2. 解æåæ© 2013å¹´5æ18æ¥Tokyo WebMining #26 2 æå¾ã®æ¥ã ãç»åå¦çã®åå¼·ã§ããã¨ãã å¾è¼©ããAV女åªã®é¡ä¼¼ç»åæ¤ç´¢ã®è©±ãèã ï¼ã±ããã 2012ï¼ DMMã«ã¯ã¢ãã£ãªã¨ã¤ããã£ãã㪠ããã§ã¦ã§ããµã¼ãã¹ä½ãã°å²ãããã 決ãã¦ä¸å身ããã®è¦æã§è§£æããã®ã§ã¯ããã¾ãã http://blog.parosky.net/archives/1506 3. è¨ç®ç°å¢ 2013å¹´5æ18æ¥Tokyo WebMining #26 3 使ç¨è¨èªï¼Python ï¼ï¼ï¼ ï¼å°ãã ãRï¼ ä½¿ç¨ã¢ã¸ã¥ã¼ã«ï¼Numpy, Scipy, OpenCV ç§å¦æè¡è¨ç®ç¨ã®ã©ã¤ãã©ãª MATLABã«ã§ãããã¨ã¯å¤§ä½ã§ãã ï numpy.ndarray åä»ãå¤æ¬¡å é å ï numpy.linalg ç·å½¢ä»£æ°è¨ç® ï scipy.cluster ä»åã¯ããã®k-meansæ³ã使ç¨
åé¨çã®æ¹ã¸ å·¥å¦é¨ãåé¨çåãæ å ± è¸è¡å¦é¨ãåé¨çåãæ å ± 大å¦é¢ã®æ å ±ã¯ãã¡ã è³æè«æ± é¡æ¸è«æ± å¦é¨ã»å¦ç§ã»ã³ã¼ã¹æ å ± å·¥å¦é¨ æ©æ¢°ã³ã¼ã¹ é»æ°é»åã³ã¼ã¹ æ å ±ã³ã¼ã¹ åå¦ã»ææã³ã¼ã¹ 建ç¯ã³ã¼ã¹ è¸è¡å¦é¨ åçå¦ç§ æ åå¦ç§ ãã¶ã¤ã³å¦ç§ ã¤ã³ã¿ã©ã¯ãã£ãã¡ãã£ã¢å¦ç§ ã¢ãã¡ã¼ã·ã§ã³å¦ç§ ã²ã¼ã å¦ç§ ãã³ã¬å¦ç§ å¦ççæ´» å¦ççæ´» ã¯ã©ãã»ãµã¼ã¯ã«ç´¹ä» å種奨å±è²» KOUGEI PEOPLEï¼ããã°éï¼æ°è¦ã¦ã£ã³ã㦠åæ¨ãã£ã³ãã¹ã¹ããªã¼ããã¥ã¼æ°è¦ã¦ã£ã³ãã¦ å ¥å¦ãå¸æãããæ¹ã¸ å¦è²» 奨å¦éã»ç¹å¾ çå¶åº¦ 大å¦æå®å¯®ã»ã¢ãã¼ã æ±äº¬å·¥è¸å¤§å¦ãç´æ¥ä½é¨ãããæ¹ã¸ ãã£ã³ãã¹è¦å¦ ãªã¼ãã³ãã£ã³ãã¹ å¦å¤é²å¦ç¸è«ä¼ åºåææ¥ ãã®ä»ãåãåããããäºæãããæ¹ã¸ ãããã質å ãåãåãã
ç®æ¬¡ 1. ãã³ã³ãã¬ãã£ã®æ°ç -ã³ã³ãã«å¿ è¦ãªæå¾ åæ°ã®è¨ç®æ¹æ³ã«ã¤ãã¦-ã 2. ããæ°å¦çã²ã¼ã ãã¶ã¤ã³ãã¨ããã¢ããã¼ãã 3. ãã³ã³ãã¬ãã£ã®æ°ç -ã¬ã¤ãã©ã¤ã³ã«åºã¥ããã²ã¼ã ãã¶ã¤ã³ ãã®1-ã 4. ãã³ã³ãã¬ãã£ã®æ°ç -ã¬ã¤ãã©ã¤ã³ã«åºã¥ããã²ã¼ã ãã¶ã¤ã³ ãã®2-ã ç®ç ã³ã³ãã¬ãã£ã®ã³ã³ãã«å¿ è¦ãªåæ°ãæ±ããåé¡ã¯ãThe Coupon Collector's Problemãã¨å¼ã°ããæ°å¦ã¢ãã«ã®æ çµã¿ã«æ²¿ã£ãç¾ããåé¡ã§ããäºãè¿°ã¹ï¼ããã¤ãã®æç¨ãªçµæã示ãã â» ããã¾ã§å人ç 究ã®ã¤ããã§æ¸ããã®ã§ï¼è²ã ä¸åãããããããã¾ããããã®éã¯ä¸è¨é ããã¨å©ããã¾ãã å®ç¾© ã³ã³ãã¬ãã£åé¡ã Coupon Collector's Problem ã«æºããå½¢ã§æ¸ãã¨ä»¥ä¸ã®æ§ã«ãªãï¼ ãå ¨é¨ã§ n 種é¡ã®ã¢ã¤ãã ããã£ã¦ï¼1ã¤ã®ã¬ãã£ã®ä¸ã«ã¢ã¤ãã ã1ã¤å ¥ã£ã¦
