数据验证工具

pip install goldencheck

pip install goldencheck[llm]

pip install goldencheck[baseline]

pip install goldencheck[baseline,semantic]

npm install goldencheck

import { scanData, TabularData } from "goldencheck/core";

import { readFile, scanData } from "goldencheck/node";

# Scan a file — discovers issues, launches interactive TUI
goldencheck data.csv

# CLI-only output (no TUI)
goldencheck data.csv --no-tui

# With LLM enhancement (requires API key)
goldencheck data.csv --llm-boost --no-tui

# Validate against saved rules (for CI/pipelines)
goldencheck validate data.csv

# JSON output for CI integration
goldencheck data.csv --no-tui --json

# Learn baseline (one-time, deep analysis)
goldencheck baseline data.csv

# Scan with drift detection (fast, uses saved baseline)
goldencheck scan new_data.csv

// Scan an array of records (edge-safe — works anywhere)
import { scanData, TabularData, Severity } from "goldencheck";

const data = new TabularData([
  { id: 1, email: "alice@example.com", age: 30, status: "active" },
  { id: 2, email: "bob@test.com", age: -5, status: "inactive" },
  { id: 3, email: "not-an-email", age: 25, status: "active" },
]);

const { findings, profile } = scanData(data);
for (const f of findings) {
  console.log(`[${f.severity === Severity.ERROR ? "ERROR" : "WARNING"}] ${f.column}: ${f.message}`);
}

// Scan a CSV file (Node.js)
import { readFile, scanData, applyConfidenceDowngrade, healthScore } from "goldencheck/node";

const data = readFile("data.csv");
const result = scanData(data, { domain: "healthcare" });
const findings = applyConfidenceDowngrade(result.findings, false);

// Health score
const byCol = {};
for (const f of findings) {
  if (f.severity >= 2) {
    byCol[f.column] ??= { errors: 0, warnings: 0 };
    byCol[f.column][f.severity === 3 ? "errors" : "warnings"]++;
  }
}
const { grade, points } = healthScore(byCol);
console.log(`Health: ${grade} (${points}/100)`);

// Validate against pinned rules
import { readFile, scanData, validateConfig, validateData } from "goldencheck/node";
import { readFileSync } from "node:fs";
import YAML from "yaml";

const config = validateConfig(YAML.parse(readFileSync("goldencheck.yml", "utf-8")));
const data = readFile("data.csv");
const findings = validateData(data, config);

// Create baseline and detect drift
import { readFile, createBaseline, serializeBaseline, scanData } from "goldencheck/node";
import { runDriftChecks, deserializeBaseline } from "goldencheck";
import { writeFileSync, readFileSync } from "node:fs";

// Learn baseline
const data = readFile("reference.csv");
const baseline = createBaseline(data);
writeFileSync("baseline.json", serializeBaseline(baseline));

// Later: detect drift
const newData = readFile("production.csv");
const saved = deserializeBaseline(readFileSync("baseline.json", "utf-8"));
const driftFindings = runDriftChecks(newData, saved);

// LLM-enhanced scanning (edge-safe)
import { scanData, TabularData, callLlm, parseLlmResponse, mergeLlmFindings, buildSampleBlocks } from "goldencheck";

const data = new TabularData(records);
const result = scanData(data, { returnSample: true });
const blocks = buildSampleBlocks(result.sample, result.findings);
const { text } = await callLlm("anthropic", JSON.stringify(blocks));
const llmResponse = parseLlmResponse(text);
if (llmResponse) {
  const enhanced = mergeLlmFindings(result.findings, llmResponse);
}

1. SCAN     →  goldencheck data.csv
                GoldenCheck profiles your data and discovers what "healthy" looks like

2. REVIEW   →  Interactive TUI shows findings sorted by severity
                Each finding has: description, affected rows, sample values

3. PIN      →  Press Space to promote findings into permanent rules
                Dismiss false positives — they won't come back

4. EXPORT   →  Press F2 to save rules to goldencheck.yml
                Human-readable YAML with your pinned rules

5. VALIDATE →  goldencheck validate data.csv
                Enforce rules in CI with exit codes (0 = pass, 1 = fail)

goldencheck scan data.csv --domain healthcare   # NPI, ICD, insurance, patient types
goldencheck scan data.csv --domain finance      # accounts, routing, CUSIP, transactions
goldencheck scan data.csv --domain ecommerce    # SKUs, orders, tracking, products

goldencheck diff data.csv                  # compare against git HEAD
goldencheck diff old.csv new.csv           # compare two files
goldencheck diff data.csv --ref main       # compare against a branch

goldencheck fix data.csv                          # safe: trim, normalize, fix encoding
goldencheck fix data.csv --mode moderate          # + standardize case
goldencheck fix data.csv --mode aggressive --force # + coerce types
goldencheck fix data.csv --dry-run                # preview changes

goldencheck watch data/ --interval 30        # re-scan every 30s
goldencheck watch data/ --exit-on error      # CI mode: fail on first error

goldencheck serve --port 8000

# Scan via file upload
curl -X POST http://localhost:8000/scan --data-binary @data.csv

# Scan via URL
curl -X POST http://localhost:8000/scan/url -d '{"url": "https://example.com/data.csv"}'

pip install goldencheck[db]
goldencheck scan-db "postgresql://user:pass@host/db" --table orders
goldencheck scan-db "snowflake://..." --query "SELECT * FROM orders WHERE date > '2024-01-01'"

goldencheck schedule data/*.csv --interval hourly --webhook https://hooks.slack.com/...
goldencheck schedule data/*.csv --interval daily --notify-on grade-drop

