-
Notifications
You must be signed in to change notification settings - Fork 0
/
R console
259 lines (240 loc) · 14.3 KB
/
R console
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
> library('openxlsx')
> library('C50')
> library('reshape2')
>
> #import data set
> dataCreditRating <- read.xlsx(xlsxFile = 'https://storage.googleapis.com/dqlab-dataset/credit_scoring_dqlab.xlsx')
Warning message:
In download.file(url = xlsxFile, destfile = tmpFile, cacheOK = FALSE, :
the 'wininet' method is deprecated for http:// and https:// URLs
> str(dataCreditRating)
'data.frame': 900 obs. of 7 variables:
$ kode_kontrak : chr "AGR-000001" "AGR-000011" "AGR-000030" "AGR-000043" ...
$ pendapatan_setahun_juta: num 295 271 159 210 165 220 70 88 163 100 ...
$ kpr_aktif : chr "YA" "YA" "TIDAK" "YA" ...
$ durasi_pinjaman_bulan : num 48 36 12 12 36 24 36 48 48 36 ...
$ jumlah_tanggungan : num 5 5 0 3 0 5 3 3 5 6 ...
$ rata_rata_overdue : chr "61 - 90 days" "61 - 90 days" "0 - 30 days" "46 - 60 days" ...
$ risk_rating : num 4 4 1 3 2 1 2 2 2 2 ...
>
>
> #dataCreditRating$risk_rating[dataCreditRating$risk_rating == '1'] <- 'satu'
> #dataCreditRating$risk_rating[dataCreditRating$risk_rating == '2'] <- 'dua'
> #dataCreditRating$risk_rating[dataCreditRating$risk_rating == '3'] <- 'tiga'
> #dataCreditRating$risk_rating[dataCreditRating$risk_rating == '4'] <- 'empat'
> #dataCreditRating$risk_rating[dataCreditRating$risk_rating == '5'] <- 'lima'
>
>
>
> #Convert the risk_rating column in a factor
> dataCreditRating$risk_rating <- as.factor(dataCreditRating$risk_rating)
> str(dataCreditRating)
'data.frame': 900 obs. of 7 variables:
$ kode_kontrak : chr "AGR-000001" "AGR-000011" "AGR-000030" "AGR-000043" ...
$ pendapatan_setahun_juta: num 295 271 159 210 165 220 70 88 163 100 ...
$ kpr_aktif : chr "YA" "YA" "TIDAK" "YA" ...
$ durasi_pinjaman_bulan : num 48 36 12 12 36 24 36 48 48 36 ...
$ jumlah_tanggungan : num 5 5 0 3 0 5 3 3 5 6 ...
$ rata_rata_overdue : chr "61 - 90 days" "61 - 90 days" "0 - 30 days" "46 - 60 days" ...
$ risk_rating : Factor w/ 5 levels "1","2","3","4",..: 4 4 1 3 2 1 2 2 2 2 ...
>
> #Remove some input variables from the dataset
> #drop_column <- c('pendapatan_setahun_juta','kpr_aktif','rata_rata_overdue','risk_rating')
> #datafeed <- dataCreditRating[,!names(dataCreditRating) %in% drop_column]
> #str(datafeed)
> input_columns <- c('jumlah_tanggungan','durasi_pinjaman_bulan')
> datafeed <- dataCreditRating[, input_columns]
> str(datafeed)
'data.frame': 900 obs. of 2 variables:
$ jumlah_tanggungan : num 5 5 0 3 0 5 3 3 5 6 ...
$ durasi_pinjaman_bulan: num 48 36 12 12 36 24 36 48 48 36 ...
>
> #Prepare random index portions for training and testing set
> set.seed(100)
> indeks_training_set <- sample(900,800) #90:10
>
> input_training_set <- datafeed[indeks_training_set,]
> input_testing_set <- datafeed[-indeks_training_set,]
> class_training_set <- dataCreditRating[indeks_training_set,]$risk_rating
>
>
> #Build a model decision tree for classification risk rating
> risk_rating_model <- C5.0(input_training_set, class_training_set, control=C5.0Control(label='Risk Rating'))
> summary(risk_rating_model)
Call:
C5.0.default(x = input_training_set, y = class_training_set, control = C5.0Control(label = "Risk Rating"))
C5.0 [Release 2.07 GPL Edition] Fri Apr 7 16:46:23 2023
-------------------------------
Class specified by attribute `Risk Rating'
Read 800 cases (3 attributes) from undefined.data
Decision tree:
jumlah_tanggungan > 4:
:...durasi_pinjaman_bulan <= 24: 4 (105/30)
: durasi_pinjaman_bulan > 24: 5 (120/51)
jumlah_tanggungan <= 4:
