Data Read In
setwd("~/Dropbox/Works/Class/Data_Science/R.WD/zmPDSwR/")
uciCar <- read.table("../../zmPDSwR/UCICar/car.data.csv", sep=",", header=TRUE)
class(uciCar)
## [1] "data.frame"
summary(uciCar)
## buying maint doors
## Length:1728 Length:1728 Length:1728
## Class :character Class :character Class :character
## Mode :character Mode :character Mode :character
## persons lug_boot safety
## Length:1728 Length:1728 Length:1728
## Class :character Class :character Class :character
## Mode :character Mode :character Mode :character
## rating
## Length:1728
## Class :character
## Mode :character
dim(uciCar)
## [1] 1728 7
str(uciCar)
## 'data.frame': 1728 obs. of 7 variables:
## $ buying : chr "vhigh" "vhigh" "vhigh" "vhigh" ...
## $ maint : chr "vhigh" "vhigh" "vhigh" "vhigh" ...
## $ doors : chr "2" "2" "2" "2" ...
## $ persons : chr "2" "2" "2" "2" ...
## $ lug_boot: chr "small" "small" "small" "med" ...
## $ safety : chr "low" "med" "high" "low" ...
## $ rating : chr "unacc" "unacc" "unacc" "unacc" ...
head(uciCar)
## buying maint doors persons lug_boot safety rating
## 1 vhigh vhigh 2 2 small low unacc
## 2 vhigh vhigh 2 2 small med unacc
## 3 vhigh vhigh 2 2 small high unacc
## 4 vhigh vhigh 2 2 med low unacc
## 5 vhigh vhigh 2 2 med med unacc
## 6 vhigh vhigh 2 2 med high unacc
d <- read.table(paste('http://archive.ics.uci.edu/ml/',
'machine-learning-databases/statlog/german/german.data',sep=''),
stringsAsFactors=F,header=F)
print(d[1:3,])
## V1 V2 V3 V4 V5 V6 V7 V8 V9 V10 V11 V12 V13 V14 V15 V16 V17
## 1 A11 6 A34 A43 1169 A65 A75 4 A93 A101 4 A121 67 A143 A152 2 A173
## 2 A12 48 A32 A43 5951 A61 A73 2 A92 A101 2 A121 22 A143 A152 1 A173
## 3 A14 12 A34 A46 2096 A61 A74 2 A93 A101 3 A121 49 A143 A152 1 A172
## V18 V19 V20 V21
## 1 1 A192 A201 1
## 2 1 A191 A201 2
## 3 2 A191 A201 1
colnames(d) <- c('Status.of.existing.checking.account',
'Duration.in.month', 'Credit.history', 'Purpose',
'Credit.amount', 'Savings account/bonds',
'Present.employment.since',
'Installment.rate.in.percentage.of.disposable.income',
'Personal.status.and.sex', 'Other.debtors/guarantors',
'Present.residence.since', 'Property', 'Age.in.years',
'Other.installment.plans', 'Housing',
'Number.of.existing.credits.at.this.bank', 'Job',
'Number.of.people.being.liable.to.provide.maintenance.for',
'Telephone', 'foreign.worker', 'Good.Loan')
options(width=132)
print(d[1:3,])
## Status.of.existing.checking.account Duration.in.month Credit.history Purpose Credit.amount Savings account/bonds
## 1 A11 6 A34 A43 1169 A65
## 2 A12 48 A32 A43 5951 A61
## 3 A14 12 A34 A46 2096 A61
## Present.employment.since Installment.rate.in.percentage.of.disposable.income Personal.status.and.sex Other.debtors/guarantors
## 1 A75 4 A93 A101
## 2 A73 2 A92 A101
## 3 A74 2 A93 A101
## Present.residence.since Property Age.in.years Other.installment.plans Housing Number.of.existing.credits.at.this.bank Job
## 1 4 A121 67 A143 A152 2 A173
## 2 2 A121 22 A143 A152 1 A173
## 3 3 A121 49 A143 A152 1 A172
## Number.of.people.being.liable.to.provide.maintenance.for Telephone foreign.worker Good.Loan
## 1 1 A192 A201 1
## 2 1 A191 A201 2
## 3 2 A191 A201 1
mapping <- list('A11'='... < 0 DM',
'A12'='0 <= ... < 200 DM',
