ee1e8abd87
* feat(tools): add seed/solution restore script * chore(curriculum): remove empty sections' markers * chore(curriculum): add seed + solution to Chinese * chore: remove old formatter * fix: update getChallenges parse translated challenges separately, without reference to the source * chore(curriculum): add dashedName to English * chore(curriculum): add dashedName to Chinese * refactor: remove unused challenge property 'name' * fix: relax dashedName requirement * fix: stray tag Remove stray `pre` tag from challenge file. Signed-off-by: nhcarrigan <nhcarrigan@gmail.com> Co-authored-by: nhcarrigan <nhcarrigan@gmail.com>
137 lines
3.7 KiB
Markdown
137 lines
3.7 KiB
Markdown
---
|
|
id: 5e94a54cc7b022105bf0fd2c
|
|
title: Word frequency
|
|
challengeType: 5
|
|
forumTopicId: 393913
|
|
dashedName: word-frequency
|
|
---
|
|
|
|
# --description--
|
|
|
|
Given a text string and an integer n, return the n most common words in the file (and the number of their occurrences) in decreasing frequency.
|
|
|
|
# --instructions--
|
|
|
|
Write a function to count the occurrences of each word and return the n most commons words along with the number of their occurences in decreasing frequency.
|
|
|
|
The function should return a 2D array with each of the elements in the following form: `[word, freq]`. `word` should be the lowercase version of the word and `freq` the number denoting the count.
|
|
|
|
The function should return an empty array, if no string is provided.
|
|
|
|
The function should be case insensitive, for example, the strings "Hello" and "hello" should be treated the same.
|
|
|
|
You can treat words that have special characters such as underscores, dashes, apostrophes, commas, etc., as distinct words.
|
|
|
|
For example, given the string "Hello hello goodbye", your function should return `[['hello', 2], ['goodbye', 1]]`.
|
|
|
|
# --hints--
|
|
|
|
`wordFrequency` should be a function.
|
|
|
|
```js
|
|
assert(typeof wordFrequency == 'function');
|
|
```
|
|
|
|
`wordFrequency` should return an array.
|
|
|
|
```js
|
|
assert(Array.isArray(wordFrequency('test')));
|
|
```
|
|
|
|
`wordFrequency("Hello hello world", 2)` should return `[['hello', 2], ['world', 1]]`
|
|
|
|
```js
|
|
assert.deepEqual(wordFrequency(example_1, 2), example_1_solution);
|
|
```
|
|
|
|
`wordFrequency("The quick brown fox jumped over the lazy dog", 1)` should return `[['the', 2]]`
|
|
|
|
```js
|
|
assert.deepEqual(wordFrequency(example_2, 1), example_2_solution);
|
|
```
|
|
|
|
`wordFrequency("Opensource opensource open-source open source", 1)` should return `[['opensource', 2]]`
|
|
|
|
```js
|
|
assert.deepEqual(wordFrequency(example_3, 1), example_3_solution);
|
|
```
|
|
|
|
`wordFrequency("Apple App apply aPP aPPlE", 3)` should return `[['app', 2], ['apple', 2], ['apply', 1]]` or `[['apple', 2], ['app', 2], ['apply', 1]]`
|
|
|
|
```js
|
|
const arr = JSON.stringify(wordFrequency(example_4, 3));
|
|
assert(arr === example_4_solution_a || arr === example_4_solution_b);
|
|
```
|
|
|
|
`wordFrequency("c d a d c a b d d c", 4)` should return `[['d', 4], ['c', 3], ['a', 2], ['b', 1]]`
|
|
|
|
```js
|
|
assert.deepEqual(wordFrequency(example_5, 4), example_5_solution);
|
|
```
|
|
|
|
`wordFrequency("", 5)` should return `[]`
|
|
|
|
```js
|
|
assert.deepEqual(wordFrequency(example_6, 5), example_6_solution);
|
|
```
|
|
|
|
# --seed--
|
|
|
|
## --before-user-code--
|
|
|
|
```js
|
|
var example_1 = 'Hello hello world';
|
|
var example_1_solution = [['hello', 2], ['world', 1]];
|
|
var example_2 = 'The quick brown fox jumped over the lazy dog';
|
|
var example_2_solution = [['the', 2]];
|
|
var example_3 = 'Opensource opensource open-source open source';
|
|
var example_3_solution = [['opensource', 2]];
|
|
var example_4 = 'Apple App apply aPP aPPlE';
|
|
var example_4_solution_a = "[[\"app\",2],[\"apple\",2],[\"apply\",1]]";
|
|
var example_4_solution_b = "[[\"apple\",2],[\"app\",2],[\"apply\",1]]";
|
|
var example_5 = 'c d a d c a b d d c';
|
|
var example_5_solution = [['d', 4], ['c', 3], ['a', 2], ['b', 1]];
|
|
var example_6 = '';
|
|
var example_6_solution = [];
|
|
```
|
|
|
|
## --seed-contents--
|
|
|
|
```js
|
|
function wordFrequency(txt, n) {
|
|
|
|
}
|
|
```
|
|
|
|
# --solutions--
|
|
|
|
```js
|
|
function wordFrequency(txt, n) {
|
|
var words = txt.split(/\s+/);
|
|
var wordCount = {};
|
|
words.forEach(word => {
|
|
if (word == '') {
|
|
return;
|
|
}
|
|
const lowerWord = word.toLowerCase();
|
|
wordCount[lowerWord] =
|
|
lowerWord in wordCount ? wordCount[lowerWord] + 1 : 1;
|
|
});
|
|
|
|
var wordsArray = [];
|
|
for (let [word, count] of Object.entries(wordCount)) {
|
|
wordsArray.push([word, count]);
|
|
}
|
|
|
|
wordsArray.sort((a, b) => {
|
|
if (a[1] !== b[1]) {
|
|
return b[1] - a[1];
|
|
} else if (a[0] !== b[0]) {
|
|
return a[0] < b[0] ? -1 : 1;
|
|
}
|
|
return 0;
|
|
});
|
|
return wordsArray.slice(0, n);
|
|
}
|
|
```
|