naive bayes classifier

const fs = require("fs")

// utils
const splitBy = del => str => str.split(del)
const nonEmpty = el => Boolean(el)
const atIndexEquals = (ind, value) => el => el[ind] === value
//

// read file
const file = fs.readFileSync("./house-votes-84.data", "utf8")
const data = file
  .split("\n")
  .filter(nonEmpty)
  .map(splitBy(","))
const step = ~~(data.length / 10)
//

// solution
const results = []
for (let i = 0; i < 10; i++) {
  const testData =
    i === 9 ? data.slice(i * step) : data.slice(i * step, i * step + step)
  const trainingData = data
    .slice(0, i * step)
    .concat(data.slice(i * step + step))

  const republicans = trainingData.filter(atIndexEquals(0, "republican"))
  const democrats = trainingData.filter(atIndexEquals(0, "democrat"))

  const p_republican = republicans.length / trainingData.length
  const p_democrat = democrats.length / trainingData.length

  const attributeProbabilities = []
  // for each attribute
  for (let i = 1; i < 17; i++) {
    const p_y_republican =
      republicans.filter(atIndexEquals(i, "y")).length / republicans.length
    const p_n_republican =
      republicans.filter(atIndexEquals(i, "n")).length / republicans.length
    const p_q_republican =
      republicans.filter(atIndexEquals(i, "?")).length / republicans.length
    const p_y_democrat =
      democrats.filter(atIndexEquals(i, "y")).length / democrats.length
    const p_n_democrat =
      democrats.filter(atIndexEquals(i, "n")).length / democrats.length
    const p_q_democrat =
      democrats.filter(atIndexEquals(i, "?")).length / democrats.length

    attributeProbabilities.push({
      p_y_republican,
      p_n_republican,
      p_q_republican,
      p_y_democrat,
      p_n_democrat,
      p_q_democrat
    })
  }

  const correctAnswers = testData.filter(currTest => {
    const res = currTest[0]
    const attributes = currTest.slice(1)

    const pDemocrat = attributes.reduce(
      (acc, attr, i) =>
        attributeProbabilities[i][`p_${attr === "?" ? "q" : attr}_democrat`] *
        acc,
      p_democrat
    )
    const pRepublican = attributes.reduce(
      (acc, attr, i) =>
        attributeProbabilities[i][`p_${attr === "?" ? "q" : attr}_republican`] *
        acc,
      p_republican
    )
    const finalDecision = pDemocrat > pRepublican ? "democrat" : "republican"

    return res === finalDecision
  }).length
  const accuracy = correctAnswers / testData.length

  console.log(`Training ${i + 1}: `, accuracy)

  results.push(accuracy)
}

const classifierAccuracy =
  results.reduce((acc, res, i) => {
    if (i === 9) {
      return res * (data.length - 9 * step) + acc
    }

    return res * step + acc
  }, 0) / data.length
console.log("Classifier: ", classifierAccuracy)