CW041025

R Markdown

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:

library(readxl)

## Warning: package 'readxl' was built under R version 4.4.3

library(C50)

## Warning: package 'C50' was built under R version 4.4.3

library(readr)

## Warning: package 'readr' was built under R version 4.4.3

library(gmodels)

## Warning: package 'gmodels' was built under R version 4.4.3

credit <- read_csv("C:/Users/khalil2823/Downloads/credit.csv")

## Rows: 1000 Columns: 21
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (13): checking_balance, credit_history, purpose, savings_balance, employ...
## dbl  (8): months_loan_duration, amount, installment_rate, residence_history,...
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

credit_rand<-credit[order(runif(1000)),]
set.seed(12345)
credit_train <- credit_rand[1:900,]
credit_test<-credit_rand[901:1000,]
stringAsFactors=TRUE

prop.table(table(credit_train$default))

## 
##         1         2 
## 0.7066667 0.2933333

prop.table(table(credit_test$default))

## 
##    1    2 
## 0.64 0.36

credit_train$default <- as.factor(credit_train$default)
credit_test$default <-as.factor(credit_test$default)

credit_model<-C5.0(credit_train[-17], credit_train$default)
summary(credit_model)

## 
## Call:
## C5.0.default(x = credit_train[-17], y = credit_train$default)
## 
## 
## C5.0 [Release 2.07 GPL Edition]      Thu Apr 17 13:03:47 2025
## -------------------------------
## 
## Class specified by attribute `outcome'
## 
## Read 900 cases (21 attributes) from undefined.data
## 
## Decision tree:
## 
## checking_balance in {unknown,> 200 DM}: 1 (416/52)
## checking_balance in {1 - 200 DM,< 0 DM}:
## :...other_debtors = guarantor:
##     :...months_loan_duration <= 16: 1 (18)
##     :   months_loan_duration > 16:
##     :   :...dependents > 1: 1 (4)
##     :       dependents <= 1:
##     :       :...purpose in {business,car (new)}: 2 (3)
##     :           purpose in {education,repairs,furniture,others,car (used),
##     :           :           domestic appliances,retraining}: 1 (3)
##     :           purpose = radio/tv:
##     :           :...months_loan_duration <= 21: 1 (4)
##     :               months_loan_duration > 21: 2 (4)
##     other_debtors in {none,co-applicant}:
##     :...credit_history in {delayed,critical}:
##         :...savings_balance in {unknown,101 - 500 DM}: 1 (31/2)
##         :   savings_balance = > 1000 DM:
##         :   :...residence_history <= 3: 2 (3/1)
##         :   :   residence_history > 3: 1 (4)
##         :   savings_balance = 501 - 1000 DM:
##         :   :...months_loan_duration <= 21: 1 (3)
##         :   :   months_loan_duration > 21: 2 (2)
##         :   savings_balance = < 100 DM:
##         :   :...months_loan_duration <= 22: 1 (62/12)
##         :       months_loan_duration > 22:
##         :       :...existing_credits > 2: 1 (2)
##         :           existing_credits <= 2:
##         :           :...purpose in {business,education,furniture,car (new),
##         :               :           others,domestic appliances,
##         :               :           retraining}: 2 (22/4)
##         :               purpose = repairs: 1 (1)
##         :               purpose = radio/tv:
##         :               :...checking_balance = 1 - 200 DM: 1 (3)
##         :               :   checking_balance = < 0 DM: 2 (2)
##         :               purpose = car (used):
##         :               :...installment_rate <= 3: 1 (4)
##         :                   installment_rate > 3: 2 (3)
##         credit_history in {repaid,fully repaid this bank,fully repaid}:
##         :...savings_balance = 501 - 1000 DM: 1 (13/3)
##             savings_balance = > 1000 DM:
##             :...other_debtors = none: 1 (10)
##             :   other_debtors = co-applicant: 2 (1)
##             savings_balance = unknown:
##             :...checking_balance = 1 - 200 DM:
##             :   :...property = other: 1 (8)
##             :   :   property = building society savings:
##             :   :   :...residence_history <= 3: 2 (4/1)
##             :   :   :   residence_history > 3: 1 (3)
##             :   :   property = real estate:
##             :   :   :...age <= 30: 2 (2)
##             :   :   :   age > 30: 1 (3)
##             :   :   property = unknown/none:
##             :   :   :...installment_rate <= 2: 2 (2)
##             :   :       installment_rate > 2: 1 (5)
##             :   checking_balance = < 0 DM:
##             :   :...foreign_worker = no: 1 (2)
##             :       foreign_worker = yes:
##             :       :...months_loan_duration <= 13: 1 (3)
##             :           months_loan_duration > 13: 2 (18/5)
##             savings_balance in {< 100 DM,101 - 500 DM}:
##             :...months_loan_duration > 42:
##                 :...employment_length in {1 - 4 yrs,> 7 yrs,unemployed,
##                 :   :                     0 - 1 yrs}: 2 (19)
##                 :   employment_length = 4 - 7 yrs:
##                 :   :...residence_history <= 3: 1 (4/1)
##                 :       residence_history > 3: 2 (4)
##                 months_loan_duration <= 42:
##                 :...installment_rate <= 3:
##                     :...personal_status = divorced male: 2 (11/3)
##                     :   personal_status = married male: 1 (12/5)
##                     :   personal_status = female:
##                     :   :...employment_length in {unemployed,
##                     :   :   :                     4 - 7 yrs}: 1 (7/1)
##                     :   :   employment_length = 0 - 1 yrs: 2 (11/2)
##                     :   :   employment_length = 1 - 4 yrs: [S1]
##                     :   :   employment_length = > 7 yrs:
##                     :   :   :...checking_balance = 1 - 200 DM: 2 (3)
##                     :   :       checking_balance = < 0 DM: 1 (1)
##                     :   personal_status = single male:
##                     :   :...property = building society savings:
##                     :       :...installment_rate <= 2: 2 (6/1)
##                     :       :   installment_rate > 2: 1 (3)
##                     :       property = real estate:
##                     :       :...months_loan_duration <= 21: 1 (13)
##                     :       :   months_loan_duration > 21: 2 (2)
##                     :       property = other:
##                     :       :...other_debtors = co-applicant: 2 (1)
##                     :       :   other_debtors = none:
##                     :       :   :...age <= 25: 2 (3)
##                     :       :       age > 25: 1 (12/1)
##                     :       property = unknown/none:
##                     :       :...housing in {own,rent}: 2 (2)
##                     :           housing = for free:
##                     :           :...savings_balance = 101 - 500 DM: 2 (1)
##                     :               savings_balance = < 100 DM:
##                     :               :...installment_rate <= 2: 1 (6)
##                     :                   installment_rate > 2: 2 (3/1)
##                     installment_rate > 3:
##                     :...foreign_worker = no: 1 (2)
##                         foreign_worker = yes:
##                         :...credit_history = fully repaid: 2 (7)
##                             credit_history in {repaid,fully repaid this bank}:
##                             :...checking_balance = < 0 DM: 2 (53/12)
##                                 checking_balance = 1 - 200 DM:
##                                 :...installment_plan = bank: 2 (5)
##                                     installment_plan in {none,stores}: [S2]
## 
## SubTree [S1]
## 
## credit_history in {repaid,fully repaid this bank}: 2 (15/5)
## credit_history = fully repaid: 1 (2)
## 
## SubTree [S2]
## 
## other_debtors = co-applicant: 2 (1)
## other_debtors = none:
## :...residence_history > 3: 1 (8)
##     residence_history <= 3:
##     :...age > 32: 2 (6)
##         age <= 32:
##         :...installment_plan = none: 1 (8/2)
##             installment_plan = stores: 2 (1)
## 
## 
## Evaluation on training data (900 cases):
## 
##      Decision Tree   
##    ----------------  
##    Size      Errors  
## 
##      64  114(12.7%)   <<
## 
## 
##     (a)   (b)    <-classified as
##    ----  ----
##     601    35    (a): class 1
##      79   185    (b): class 2
## 
## 
##  Attribute usage:
## 
##  100.00% checking_balance
##   53.78% other_debtors
##   49.78% credit_history
##   49.78% savings_balance
##   43.67% months_loan_duration
##   24.33% installment_rate
##   12.67% personal_status
##   12.67% foreign_worker
##    8.78% property
##    7.33% employment_length
##    5.44% purpose
##    5.00% residence_history
##    4.11% existing_credits
##    3.89% age
##    3.22% installment_plan
##    2.00% dependents
##    1.33% housing
## 
## 
## Time: 0.0 secs

