data_input.R

ls()

## character(0)

rm(list=ls())
BigDiamonds <- read.csv("C:/Users/dell/Desktop/BigDiamonds.csv")
memory.size() #how much memory I am taking

## [1] 110.43

memory.limit() #how much memory I am have

## [1] 1535

gc() #garbage collection

##           used (Mb) gc trigger  (Mb) max used  (Mb)
## Ncells  534481 14.3    1770749  47.3  1135222  30.4
## Vcells 7311563 55.8   13597805 103.8 13533015 103.3

memory.size()

## [1] 74.32

ls()

## [1] "BigDiamonds"

library(data.table)
newDiamonds <- fread("C:/Users/dell/Desktop/BigDiamonds.csv")

## 
Read 36.8% of 598024 rows
Read 55.2% of 598024 rows
Read 66.9% of 598024 rows
Read 76.9% of 598024 rows
Read 88.6% of 598024 rows
Read 598024 rows and 13 (of 13) columns from 0.049 GB file in 00:00:08

getwd()

## [1] "C:/Users/dell/Desktop"

setwd("C:/Users/dell/Desktop")
library(microbenchmark)
microbenchmark(read.csv("BigDiamonds.csv"),fread("BigDiamonds.csv"),times=2)

## 
Read 40.1% of 598024 rows
Read 53.5% of 598024 rows
Read 63.5% of 598024 rows
Read 73.6% of 598024 rows
Read 97.0% of 598024 rows
Read 598024 rows and 13 (of 13) columns from 0.049 GB file in 00:00:07
## 
Read 35.1% of 598024 rows
Read 46.8% of 598024 rows
Read 58.5% of 598024 rows
Read 80.3% of 598024 rows
Read 598024 rows and 13 (of 13) columns from 0.049 GB file in 00:00:07

## Unit: seconds
##                         expr       min        lq      mean    median
##  read.csv("BigDiamonds.csv") 26.244123 26.244123 27.031471 27.031471
##     fread("BigDiamonds.csv")  6.320733  6.320733  6.449165  6.449165
##         uq       max neval cld
##  27.818819 27.818819     2   b
##   6.577597  6.577597     2  a

gc()

##            used  (Mb) gc trigger  (Mb) max used  (Mb)
## Ncells  1356868  36.3    2164898  57.9  1786574  47.8
## Vcells 13740515 104.9   28933293 220.8 28927379 220.7

library(readr)

microbenchmark(
  read.csv("BigDiamonds.csv"),
  fread("BigDiamonds.csv"),
  read_csv("BigDiamonds.csv"),
  times=1)

## Warning: 597311 problems parsing 'BigDiamonds.csv'. See problems(...) for
## more details.

## 
Read 23.4% of 598024 rows
Read 46.8% of 598024 rows
Read 65.2% of 598024 rows
Read 76.9% of 598024 rows
Read 88.6% of 598024 rows
Read 598024 rows and 13 (of 13) columns from 0.049 GB file in 00:00:07

## Unit: seconds
##                         expr       min        lq      mean    median
##  read.csv("BigDiamonds.csv") 24.508083 24.508083 24.508083 24.508083
##     fread("BigDiamonds.csv")  6.982418  6.982418  6.982418  6.982418
##  read_csv("BigDiamonds.csv")  5.780868  5.780868  5.780868  5.780868
##         uq       max neval
##  24.508083 24.508083     1
##   6.982418  6.982418     1
##   5.780868  5.780868     1