Created
December 16, 2016 11:12
-
-
Save bozhink/0c62b88e1b761c669af9ff2d152c82d3 to your computer and use it in GitHub Desktop.
Calculate word frequency
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
// source: https://blog.heroku.com/kafka-data-pipelines-frp-node?c=7013A000000tyBBQAY&utm_campaign=Newsletter_December_2016&utm_medium=email&utm_source=newsletter&utm_content=blog&utm_term=kafka-data-pipelines-frp-node | |
function wordFreq(accumulator, string) { | |
return _.replace(string, /[\.!\?"'#,\(\):;-]/g, '') //remove special characters | |
.split(/\s/) | |
.map(word => word.toLowerCase()) | |
.filter(word => ( !_.includes(stopWords, word) )) //dump words in stop list | |
.filter(word => ( word.match(/.{2,}/) )) //dump single char words | |
.filter(word => ( !word.match(/\d+/) )) //dump all numeric words | |
.filter(word => ( !word.match(/http/) )) //dump words containing http | |
.filter(word => ( !word.match(/@/) )) //dump words containing @ | |
.reduce((map, word) => | |
Object.assign(map, { | |
[word]: (map[word]) ? map[word] + 1 : 1, | |
}), accumulator | |
) | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment