My Bank case study- Random Forest
Anand
December 9, 2017
Reading the file
setwd("E:/Great Lakes/Data Mining/Assignment")
ploan <- read.csv("PL_XSELL.csv",header=TRUE)converting to factor data type
ploan$FLG_HAS_ANY_CHGS <- as.factor(ploan$FLG_HAS_ANY_CHGS)
ploan$FLG_HAS_CC <- as.factor(ploan$FLG_HAS_CC)
ploan$FLG_HAS_NOMINEE <- as.factor(ploan$FLG_HAS_NOMINEE)
ploan$FLG_HAS_OLD_LOAN <- as.factor(ploan$FLG_HAS_OLD_LOAN)
ploan$ACC_OP_DATE <- as.Date(ploan$ACC_OP_DATE, format = "%m/%d/%Y")checking for missing values
library(VIM)## Warning: package 'VIM' was built under R version 3.4.3## Loading required package: colorspace## Loading required package: grid## Loading required package: data.table## Warning: package 'data.table' was built under R version 3.4.3## VIM is ready to use.
## Since version 4.0.0 the GUI is in its own package VIMGUI.
##
## Please use the package to use the new (and old) GUI.## Suggestions and bug-reports can be submitted at: https://github.com/alexkowa/VIM/issues##
## Attaching package: 'VIM'## The following object is masked from 'package:datasets':
##
## sleepaggr(ploan,prop = F,cex.axis = 0.4,numbers=T)
feature engineering
quantile(ploan$BALANCE)## 0% 25% 50% 75% 100%
## 0.00 64754.03 231675.85 653876.85 8360430.57ploan$LOW_BAL <- ifelse(ploan$BALANCE < 231676 ,0,1)
lowbal<- ifelse (ploan$LOW_BAL == 0 & ploan$TARGET == 1,1,0)
totbal <- sum(lowbal)
prebal <- (totbal/2512)*100
quantile(ploan$HOLDING_PERIOD)## 0% 25% 50% 75% 100%
## 1 7 15 22 31ploan$LOW_BAL <- as.factor(ploan$LOW_BAL)
ploan$LOW_HOLD <- ifelse(ploan$HOLDING_PERIOD < 15 ,0,1)
lowhold <- ifelse (ploan$LOW_HOLD == 0 & ploan$TARGET == 1,1,0)
tothold <- sum(lowhold)
prehold <- (tothold/2512)*100
ploan$LOW_HOLD <- as.factor(ploan$LOW_HOLD)response rate
resprate <- (sum(ploan$TARGET)/nrow(ploan))* 100
resprate## [1] 12.56descriptive stastics
summary(ploan)## CUST_ID TARGET AGE GENDER
## C1 : 1 Min. :0.0000 Min. :21.00 F: 5433
## C10 : 1 1st Qu.:0.0000 1st Qu.:30.00 M:14376
## C100 : 1 Median :0.0000 Median :38.00 O: 191
## C1000 : 1 Mean :0.1256 Mean :38.42
## C10000 : 1 3rd Qu.:0.0000 3rd Qu.:46.00
## C10001 : 1 Max. :1.0000 Max. :55.00
## (Other):19994
## BALANCE OCCUPATION AGE_BKT SCR
## Min. : 0 PROF :5417 <25 :1753 Min. :100.0
## 1st Qu.: 64754 SAL :5855 >50 :3035 1st Qu.:227.0
## Median : 231676 SELF-EMP:3568 26-30:3434 Median :364.0
## Mean : 511362 SENP :5160 31-35:3404 Mean :440.2
## 3rd Qu.: 653877 36-40:2814 3rd Qu.:644.0
## Max. :8360431 41-45:3067 Max. :999.0
## 46-50:2493
## HOLDING_PERIOD ACC_TYPE ACC_OP_DATE LEN_OF_RLTN_IN_MNTH
## Min. : 1.00 CA: 4241 Min. :1999-01-02 Min. : 29.0
## 1st Qu.: 7.00 SA:15759 1st Qu.:2003-01-26 1st Qu.: 79.0
## Median :15.00 Median :2006-12-23 Median :125.0
## Mean :14.96 Mean :2006-12-25 Mean :125.2
## 3rd Qu.:22.00 3rd Qu.:2010-11-16 3rd Qu.:172.0
## Max. :31.00 Max. :2015-01-01 Max. :221.0
##
## NO_OF_L_CR_TXNS NO_OF_L_DR_TXNS TOT_NO_OF_L_TXNS
## Min. : 0.00 Min. : 0.000 Min. : 0.00
## 1st Qu.: 6.00 1st Qu.: 2.000 1st Qu.: 9.00
## Median :10.00 Median : 5.000 Median : 14.00
## Mean :12.35 Mean : 6.634 Mean : 18.98
## 3rd Qu.:14.00 3rd Qu.: 7.000 3rd Qu.: 21.00
## Max. :75.00 Max. :74.000 Max. :149.00
##
## NO_OF_BR_CSH_WDL_DR_TXNS NO_OF_ATM_DR_TXNS NO_OF_NET_DR_TXNS
## Min. : 0.000 Min. : 0.000 Min. : 0.000
## 1st Qu.: 1.000 1st Qu.: 0.000 1st Qu.: 0.000
## Median : 1.000 Median : 1.000 Median : 0.000
## Mean : 1.883 Mean : 1.029 Mean : 1.172
## 3rd Qu.: 2.000 3rd Qu.: 1.000 3rd Qu.: 1.000
## Max. :15.000 Max. :25.000 Max. :22.000
##
## NO_OF_MOB_DR_TXNS NO_OF_CHQ_DR_TXNS FLG_HAS_CC AMT_ATM_DR
## Min. : 0.0000 Min. : 0.000 0:13892 Min. : 0
## 1st Qu.: 0.0000 1st Qu.: 0.000 1: 6108 1st Qu.: 0
## Median : 0.0000 Median : 2.000 Median : 6900
## Mean : 0.4118 Mean : 2.138 Mean : 10990
## 3rd Qu.: 0.0000 3rd Qu.: 4.000 3rd Qu.: 15800
## Max. :25.0000 Max. :15.000 Max. :199300
##
## AMT_BR_CSH_WDL_DR AMT_CHQ_DR AMT_NET_DR AMT_MOB_DR
## Min. : 0 Min. : 0 Min. : 0 Min. : 0
## 1st Qu.: 2990 1st Qu.: 0 1st Qu.: 0 1st Qu.: 0
## Median :340150 Median : 23840 Median : 0 Median : 0
## Mean :378475 Mean : 124520 Mean :237308 Mean : 22425
## 3rd Qu.:674675 3rd Qu.: 72470 3rd Qu.:473971 3rd Qu.: 0
## Max. :999930 Max. :4928640 Max. :999854 Max. :199667
##
## AMT_L_DR FLG_HAS_ANY_CHGS AMT_OTH_BK_ATM_USG_CHGS
## Min. : 0 0:17788 Min. : 0.000
## 1st Qu.: 237936 1: 2212 1st Qu.: 0.000
## Median : 695115 Median : 0.000
## Mean : 773717 Mean : 1.099
## 3rd Qu.:1078927 3rd Qu.: 0.000
## Max. :6514921 Max. :250.000
##
## AMT_MIN_BAL_NMC_CHGS NO_OF_IW_CHQ_BNC_TXNS NO_OF_OW_CHQ_BNC_TXNS
## Min. : 0.000 Min. :0.00000 Min. :0.0000
## 1st Qu.: 0.000 1st Qu.:0.00000 1st Qu.:0.0000
## Median : 0.000 Median :0.00000 Median :0.0000
## Mean : 1.292 Mean :0.04275 Mean :0.0444
## 3rd Qu.: 0.000 3rd Qu.:0.00000 3rd Qu.:0.0000
## Max. :170.000 Max. :2.00000 Max. :2.0000
##
## AVG_AMT_PER_ATM_TXN AVG_AMT_PER_CSH_WDL_TXN AVG_AMT_PER_CHQ_TXN
## Min. : 0 Min. : 0 Min. : 0
## 1st Qu.: 0 1st Qu.: 1266 1st Qu.: 0
## Median : 6000 Median :147095 Median : 8645
## Mean : 7409 Mean :242237 Mean : 25093
## 3rd Qu.:13500 3rd Qu.:385000 3rd Qu.: 28605
## Max. :25000 Max. :999640 Max. :537842
##
## AVG_AMT_PER_NET_TXN AVG_AMT_PER_MOB_TXN FLG_HAS_NOMINEE FLG_HAS_OLD_LOAN
## Min. : 0 Min. : 0 0: 1977 0:10141
## 1st Qu.: 0 1st Qu.: 0 1:18023 1: 9859
## Median : 0 Median : 0
## Mean :179059 Mean : 20304
## 3rd Qu.:257699 3rd Qu.: 0
## Max. :999854 Max. :199667
##
## random LOW_BAL LOW_HOLD
## Min. :0.0000114 0:10000 0: 9726
## 1st Qu.:0.2481866 1:10000 1:10274
## Median :0.5061214
## Mean :0.5019330
## 3rd Qu.:0.7535712
## Max. :0.9999471
## str(ploan)## 'data.frame': 20000 obs. of 42 variables:
## $ CUST_ID : Factor w/ 20000 levels "C1","C10","C100",..: 17699 16532 11027 17984 2363 11747 18115 15556 15216 12494 ...
