Hi, I've extracted sample data of four place_ids and plotted x, y, accuracy:
\n\nfour<-train[place_id %in% c("8523065625","1757726713","1137537235","6567393236"),]\nfour$color<-ifelse(four$place_id=="8523065625","red",ifelse(four$place_id=="1757726713","blue",ifelse(four$place_id=="1137537235","green","black")))\nlibrary(rgl)\nplot3d(four$x,four$y,four$accuracy,col=four$color)\nIt looks like the higher accuracy is, the lower variation over x we have.
\n\nAlso interesting observation is that the plot of accuracy seems like mixture of four Weibull distribution, which is used "To model fading channels in wireless communications, as the Weibull fading model seems to exhibit good fit to experimental fading channel measurements" according to wiki.
", "messages": [ { "id": 119724, "postDate": "2016-05-12T13:45:02.847Z", "content": "Hi, I've extracted sample data of four place_ids and plotted x, y, accuracy:
\n\nfour<-train[place_id %in% c("8523065625","1757726713","1137537235","6567393236"),]\nfour$color<-ifelse(four$place_id=="8523065625","red",ifelse(four$place_id=="1757726713","blue",ifelse(four$place_id=="1137537235","green","black")))\nlibrary(rgl)\nplot3d(four$x,four$y,four$accuracy,col=four$color)\nIt looks like the higher accuracy is, the lower variation over x we have.
\n\nAlso interesting observation is that the plot of accuracy seems like mixture of four Weibull distribution, which is used "To model fading channels in wireless communications, as the Weibull fading model seems to exhibit good fit to experimental fading channel measurements" according to wiki.
", "rawMarkdown": "Hi, I've extracted sample data of four place_ids and plotted x, y, accuracy:\r\n\r\n four<-train[place_id %in% c(\"8523065625\",\"1757726713\",\"1137537235\",\"6567393236\"),]\r\n four$color<-ifelse(four$place_id==\"8523065625\",\"red\",ifelse(four$place_id==\"1757726713\",\"blue\",ifelse(four$place_id==\"1137537235\",\"green\",\"black\")))\r\n library(rgl)\r\n plot3d(four$x,four$y,four$accuracy,col=four$color)\r\n\r\nIt looks like the higher accuracy is, the lower variation over x we have.\r\n\r\nAlso interesting observation is that the plot of accuracy seems like mixture of four Weibull distribution, which is used \"To model fading channels in wireless communications, as the Weibull fading model seems to exhibit good fit to experimental fading channel measurements\" according to wiki.\r\n", "votes": 7 } ], "comments": [], "raw_markdown_by_id": { "119724": "Hi, I've extracted sample data of four place_ids and plotted x, y, accuracy:\r\n\r\n four<-train[place_id %in% c(\"8523065625\",\"1757726713\",\"1137537235\",\"6567393236\"),]\r\n four$color<-ifelse(four$place_id==\"8523065625\",\"red\",ifelse(four$place_id==\"1757726713\",\"blue\",ifelse(four$place_id==\"1137537235\",\"green\",\"black\")))\r\n library(rgl)\r\n plot3d(four$x,four$y,four$accuracy,col=four$color)\r\n\r\nIt looks like the higher accuracy is, the lower variation over x we have.\r\n\r\nAlso interesting observation is that the plot of accuracy seems like mixture of four Weibull distribution, which is used \"To model fading channels in wireless communications, as the Weibull fading model seems to exhibit good fit to experimental fading channel measurements\" according to wiki.\r\n" } }