ã»ã¤ããçµ±è¨å¦ çµ±è¨ã®å¤±æãã¦ã½ãæ´ãã®ã§ã¯ãªããçµ±è¨ãæ£ãã使ãããæåäºä¾ãï¼ï¼ã®ã¨ãã½ã¼ãã§è§£èª¬ãããçµ±è¨å¦ã®ææãç¾å®ã®ç¤¾ä¼ã«å¿ç¨ããã«ã¯ãé£ããè¨ç®ãã§ããã ãã§ã¯ã¾ã£ããä¸ååã§ããã®æ°åã人éã«ããããå¿çå¹æããå®éã®çµæ¸å¹æãããèããªããã°ãªããªãã¨ãããã¨ããããããæ¬ã æåã®ã¨ãã½ã¼ãã¯ãã£ãºãã¼ã©ã³ãã®ãã¡ã¹ããã¹ã¯çµ±è¨å¦ã®æåä¾ã ããã¡ã¹ããã¹çºå¸ã«ãã£ã¦ã¢ãã©ã¯ã·ã§ã³ã®å¾ ã¡è¡åãçããªãããã§ã¯ãªããããããã¡ã¹ããã¹ã«ããããã£ãºãã¼ã®ãã¼ããã¼ã¯ã§ã¢ãã©ã¯ã·ã§ã³ãå¾ ã¤è¡åã¯å¹´ã é·ããªã£ã¦ããã«ãããããããåºå£èª¿æ»ã«ããã¨ã²ã¹ãã®æºè¶³åº¦ã¯ä¸æãç¶ãã¦ããããããã§ããã ãã¡ã¹ããã¹ã®å½¹å²ã¯å¾ ã¡æéãçããããã¨ã§ã¯ãªãã£ãããã¹ããã£ã¦ããã¢ãã©ã¯ã·ã§ã³ã®å容è½åã¯å¤ãããªãããã ãçµ±è¨å¦çã«ã¯ãã¹ã®çã®æ©è½ã¯ã²ã¹ãã®å¾ ã¡æéã®ã°ãã¤ããæé¤ãããã¨ã«
è¦ç´ã¨ãããè¨ãããã㨠調ã¹ã¦ã¿ãã¨ããã³åã®ã³ã¡ã³ãã¯10代ã«ãããã®ãã»ã¨ãã©ã ã£ãï¼ç¹ã«ä¸å¦çï¼ã ã³ã¡ã³ãã®ç©ºæ°ã¯å½¼ãå°ä¸å¦çãä½ã£ã¦ããããããªãã®ãã 価å¤è¦³ãããªãéãããªãåããæ¹ããããã§ãªããã æè¿ã®ãã³åã³ã¡ã³ãã¨ç©ºæ° æè¿ãã³åã®ã³ã¡ã³ããè¦ã¦ãã¦ããªãã¨ãªãã³ã¡ã³ããã¤ã¾ããªããªãã¨æãã å§å©ã®ã³ã¡ã³ãã¯è«å¤ã ãã©ãæ®éã®ã³ã¡ã³ãã§ã ããã¼ãã»ã»ã»ããã§ã¦ããï¼ã ããã®æ²ãããªã«ããããªãã»ã»ã»ã ã¿ããã«ããã¿ããªãã¨ã®æè¦ã®ãºã¬ãæã«æ¯ã¹ãã¨ç®ç«ã¤ããã«ãªã£ã¦ããããã«æãã ã©ãããèªåã¯ãã³åå ã§ã®æ¨æºçãªä¾¡å¤è¦³ã®ã©ã¤ã³ããé¸è±ãã¦ãã¾ã£ãã®ãã ã ã¨ãããããã®ãæ¨æºçãªä¾¡å¤è¦³ãã¨ã¯èª°ãã©ã®ããã«ä½ãã ãã®ãï¼ å®éããã«ãã人ã¨è¡¨é¢ä¸ããã«ãã人ã®éã æ®éã«èããã¨ããã®ãæ¨æºçãªä¾¡å¤è¦³ãã¯ããã®å ´ã«ãã人éã®å¹³åçãªãã®ã«ãªãã¯ãã 10
ã©ã³ãã³ã°
ã©ã³ãã³ã°
ã©ã³ãã³ã°
ãªãªã¼ã¹ãé害æ å ±ãªã©ã®ãµã¼ãã¹ã®ãç¥ãã
ææ°ã®äººæ°ã¨ã³ããªã¼ã®é ä¿¡
å¦çãå®è¡ä¸ã§ã
j次ã®ããã¯ãã¼ã¯
kåã®ããã¯ãã¼ã¯
lãã¨ã§èªã
eã³ã¡ã³ãä¸è¦§ãéã
oãã¼ã¸ãéã
{{#tags}}- {{label}}
{{/tags}}