## $ TARGET : int 0 0 0 0 0 0 0 0 0 0 ...
## $ AGE : int 27 47 40 53 36 42 30 53 42 30 ...
## $ GENDER : Factor w/ 3 levels "F","M","O": 2 2 2 2 2 1 2 1 1 2 ...
## $ BALANCE : num 3384 287489 18217 71720 1671623 ...
## $ OCCUPATION : Factor w/ 4 levels "PROF","SAL","SELF-EMP",..: 3 2 3 2 1 1 1 2 3 1 ...
## $ AGE_BKT : Factor w/ 7 levels "<25",">50","26-30",..: 3 7 5 2 5 6 3 2 6 3 ...
## $ SCR : int 776 324 603 196 167 493 479 562 105 170 ...
## $ HOLDING_PERIOD : int 30 28 2 13 24 26 14 25 15 13 ...
## $ ACC_TYPE : Factor w/ 2 levels "CA","SA": 2 2 2 1 2 2 2 1 2 2 ...
## $ ACC_OP_DATE : Date, format: "2005-03-23" "2008-10-11" ...
## $ LEN_OF_RLTN_IN_MNTH : int 146 104 61 107 185 192 177 99 88 111 ...
## $ NO_OF_L_CR_TXNS : int 7 8 10 36 20 5 6 14 18 14 ...
## $ NO_OF_L_DR_TXNS : int 3 2 5 14 1 2 6 3 14 8 ...
## $ TOT_NO_OF_L_TXNS : int 10 10 15 50 21 7 12 17 32 22 ...
## $ NO_OF_BR_CSH_WDL_DR_TXNS: int 0 0 1 4 1 1 0 3 6 3 ...
## $ NO_OF_ATM_DR_TXNS : int 1 1 1 2 0 1 1 0 2 1 ...
## $ NO_OF_NET_DR_TXNS : int 2 1 1 3 0 0 1 0 4 0 ...
## $ NO_OF_MOB_DR_TXNS : int 0 0 0 1 0 0 0 0 1 0 ...
## $ NO_OF_CHQ_DR_TXNS : int 0 0 2 4 0 0 4 0 1 4 ...
## $ FLG_HAS_CC : Factor w/ 2 levels "0","1": 1 1 1 1 1 2 1 1 2 1 ...
## $ AMT_ATM_DR : int 13100 6600 11200 26100 0 18500 6200 0 35400 18000 ...
## $ AMT_BR_CSH_WDL_DR : int 0 0 561120 673590 808480 379310 0 945160 198430 869880 ...
## $ AMT_CHQ_DR : int 0 0 49320 60780 0 0 10580 0 51490 32610 ...
## $ AMT_NET_DR : num 973557 799813 997570 741506 0 ...
## $ AMT_MOB_DR : int 0 0 0 71388 0 0 0 0 170332 0 ...
## $ AMT_L_DR : num 986657 806413 1619210 1573364 808480 ...
## $ FLG_HAS_ANY_CHGS : Factor w/ 2 levels "0","1": 1 2 2 1 1 1 2 1 1 1 ...
## $ AMT_OTH_BK_ATM_USG_CHGS : int 0 0 0 0 0 0 0 0 0 0 ...
## $ AMT_MIN_BAL_NMC_CHGS : int 0 0 0 0 0 0 0 0 0 0 ...
## $ NO_OF_IW_CHQ_BNC_TXNS : int 0 0 0 0 0 0 0 0 0 0 ...
## $ NO_OF_OW_CHQ_BNC_TXNS : int 0 0 1 0 0 0 0 0 0 0 ...
## $ AVG_AMT_PER_ATM_TXN : num 13100 6600 11200 13050 0 ...
## $ AVG_AMT_PER_CSH_WDL_TXN : num 0 0 561120 168398 808480 ...
## $ AVG_AMT_PER_CHQ_TXN : num 0 0 24660 15195 0 ...
