git clone https://github.com/Timeverse/My-TW-Coverage
cd My-TW-Coverage
pip install yfinance pandas tabulate

My-TW-Coverage/
├── Pilot_Reports/             # 1,735 ticker reports across 99 sectors
│   ├── Semiconductors/        # 155 tickers
│   ├── Electronic Components/ # 267 tickers
│   ├── Computer Hardware/     # 114 tickers
│   └── ... (99 sector folders)
├── scripts/
│   ├── utils.py               # Shared utilities
│   ├── add_ticker.py          # Generate new ticker reports
│   ├── update_financials.py   # Refresh financial tables + valuation
│   ├── update_valuation.py    # Refresh valuation multiples only (fast)
│   ├── update_enrichment.py   # Update business descriptions from JSON
│   ├── audit_batch.py         # Quality auditing
│   ├── discover.py            # Buzzword → related companies search
│   ├── build_wikilink_index.py# Rebuild WIKILINKS.md index
│   ├── build_themes.py        # Generate thematic investment screens
│   └── build_network.py       # Generate D3.js network graph
├── WIKILINKS.md               # Auto-generated browsable wikilink index
├── network/index.html         # Interactive D3.js wikilink network
├── themes/                    # Thematic investment screens (auto-generated)
└── task.md                    # Batch definitions and progress tracking

undefined

undefined

undefined

undefined

undefined

undefined

python scripts/update_valuation.py 2330
python scripts/update_valuation.py --batch 101
python scripts/update_valuation.py --sector Semiconductors
python scripts/update_valuation.py                          # All tickers

undefined

Common buzzword examples:
- `"CoWoS"` — TSMC advanced packaging supply chain
- `"HBM"` — High Bandwidth Memory ecosystem
- `"電動車"` — EV component suppliers
- `"AI 伺服器"` — AI server supply chain (148 companies)
- `"光阻液"` — Photoresist suppliers and consumers
- `"碳化矽"` — Silicon carbide (SiC) companies

python scripts/update_enrichment.py --data enrichment.json 2330
python scripts/update_enrichment.py --data enrichment.json --batch 101
python scripts/update_enrichment.py --data enrichment.json --sector Semiconductors

{
  "2330": {
    "desc": "台積電為全球最大晶圓代工廠，專注於 [[CoWoS]]、[[3奈米]] 先進製程，為 [[Apple]]、[[NVIDIA]] 等科技巨頭提供晶片製造服務。",
    "supply_chain": "**上游:**\n- [[ASML]] (EUV 微影設備)\n- [[Applied Materials]] (薄膜沉積)\n**中游:**\n- **台積電** (晶圓代工)\n**下游:**\n- [[Apple]]\n- [[NVIDIA]]",
    "cust": "### 主要客戶\n- [[Apple]] (約25%營收)\n- [[NVIDIA]]\n- [[AMD]]\n\n### 主要供應商\n- [[ASML]]\n- [[Tokyo Electron]]"
  },
  "2454": {
    "desc": "...",
    "supply_chain": "...",
    "cust": "..."
  }
}

undefined

Audit checks:
- Minimum 8 wikilinks per report
- No generic terms in brackets (e.g. `[[公司]]`, `[[產品]]`)
- No placeholder text remaining
- No English text in Chinese-language sections
- Metadata completeness (板塊, 產業, 市值, 企業價值)
- Section depth (業務簡介, 供應鏈位置, 主要客戶及供應商, 財務概況 all present)

python scripts/build_wikilink_index.py

undefined

Output in `themes/` — each page shows companies grouped by upstream/midstream/downstream role.

undefined

Opens `network/index.html` in browser — D3.js force-directed graph. Node colors:
- 🔴 Red = Taiwan company
- 🔵 Blue = International company
- 🟢 Green = Technology
- 🟠 Orange = Material
- 🟣 Purple = Application

import re
from pathlib import Path

def get_report(ticker: str, reports_dir: str = "Pilot_Reports") -> dict:
    """Find and parse a ticker report."""
    base = Path(reports_dir)
    # Find the file across all sector subdirectories
    matches = list(base.rglob(f"{ticker}_*.md"))
    if not matches:
        return {}
    
    content = matches[0].read_text(encoding="utf-8")
    
    # Extract all wikilinks
    wikilinks = re.findall(r'\[\[([^\]]+)\]\]', content)
    
    # Extract sector metadata
    sector_match = re.search(r'\*\*產業:\*\*\s*(.+)', content)
    board_match = re.search(r'\*\*板塊:\*\*\s*(.+)', content)
    
    return {
        "ticker": ticker,
        "file": str(matches[0]),
        "sector": sector_match.group(1).strip() if sector_match else None,
        "board": board_match.group(1).strip() if board_match else None,
        "wikilinks": list(set(wikilinks)),
        "wikilink_count": len(set(wikilinks)),
        "content": content
    }

undefined

import re
from pathlib import Path
from collections import defaultdict

def build_wikilink_index(reports_dir: str = "Pilot_Reports") -> dict:
    """
    Returns: {entity: [list of tickers that mention it]}
    """
    index = defaultdict(list)
    
    for md_file in Path(reports_dir).rglob("*.md"):
        # Extract ticker from filename (e.g. "2330_台積電.md" -> "2330")
        ticker = md_file.stem.split("_")[0]
        content = md_file.read_text(encoding="utf-8")
        wikilinks = set(re.findall(r'\[\[([^\]]+)\]\]', content))
        
        for link in wikilinks:
            index[link].append(ticker)
    
