feat(tables): summary data tables in Markdown

src/tables/summary_tables.py

@@ -0,0 +1,317 @@
+"""Summary Table Generators — Markdown format
+
+Generates 6 summary Markdown tables from the data modules:
+  1. Bubble Indicators Comparison
+  2. Hyperscaler Capex by Year/Company
+  3. AI Startup Valuations
+  4. Agent Adoption Survey Data
+  5. Productivity Case Study Metrics
+  6. Failure Modes
+
+Output: output/tables/summary_tables.md
+"""
+
+from __future__ import annotations
+
+import sys
+from pathlib import Path
+
+# Ensure project root is on the path for imports
+project_root = Path(__file__).resolve().parent.parent.parent
+if str(project_root) not in sys.path:
+    sys.path.insert(0, str(project_root))
+
+from src.data.market_bubbles import (
+    shiller_cape,
+    shiller_cape_meta,
+    buffett_indicator,
+    buffett_indicator_meta,
+    sp500_pe,
+    sp500_pe_meta,
+    sp500_dividend_yield,
+    sp500_dividend_yield_meta,
+)
+from src.data.ai_infrastructure import hyperscaler_capex_annual
+from src.data.agent_adoption import agent_survey_data
+from src.data.productivity import case_studies, failure_modes
+
+
+def _fmt_capex(value: float, is_range: bool, range_low: float | None, range_high: float | None) -> str:
+    """Format capex value, handling ranges."""
+    if is_range and range_low is not None and range_high is not None:
+        return f"${range_low:.0f}-${range_high:.0f}B"
+    if is_range and range_low is not None and range_high is None:
+        return f"${value:.0f}B+"
+    if is_range:
+        return f"~${value:.0f}B"
+    return f"${value:.0f}B"
+
+
+def _generate_table_1() -> list[str]:
+    """Table 1: Bubble Indicators Comparison."""
+    md = []
+    md.append("## 1. Bubble Indicators Comparison\n")
+    md.append("| Indicator | Current Value | Historical Mean | Zone | Source |")
+    md.append("|---|---|---|---|---|")
+
+    cape_current = shiller_cape[-1]["value"]
+    cape_mean = shiller_cape_meta["historical_mean"]
+    md.append(f"| Shiller CAPE | {cape_current} | {cape_mean} | Bubble (>30) | Yale/Shiller |")
+
+    buffett_current = buffett_indicator[-1]["value"]
+    buffett_meta_mean = "~105%"
+    md.append(f"| Buffett Indicator | {buffett_current:.0f}% | {buffett_meta_mean} | Bubble (>200%) | Composite |")
+
+    pe_current = sp500_pe[-1]["value"]
+    pe_mean = sp500_pe_meta["historical_mean"]
+    md.append(f"| S&P 500 P/E | {pe_current} | ~{pe_mean} | Warning | multpl.com |")
+
+    dy_current = sp500_dividend_yield[-1]["value"]
+    dy_mean = sp500_dividend_yield_meta["historical_mean"]
+    md.append(f"| Dividend Yield | {dy_current}% | ~{dy_mean}% | Near historic low | multpl.com |")
+
+    return md
+
+
+def _generate_table_2() -> list[str]:
+    """Table 2: Hyperscaler Capex by Year/Company."""
+    md = []
+    md.append("## 2. Hyperscaler Capex by Year/Company\n")
+    md.append("| Year | Microsoft | Alphabet | Meta | Amazon | Combined |")
+    md.append("|---|---|---|---|---|---|")
+
+    companies = ["Microsoft", "Alphabet", "Meta", "Amazon"]
+    years = sorted(set(entry["year"] for entry in hyperscaler_capex_annual))
+
+    for year in years:
+        row = [str(year)]
+        total = 0.0
+        for company in companies:
+            entry = next(
+                (e for e in hyperscaler_capex_annual if e["year"] == year and e["company"] == company),
+                None,
+            )
+            if entry is None:
+                row.append("—")
+            else:
+                formatted = _fmt_capex(
+                    entry["capex_billions"],
+                    entry.get("is_range", False),
+                    entry.get("range_low"),
+                    entry.get("range_high"),
+                )
+                row.append(formatted)
+                total += entry["capex_billions"]
+
+        # Combine into a combined column
+        combined = f"${total:.1f}B"
+        # If any entry is a range, mark combined with ~
+        has_range = any(
+            e.get("is_range", False)
+            for e in hyperscaler_capex_annual
+            if e["year"] == year and e["company"] in companies
+        )
+        if has_range:
+            combined = f"~${total:.0f}B"
+        row.append(combined)
+
+        md.append("| " + " | ".join(row) + " |")
+
+    return md
+
+
+def _generate_table_3() -> list[str]:
+    """Table 3: AI Startup Valuations.
