compliance", "audit", "ethics", "policy"]

    e_count = sum(text.count(word) for word in environmental_keywords)
    s_count = sum(text.count(word) for word in social_keywords)
    g_count = sum(text.count(word) for word in governance_keywords)

    total = max(e_count + s_count + g_count, 1)

    return {
        "Environmental": e_count,
        "Social": s_count,
        "Governance": g_count,
        "Total": total
    }


def generate_esg_statistics_chart(text):
    stats = compute_esg_keyword_distribution(text)

    fig = go.Figure(data=[
        go.Pie(
            labels=["Environmental", "Social", "Governance"],
            values=[
                stats["Environmental"],
                stats["Social"],
                stats["Governance"]
            ],
            hole=0.5
        )
    ])

    fig.update_layout(
        title="ESG Keyword Distribution (Donut Chart)",
        template="plotly_dark"
    )

    return fig