For　computing　the　k-means　clustering　of　the　streaming　and　distributed　big　sparse　data,　we　present　an　algorithm　to　obtain　the　sparse　coreset　for　the　k-means　in　polynomial　time.　This　algorithm　is　mainly　based　on　the　explicit　form　of　the　center　of　mass　and　the　approximate　k-means.　Because　of　the　existence　of　the　approximation,　the　coreset　of　the　output　inevitably　has　a　factor,　which　can　be　controlled　to　be　a　very　small　constant.