Chris Pollett > Students >

    ( Print View)



    [CS 297 Proposal]





    [CS297 Report-PDF]

    [CS 298 Proposal]

    [CS298 Report-PDF]

    [CS298 slides-PDF]

Generate a Chinese words frequency file for Yioop to suggest Chinese words based on input


The goal of the term project is to add some features to Yioop. So, I decided to get familiar with Yioop first by doing some enhacement to it. For this deliverable, I was given a list of Chinese words and my task is to find the frequency of those words and use the yioop tool to add the words.


1. The frequency of the words is retrieved from Google trends using pytrends. The frequency are calculated by the average of the weekly hotness: if the words are hot for the whole year, it is a frequently seached word; if it is hot in a short time, then it is not a frequently seached word. I rank the words based on this rule.

Chinese Suggest word

2. Fixed 2 minor bugs. First one is the Chinese stopwordsRemover was not working as expected. Second one is that a single Chinese character input in the yioop search bar is not correctly encoded for searching

3. Added a sorting statement so the suggestion words are ordered by frequency instead of lexicon order

suggest word lexicographic order