df<- read.csv("C:/Users/Public/ToyotaCorolla.csv")
categorical_variable <- sapply(df, class)
categorical_variable
## Id Model Price Age_08_04
## "integer" "character" "integer" "integer"
## Mfg_Month Mfg_Year KM Fuel_Type
## "integer" "integer" "integer" "character"
## HP Met_Color Color Automatic
## "integer" "integer" "character" "integer"
## CC Doors Cylinders Gears
## "integer" "integer" "integer" "integer"
## Quarterly_Tax Weight Mfr_Guarantee BOVAG_Guarantee
## "integer" "integer" "integer" "integer"
## Guarantee_Period ABS Airbag_1 Airbag_2
## "integer" "integer" "integer" "integer"
## Airco Automatic_airco Boardcomputer CD_Player
## "integer" "integer" "integer" "integer"
## Central_Lock Powered_Windows Power_Steering Radio
## "integer" "integer" "integer" "integer"
## Mistlamps Sport_Model Backseat_Divider Metallic_Rim
## "integer" "integer" "integer" "integer"
## Radio_cassette Parking_Assistant Tow_Bar
## "integer" "integer" "integer"
dummy_var <- model.matrix(~factor(categorical_variable))
dum <- lapply(dummy_var,as.numeric)
dum
## [[1]]
## [1] 1
##
## [[2]]
## [1] 1
##
## [[3]]
## [1] 1
##
## [[4]]
## [1] 1
##
## [[5]]
## [1] 1
##
## [[6]]
## [1] 1
##
## [[7]]
## [1] 1
##
## [[8]]
## [1] 1
##
## [[9]]
## [1] 1
##
## [[10]]
## [1] 1
##
## [[11]]
## [1] 1
##
## [[12]]
## [1] 1
##
## [[13]]
## [1] 1
##
## [[14]]
## [1] 1
##
## [[15]]
## [1] 1
##
## [[16]]
## [1] 1
##
## [[17]]
## [1] 1
##
## [[18]]
## [1] 1
##
## [[19]]
## [1] 1
##
## [[20]]
## [1] 1
##
## [[21]]
## [1] 1
##
## [[22]]
## [1] 1
##
## [[23]]
## [1] 1
##
## [[24]]
## [1] 1
##
## [[25]]
## [1] 1
##
## [[26]]
## [1] 1
##
## [[27]]
## [1] 1
##
## [[28]]
## [1] 1
##
## [[29]]
## [1] 1
##
## [[30]]
## [1] 1
##
## [[31]]
## [1] 1
##
## [[32]]
## [1] 1
##
## [[33]]
## [1] 1
##
## [[34]]
## [1] 1
##
## [[35]]
## [1] 1
##
## [[36]]
## [1] 1
##
## [[37]]
## [1] 1
##
## [[38]]
## [1] 1
##
## [[39]]
## [1] 1
##
## [[40]]
## [1] 1
##
## [[41]]
## [1] 0
##
## [[42]]
## [1] 1
##
## [[43]]
## [1] 1
##
## [[44]]
## [1] 1
##
## [[45]]
## [1] 1
##
## [[46]]
## [1] 1
##
## [[47]]
## [1] 0
##
## [[48]]
## [1] 1
##
## [[49]]
## [1] 1
##
## [[50]]
## [1] 0
##
## [[51]]
## [1] 1
##
## [[52]]
## [1] 1
##
## [[53]]
## [1] 1
##
## [[54]]
## [1] 1
##
## [[55]]
## [1] 1
##
## [[56]]
## [1] 1
##
## [[57]]
## [1] 1
##
## [[58]]
## [1] 1
##
## [[59]]
## [1] 1
##
## [[60]]
## [1] 1
##
## [[61]]
## [1] 1
##
## [[62]]
## [1] 1
##
## [[63]]
## [1] 1
##
## [[64]]
## [1] 1
##
## [[65]]
## [1] 1
##
## [[66]]
## [1] 1
##
## [[67]]
## [1] 1
##
## [[68]]
## [1] 1
##
## [[69]]
## [1] 1
##
## [[70]]
## [1] 1
##
## [[71]]
## [1] 1
##
## [[72]]
## [1] 1
##
## [[73]]
## [1] 1
##
## [[74]]
## [1] 1
##
## [[75]]
## [1] 1
##
## [[76]]
## [1] 1
##
## [[77]]
## [1] 1
##
## [[78]]
## [1] 1
correlation <- cor(na.omit(df[, -c(1,2,5,6,8,10:12,14,16,19:39)]))
## Warning in cor(na.omit(df[, -c(1, 2, 5, 6, 8, 10:12, 14, 16, 19:39)])): the
## standard deviation is zero
plot(na.omit(df[, -c(1,2,5,6,8,10:12,14,16,19:39)]))
correlation
## Price Age_08_04 KM HP CC
## Price 1.0000000 -0.87659050 -0.56996016 0.31498983 0.12638920
## Age_08_04 -0.8765905 1.00000000 0.50567218 -0.15662202 -0.09808374
## KM -0.5699602 0.50567218 1.00000000 -0.33353795 0.10268289
## HP 0.3149898 -0.15662202 -0.33353795 1.00000000 0.03585580
## CC 0.1263892 -0.09808374 0.10268289 0.03585580 1.00000000
## Cylinders NA NA NA NA NA
## Quarterly_Tax 0.2191969 -0.19843051 0.27816470 -0.29843172 0.30699580
## Weight 0.5811976 -0.47025318 -0.02859846 0.08961406 0.33563740
## Cylinders Quarterly_Tax Weight
## Price NA 0.2191969 0.58119759
## Age_08_04 NA -0.1984305 -0.47025318
## KM NA 0.2781647 -0.02859846
## HP NA -0.2984317 0.08961406
## CC NA 0.3069958 0.33563740
## Cylinders 1 NA NA
## Quarterly_Tax NA 1.0000000 0.62613373
## Weight NA 0.6261337 1.00000000