:...jumlah_tanggungan > 2: 3 (216/20)
jumlah_tanggungan <= 2:
:...durasi_pinjaman_bulan <= 36: 1 (264/80)
durasi_pinjaman_bulan > 36:
:...jumlah_tanggungan <= 0: 2 (37/7)
jumlah_tanggungan > 0: 3 (58/4)
Evaluation on training data (800 cases):
Decision Tree
----------------
Size Errors
6 192(24.0%) <<
(a) (b) (c) (d) (e) <-classified as
---- ---- ---- ---- ----
184 2 5 6 6 (a): class 1
80 30 19 6 11 (b): class 2
3 250 (c): class 3
2 75 34 (d): class 4
18 69 (e): class 5
Attribute usage:
100.00% jumlah_tanggungan
73.00% durasi_pinjaman_bulan
Time: 0.0 secs
> plot(risk_rating_model)
>
> #using the model for prediction testing
> predict(risk_rating_model,input_testing_set)
[1] 1 1 3 3 5 5 1 1 1 3 1 2 1 1 3 3 1 3 3 3 3 3 1 5 1 1 3 1 3 5 1 1 2 1 5 1 1 5 3 3 3 3 4 3 3 1 3 5 2 3 2 5 3 5 1 5
[57] 4 5 3 4 1 3 4 4 3 5 5 5 3 1 1 1 1 3 5 1 4 5 3 1 3 3 3 3 3 1 3 3 5 4 5 3 3 3 1 1 5 5 3 3
Levels: 1 2 3 4 5
>
> #comparison of the actual and prediction data for risk rating
> comparison_data <- input_testing_set
> comparison_data$actual_risk_rating <- dataCreditRating[-indeks_training_set,]$risk_rating
> comparison_data$prediction_results <- predict(risk_rating_model,input_testing_set)
> comparison_data
jumlah_tanggungan durasi_pinjaman_bulan actual_risk_rating prediction_results
3 0 12 1 1
5 0 36 2 1
8 3 48 2 3
40 3 36 2 3
41 6 48 2 5
44 5 48 2 5
58 0 12 1 1
70 0 12 1 1
109 0 12 1 1
110 4 12 3 3
122 0 12 1 1
151 0 48 2 2
179 1 36 1 1
180 1 36 2 1
182 4 24 3 3
195 3 48 3 3
200 0 24 1 1
217 4 12 3 3
230 2 48 3 3
231 3 12 3 3
234 3 24 3 3
236 4 24 3 3
238 0 24 1 1
245 5 36 4 5
252 0 24 1 1
253 0 24 1 1
260 1 48 3 3
265 0 36 2 1
275 3 12 3 3
279 6 36 5 5
285 1 36 1 1
295 0 24 1 1
317 0 48 2 2
343 0 24 1 1
350 6 48 5 5
352 1 12 1 1
356 2 36 2 1
369 6 48 5 5
373 3 48 3 3
375 2 48 3 3
384 3 24 3 3
388 3 36 3 3
399 6 24 4 4
419 3 48 3 3
433 4 24 3 3
437 1 36 1 1
446 3 24 3 3
455 5 48 5 5
493 0 48 2 2
496 3 12 3 3
501 0 48 3 2
521 5 48 4 5
524 2 48 3 3
527 5 36 5 5
534 1 36 1 1
536 6 48 5 5
544 5 12 4 4
548 6 48 5 5
561 3 12 3 3
565 6 12 4 4
574 1 24 1 1
577 2 48 3 3
587 6 12 4 4
594 6 12 4 4
612 4 24 3 3
616 6 48 5 5
621 5 36 5 5
632 6 48 5 5
641 4 36 3 3
645 2 12 2 1
657 2 12 1 1
675 2 12 1 1
687 2 12 1 1
697 4 36 3 3
704 6 48 5 5
707 2 12 1 1
716 5 12 4 4
721 5 36 5 5
729 1 48 3 3
737 2 12 1 1
743 3 36 3 3
748 1 48 3 3
749 4 36 3 3
786 1 48 3 3
799 3 12 3 3
801 2 24 1 1
806 4 24 3 3
814 3 36 3 3
825 6 36 5 5
831 6 24 4 4
861 5 48 5 5
863 3 12 3 3
869 3 48 3 3
870 3 48 3 3
872 2 24 1 1
880 1 36 2 1
888 5 48 5 5
890 5 48 5 5
893 3 48 3 3
897 2 48 3 3
>
> #make confusion matrix for the testing data set
> dcast(prediction_results~actual_risk_rating, data=comparison_data)
Using prediction_results as value column: use value.var to override.
Aggregation function missing: defaulting to length
prediction_results 1 2 3 4 5
1 1 24 6 0 0 0
2 2 0 3 1 0 0
3 3 0 2 37 0 0
4 4 0 0 0 7 0
5 5 0 2 0 2 16
>
> #calculating the number of correct prediction
> nrow(comparison_data[comparison_data$actual_risk_rating==comparison_data$prediction_results,])
[1] 87
> #calculating the number of wrong prediction
> nrow(comparison_data[comparison_data$actual_risk_rating!=comparison_data$prediction_results,])
[1] 13
>
> #if we have the new data and want to predict the new risk rating for the data
> new_data <- data.frame(jumlah_tanggungan=c(3,2,1,4,5), durasi_pinjaman_bulan=c(24,12,28,24,36))
> new_data$prediction_risk_rating <- predict(risk_rating_model,new_data)
> new_data
jumlah_tanggungan durasi_pinjaman_bulan prediction_risk_rating
1 3 24 3
2 2 12 1
3 1 28 1
4 4 24 3
5 5 36 5
>