'A13'='... >= 200 DM / salary assignments for at least 1 year',
'A14'='no checking account',
'A30'='no credits taken/all credits paid back duly',
'A31'='all credits at this bank paid back duly',
'A32'='existing credits paid back duly till now',
'A33'='delay in paying off in the past',
'A34'='critical account/other credits existing (not at this bank)',
'A40'='car (new)',
'A41'='car (used)',
'A42'='furniture/equipment',
'A43'='radio/television',
'A44'='domestic appliances',
'A45'='repairs',
'A46'='education',
'A47'='(vacation - does not exist?)',
'A48'='retraining',
'A49'='business',
'A410'='others',
'A61'='... < 100 DM',
'A62'='100 <= ... < 500 DM',
'A63'='500 <= ... < 1000 DM',
'A64'='.. >= 1000 DM',
'A65'='unknown/ no savings account',
'A71'='unemployed',
'A72'='... < 1 year',
'A73'='1 <= ... < 4 years',
'A74'='4 <= ... < 7 years',
'A75'='.. >= 7 years',
'A91'='male : divorced/separated',
'A92'='female : divorced/separated/married',
'A93'='male : single',
'A94'='male : married/widowed',
'A95'='female : single',
'A101'='none',
'A102'='co-applicant',
'A103'='guarantor',
'A121'='real estate',
'A122'='if not A121 : building society savings agreement/life insurance',
'A123'='if not A121/A122 : car or other, not in attribute 6',
'A124'='unknown / no property',
'A141'='bank',
'A142'='stores',
'A143'='none',
'A151'='rent',
'A152'='own',
'A153'='for free',
'A171'='unemployed/ unskilled - non-resident',
'A172'='unskilled - resident',
'A173'='skilled employee / official',
'A174'='management/ self-employed/highly qualified employee/ officer',
'A191'='none',
'A192'='yes, registered under the customers name',
'A201'='yes',
'A202'='no')
- Listing 2.6의 구조를 파악하기 위해서
sapply(d, class)
## Status.of.existing.checking.account Duration.in.month
## "character" "integer"
## Credit.history Purpose
## "character" "character"
## Credit.amount Savings account/bonds
## "integer" "character"
## Present.employment.since Installment.rate.in.percentage.of.disposable.income
## "character" "integer"
## Personal.status.and.sex Other.debtors/guarantors
## "character" "character"
## Present.residence.since Property
## "integer" "character"
## Age.in.years Other.installment.plans
## "integer" "character"
## Housing Number.of.existing.credits.at.this.bank
## "character" "integer"
## Job Number.of.people.being.liable.to.provide.maintenance.for
## "character" "integer"
## Telephone foreign.worker
## "character" "character"
## Good.Loan
## "integer"
head(d[, 4])
## [1] "A43" "A43" "A46" "A42" "A40" "A46"
mapping[head(d[, 4])]
## $A43
## [1] "radio/television"
##
## $A43
## [1] "radio/television"
##
## $A46
## [1] "education"
##
## $A42
## [1] "furniture/equipment"
##
## $A40
## [1] "car (new)"
##
## $A46
## [1] "education"
as.character(mapping[head(d[, 4])])
## [1] "radio/television" "radio/television" "education" "furniture/equipment" "car (new)"
## [6] "education"
d.2 <- d
for(i in 1:dim(d)[2]) {
if(class(d[, i])=="character") {
d[, i] <- as.factor(as.character(mapping[d[, i]]))
}
}
str(d)
## 'data.frame': 1000 obs. of 21 variables:
## $ Status.of.existing.checking.account : Factor w/ 4 levels "... < 0 DM","... >= 200 DM / salary assignments for at least 1 year",..: 1 3 4 1 1 4 4 3 4 3 ...