# Using OpenAI
export OPENAI_API_KEY=sk-...
goldencheck data.csv --llm-boost --llm-provider openai --no-tui

# Using Anthropic
export ANTHROPIC_API_KEY=sk-ant-...
goldencheck data.csv --llm-boost --no-tui

export GOLDENCHECK_LLM_BUDGET=0.50  # max spend per scan in USD

version: 1

settings:
  sample_size: 100000
  fail_on: error

columns:
  email:
    type: string
    required: true
    format: email
    unique: true

  age:
    type: integer
    range: [0, 120]

  status:
    type: string
    enum: [active, inactive, pending, closed]

relations:
  - type: temporal_order
    columns: [start_date, end_date]

ignore:
  - column: notes
    check: nullability

npx goldencheck-js scan data.csv --json
npx goldencheck-js scan data.csv --domain healthcare
npx goldencheck-js health-score data.csv
npx goldencheck-js profile data.csv
npx goldencheck-js validate data.csv --config goldencheck.yml
npx goldencheck-js baseline data.csv --output baseline.json
npx goldencheck-js fix data.csv --mode safe
npx goldencheck-js diff old.csv new.csv
npx goldencheck-js demo

goldencheck (npm)
├── goldencheck/core    # Edge-safe: browsers, Workers, Edge Runtime
│   ├── types           # Finding, Severity, DatasetProfile, Config types
│   ├── data            # TabularData — zero-dep columnar abstraction
│   ├── profilers       # 10 column profilers + 4 relation profilers
│   ├── semantic        # Type classifier, suppression, 3 domain packs
│   ├── engine          # Scanner, confidence, validator, triage, differ, fixer
│   ├── baseline        # Statistical profiling, constraints, correlation, patterns
│   ├── drift           # 13 drift checks against saved baseline
│   ├── llm             # Anthropic + OpenAI via fetch(), merger, budget
│   ├── agent           # Strategy, handoff, review queue
│   └── reporters       # JSON, CI
└── goldencheck/node    # Node.js >= 20
    ├── reader          # CSV, Parquet (via nodejs-polars)
    ├── mcp             # MCP server (7 tools)
    ├── a2a             # Agent-to-Agent HTTP server
    ├── tui             # ANSI terminal output
    ├── db-scanner      # Postgres, MySQL, SQLite
    └── watcher         # Directory polling

pip install dqbench goldencheck
dqbench run goldencheck

pip install goldencheck[mcp]

{
  "mcpServers": {
    "goldencheck": {
      "command": "goldencheck",
      "args": ["mcp-serve"]
    }
  }
}

{
  "mcpServers": {
    "goldencheck": {
      "url": "https://goldencheck-mcp-production.up.railway.app/mcp/"
    }
  }
}

pip install goldencheck[mcp]
goldencheck mcp-serve

from goldencheck.engine.scanner import scan_file
from goldencheck.engine.confidence import apply_confidence_downgrade
from goldencheck.notebook import ScanResult

findings, profile = scan_file("data.csv")
findings = apply_confidence_downgrade(findings, llm_boost=False)

# Rich HTML display in notebooks
ScanResult(findings=findings, profile=profile)

import goldencheck

# Scan a CSV for quality issues
findings = goldencheck.scan_file("data.csv")
for f in findings:
    print(f"[{f.severity}] {f.column}: {f.check} — {f.message}")

# Create baseline and detect drift
from goldencheck import create_baseline, scan_file
baseline = create_baseline("data.csv")
baseline.save("goldencheck_baseline.yaml")
findings, profile = scan_file("data.csv", baseline="goldencheck_baseline.yaml")

# Health score
score = goldencheck.health_score("data.csv")
print(score)  # e.g. "B (78/100)"

import { scanData, TabularData, Severity } from "goldencheck";

// Scan records (edge-safe)
const data = new TabularData(records);
const { findings, profile } = scanData(data);
for (const f of findings) {
  console.log(`[${f.severity === Severity.ERROR ? "ERROR" : "WARNING"}] ${f.column}: ${f.message}`);
}

import { readFile, scanData, applyConfidenceDowngrade, healthScore } from "goldencheck/node";

// Scan a CSV file (Node.js)
const data = readFile("data.csv");
const result = scanData(data, { domain: "healthcare" });
const findings = applyConfidenceDowngrade(result.findings, false);

// Health score
const byCol = {};
for (const f of findings) {
  if (f.severity >= 2) {
    byCol[f.column] ??= { errors: 0, warnings: 0 };
    byCol[f.column][f.severity === 3 ? "errors" : "warnings"]++;
  }
}
const { grade, points } = healthScore(byCol);
console.log(`Health: ${grade} (${points}/100)`);

import { readFile, createBaseline, serializeBaseline } from "goldencheck/node";
import { runDriftChecks, deserializeBaseline } from "goldencheck";
import { writeFileSync, readFileSync } from "node:fs";

// Create baseline and detect drift
const data = readFile("reference.csv");
const baseline = createBaseline(data);
writeFileSync("baseline.json", serializeBaseline(baseline));

const newData = readFile("production.csv");
const saved = deserializeBaseline(readFileSync("baseline.json", "utf-8"));
const driftFindings = runDriftChecks(newData, saved);