Evaluation Results

import { EvalResults, createEvalResults } from 'praisonai';

const results = createEvalResults();

// Add test results
results.add({
  name: 'accuracy-test-1',
  passed: true,
  score: 0.95,
  duration: 150,
  input: 'What is 2+2?',
  output: '4',
  expected: '4'
});

results.add({
  name: 'accuracy-test-2',
  passed: false,
  score: 0.6,
  duration: 200,
  input: 'Explain quantum computing',
  output: 'A type of computing...',
  expected: 'Uses quantum mechanics...',
  error: 'Incomplete explanation'
});

import { EvalResults } from 'praisonai';

const results = new EvalResults();

// Add multiple results...
results.add({ name: 'test-1', passed: true, score: 0.9, duration: 100 });
results.add({ name: 'test-2', passed: true, score: 0.85, duration: 120 });
results.add({ name: 'test-3', passed: false, score: 0.5, duration: 200 });

// Get aggregated stats
const stats = results.aggregate();

console.log('Evaluation Summary:');
console.log(`  Total: ${stats.totalTests}`);
console.log(`  Passed: ${stats.passedTests}`);
console.log(`  Failed: ${stats.failedTests}`);
console.log(`  Pass Rate: ${(stats.passRate * 100).toFixed(1)}%`);
console.log(`  Avg Score: ${(stats.avgScore * 100).toFixed(1)}%`);
console.log(`  Avg Duration: ${stats.avgDuration}ms`);

import { EvalResults } from 'praisonai';

const results = new EvalResults();

// Add results with categories
const r1 = results.add({ name: 'math-1', passed: true, score: 0.95, duration: 100 });
const r2 = results.add({ name: 'math-2', passed: true, score: 0.9, duration: 110 });
const r3 = results.add({ name: 'writing-1', passed: false, score: 0.6, duration: 200 });

results.categorize(r1.id, 'math');
results.categorize(r2.id, 'math');
results.categorize(r3.id, 'writing');

// Get stats by category
const byCategory = results.aggregateByCategory();

for (const [category, stats] of byCategory) {
  console.log(`\n${category}:`);
  console.log(`  Pass Rate: ${(stats.passRate * 100).toFixed(1)}%`);
  console.log(`  Avg Score: ${(stats.avgScore * 100).toFixed(1)}%`);
}

import { EvalResults } from 'praisonai';

const results = new EvalResults();

// Add results over time (simulated)
for (let i = 0; i < 100; i++) {
  results.add({
    name: `test-${i}`,
    passed: Math.random() > 0.2,
    score: 0.7 + Math.random() * 0.3,
    duration: 100 + Math.random() * 100
  });
}

// Get trend over time windows
const trend = results.getTrend(60000); // 1-minute windows

console.log('Trend Analysis:');
for (const point of trend) {
  console.log(`  ${new Date(point.timestamp).toISOString()}`);
  console.log(`    Pass Rate: ${(point.passRate * 100).toFixed(1)}%`);
  console.log(`    Tests: ${point.testCount}`);
}

import { EvalResults } from 'praisonai';

const results = new EvalResults();
// Add results...

// Format as table
console.log(results.formatTable());
/*
| Name | Passed | Score | Duration |
|------|--------|-------|----------|
| test-1 | ✅ | 95.0% | 100ms |
| test-2 | ❌ | 60.0% | 200ms |
*/

// Format summary
console.log(results.formatSummary());
// Tests: 10 | Pass: 8 | Fail: 2 | Rate: 80.0% | Avg Score: 85.0%

import { EvalResults } from 'praisonai';

const results = new EvalResults();
// Add results...

// Export for storage
const exported = results.export();
const json = JSON.stringify(exported);

// Save to file
await fs.writeFile('eval-results.json', json);

// Later: Import results
const loaded = JSON.parse(await fs.readFile('eval-results.json', 'utf-8'));
const newResults = new EvalResults();
newResults.import(loaded);

import { Agent, EvalSuite, EvalResults } from 'praisonai';

const agent = new Agent({
  name: 'Test Agent',
  instructions: 'You are a helpful assistant.'
});

const suite = new EvalSuite();
const collector = new EvalResults();

// Run evaluation suite
const testCases = [
  { input: 'Hello', expected: 'greeting' },
  { input: 'Bye', expected: 'farewell' }
];

for (const test of testCases) {
  const response = await agent.chat(test.input);
  const result = await suite.runAccuracy(test.input, {
    input: test.input,
    expectedOutput: test.expected,
    actualOutput: response
  });
  
  // Collect result
  collector.add({
    name: test.input,
    passed: result.passed,
    score: result.score,
    duration: result.duration || 0,
    input: test.input,
    output: response,
    expected: test.expected
  });
}

// Analyze collected results
console.log(collector.formatSummary());