## $ Duration.in.month : int 6 48 12 42 24 36 24 36 12 30 ...
## $ Credit.history : Factor w/ 5 levels "all credits at this bank paid back duly",..: 2 4 2 4 3 4 4 4 4 2 ...
## $ Purpose : Factor w/ 10 levels "business","car (new)",..: 8 8 5 6 2 5 6 3 8 2 ...
## $ Credit.amount : int 1169 5951 2096 7882 4870 9055 2835 6948 3059 5234 ...
## $ Savings account/bonds : Factor w/ 5 levels ".. >= 1000 DM",..: 5 2 2 2 2 5 4 2 1 2 ...
## $ Present.employment.since : Factor w/ 5 levels ".. >= 7 years",..: 1 3 4 4 3 3 1 3 4 5 ...
## $ Installment.rate.in.percentage.of.disposable.income : int 4 2 2 2 3 2 3 2 2 4 ...
## $ Personal.status.and.sex : Factor w/ 4 levels "female : divorced/separated/married",..: 4 1 4 4 4 4 4 4 2 3 ...
## $ Other.debtors/guarantors : Factor w/ 3 levels "co-applicant",..: 3 3 3 2 3 3 3 3 3 3 ...
## $ Present.residence.since : int 4 2 3 4 4 4 4 2 4 2 ...
## $ Property : Factor w/ 4 levels "if not A121 : building society savings agreement/life insurance",..: 3 3 3 1 4 4 1 2 3 2 ...
## $ Age.in.years : int 67 22 49 45 53 35 53 35 61 28 ...
## $ Other.installment.plans : Factor w/ 3 levels "bank","none",..: 2 2 2 2 2 2 2 2 2 2 ...
## $ Housing : Factor w/ 3 levels "for free","own",..: 2 2 2 1 1 1 2 3 2 2 ...
## $ Number.of.existing.credits.at.this.bank : int 2 1 1 1 2 1 1 1 1 2 ...
## $ Job : Factor w/ 4 levels "management/ self-employed/highly qualified employee/ officer",..: 2 2 4 2 2 4 2 1 4 1 ...
## $ Number.of.people.being.liable.to.provide.maintenance.for: int 1 1 2 2 2 2 1 1 1 1 ...
## $ Telephone : Factor w/ 2 levels "none","yes, registered under the customers name": 2 1 1 1 1 2 1 2 1 1 ...
## $ foreign.worker : Factor w/ 2 levels "no","yes": 2 2 2 2 2 2 2 2 2 2 ...
## $ Good.Loan : int 1 2 1 1 2 1 1 1 1 2 ...
d$Good.Loan <- factor(ifelse(d$Good.Loan == 1, "GoodLoan", "BadLoan"))
str(d)
## 'data.frame': 1000 obs. of 21 variables:
## $ Status.of.existing.checking.account : Factor w/ 4 levels "... < 0 DM","... >= 200 DM / salary assignments for at least 1 year",..: 1 3 4 1 1 4 4 3 4 3 ...
## $ Duration.in.month : int 6 48 12 42 24 36 24 36 12 30 ...
## $ Credit.history : Factor w/ 5 levels "all credits at this bank paid back duly",..: 2 4 2 4 3 4 4 4 4 2 ...
## $ Purpose : Factor w/ 10 levels "business","car (new)",..: 8 8 5 6 2 5 6 3 8 2 ...
## $ Credit.amount : int 1169 5951 2096 7882 4870 9055 2835 6948 3059 5234 ...
## $ Savings account/bonds : Factor w/ 5 levels ".. >= 1000 DM",..: 5 2 2 2 2 5 4 2 1 2 ...
## $ Present.employment.since : Factor w/ 5 levels ".. >= 7 years",..: 1 3 4 4 3 3 1 3 4 5 ...
## $ Installment.rate.in.percentage.of.disposable.income : int 4 2 2 2 3 2 3 2 2 4 ...
## $ Personal.status.and.sex : Factor w/ 4 levels "female : divorced/separated/married",..: 4 1 4 4 4 4 4 4 2 3 ...
## $ Other.debtors/guarantors : Factor w/ 3 levels "co-applicant",..: 3 3 3 2 3 3 3 3 3 3 ...
## $ Present.residence.since : int 4 2 3 4 4 4 4 2 4 2 ...
## $ Property : Factor w/ 4 levels "if not A121 : building society savings agreement/life insurance",..: 3 3 3 1 4 4 1 2 3 2 ...
