Geek Answers Handbook

Word frequency in javascript

enter image description here

How can I implement a javascript function to calculate the frequency of each word in a given sentence.

this is my code:

function search () {
  var data = document.getElementById('txt').value;
  var temp = data;
  var words = new Array();
  words = temp.split(" ");
  var uniqueWords = new Array();
  var count = new Array();


  for (var i = 0; i < words.length; i++) {
    //var count=0;
    var f = 0;
    for (j = 0; j < uniqueWords.length; j++) {
      if (words[i] == uniqueWords[j]) {
        count[j] = count[j] + 1;
        //uniqueWords[j]=words[i];
        f = 1;
      }
    }
    if (f == 0) {
      count[i] = 1;
      uniqueWords[i] = words[i];
    }
    console.log("count of " + uniqueWords[i] + " - " + count[i]);
  }
}

I was unable to trace the problem. Help is very susceptible. output in this format: qty - 1 qty - 2 ..

input: this is anil is kum anil

+4
source share
5 answers

I feel that you have overly complex things, having multiple arrays, rows, and participating in a frequent (and hard to follow) context switch between loops and nested loops.

Below is an approach that I would recommend you consider. I added comments to explain every step along the way. If any of this is unclear, let me know in the comments and I will proceed to improve clarity.

(function () {

    /* Below is a regular expression that finds alphanumeric characters
       Next is a string that could easily be replaced with a reference to a form control
       Lastly, we have an array that will hold any words matching our pattern */
    var pattern = /\w+/g,
        string = "I I am am am yes yes.",
        matchedWords = string.match( pattern );

    /* The Array.prototype.reduce method assists us in producing a single value from an
       array. In this case, we're going to use it to output an object with results. */
    var counts = matchedWords.reduce(function ( stats, word ) {

        /* `stats` is the object that we'll be building up over time.
           `word` is each individual entry in the `matchedWords` array */
        if ( stats.hasOwnProperty( word ) ) {
            /* `stats` already has an entry for the current `word`.
               As a result, let increment the count for that `word`. */
            stats[ word ] = stats[ word ] + 1;
        } else {
            /* `stats` does not yet have an entry for the current `word`.
               As a result, let add a new entry, and set count to 1. */
            stats[ word ] = 1;
        }

        /* Because we are building up `stats` over numerous iterations,
           we need to return it for the next pass to modify it. */
        return stats;

    }, {} );

    /* Now that `counts` has our object, we can log it. */
    console.log( counts );

}());
+13
source

JavaScript, :

function wordFreq(string) {
    var words = string.replace(/[.]/g, '').split(/\s/);
    var freqMap = {};
    words.forEach(function(w) {
        if (!freqMap[w]) {
            freqMap[w] = 0;
        }
        freqMap[w] += 1;
    });

    return freqMap;
}

. , , :

console.log(wordFreq("I am the big the big bull."));
> Object {I: 1, am: 1, the: 2, big: 2, bull: 1}

Object.keys(result).sort().forEach(result) {...}. , :

var freq = wordFreq("I am the big the big bull.");
Object.keys(freq).sort().forEach(function(word) {
    console.log("count of " + word + " is " + freq[word]);
});

:

count of I is 1
count of am is 1
count of big is 2
count of bull is 1
count of the is 2

JSFiddle: http://jsfiddle.net/ah6wsbs6/

wordFreq ES6:

function wordFreq(string) {
  return string.replace(/[.]/g, '')
    .split(/\s/)
    .reduce((map, word) =>
      Object.assign(map, {
        [word]: (map[word])
          ? map[word] + 1
          : 1,
      }),
      {}
    );
}

JSFiddle: http://jsfiddle.net/r1Lo79us/

+10

...

<!DOCTYPE html>
<html>
<head>
<title>string frequency</title>
<style type="text/css">
#text{
    width:250px;
}
</style>
</head>

<body >

<textarea id="txt" cols="25" rows="3" placeholder="add your text here">   </textarea></br>
<button type="button" onclick="search()">search</button>

    <script >

        function search()
        {
            var data=document.getElementById('txt').value;
            var temp=data;
            var words=new Array();
            words=temp.split(" ");

            var unique = {};


            for (var i = 0; i < words.length; i++) {
                var word = words[i];
                console.log(word);

                if (word in unique)
                {
                    console.log("word found");
                    var count  = unique[word];
                    count ++;
                    unique[word]=count;
                }
                else
                {
                    console.log("word NOT found");
                    unique[word]=1;
                }
            }
            console.log(unique);
        }

    </script>

</body>

, . , , , , , .

Javascript , , .

, , .

, ;)

, . ", , " , "" "" , .

+1

, , , OP ( ).

OP :

if(f==0){
    count[i]=1;
    uniqueWords[i]=words[i];
}

( ) uniqueWords , words. , uniqueWords. undefined.

uniqueWords. - :

["this", "is", "anil", 4: "kum", 5: "the" ]

, 3.

words.

:

function search()
{
    var data=document.getElementById('txt').value;
    var temp=data;
    var words=new Array();
    words=temp.split(" ");
    var uniqueWords=new Array();
    var count=new Array();


    for (var i = 0; i < words.length; i++) {
        //var count=0;
        var f=0;
        for(j=0;j<uniqueWords.length;j++){
            if(words[i]==uniqueWords[j]){
                count[j]=count[j]+1;
                //uniqueWords[j]=words[i];
                f=1;
            }
        }
        if(f==0){
            count[i]=1;
            uniqueWords[i]=words[i];
        }
    }
    for ( i = 0; i < uniqueWords.length; i++) {
        if (typeof uniqueWords[i] !== 'undefined')
            console.log("count of "+uniqueWords[i]+" - "+count[i]);       
    }
}

if not undefined.

Fiddle: https://jsfiddle.net/cdLgaq3a/

+1

I would go with Sampson to reduce the method, to slightly increase the efficiency . There is a modified version, more prepared for production. This is not ideal, but it should cover the vast majority of scenarios (ie, "Good enough").

function calcWordFreq(s) {
  // Normalize
  s = s.toLowerCase();
  // Strip quotes and brackets
  s = s.replace(/["""(\[{}\])]|\B['‘]([^']+)[']/g, '$1');
  // Strip dashes and ellipses
  s = s.replace(/[‒–—―…]|--|\.\.\./g, ' ');
  // Strip punctuation marks
  s = s.replace(/[!?;:.,]\B/g, '');
  return s.match(/\S+/g).reduce(function(oFreq, sWord) {
    if (oFreq.hasOwnProperty(sWord)) ++oFreq[sWord];
    else oFreq[sWord] = 1;
    return oFreq;
  }, {});
}

calcWordFreq('A 'bad, "BAD" wolf-man...a good ol\' spook -- I\'m frightened!') is returning

{
  "a": 2
  "bad": 2
  "frightened": 1
  "good": 1
  "i'm": 1
  "ol'": 1
  "spook": 1
  "wolf-man": 1
}
0
source

More articles:


All Articles