This is an R Markdown document. Markdown is a simple formatting syntax for authoring HTML, PDF, and MS Word documents. For more details on using R Markdown see http://rmarkdown.rstudio.com.
When you click the Knit button a document will be generated that includes both content as well as the output of any embedded R code chunks within the document. You can embed an R code chunk like this:
summary(cars)## speed dist
## Min. : 4.0 Min. : 2.00
## 1st Qu.:12.0 1st Qu.: 26.00
## Median :15.0 Median : 36.00
## Mean :15.4 Mean : 42.98
## 3rd Qu.:19.0 3rd Qu.: 56.00
## Max. :25.0 Max. :120.00You can also embed plots, for example:
library(readr)
credit <- read.csv("C:/Users/nirma/Downloads/credit.csv", stringsAsFactors=TRUE)
View(credit)
#entropy
ColorG<--((1/3*log2(1/3)+2/3*log2(2/3)))
ColorG## [1] 0.9182958ColorY<--((8/13*log2(8/13)+5/13*log2(5/13)))
ColorY## [1] 0.9612366#ATTRIBUTE ENTROPY
str(credit)## 'data.frame': 1000 obs. of 17 variables:
## $ checking_balance : Factor w/ 4 levels "< 0 DM","> 200 DM",..: 1 3 4 1 1 4 4 3 4 3 ...
## $ months_loan_duration: int 6 48 12 42 24 36 24 36 12 30 ...
## $ credit_history : Factor w/ 5 levels "critical","good",..: 1 2 1 2 4 2 2 2 2 1 ...
## $ purpose : Factor w/ 6 levels "business","car",..: 5 5 4 5 2 4 5 2 5 2 ...
## $ amount : int 1169 5951 2096 7882 4870 9055 2835 6948 3059 5234 ...
## $ savings_balance : Factor w/ 5 levels "< 100 DM","> 1000 DM",..: 5 1 1 1 1 5 4 1 2 1 ...
## $ employment_duration : Factor w/ 5 levels "< 1 year","> 7 years",..: 2 3 4 4 3 3 2 3 4 5 ...
## $ percent_of_income : int 4 2 2 2 3 2 3 2 2 4 ...
## $ years_at_residence : int 4 2 3 4 4 4 4 2 4 2 ...
## $ age : int 67 22 49 45 53 35 53 35 61 28 ...
## $ other_credit : Factor w/ 3 levels "bank","none",..: 2 2 2 2 2 2 2 2 2 2 ...
## $ housing : Factor w/ 3 levels "other","own",..: 2 2 2 1 1 1 2 3 2 2 ...
## $ existing_loans_count: int 2 1 1 1 2 1 1 1 1 2 ...
## $ job : Factor w/ 4 levels "management","skilled",..: 2 2 4 2 2 4 2 1 4 1 ...
## $ dependents : int 1 1 2 2 2 2 1 1 1 1 ...
## $ phone : Factor w/ 2 levels "no","yes": 2 1 1 1 1 2 1 2 1 1 ...
## $ default : Factor w/ 2 levels "no","yes": 1 2 1 1 2 1 1 1 1 2 ...credit<-credit[-1001,]
credit[155, 1]=as.factor("1 - 200 DM")
credit[155,1]## [1] 1 - 200 DM
## Levels: < 0 DM > 200 DM 1 - 200 DM unknowntable(credit$checking_balance)##
## < 0 DM > 200 DM 1 - 200 DM unknown
## 274 63 269 394prop.table(table(credit$checking_balance))##
## < 0 DM > 200 DM 1 - 200 DM unknown
## 0.274 0.063 0.269 0.394str(credit$checking_balance)## Factor w/ 4 levels "< 0 DM","> 200 DM",..: 1 3 4 1 1 4 4 3 4 3 ...table(credit$savings_balance)##
## < 100 DM > 1000 DM 100 - 500 DM 500 - 1000 DM unknown
## 603 48 103 63 183prop.table(table(credit$savings_balance))##
## < 100 DM > 1000 DM 100 - 500 DM 500 - 1000 DM unknown
## 0.603 0.048 0.103 0.063 0.183summary(credit$months_loan_duration)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 4.0 12.0 18.0 20.9 24.0 72.0summary(credit$amount)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 250 1366 2320 3271 3972 18424str(credit$default)## Factor w/ 2 levels "no","yes": 1 2 1 1 2 1 1 1 1 2 ...credit$default<-factor(credit$default)
str(credit$default)## Factor w/ 2 levels "no","yes": 1 2 1 1 2 1 1 1 1 2 ...table(credit$default)##
## no yes
## 700 300prop.table(table(credit$default))##
## no yes
## 0.7 0.3set.seed(12345)
credit_rand<-credit[order(runif(1000)), ]
head(credit_rand)## checking_balance months_loan_duration credit_history purpose
## 14 < 0 DM 24 critical car
## 448 1 - 200 DM 7 good furniture/appliances
## 697 1 - 200 DM 12 good furniture/appliances
## 32 < 0 DM 24 good furniture/appliances
## 196 1 - 200 DM 9 critical education
## 83 unknown 18 good business
## amount savings_balance employment_duration percent_of_income
## 14 1199 < 100 DM > 7 years 4
## 448 2576 < 100 DM 1 - 4 years 2
## 697 1103 < 100 DM 4 - 7 years 4
## 32 4020 < 100 DM 1 - 4 years 2
## 196 1501 < 100 DM > 7 years 2
## 83 1568 100 - 500 DM 1 - 4 years 3
## years_at_residence age other_credit housing existing_loans_count job
## 14 4 60 none own 2 unskilled
## 448 2 35 none own 1 skilled
## 697 3 29 none own 2 skilled
## 32 2 27 store own 1 skilled
## 196 3 34 none own 2 management
## 83 4 24 none rent 1 unskilled
## dependents phone default
## 14 1 no yes
## 448 1 no no
## 697 1 no no
## 32 1 no no
## 196 1 yes yes
## 83 1 no nocredit_train <- credit_rand[1:900, ]
credit_test <- credit_rand[901:1000, ]
library(C50)## Warning: package 'C50' was built under R version 4.3.3m<-C5.0(credit_train, credit_train$default, trials=1, costs=NULL)
m##
## Call:
## C5.0.default(x = credit_train, y = credit_train$default, trials = 1, costs
## = NULL)
##
## Classification Tree
## Number of samples: 900
## Number of predictors: 17
##
## Tree size: 2
##
## Non-standard options: attempt to group attributesNote that the echo = FALSE parameter was added to the
code chunk to prevent printing of the R code that generated the
plot.