## $ Age.in.years : int 67 22 49 45 53 35 53 35 61 28 ...
## $ Other.installment.plans : Factor w/ 3 levels "bank","none",..: 2 2 2 2 2 2 2 2 2 2 ...
## $ Housing : Factor w/ 3 levels "for free","own",..: 2 2 2 1 1 1 2 3 2 2 ...
## $ Number.of.existing.credits.at.this.bank : int 2 1 1 1 2 1 1 1 1 2 ...
## $ Job : Factor w/ 4 levels "management/ self-employed/highly qualified employee/ officer",..: 2 2 4 2 2 4 2 1 4 1 ...
## $ Number.of.people.being.liable.to.provide.maintenance.for: int 1 1 2 2 2 2 1 1 1 1 ...
## $ Telephone : Factor w/ 2 levels "none","yes, registered under the customers name": 2 1 1 1 1 2 1 2 1 1 ...
## $ foreign.worker : Factor w/ 2 levels "no","yes": 2 2 2 2 2 2 2 2 2 2 ...
## $ Good.Loan : Factor w/ 2 levels "BadLoan","GoodLoan": 2 1 2 2 1 2 2 2 2 1 ...
l.char <- sapply(d.2, class) == "character"
l.char
## Status.of.existing.checking.account Duration.in.month
## TRUE FALSE
## Credit.history Purpose
## TRUE TRUE
## Credit.amount Savings account/bonds
## FALSE TRUE
## Present.employment.since Installment.rate.in.percentage.of.disposable.income
## TRUE FALSE
## Personal.status.and.sex Other.debtors/guarantors
## TRUE TRUE
## Present.residence.since Property
## FALSE TRUE
## Age.in.years Other.installment.plans
## FALSE TRUE
## Housing Number.of.existing.credits.at.this.bank
## TRUE FALSE
## Job Number.of.people.being.liable.to.provide.maintenance.for
## TRUE FALSE
## Telephone foreign.worker
## TRUE TRUE
## Good.Loan
## FALSE
names(l.char) <- NULL
l.char
## [1] TRUE FALSE TRUE TRUE FALSE TRUE TRUE FALSE TRUE TRUE FALSE TRUE FALSE TRUE TRUE FALSE TRUE FALSE TRUE TRUE FALSE
which(l.char)
## [1] 1 3 4 6 7 9 10 12 14 15 17 19 20
d.char <- subset(d.2, select = l.char)
str(d.char)
## 'data.frame': 1000 obs. of 13 variables:
## $ Status.of.existing.checking.account: chr "A11" "A12" "A14" "A11" ...
## $ Credit.history : chr "A34" "A32" "A34" "A32" ...
## $ Purpose : chr "A43" "A43" "A46" "A42" ...
## $ Savings account/bonds : chr "A65" "A61" "A61" "A61" ...
## $ Present.employment.since : chr "A75" "A73" "A74" "A74" ...
## $ Personal.status.and.sex : chr "A93" "A92" "A93" "A93" ...
## $ Other.debtors/guarantors : chr "A101" "A101" "A101" "A103" ...
## $ Property : chr "A121" "A121" "A121" "A122" ...
## $ Other.installment.plans : chr "A143" "A143" "A143" "A143" ...
## $ Housing : chr "A152" "A152" "A152" "A153" ...
## $ Job : chr "A173" "A173" "A172" "A173" ...
## $ Telephone : chr "A192" "A191" "A191" "A191" ...
## $ foreign.worker : chr "A201" "A201" "A201" "A201" ...
d.factor <- sapply(d.char, function(x) factor(as.character(mapping[x])), simplify=FALSE)
str(d.factor)
## List of 13
## $ Status.of.existing.checking.account: Factor w/ 4 levels "... < 0 DM","... >= 200 DM / salary assignments for at least 1 year",..: 1 3 4 1 1 4 4 3 4 3 ...
## $ Credit.history : Factor w/ 5 levels "all credits at this bank paid back duly",..: 2 4 2 4 3 4 4 4 4 2 ...
## $ Purpose : Factor w/ 10 levels "business","car (new)",..: 8 8 5 6 2 5 6 3 8 2 ...
## $ Savings account/bonds : Factor w/ 5 levels ".. >= 1000 DM",..: 5 2 2 2 2 5 4 2 1 2 ...
## $ Present.employment.since : Factor w/ 5 levels ".. >= 7 years",..: 1 3 4 4 3 3 1 3 4 5 ...
## $ Personal.status.and.sex : Factor w/ 4 levels "female : divorced/separated/married",..: 4 1 4 4 4 4 4 4 2 3 ...
## $ Other.debtors/guarantors : Factor w/ 3 levels "co-applicant",..: 3 3 3 2 3 3 3 3 3 3 ...
## $ Property : Factor w/ 4 levels "if not A121 : building society savings agreement/life insurance",..: 3 3 3 1 4 4 1 2 3 2 ...