    # Sort by mention count
    return dict(sorted(index.items(), key=lambda x: len(x[1]), reverse=True))

undefined

def supply_chain_overlap(entity_a: str, entity_b: str, reports_dir: str = "Pilot_Reports"):
    """Find tickers that appear in both entities' supply chains."""
    index = build_wikilink_index(reports_dir)
    
    set_a = set(index.get(entity_a, []))
    set_b = set(index.get(entity_b, []))
    overlap = set_a & set_b
    
    print(f"{entity_a}: {len(set_a)} companies")
    print(f"{entity_b}: {len(set_b)} companies")
    print(f"Overlap: {len(overlap)} companies — {sorted(overlap)}")
    return overlap

undefined

import subprocess
import sys

def update_sector_financials(sector: str, valuation_only: bool = False):
    """Update financials for all tickers in a sector."""
    script = "update_valuation.py" if valuation_only else "update_financials.py"
    cmd = [sys.executable, f"scripts/{script}", "--sector", sector]
    
    result = subprocess.run(cmd, capture_output=True, text=True)
    
    if result.returncode != 0:
        print(f"Error: {result.stderr}")
    else:
        print(result.stdout)
    
    return result.returncode

undefined

import json

def build_enrichment_entry(ticker: str, company_name: str,
                           description: str, upstream: list[str],
                           midstream: str, downstream: list[str],
                           customers: list[str], suppliers: list[str]) -> dict:
    """
    Build a properly formatted enrichment entry.
    All entity names in lists will be wrapped in [[wikilinks]].
    """
    def wikify(items):
        return "\n".join(f"- [[{item}]]" for item in items)
    
    supply_chain = (
        f"**上游:**\n{wikify(upstream)}\n"
        f"**中游:**\n- **{company_name}** ({midstream})\n"
        f"**下游:**\n{wikify(downstream)}"
    )
    
    cust_section = (
        f"### 主要客戶\n{wikify(customers)}\n\n"
        f"### 主要供應商\n{wikify(suppliers)}"
    )
    
    return {
        "desc": description,
        "supply_chain": supply_chain,
        "cust": cust_section
    }

undefined

import subprocess
import json

def audit_and_report(batch_id: int) -> dict:
    """Run audit and parse results."""
    result = subprocess.run(
        ["python", "scripts/audit_batch.py", str(batch_id), "-v"],
        capture_output=True, text=True
    )
    
    output = result.stdout
    
    # Parse pass/fail counts from output
    passed = output.count("✓") 
    failed = output.count("✗")
    
    return {
        "batch": batch_id,
        "passed": passed,
        "failed": failed,
        "pass_rate": passed / (passed + failed) if (passed + failed) > 0 else 0,
        "output": output
    }

results = audit_and_report(101)
print(f"Batch 101: {results['passed']} passed, {results['failed']} failed")
print(f"Pass rate: {results['pass_rate']:.1%}")

undefined

undefined

undefined

undefined

undefined

undefined

undefined

for md_file in Path(reports_dir).rglob("*.md"):
    content = md_file.read_text(encoding="utf-8")
    
    if f"[[{technology}]]" not in content:
        continue
    
    ticker = md_file.stem.split("_")[0]
    company = md_file.stem.split("_", 1)[1] if "_" in md_file.stem else ""
    
    # Detect position in supply chain
    if f"**上游:**" in content and f"[[{technology}]]" in content.split("**上游:**")[1].split("**中游:**")[0]:
        results["upstream"].append(f"{ticker} {company}")
    elif f"[[{technology}]]" in content and "**中游:**" in content:
        mid_section = content.split("**中游:**")[1].split("**下游:**")[0] if "**下游:**" in content else ""
        if f"[[{technology}]]" in mid_section:
            results["midstream"].append(f"{ticker} {company}")
    else:
        results["downstream"].append(f"{ticker} {company}")

return results

undefined

import yfinance as yf

**Report not found by scripts:**
- Filename must match pattern: `{TICKER}_{CompanyName}.md`
- Must be inside a subfolder of `Pilot_Reports/`
- Use `python scripts/utils.py` to test file discovery

**Audit fails "too few wikilinks":**
- Minimum 8 unique `[[wikilinks]]` required per report
- Use `update_enrichment.py` to add richer content
- Run `discover.py --apply` to auto-tag relevant wikilinks

**`build_network.py` produces empty graph:**
```bash

**Enrichment JSON rejected:**
- Ensure file is valid UTF-8 with `ensure_ascii=False`
- Keys must be ticker strings (`"2330"`, not `2330`)
- Required keys per entry: `desc`, `supply_chain`, `cust`
- Content must be in Traditional Chinese; English only for proper nouns

**Finding batch numbers:**
- See `task.md` for batch definitions and which tickers are in each batch
- Batches are used for incremental processing of the 1,735 tickers