## $ AVG_AMT_PER_NET_TXN : num 486779 799813 997570 247169 0 ...
## $ AVG_AMT_PER_MOB_TXN : num 0 0 0 71388 0 ...
## $ FLG_HAS_NOMINEE : Factor w/ 2 levels "0","1": 2 2 2 2 2 2 1 2 2 1 ...
## $ FLG_HAS_OLD_LOAN : Factor w/ 2 levels "0","1": 2 1 2 1 1 2 2 2 2 1 ...
## $ random : num 1.14e-05 1.11e-04 1.20e-04 1.37e-04 1.74e-04 ...
## $ LOW_BAL : Factor w/ 2 levels "0","1": 1 2 1 1 2 2 1 1 1 2 ...
## $ LOW_HOLD : Factor w/ 2 levels "0","1": 2 2 1 1 2 2 1 2 2 1 ...dim(ploan)## [1] 20000 42library(psych)
describe(ploan)## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning
## Inf## Warning in FUN(newX[, i], ...): no non-missing arguments to max; returning
## -Inf## vars n mean sd median
## CUST_ID* 1 20000 10000.50 5773.65 10000.50
## TARGET 2 20000 0.13 0.33 0.00
## AGE 3 20000 38.42 9.58 38.00
## GENDER* 4 20000 1.74 0.46 2.00
## BALANCE 5 20000 511362.19 723592.96 231675.85
## OCCUPATION* 6 20000 2.42 1.14 2.00
## AGE_BKT* 7 20000 4.08 1.85 4.00
## SCR 8 20000 440.15 249.89 364.00
## HOLDING_PERIOD 9 20000 14.96 8.64 15.00
## ACC_TYPE* 10 20000 1.79 0.41 2.00
## ACC_OP_DATE* 11 20000 NaN NA NA
## LEN_OF_RLTN_IN_MNTH 12 20000 125.24 54.95 125.00
## NO_OF_L_CR_TXNS 13 20000 12.35 12.15 10.00
## NO_OF_L_DR_TXNS 14 20000 6.63 7.68 5.00
## TOT_NO_OF_L_TXNS 15 20000 18.98 17.76 14.00
## NO_OF_BR_CSH_WDL_DR_TXNS 16 20000 1.88 2.26 1.00
## NO_OF_ATM_DR_TXNS 17 20000 1.03 1.50 1.00
## NO_OF_NET_DR_TXNS 18 20000 1.17 2.40 0.00
## NO_OF_MOB_DR_TXNS 19 20000 0.41 2.01 0.00
## NO_OF_CHQ_DR_TXNS 20 20000 2.14 2.38 2.00
## FLG_HAS_CC* 21 20000 1.31 0.46 1.00
## AMT_ATM_DR 22 20000 10990.01 15304.89 6900.00
## AMT_BR_CSH_WDL_DR 23 20000 378474.48 331417.73 340150.00
## AMT_CHQ_DR 24 20000 124520.01 439379.54 23840.00
## AMT_NET_DR 25 20000 237307.77 319067.66 0.00
## AMT_MOB_DR 26 20000 22424.70 49484.80 0.00
## AMT_L_DR 27 20000 773716.97 712659.17 695115.00
## FLG_HAS_ANY_CHGS* 28 20000 1.11 0.31 1.00
## AMT_OTH_BK_ATM_USG_CHGS 29 20000 1.10 14.22 0.00
## AMT_MIN_BAL_NMC_CHGS 30 20000 1.29 14.76 0.00
## NO_OF_IW_CHQ_BNC_TXNS 31 20000 0.04 0.20 0.00
## NO_OF_OW_CHQ_BNC_TXNS 32 20000 0.04 0.21 0.00
## AVG_AMT_PER_ATM_TXN 33 20000 7408.84 