## $ Other.installment.plans : Factor w/ 3 levels "bank","none",..: 2 2 2 2 2 2 2 2 2 2 ...
## $ Housing : Factor w/ 3 levels "for free","own",..: 2 2 2 1 1 1 2 3 2 2 ...
## $ Job : Factor w/ 4 levels "management/ self-employed/highly qualified employee/ officer",..: 2 2 4 2 2 4 2 1 4 1 ...
## $ Telephone : Factor w/ 2 levels "none","yes, registered under the customers name": 2 1 1 1 1 2 1 2 1 1 ...
## $ foreign.worker : Factor w/ 2 levels "no","yes": 2 2 2 2 2 2 2 2 2 2 ...
d.2[l.char] <- d.factor
str(d.2)
## 'data.frame': 1000 obs. of 21 variables:
## $ Status.of.existing.checking.account : Factor w/ 4 levels "... < 0 DM","... >= 200 DM / salary assignments for at least 1 year",..: 1 3 4 1 1 4 4 3 4 3 ...
## $ Duration.in.month : int 6 48 12 42 24 36 24 36 12 30 ...
## $ Credit.history : Factor w/ 5 levels "all credits at this bank paid back duly",..: 2 4 2 4 3 4 4 4 4 2 ...
## $ Purpose : Factor w/ 10 levels "business","car (new)",..: 8 8 5 6 2 5 6 3 8 2 ...
## $ Credit.amount : int 1169 5951 2096 7882 4870 9055 2835 6948 3059 5234 ...
## $ Savings account/bonds : Factor w/ 5 levels ".. >= 1000 DM",..: 5 2 2 2 2 5 4 2 1 2 ...
## $ Present.employment.since : Factor w/ 5 levels ".. >= 7 years",..: 1 3 4 4 3 3 1 3 4 5 ...
## $ Installment.rate.in.percentage.of.disposable.income : int 4 2 2 2 3 2 3 2 2 4 ...
## $ Personal.status.and.sex : Factor w/ 4 levels "female : divorced/separated/married",..: 4 1 4 4 4 4 4 4 2 3 ...
## $ Other.debtors/guarantors : Factor w/ 3 levels "co-applicant",..: 3 3 3 2 3 3 3 3 3 3 ...
## $ Present.residence.since : int 4 2 3 4 4 4 4 2 4 2 ...
## $ Property : Factor w/ 4 levels "if not A121 : building society savings agreement/life insurance",..: 3 3 3 1 4 4 1 2 3 2 ...
## $ Age.in.years : int 67 22 49 45 53 35 53 35 61 28 ...
## $ Other.installment.plans : Factor w/ 3 levels "bank","none",..: 2 2 2 2 2 2 2 2 2 2 ...
## $ Housing : Factor w/ 3 levels "for free","own",..: 2 2 2 1 1 1 2 3 2 2 ...
## $ Number.of.existing.credits.at.this.bank : int 2 1 1 1 2 1 1 1 1 2 ...
## $ Job : Factor w/ 4 levels "management/ self-employed/highly qualified employee/ officer",..: 2 2 4 2 2 4 2 1 4 1 ...
## $ Number.of.people.being.liable.to.provide.maintenance.for: int 1 1 2 2 2 2 1 1 1 1 ...
## $ Telephone : Factor w/ 2 levels "none","yes, registered under the customers name": 2 1 1 1 1 2 1 2 1 1 ...
## $ foreign.worker : Factor w/ 2 levels "no","yes": 2 2 2 2 2 2 2 2 2 2 ...
## $ Good.Loan : int 1 2 1 1 2 1 1 1 1 2 ...
d.2$Good.Loan <- factor(ifelse(d.2$Good.Loan == 1, "GoodLoan", "BadLoan"))
str(d.2)
## 'data.frame': 1000 obs. of 21 variables:
## $ Status.of.existing.checking.account : Factor w/ 4 levels "... < 0 DM","... >= 200 DM / salary assignments for at least 1 year",..: 1 3 4 1 1 4 4 3 4 3 ...