+
+    Data sourced from CB Insights, company filings, and analyst reports as of Q1 2026.
+    No dedicated data module exists; values are embedded per research findings.
+    """
+    md = []
+    md.append("## 3. AI Startup Valuations\n")
+    md.append("| Company | Valuation | Revenue Multiple | Date | Source |")
+    md.append("|---|---|---|---|---|")
+
+    valuations = [
+        ("OpenAI", "$840B", "31x revenue", "Q1 2026", "CB Insights"),
+        ("Anthropic", "$380B", "40x revenue", "Q1 2026", "CB Insights"),
+        ("Perplexity AI", "$5.3B", "27x revenue", "Q1 2025", "Crunchbase"),
+        ("Scale AI", "$14B", "7x revenue", "2024", "Crunchbase"),
+        ("Mistral AI", "$8B", "40x revenue", "2024", "Company filings"),
+        ("Cohere", "$3.7B", "N/A (pre-profit)", "2024", "Crunchbase"),
+        ("Hugging Face", "$4.5B", "N/A (pre-profit)", "2024", "Crunchbase"),
+    ]
+
+    for company, valuation, rev_multiple, date, source in valuations:
+        md.append(f"| {company} | {valuation} | {rev_multiple} | {date} | {source} |")
+
+    return md
+
+
+def _generate_table_4() -> list[str]:
+    """Table 4: Agent Adoption Survey Data."""
+    md = []
+    md.append("## 4. Agent Adoption Survey Data\n")
+    md.append("| Survey | Production % | Scaling % | Sample Size | Date |")
+    md.append("|---|---|---|---|---|")
+
+    # LangChain 2025
+    lc = agent_survey_data["langchain_2025"]
+    md.append(
+        f"| LangChain 2025 | {lc['production']}% | — | {lc['sample_size']:,} | {lc['date']} |"
+    )
+
+    # McKinsey 2025
+    mc = agent_survey_data["mckinsey_2025"]
+    md.append(
+        f"| McKinsey 2025 | — | {mc['agentic_ai_scaling']}% | {mc['sample_size']:,} | {mc['date']} |"
+    )
+
+    # PwC 2025
+    pw = agent_survey_data["pwc_2025"]
+    md.append(
+        f"| PwC 2025 | {pw['ai_agents_already_adopted']}% | — | {pw['sample_size']:,} | {pw['date']} |"
+    )
+
+    return md
+
+
+def _generate_table_5() -> list[str]:
+    """Table 5: Productivity Case Study Metrics."""