7210.17 6000.00
## AVG_AMT_PER_CSH_WDL_TXN 34 20000 242236.48 269837.89 147095.00
## AVG_AMT_PER_CHQ_TXN 35 20000 25092.48 49387.20 8645.00
## AVG_AMT_PER_NET_TXN 36 20000 179059.03 281706.86 0.00
## AVG_AMT_PER_MOB_TXN 37 20000 20303.92 46472.89 0.00
## FLG_HAS_NOMINEE* 38 20000 1.90 0.30 2.00
## FLG_HAS_OLD_LOAN* 39 20000 1.49 0.50 1.00
## random 40 20000 0.50 0.29 0.51
## LOW_BAL* 41 20000 1.50 0.50 1.50
## LOW_HOLD* 42 20000 1.51 0.50 2.00
## trimmed mad min max range skew
## CUST_ID* 10000.50 7413.00 1 20000.0 19999.0 0.00
## TARGET 0.03 0.00 0 1.0 1.0 2.26
## AGE 38.33 11.86 21 55.0 34.0 0.09
## GENDER* 1.79 0.00 1 3.0 2.0 -0.79
## BALANCE 353637.08 294970.24 0 8360430.6 8360430.6 2.78
## OCCUPATION* 2.40 1.48 1 4.0 3.0 0.16
## AGE_BKT* 4.09 2.97 1 7.0 6.0 0.02
## SCR 420.92 262.42 100 999.0 899.0 0.56
## HOLDING_PERIOD 14.84 10.38 1 31.0 30.0 0.07
## ACC_TYPE* 1.86 0.00 1 2.0 1.0 -1.41
## ACC_OP_DATE* NaN NA Inf -Inf -Inf NA
## LEN_OF_RLTN_IN_MNTH 125.26 69.68 29 221.0 192.0 0.00
## NO_OF_L_CR_TXNS 10.01 5.93 0 75.0 75.0 2.46
## NO_OF_L_DR_TXNS 5.21 2.97 0 74.0 74.0 3.92
## TOT_NO_OF_L_TXNS 15.77 8.90 0 149.0 149.0 2.81
## NO_OF_BR_CSH_WDL_DR_TXNS 1.42 1.48 0 15.0 15.0 2.34
## NO_OF_ATM_DR_TXNS 0.87 1.48 0 25.0 25.0 8.47
## NO_OF_NET_DR_TXNS 0.60 0.00 0 22.0 22.0 4.24
## NO_OF_MOB_DR_TXNS 0.16 0.00 0 25.0 25.0 11.02
## NO_OF_CHQ_DR_TXNS 1.75 2.97 0 15.0 15.0 1.56
## FLG_HAS_CC* 1.26 0.00 1 2.0 1.0 0.84
## AMT_ATM_DR 7968.07 10229.94 0 199300.0 199300.0 3.65
## AMT_BR_CSH_WDL_DR 356596.13 497871.91 0 999930.0 999930.0 0.31
## AMT_CHQ_DR 33171.50 35345.18 0 4928640.0 4928640.0 7.18
## AMT_NET_DR 185143.02 0.00 0 999854.0 999854.0 1.00
## AMT_MOB_DR 8796.85 0.00 0 199667.0 199667.0 2.16
## AMT_L_DR 689894.96 628954.50 0 6514921.0 6514921.0 2.53
## FLG_HAS_ANY_CHGS* 1.01 0.00 1 2.0 1.0 2.48
## AMT_OTH_BK_ATM_USG_CHGS 0.00 0.00 0 250.0 250.0 14.07
## AMT_MIN_BAL_NMC_CHGS 0.00 0.00 0 170.0 170.0 11.34
## NO_OF_IW_CHQ_BNC_TXNS 0.00 0.00 0 2.0 2.0 4.57
## NO_OF_OW_CHQ_BNC_TXNS 0.00 0.00 0 2.0 2.0 4.44
## AVG_AMT_PER_ATM_TXN 6714.08 8895.60 0 25000.0 25000.0 0.51
## AVG_AMT_PER_CSH_WDL_TXN 197101.27 