ls()
## character(0)
rm(list=ls())
gc()
## used (Mb) gc trigger (Mb) max used (Mb)
## Ncells 290539 7.8 460000 12.3 350000 9.4
## Vcells 320228 2.5 786432 6.0 677388 5.2
library(data.table)
getwd()
## [1] "C:/Users/dell/Desktop"
setwd("C:/Users/dell/Desktop")
dir()
## [1] "1.png"
## [2] "2.png"
## [3] "5128OS_09_01.jpg"
## [4] "adult.data.txt"
## [5] "airline.sas7bdat"
## [6] "Analytics decisionstats.com Audience Overview 20110617-20120717.csv"
## [7] "basicR.html"
## [8] "basicR.R"
## [9] "BigDiamonds.csv"
## [10] "BigDiamonds.csv.zip"
## [11] "Boston.csv"
## [12] "Cars.sav"
## [13] "casestudy"
## [14] "ccFraud.csv"
## [15] "Certificate Doc.docx"
## [16] "CmapServer Download _ Cmap.html"
## [17] "CmapServer Download _ Cmap_files"
## [18] "Coxcombs.jpg"
## [19] "cricketparsing.R"
## [20] "data input.R"
## [21] "data_input.html"
## [22] "datatable"
## [23] "datatablerevised.R"
## [24] "datatablerevised.spin.R"
## [25] "datatablerevised.spin.Rmd"
## [26] "day8 session 4.fbr"
## [27] "day9 session 1.fbr"
## [28] "desktop.ini"
## [29] "Dropbox.lnk"
## [30] "exam.html"
## [31] "exam.R"
## [32] "ie_data.xls"
## [33] "lastsave.txt"
## [34] "lastsave2"
## [35] "library.docx"
## [36] "Minard.png"
## [37] "modules"
## [38] "modules.zip"
## [39] "my first code.R"
## [40] "mycode.docx"
## [41] "mycode.html"
## [42] "mycode.R"
## [43] "myfirstRcode.R"
## [44] "New folder"
## [45] "New Folder (2)"
## [46] "new1"
## [47] "Quiz 1 R.docx"
## [48] "rfmanalysis2.html"
## [49] "rfmanalysis2.R"
## [50] "rsconnect"
## [51] "SnowMap_Points.png"
## [52] "test.csv"
## [53] "Untitled (3).wma"
## [54] "Untitled (3).wma.wav"
## [55] "Untitled 88.wma"
diamonds=fread("BigDiamonds.csv")
##
Read 41.8% of 598024 rows
Read 61.9% of 598024 rows
Read 80.3% of 598024 rows
Read 97.0% of 598024 rows
Read 598024 rows and 13 (of 13) columns from 0.049 GB file in 00:00:06
tables()
## NAME NROW NCOL MB
## [1,] diamonds 598,024 13 75
## COLS
## [1,] V1,carat,cut,color,clarity,table,depth,cert,measurements,price,x,y,z
## KEY
## [1,]
## Total: 75MB
setkey(diamonds,V1)
head(diamonds,10)
## V1 carat cut color clarity table depth cert measurements
## 1: 1 0.25 V.Good K I1 59 63.7 GIA 3.96 x 3.95 x 2.52
## 2: 10 0.20 Good F SI1 65 54.9 GIA 3.83 x 4.00 x 2.14
## 3: 100 0.24 V.Good I SI1 57 63.0 IGI 3.96 x 4.00 x 2.50
## 4: 1000 0.29 V.Good D SI2 58 63.7 GIA 4.19 x 4.16 x 2.66
## 5: 10000 0.40 Ideal J SI2 59 62.6 IGI 4.68 x 4.72 x 2.94
## 6: 100000 0.30 Ideal E VVS2 59 60.4 GIA 4.33 x 4.31 x 2.61
## 7: 100001 0.30 Ideal E VVS2 56 62.3 GIA 4.28 x 4.26 x 2.66
## 8: 100002 0.41 Good E VS1 65 59.3 GIA 4.71 x 4.92 x 2.85
## 9: 100003 0.33 V.Good E VVS2 58 62.6 GIA 4.39 x 4.36 x 2.74
## 10: 100004 0.31 Ideal G VVS2 57 61.7 GIA 4.35 x 4.34 x 2.68
## price x y z
## 1: NA 3.96 3.95 2.52
## 2: NA 3.83 4.00 2.14
## 3: NA 3.96 4.00 2.50
## 4: 340 4.19 4.16 2.66
## 5: 493 4.68 4.72 2.94
## 6: 890 4.33 4.31 2.61
## 7: 890 4.28 4.26 2.66
## 8: 890 4.71 4.92 2.85
## 9: 890 4.39 4.36 2.74
## 10: 890 4.35 4.34 2.68
diamonds[color=="J",mean(price,na.rm = T),]
## [1] 9423.581
diamonds[,mean(price,na.rm = T),color]
## color V1
## 1: K 9694.257
## 2: F 8234.730
## 3: I 9541.319
## 4: D 8266.346
## 5: J 9423.581
## 6: E 7282.990
## 7: G 8984.200
## 8: H 9941.795
## 9: L 7109.228
diamonds[carat>2,.(.N,mean(price,na.rm = T),mean(carat,na.rm = T)),.(cut,color)]
## cut color N V2 V3
## 1: Good D 246 31198.40 2.404878
## 2: V.Good K 1915 26307.26 2.988731
## 3: Ideal F 6235 37875.75 2.496457
## 4: Good G 729 29543.15 2.525514
## 5: Ideal G 8834 34831.33 2.555443
## 6: V.Good J 2684 28808.93 2.940697
## 7: V.Good G 3140 32462.86 2.607363
## 8: V.Good E 1727 34536.84 2.420376
## 9: Good H 826 28792.20 2.661768
## 10: Good J 604 27417.58 2.951374
## 11: V.Good D 1178 34314.22 2.439414
## 12: Good I 779 26607.77 2.796624
## 13: V.Good I 3462 27380.26 2.649792
## 14: Ideal J 7736 27902.59 2.788342
## 15: Good K 482 26264.28 2.950187
## 16: Ideal H 11678 33096.62 2.626627
## 17: Ideal K 5329 23929.88 2.774278
## 18: V.Good H 3619 28889.99 2.626209
## 19: Good F 543 33422.36 2.590424
## 20: Ideal E 4287 40712.74 2.420217
## 21: Good E 351 29781.27 2.437778
## 22: Ideal L 1393 21266.51 2.889275
## 23: V.Good F 2332 32818.06 2.512959
## 24: V.Good L 590 24626.25 3.152237
## 25: Good L 204 25435.75 3.303529
## 26: Ideal I 10507 28943.56 2.637584
## 27: Ideal D 2938 41906.17 2.375524
## cut color N V2 V3