credit_pred <- predict(credit_model, credit_test[-17])

CrossTable(credit_test$default, credit_pred,
           prop.chisq = FALSE, prop.c = FALSE, prop.r = FALSE,
           dnn = c('Actual Default', 'Predicted Default'))

## 
##  
##    Cell Contents
## |-------------------------|
## |                       N |
## |         N / Table Total |
## |-------------------------|
## 
##  
## Total Observations in Table:  100 
## 
##  
##                | Predicted Default 
## Actual Default |         1 |         2 | Row Total | 
## ---------------|-----------|-----------|-----------|
##              1 |        54 |        10 |        64 | 
##                |     0.540 |     0.100 |           | 
## ---------------|-----------|-----------|-----------|
##              2 |        21 |        15 |        36 | 
##                |     0.210 |     0.150 |           | 
## ---------------|-----------|-----------|-----------|
##   Column Total |        75 |        25 |       100 | 
## ---------------|-----------|-----------|-----------|
## 
## 

matrix_dimensions <-list(c("no", "yes"), c("no", "yes"))
names(matrix_dimensions) <- c("predicted", "actual")

error_cost <- matrix(c(0,1,4,0), nrow = 2)

credit_cost <- C5.0(credit_train[-17], credit_train$default, costs = error_cost)

## Warning: no dimnames were given for the cost matrix; the factor levels will be
## used

credit_cost_pred <- predict(credit_cost, credit_test[-17])

CrossTable(credit_test$default, credit_cost_pred,
           prop.chisq = FALSE, prop.c = FALSE, prop.r = FALSE,
           dnn = c('Actual Default', 'Predicted Default'))

## 
##  
##    Cell Contents
## |-------------------------|
## |                       N |
## |         N / Table Total |
## |-------------------------|
## 
##  
## Total Observations in Table:  100 
## 
##  
##                | Predicted Default 
## Actual Default |         1 |         2 | Row Total | 
## ---------------|-----------|-----------|-----------|
##              1 |        32 |        32 |        64 | 
##                |     0.320 |     0.320 |           | 
## ---------------|-----------|-----------|-----------|
##              2 |         8 |        28 |        36 | 
##                |     0.080 |     0.280 |           | 
## ---------------|-----------|-----------|-----------|
##   Column Total |        40 |        60 |       100 | 
## ---------------|-----------|-----------|-----------|
## 
## 

Including Plots

You can also embed plots, for example:

Note that the echo = FALSE parameter was added to the code chunk to prevent printing of the R code that generated the plot.