218083.05 0 999640.0 999640.0 1.14
## AVG_AMT_PER_CHQ_TXN 14036.18 12817.08 0 537842.2 537842.2 4.52
## AVG_AMT_PER_NET_TXN 118388.89 0.00 0 999854.0 999854.0 1.50
## AVG_AMT_PER_MOB_TXN 7187.16 0.00 0 199667.0 199667.0 2.34
## FLG_HAS_NOMINEE* 2.00 0.00 1 2.0 1.0 -2.69
## FLG_HAS_OLD_LOAN* 1.49 0.00 1 2.0 1.0 0.03
## random 0.50 0.37 0 1.0 1.0 -0.02
## LOW_BAL* 1.50 0.74 1 2.0 1.0 0.00
## LOW_HOLD* 1.52 0.00 1 2.0 1.0 -0.05
## kurtosis se
## CUST_ID* -1.20 40.83
## TARGET 3.10 0.00
## AGE -1.16 0.07
## GENDER* -0.61 0.00
## BALANCE 10.61 5116.57
## OCCUPATION* -1.39 0.01
## AGE_BKT* -1.12 0.01
## SCR -0.94 1.77
## HOLDING_PERIOD -1.10 0.06
## ACC_TYPE* -0.02 0.00
## ACC_OP_DATE* NA NA
## LEN_OF_RLTN_IN_MNTH -1.18 0.39
## NO_OF_L_CR_TXNS 7.05 0.09
## NO_OF_L_DR_TXNS 23.77 0.05
## TOT_NO_OF_L_TXNS 11.87 0.13
## NO_OF_BR_CSH_WDL_DR_TXNS 6.46 0.02
## NO_OF_ATM_DR_TXNS 102.86 0.01
## NO_OF_NET_DR_TXNS 25.25 0.02
## NO_OF_MOB_DR_TXNS 126.87 0.01
## NO_OF_CHQ_DR_TXNS 3.07 0.02
## FLG_HAS_CC* -1.29 0.00
## AMT_ATM_DR 25.73 108.22
## AMT_BR_CSH_WDL_DR -1.32 2343.48
## AMT_CHQ_DR 59.45 3106.88
## AMT_NET_DR -0.49 2256.15
## AMT_MOB_DR 3.39 349.91
## AMT_L_DR 12.74 5039.26
## FLG_HAS_ANY_CHGS* 4.17 0.00
## AMT_OTH_BK_ATM_USG_CHGS 206.79 0.10
## AMT_MIN_BAL_NMC_CHGS 126.57 0.10
## NO_OF_IW_CHQ_BNC_TXNS 19.27 0.00
## NO_OF_OW_CHQ_BNC_TXNS 17.83 0.00
## AVG_AMT_PER_ATM_TXN -1.05 50.98
## AVG_AMT_PER_CSH_WDL_TXN 0.30 1908.04
## AVG_AMT_PER_CHQ_TXN 27.72 349.22
## AVG_AMT_PER_NET_TXN 0.92 1991.97
## AVG_AMT_PER_MOB_TXN 4.36 328.61
## FLG_HAS_NOMINEE* 5.23 0.00
## FLG_HAS_OLD_LOAN* -2.00 0.00
## random -1.21 0.00
## LOW_BAL* -2.00 0.00
## LOW_HOLD* -2.00 0.00par(mfrow=c(2, 2), oma=c(0,0,3,0))
plot(ploan$BALANCE ~ ploan$TARGET,xlab='TARGET', ylab='BALANCE')
plot(ploan$SCR~ ploan$TARGET,xlab='TARGET', ylab='SCR')
plot(ploan$TOT_NO_OF_L_TXNS ~ ploan$TARGET,xlab='TARGET', ylab='NO_OF_ATM_DR_TXNS')
plot(ploan$NO_OF_ATM_DR_TXNS ~ ploan$TARGET,xlab='TARGET', ylab='TOT_NO_OF_L_TXNS')
plot(ploan$NO_OF_NET_DR_TXNS ~ ploan$TARGET,xlab='TARGET', ylab='NO_OF_NET_DR_TXNS')
plot(ploan$NO_OF_CHQ_DR_TXNS ~ ploan$TARGET,xlab='TARGET', ylab='NO_OF_CHQ_DR_TXNS')
