StatisticsCalculator

const calculator = new StatisticsCalculator();
const tokenizer = new TokenizationService();

const text = "Hello world! This is a test.";
const tokenResult = await tokenizer.tokenizeText(text, 'gpt-4o');

const stats = calculator.calculateStatistics(text, tokenResult, 'gpt-4o');

console.log(stats);
// {
//   tokenCount: 8,
//   charCount: 29,
//   wordCount: 6,
//   costEstimate: 0.00002,
//   contextUtilization: 0.00625,
//   tokensPerWord: 1.33,
//   inputCostPer1M: 2.50,
//   outputCostPer1M: 10.00
// }

const calculator = new StatisticsCalculator();

console.log(calculator.countWords('Hello world'));
// 2

console.log(calculator.countWords('  Multiple   spaces   between  '));
// 3

console.log(calculator.countWords(''));
// 0

console.log(calculator.countWords('One-hyphenated-word'));
// 1

const calculator = new StatisticsCalculator();
const modelInfo = MODELS_DATA['gpt-4o'];

// Calculate cost for 1,000 tokens
const cost1k = calculator.calculateCost(1000, modelInfo);
console.log(`1K tokens: $${cost1k.toFixed(6)}`);
// 1K tokens: $0.002500

// Calculate cost for 1,000,000 tokens
const cost1m = calculator.calculateCost(1000000, modelInfo);
console.log(`1M tokens: $${cost1m.toFixed(2)}`);
// 1M tokens: $2.50

const calculator = new StatisticsCalculator();

// GPT-4o has 128K context
console.log(calculator.calculateContextUtilization(1000, 128000));
// 0.78 (less than 1%)

console.log(calculator.calculateContextUtilization(64000, 128000));
// 50.0 (half the context)

console.log(calculator.calculateContextUtilization(128000, 128000));
// 100.0 (full context)

console.log(calculator.calculateContextUtilization(150000, 128000));
// 100.0 (capped at 100%, actually exceeds)

const calculator = new StatisticsCalculator();

// GPT-4o has 128K context limit
console.log(calculator.exceedsContextLimit(100000, 'gpt-4o'));
// false

console.log(calculator.exceedsContextLimit(150000, 'gpt-4o'));
// true

// GPT-3.5 has 16K context limit
console.log(calculator.exceedsContextLimit(20000, 'gpt-3.5-turbo'));
// true

const calculator = new StatisticsCalculator();

// GPT-4o: 128K context
console.log(calculator.getContextWarning(50000, 'gpt-4o'));
// null (39% usage)

console.log(calculator.getContextWarning(100000, 'gpt-4o'));
// "ℹ️ Alto uso del contexto (78.1% utilizado)"

console.log(calculator.getContextWarning(120000, 'gpt-4o'));
// "⚠️ Cerca del límite de contexto (93.8% utilizado)"

console.log(calculator.getContextWarning(150000, 'gpt-4o'));
// "⚠️ Texto excede el límite de contexto del modelo (128,000 tokens)"

const calculator = new StatisticsCalculator();

const rawStats = {
  tokenCount: 15847,
  charCount: 72456,
  wordCount: 11234,
  costEstimate: 0.03961175,
  contextUtilization: 12.380469,
  tokensPerWord: 1.410987,
  inputCostPer1M: 2.50,
  outputCostPer1M: 10.00
};

const formatted = calculator.formatStatistics(rawStats);

console.log(formatted);
// {
//   tokenCount: "15,847",
//   charCount: "72,456",
//   wordCount: "11,234",
//   costEstimate: "$0.039612",
//   contextUtilization: "12.4%",
//   tokensPerWord: "1.41",
//   inputCostPer1M: "$2.50/1M",
//   outputCostPer1M: "$10.00/1M"
// }

const calculator = new StatisticsCalculator();
const tokenizer = new TokenizationService();
await tokenizer.waitForInitialization();

const text = "Long text for comparison...";

const comparison = await calculator.compareModels(
  text,
  ['gpt-4o', 'claude-3.5-sonnet', 'llama-3.1-70b'],
  tokenizer
);

comparison.forEach(result => {
  console.log(`${result.modelId} (${result.company}):`);
  console.log(`  Tokens: ${result.formatted.tokenCount}`);
  console.log(`  Cost: ${result.formatted.costEstimate}`);
});

const calculator = new StatisticsCalculator();

const stats = {
  tokenCount: 1000,
  charCount: 4500,
  wordCount: 750,
  costEstimate: 0.0025
};

const metrics = calculator.getEfficiencyMetrics(stats);

console.log(metrics);
// {
//   costEfficiency: 2.5,        // $2.50 per 1000 tokens
//   compressionRatio: 0.222,    // 0.22 tokens per character
//   verbosityIndex: 1.333       // 1.33 tokens per word
// }

const calculator = new StatisticsCalculator();
const tokenizer = new TokenizationService();
await tokenizer.waitForInitialization();

const text = `
  This is a sample text for comprehensive tokenization analysis.
  We'll analyze tokens, costs, and efficiency metrics.
`;

const modelId = 'gpt-4o';

// Tokenize
const tokenResult = await tokenizer.tokenizeText(text, modelId);

// Calculate statistics
const stats = calculator.calculateStatistics(text, tokenResult, modelId);

// Get formatted display values
const formatted = calculator.formatStatistics(stats);

// Check for warnings
const warning = calculator.getContextWarning(stats.tokenCount, modelId);

// Get efficiency metrics
const efficiency = calculator.getEfficiencyMetrics(stats);

console.log('Statistics:', formatted);
if (warning) console.log('Warning:', warning);
console.log('Efficiency:', efficiency);