## $ Duration.in.month : int 6 48 12 42 24 36 24 36 12 30 ...
## $ Credit.history : Factor w/ 5 levels "all credits at this bank paid back duly",..: 2 4 2 4 3 4 4 4 4 2 ...
## $ Purpose : Factor w/ 10 levels "business","car (new)",..: 8 8 5 6 2 5 6 3 8 2 ...
## $ Credit.amount : int 1169 5951 2096 7882 4870 9055 2835 6948 3059 5234 ...
## $ Savings account/bonds : Factor w/ 5 levels ".. >= 1000 DM",..: 5 2 2 2 2 5 4 2 1 2 ...
## $ Present.employment.since : Factor w/ 5 levels ".. >= 7 years",..: 1 3 4 4 3 3 1 3 4 5 ...
## $ Installment.rate.in.percentage.of.disposable.income : int 4 2 2 2 3 2 3 2 2 4 ...
## $ Personal.status.and.sex : Factor w/ 4 levels "female : divorced/separated/married",..: 4 1 4 4 4 4 4 4 2 3 ...
## $ Other.debtors/guarantors : Factor w/ 3 levels "co-applicant",..: 3 3 3 2 3 3 3 3 3 3 ...
## $ Present.residence.since : int 4 2 3 4 4 4 4 2 4 2 ...
## $ Property : Factor w/ 4 levels "if not A121 : building society savings agreement/life insurance",..: 3 3 3 1 4 4 1 2 3 2 ...
## $ Age.in.years : int 67 22 49 45 53 35 53 35 61 28 ...
## $ Other.installment.plans : Factor w/ 3 levels "bank","none",..: 2 2 2 2 2 2 2 2 2 2 ...
## $ Housing : Factor w/ 3 levels "for free","own",..: 2 2 2 1 1 1 2 3 2 2 ...
## $ Number.of.existing.credits.at.this.bank : int 2 1 1 1 2 1 1 1 1 2 ...
## $ Job : Factor w/ 4 levels "management/ self-employed/highly qualified employee/ officer",..: 2 2 4 2 2 4 2 1 4 1 ...
## $ Number.of.people.being.liable.to.provide.maintenance.for: int 1 1 2 2 2 2 1 1 1 1 ...
## $ Telephone : Factor w/ 2 levels "none","yes, registered under the customers name": 2 1 1 1 1 2 1 2 1 1 ...
## $ foreign.worker : Factor w/ 2 levels "no","yes": 2 2 2 2 2 2 2 2 2 2 ...
## $ Good.Loan : Factor w/ 2 levels "BadLoan","GoodLoan": 2 1 2 2 1 2 2 2 2 1 ...
d[1:3, "Purpose"]
## [1] radio/television radio/television education
## 10 Levels: business car (new) car (used) domestic appliances education furniture/equipment others radio/television ... retraining
summary(d$Purpose)
## business car (new) car (used) domestic appliances education furniture/equipment
## 97 234 103 12 50 181
## others radio/television repairs retraining
## 12 280 22 9
(tbl <- table("Purpose" = d$Purpose, "Good Loan?" = d$Good.Loan))
## Good Loan?
## Purpose BadLoan GoodLoan
## business 34 63
## car (new) 89 145
## car (used) 17 86
## domestic appliances 4 8
## education 22 28
## furniture/equipment 58 123
## others 5 7
## radio/television 62 218
## repairs 8 14
## retraining 1 8
(tbl.df <- data.frame(tbl))
## Purpose Good.Loan. Freq
## 1 business BadLoan 34
## 2 car (new) BadLoan 89
## 3 car (used) BadLoan 17
## 4 domestic appliances BadLoan 4
## 5 education BadLoan 22
## 6 furniture/equipment BadLoan 58
## 7 others BadLoan 5
## 8 radio/television BadLoan 62
## 9 repairs BadLoan 8
## 10 retraining BadLoan 1
## 11 business GoodLoan 63
## 12 car (new) GoodLoan 145
## 13 car (used) GoodLoan 86
## 14 domestic appliances GoodLoan 8
## 15 education GoodLoan 28
## 16 furniture/equipment GoodLoan 123
## 17 others GoodLoan 7
## 18 radio/television GoodLoan 218
## 19 repairs GoodLoan 14
## 20 retraining GoodLoan 8
options(digits=2)
prop.table(table("Purpose" = d$Purpose, "Good Loan?" = d$Good.Loan), 1)