+    md = []
+    md.append("## 5. Productivity Case Study Metrics\n")
+    md.append("| Company | System | Key Metric | Value | Confidence |")
+    md.append("|---|---|---|---|---|")
+
+    # Klarna
+    klarna = case_studies[0]
+    md.append(
+        f"| {klarna['company']} | {klarna['system']} | FTE equivalent | "
+        f"{klarna['metrics']['fte_equivalent']:,} | {klarna['confidence']} |"
+    )
+    md.append(
+        f"| {klarna['company']} | {klarna['system']} | Resolution time reduction | "
+        f"{klarna['metrics']['resolution_time_reduction_percent']}% | {klarna['confidence']} |"
+    )
+    md.append(
+        f"| {klarna['company']} | {klarna['system']} | Task automation | "
+        f"{klarna['metrics']['task_automation_percent']}% | {klarna['confidence']} |"
+    )
+
+    # JPMorgan
+    jpm = case_studies[1]
+    md.append(
+        f"| {jpm['company']} | {jpm['system']} | Hours saved/year | "
+        f"{jpm['metrics']['hours_saved_annually']:,} | {jpm['confidence']} |"
+    )
+    md.append(
+        f"| {jpm['company']} | {jpm['system']} | Contracts processed/year | "
+        f"{jpm['metrics']['contracts_processed_annually']:,} | {jpm['confidence']} |"
+    )
+    md.append(
+        f"| {jpm['company']} | {jpm['system']} | Annual value | "
+        f"${jpm['metrics']['annual_value_usd']:,.0f} | {jpm['confidence']} |"
+    )
+
+    # ServiceNow / SnowGeek
+    sn = case_studies[2]
+    short_name = "ServiceNow (SnowGeek)"
+    md.append(
+        f"| {short_name} | {sn['system']} | Midnight escalation reduction | "
+        f"{sn['metrics']['midnight_escalation_reduction_percent']}% | {sn['confidence']} |"
+    )
+    md.append(
+        f"| {short_name} | {sn['system']} | MTTR improvement | "
+        f"{sn['metrics']['mttr_improvement_percent']}% | {sn['confidence']} |"
+    )
+    md.append(
+        f"| {short_name} | {sn['system']} | Annual downtime savings | "
+        f"${sn['metrics']['annual_downtime_savings_usd']:,} | {sn['confidence']} |"
+    )
+
+    # Morgan Stanley (LOW confidence)
+    ms = case_studies[3]
+    md.append(
+        f"| {ms['company']} | {ms['system']} | Developer hours saved | "
+        f"{ms['metrics']['developer_hours_saved']:,} | {ms['confidence']} |"
+    )
+
+    return md
+
+
+def _generate_table_6() -> list[str]:
+    """Table 6: Failure Modes."""
+    md = []
+    md.append("## 6. Failure Modes\n")
+    md.append("| Finding | Rate | Source | Confidence |")
+    md.append("|---|---|---|---|")
+
+    for fm in failure_modes:
+        # Format the finding as a concise description
+        if "detail" in fm:
+            # Extract the rate and description from detail
+            detail = fm["detail"]
+        else:
+            detail = fm.get("note", fm["category"])
+
+        rate = f"{fm['rate_percent']}%" if "rate_percent" in fm else "—"
+        source = fm.get("source", "—")
+        confidence = fm.get("confidence", "—")
+
+        # Use the category as a shorthand for the finding
+        finding = detail.split("\n")[0] if detail else fm["category"]
+
+        md.append(f"| {finding} | {rate} | {source} | {confidence} |")
+
+    return md
+
+
+def generate_tables() -> str:
+    """Generate all 6 summary tables as Markdown."""
+    md = []
+
+    # Header
+    md.append("# AI Bubble Case Study — Summary Tables\n")
+    md.append("> Generated from `src.data.*` modules. Data retrieved June 2026.\n")
+
+    # Table 1: Bubble Indicators
+    md.extend(_generate_table_1())
+    md.append("")
+
+    # Table 2: Hyperscaler Capex
+    md.extend(_generate_table_2())
+    md.append("")
+
+    # Table 3: AI Startup Valuations
+    md.extend(_generate_table_3())
+    md.append("")
+
+    # Table 4: Agent Adoption Survey
+    md.extend(_generate_table_4())
+    md.append("")
+
+    # Table 5: Productivity Case Study Metrics
+    md.extend(_generate_table_5())
+    md.append("")
+
+    # Table 6: Failure Modes
+    md.extend(_generate_table_6())
+    md.append("")
+
+    # Footer
+    md.append("---")
+    md.append("*Tables generated programmatically from research data modules.*")
+
+    return "\n".join(md)
+
+
+def main():
+    md_content = generate_tables()
+    output_path = "output/tables/summary_tables.md"
+    with open(output_path, "w") as f:
+        f.write(md_content)
+    print(f"Tables saved: {output_path}")
+    print(f"Content length: {len(md_content)} characters")
+
+
+if __name__ == "__main__":
+    main()