JavaScript Computing Correlation

jscorrelation.md

• function that computes the ϕ coefficient from such an array:

function phi(table) {
  return (table[3] * table[0] - table[2] * table[1]) /
    Math.sqrt((table[2] + table[3]) *
              (table[0] + table[1]) *
              (table[1] + table[3]) *
              (table[0] + table[2]));
}
console.log(phi([76, 9, 4, 1]));
// → 0.068599434

• extract a two-by-two table for a specific event from the journal, we must loop over all the entries and tally how many times the event occurs

function tableFor(event, journal) {
  let table = [0, 0, 0, 0];
  for (let i = 0; i < journal.length; i++) {
    let entry = journal[i], index = 0;
    if (entry.events.includes(event)) index += 1;
    if (entry.squirrel) index += 2;
    table[index] += 1;
  }
  return table;
}
console.log(tableFor("pizza", JOURNAL));
// → [76, 9, 4, 1]

• to compute a correlation for every type of event that occurs in the data set, we need to find every type of event

function journalEvents(journal) {
  let events = [];
  for (let entry of journal) {
    for (let event of entry.events) {
      if (!events.includes(event)) {
        events.push(event);
      }
    }
  }
  return events;
}
console.log(journalEvents(JOURNAL));
// → ["carrot", "exercise", "weekend", "bread", …]

• By going over all the events and adding those that aren’t already in there to the events array, the function collects every type of event. Using that, we can see all the correlations.

for (let event of journalEvents(JOURNAL)) {
  console.log(event + ":", phi(tableFor(event, JOURNAL)));
}
// → carrot:         0.0140970969
// → exercise:       0.0685994341
// → weekend:        0.1371988681
// → bread:         -0.0757554019
// → pudding:       -0.0648203724
// → brushed teeth: -0.3805211953
// → candy:          0.1296407447
// → work:          -0.1371988681
// → spaghetti:      0.2425356250
// → reading:        0.1106828054
// → peanuts:        0.5902679812
// and so on

• we can manually see the highest two correlations we can combine them to see the correlation

for (let entry of JOURNAL) {
  if (entry.events.includes("peanuts") &&
     !entry.events.includes("brushed teeth")) {
    entry.events.push("peanut teeth");
  }
}
console.log(phi(tableFor("peanut teeth", JOURNAL)));
// → 1