簡體   English   中英

如何檢查字符串中的單詞對?

[英]How do I check for word pairs in a string?

我有下面的代碼,它可以完美地創建一個字符串(大量 .txt 文件)中出現的單詞的 CSV 列表,如下所示:

Name;Total
THE;23562
OF;15954
AND;15318
IN;12159
TO;11879
A;11145
I;6135
WAS;6045
etc...

我現在想要的是兩個單詞對,如果證明足夠簡單,甚至可能是三個單詞對。 所以像

Name;Total
OF THE;25
FROM THE;20
BY WHICH;13
OF WHICH;5
etc...

如何修改現有代碼以檢查成對而不是單個單詞?

//chrisjopa.com/2016/04/21/counting-word-frequencies-with-javascript/

var fs = require('fs');
var file = 'INPUT.txt';

//Create Headers for the CSV File
const createCsvWriter = require('csv-writer').createObjectCsvWriter;  
const csvWriter = createCsvWriter({  

//Define Pathname to your choice
  path: 'Data1.csv',
  header: [
    {id: 'name', title: 'Name'},
    {id: 'total', title: 'Total'},
  ]
});

// read file from current directory
fs.readFile(file, 'utf8', function (err, data) {

  if (err) throw err;

  var wordsArray = splitByWords(data);
  var wordsMap = createWordMap(wordsArray);
  var finalWordsArray = sortByCount(wordsMap);

//Write CSV Output File
  csvWriter  
  .writeRecords(finalWordsArray)
  .then(()=> console.log('DONE'));

});


function splitByWords (text) {

  // Removes all special characters, then white spaces, 
  //then converts to all capital letters, then splits the words
  var noPunctuation = text.replace(/[\.,-\/#!$%\^&\*;:{}�=\-_'`’~"()@\+\?><\[\]\+]/g, '');
  var noExtraSpaces = noPunctuation.replace(/\s{2,}/g," ");
  var allUpperCase  = noExtraSpaces.toUpperCase();
  var wordsArray    = allUpperCase.split(/\s+/);
  return wordsArray;
}

//This is the part in the code that I feel is the place to check for word 
//pairs, but I'm not sure how I'm supposed to write it.
function createWordMap (wordsArray, ) {

  // create map for word counts
  var wordsMap = {};

  wordsArray.forEach(function (key) {
    if (wordsMap.hasOwnProperty(key)) {
      wordsMap[key]++;
    } else {
      wordsMap[key] = 1;
    }
  });

  return wordsMap;

}


function sortByCount (wordsMap) {

  // sort by count in descending order
  var finalWordsArray = [];
  finalWordsArray = Object.keys(wordsMap).map(function(key) {
    return {

      name: key,
      total: wordsMap[key]

    };
  });

  finalWordsArray.sort(function(a, b) {
    return b.total - a.total;
  });

  return finalWordsArray;

}

wordsArray ,創建另一個數組,將每對單詞放在一起。 例如,從wordsArray

['Foo', 'Bar', 'Baz', 'Buzz']

創建:

['Foo Bar', 'Bar Baz', 'Baz Buzz']

然后,您可以使用完全相同的函數來計算每對出現的次數 - 只需使用它調用createWordMap (然后使用sortByCount )。 例如:

 const wordsArray = ['Foo', 'Bar', 'Baz', 'Buzz', 'Foo', 'Bar']; const wordPairsArray = []; for (let i = 1; i < wordsArray.length; i++) { wordPairsArray.push(wordsArray[i - 1] + ' ' + wordsArray[i]); } const wordPairMap = createWordMap(wordPairsArray); const wordPairCount = sortByCount(wordPairMap); console.log(wordPairCount); // the following is your original code: function createWordMap(wordsArray, ) { // create map for word counts var wordsMap = {}; wordsArray.forEach(function(key) { if (wordsMap.hasOwnProperty(key)) { wordsMap[key]++; } else { wordsMap[key] = 1; } }); return wordsMap; } function sortByCount(wordsMap) { // sort by count in descending order var finalWordsArray = []; finalWordsArray = Object.keys(wordsMap).map(function(key) { return { name: key, total: wordsMap[key] }; }); finalWordsArray.sort(function(a, b) { return b.total - a.total; }); return finalWordsArray; }

要將其擴展到不僅僅是對,只需更改循環以將動態數量的元素連接在一起:

 function combineWords(words, wordsInItem) { const items = []; for (let i = wordsInItem - 1; i < words.length; i++) { const start = i - (wordsInItem - 1); const end = i + 1; items.push(words.slice(start, end).join(' ')); } return items; } function getCount(words, wordsInItem) { const combinedWords = combineWords(words, wordsInItem); const map = createWordMap(combinedWords); const count = sortByCount(map); console.log(count); } getCount(['Foo', 'Bar', 'Baz', 'Buzz', 'Foo', 'Bar'], 2); getCount(['Foo', 'Bar', 'Baz', 'Buzz', 'Foo', 'Bar', 'Baz'], 3); // the following is your original code: function createWordMap(wordsArray, ) { // create map for word counts var wordsMap = {}; wordsArray.forEach(function(key) { if (wordsMap.hasOwnProperty(key)) { wordsMap[key]++; } else { wordsMap[key] = 1; } }); return wordsMap; } function sortByCount(wordsMap) { // sort by count in descending order var finalWordsArray = []; finalWordsArray = Object.keys(wordsMap).map(function(key) { return { name: key, total: wordsMap[key] }; }); finalWordsArray.sort(function(a, b) { return b.total - a.total; }); return finalWordsArray; }

暫無
暫無

聲明:本站的技術帖子網頁,遵循CC BY-SA 4.0協議,如果您需要轉載,請注明本站網址或者原文地址。任何問題請咨詢:yoyou2525@163.com.

 
粵ICP備18138465號  © 2020-2024 STACKOOM.COM