## Good Loan?
## Purpose BadLoan GoodLoan
## business 0.35 0.65
## car (new) 0.38 0.62
## car (used) 0.17 0.83
## domestic appliances 0.33 0.67
## education 0.44 0.56
## furniture/equipment 0.32 0.68
## others 0.42 0.58
## radio/television 0.22 0.78
## repairs 0.36 0.64
## retraining 0.11 0.89
library(ggplot2)
ggplot(d) + geom_bar(aes(x=Purpose, fill=Good.Loan))
ggplot(d) + geom_bar(aes(x=Purpose, fill=Good.Loan)) + coord_flip()
ggplot(d) + geom_bar(aes(x=Purpose, fill=Good.Loan), position="dodge")
ggplot(d) + geom_bar(aes(x=Purpose, fill=Good.Loan), position="dodge") + coord_flip()
ggplot(d) + geom_bar(aes(x=Purpose, fill=Good.Loan), position="fill")
ggplot(d) + geom_bar(aes(x=Purpose, fill=Good.Loan), position="fill") + coord_flip()
ggplot(d) + geom_bar(aes(x=Purpose, fill=Good.Loan), position="fill") + coord_flip() + ylab("Proportion")
tbl.df
## Purpose Good.Loan. Freq
## 1 business BadLoan 34
## 2 car (new) BadLoan 89
## 3 car (used) BadLoan 17
## 4 domestic appliances BadLoan 4
## 5 education BadLoan 22
## 6 furniture/equipment BadLoan 58
## 7 others BadLoan 5
## 8 radio/television BadLoan 62
## 9 repairs BadLoan 8
## 10 retraining BadLoan 1
## 11 business GoodLoan 63
## 12 car (new) GoodLoan 145
## 13 car (used) GoodLoan 86
## 14 domestic appliances GoodLoan 8
## 15 education GoodLoan 28
## 16 furniture/equipment GoodLoan 123
## 17 others GoodLoan 7
## 18 radio/television GoodLoan 218
## 19 repairs GoodLoan 14
## 20 retraining GoodLoan 8
names(tbl.df)[2] <- c("Status")
ggplot(tbl.df, aes(x=Purpose, y=Freq, fill=Status)) + geom_bar(stat="identity")
ggplot(tbl.df, aes(x=Purpose, y=Freq, fill=Status)) + geom_bar(stat="identity") +
coord_flip()
ggplot(tbl.df, aes(x=Purpose, y=Freq, fill=Status)) + geom_bar(stat="identity", position="dodge")
ggplot(tbl.df, aes(x=Purpose, y=Freq, fill=Status)) + geom_bar(stat="identity", position="dodge") +
coord_flip()
ggplot(tbl.df, aes(x=Purpose, y=Freq, fill=Status)) + geom_bar(stat="identity", position="fill")
ggplot(tbl.df, aes(x=Purpose, y=Freq, fill=Status)) + geom_bar(stat="identity", position="fill") +
coord_flip()
ggplot(tbl.df, aes(x=Purpose, y=Freq, fill=Status)) + geom_bar(stat="identity", position="fill") +
coord_flip() +
xlab("Purpose") + ylab("Proportion")
ggplot(tbl.df, aes(x=reorder(Purpose, Freq), y=Freq, fill=Status)) + geom_bar(stat="identity") +
coord_flip() +
xlab("Purpose")
theme.kr <- theme(axis.title.x = element_text(family="HCR Batang LVT"),
axis.title.y = element_text(family="HCR Batang LVT"),
axis.text.x = element_text(family="HCR Batang LVT"),
axis.text.y = element_text(family="HCR Batang LVT"),
plot.title = element_text(family="HCR Batang LVT"),
legend.title = element_text(family="HCR Batang LVT"),
legend.text = element_text(family="HCR Batang LVT"))
ggplot(d) + geom_bar(aes(x=Purpose, fill=Good.Loan), position="fill") + coord_flip() +
theme.kr +
ylab("비율") + xlab("대출목적") +
labs(fill="신용판정") +
ggtitle("대출 목적과 신용등급") +
scale_fill_discrete(labels=c("불량", "양호"))
ggplot(tbl.df, aes(x=reorder(Purpose, Freq), y=Freq, fill=Status)) + geom_bar(stat="identity") + coord_flip() +
theme.kr +
ylab("인원") + xlab("대출목적") +
labs(fill="신용판정") +
ggtitle("대출 목적과 신용등급") +
scale_fill_discrete(labels=c("불량", "양호"))
