ÀûÓù¤ÉÌÐÅÏ¢¡¢ÆóÒµ»ù±¾ÐÅÏ¢¡¢Ë°ÎñÐÅÏ¢µÈ¼Ç¼£¬ÎÒÃÇ¿ÉÒÔ¹¹½¨³öÒ»¸öÍøÂçÍØÆË½á¹¹£¬ÒÔ¹¹½¨ÆóÒµµÄÏàÓ¦ÊôÐÔ±êÇ©£¬ÊôÐÔ±êÇ©¿ÉÒÔ·´Ïò±ê¼Ç»ØÆóÒµ£¬´Ó¶øÆóÒµ¾ßÓÐȺÌåÊôÐÔ¡£
ͼ3-14ÆóÒµ¾ÛÀàͼ
¾ÛÀà·ÖÎöʱÊý¾ÝÍÚ¾òµÄÒ»¸öÖØÒª·ÖÖ§£¬Ä¿±êÊǽ«Êý¾Ý¶ÔÏó·Ö×é³ÉΪ¶à¸öÀà»ò´Ø£¬ÔÚͬһ¸öÀàÖеĶÔÏóÖ®¼äÓнϸߵÄÏàËÆ¶È£¬¶ø²»Í¬ÀàÖеĶÔÏó²î±ð½Ï´ó¡£ÔçÆÚµÄ¾ÛÀà¶à²ÉÓÃÎ޼ල·½Ê½£¬µ«Ëæ×ÅÊý¾ÝÍÚ¾òÁìÓòµÄÀ©Õ¹£¬ºÜ¶àµÄÐÐÒµÎÊÌ⣬ÐèÒªÓмලµÄÊý¾ÝÍÚ¾ò¼¼Êõ¡£
ͼ3-15»ùÓÚÄÚ´æ¼ÆËãµÄ·Ö²¼Ê½¾ÛÀàËã·¨
48
Ë㷨Ŀ±êÊÇÄ£¿é¶Èº¯Êý£¬¸Ãº¯Êý¶¨ÒåΪ´ØÄÚʵ¼ÊÁ¬½ÓÊýÄ¿ÓëËæ»úÁ¬½ÓÇé¿öÏÂÝýÄÚÆÚÍûÁ¬½ÓÊýĿ֮²î£¬ÓÃÀ´ºâÁ¿ÆóÒµÏîÄ¿µÄ»®·ÖÖÊÁ¿£¬Õû¸ö¹ý³Ì×Ôµ×ÏòÉϽøÐС£
ͼ3-16 ¾ÛÀàË㷨ģ¿éͼ
ͼ3-17 ¾ÛÀàË㷨ģ¿éͼ
ÄÚ´æ¼ÆË㣨In-Memory Processing£©£¬ÊµÖÊÉϾÍÊÇCPUÖ±½Ó
49
´ÓÄÚ´æ¶ø·ÇÓ²ÅÌÉ϶ÁÈ¡Êý¾Ý£¬²¢¶ÔÊý¾Ý½øÐмÆËã¡¢·ÖÎö¡£ÓÈÆäÊǶÔÓÚ¸´ÔÓµÄÄ£ÐÍ£¬ÍùÍùÐèÒª½Ï¶àµü´ú´ÎÊý²ÅÄÜÊÕÁ²£¬¶ø»ùÓÚ´ÅÅ̵ķÖÎö·½Ê½£¨HadoopÉϵÄMahout£©ÔòIO¿ªÏú¾Þ´ó¡£ £¨2£©»ùÓÚÄÚ´æ¼ÆËãµÄ·Ö²¼Ê½·ÖÀàËã·¨
·ÖÀàÎÊÌâÊÇ»úÆ÷ѧϰÖеľµäÎÊÌ⣬Îı¾¡¢ÓïÒô¡¢Í¼ÏñµÈ¸÷ÖÖÁìÓò¶¼Óй㷺ӦÓá£ÄâÕë¶Ô¾ß±¸ºËÃܶȼ¼ÊõµÄ·ÖÀà·½·¨ÊµÏÖ»ùÓÚÄÚ´æµÄ·Ö²¼Ê½Ëã·¨¡£Ëù²Î¿¼µÄ·½·¨ÊÇDLR:Density-based Logistic Regression (Chen et al. KDD 2013)
ͼ3-18 ·ÖÀàË㷨ģ¿éͼ
£¨3£©¸ßά¶ÈÒì¹¹Êý¾ÝµÄ½µÎ¬Ëã·¨
Êý¾ÝºÍάÊýÖ®¼äÍùÍùÓÐÏà¹ØÐÔ£¬Óü¸¸ö½ÏÉÙµÄ×ÛºÏÖ¸±êÀ´´úÌæÔÀ´½Ï¶àµÄÖ¸±ê£¬¶øÕâЩ½ÏÉÙµÄ×ÛºÏÖ¸±ê¼ÈÄܾ¡¿ÉÄÜ¶àµØ·´Ó³ÔÀ´½Ï¶àÖ¸±êµÄÓÐÓÃÐÅÏ¢£¬ÇÒÏ໥֮¼äÓÖÊÇÎ޹صġ£
50
ͼ3-19¸ßγ¶ÈÒì¹¹Êý¾ÝµÄ½µÎ¬Ëã·¨
3.7´óÊý¾Ý´æ´¢Éè¼Æ
3.7.1Êý¾Ý·Ö¼¶´æ´¢ £¨1£©Êý¾Ý·Ö¼¶´æ´¢ÔÔò
Êý¾ÝÉúÃüÖÜÆÚÖÐÔÚÏßÊý¾Ý¶Ô¸ßÐÔÄÜ´æ´¢µÄÐèÇó£¬ÒÔ¼°Ëæ×ÅÊý¾ÝÉúÃüÖÜÆÚµÄ±ä¸ü£¬Öð½¥ÏòÒ»°ãÐÔÄÜ´æ´¢µÄÇ¨ÒÆ£¬ÊÇ·Ö¼¶´æ´¢¹ÜÀíµÄÒ»ÌõÖ÷Ïß¡£Í¬Ê±¼æ¹Ë¿¼ÂÇÆäËû·Ö¼¶ÔÔò£¬¹²Í¬×÷ÓÃÓ°ÏìÊý¾ÝÇ¨ÒÆ»úÖÆ¡£
£¨2£©Êý¾ÝÈÚºÏÓë·Ö¼¶´æ´¢ÊµÊ©
½«ºËÐÄÄ£ÐÍ£¨¼´ÖжȻã×ܵÄÄ£ÐÍ£©Í¨¹ý¸ÄÔìÈÚÈëµ½ÏÖÓÐÖ÷Êý¾Ý²Ö¿âµÄºËÐÄÄ£ÐÍÖУ¬¼õÉÙÊý¾ÝÈßÓ࣬ÌáÉýÊý¾ÝÖÊÁ¿¡£
½«Ö÷Êý¾Ý²Ö¿âÖеÄÀúÊ·Êý¾ÝºÍÇåµ¥Êý¾ÝÇ¨ÒÆµ½µÍ³É±¾·Ö²¼Ê½Êý¾Ý¿â£¬¼õÇáÖ÷Êý¾Ý²Ö¿âµÄ¼ÆËãÓë´æ´¢Ñ¹Á¦²¢Ö§³ÅÉî¶ÈÊý¾Ý·ÖÎö¡£
51