plot(ploan$NO_OF_L_CR_TXNS ~ ploan$TARGET,xlab='TARGET', ylab='NO_OF_L_CR_TXNS')
plot(ploan$HOLDING_PERIOD ~ ploan$TARGET,xlab='TARGET', ylab='HOLDING_PERIOD')
plot(ploan$NO_OF_L_DR_TXNS ~ ploan$TARGET,xlab='TARGET', ylab='NO_OF_L_DR_TXNS')
plot(ploan$AMT_L_DR ~ ploan$TARGET,xlab='TARGET', ylab='AMT_L_DR')
plot(ploan$AMT_BR_CSH_WDL_DR ~ ploan$TARGET,xlab='TARGET', ylab='AMT_BR_CSH_WDL_DR')
plot(ploan$OCCUPATION ~ ploan$TARGET,xlab='TARGET', ylab='OCCUPATION')
plot(ploan$AGE_BKT ~ ploan$TARGET,xlab='TARGET', ylab='AGE_BKT')
plot(ploan$FLG_HAS_CC ~ ploan$TARGET,xlab='TARGET', ylab='FLG_HAS_CC')
plot(ploan$GENDER ~ ploan$TARGET,xlab='TARGET', ylab='GENDER')
plot(ploan$TOT_NO_OF_L_TXNS ~ ploan$TARGET,xlab='TARGET', ylab='TOT_NO_OF_L_TXNS')
boxplot(ploan$BALANCE,main ="BALANCE")
boxplot(ploan$SCR,main ="SCR")
boxplot(ploan$TOT_NO_OF_L_TXNS,main ="TOT_NO_OF_L_TXNS")
boxplot(ploan$NO_OF_L_CR_TXNS,main = "NO_OF_L_CR_TXNS")
boxplot(ploan$NO_OF_ATM_DR_TXNS,main = "NO_OF_ATM_DR_TXNS")
boxplot(ploan$NO_OF_NET_DR_TXNS,main = "NO_OF_NET_DR_TXNS")
boxplot(ploan$NO_OF_CHQ_DR_TXNS,main = "NO_OF_CHQ_DR_TXNS ")
boxplot(ploan$NO_OF_L_CR_TXNS,main = "NO_OF_L_CR_TXNS")
hist(ploan$BALANCE,main ="BALANCE", xlab=NA, ylab=NA)
hist(ploan$SCR,main ="SCR", xlab=NA, ylab=NA)
hist(ploan$TOT_NO_OF_L_TXNS,main ="TOT_NO_OF_L_TXNS", xlab=NA, ylab=NA)
hist(ploan$NO_OF_L_CR_TXNS,main = "NO_OF_L_CR_TXNS", xlab=NA, ylab=NA)
hist(ploan$NO_OF_ATM_DR_TXNS,main ="NO_OF_ATM_DR_TXNS", xlab=NA, ylab=NA)
hist(ploan$NO_OF_NET_DR_TXNS,main ="NO_OF_NET_DR_TXNS", xlab=NA, ylab=NA)
hist(ploan$NO_OF_NET_DR_TXNS,main ="NO_OF_NET_DR_TXNS", xlab=NA, ylab=NA)
hist(ploan$NO_OF_L_CR_TXNS,main ="NO_OF_L_CR_TXNS", xlab=NA, ylab=NA)
boxplot(ploan$HOLDING_PERIOD,main="HOLDING_PERIOD")
boxplot(ploan$NO_OF_L_DR_TXNS,main="NO_OF_L_DR_TXNS")
boxplot(ploan$AMT_L_DR,main="AMT_L_DR")
boxplot(ploan$AMT_BR_CSH_WDL_DR ,main="AMT_BR_CSH_WDL_DR ")
hist(ploan$HOLDING_PERIOD,main="HOLDING_PERIOD", xlab=NA, ylab=NA)
hist(ploan$NO_OF_L_DR_TXNS,main="NO_OF_L_DR_TXNS", xlab=NA, ylab=NA)
hist(ploan$AMT_L_DR,main="AMT_L_DR", xlab=NA, ylab=NA)
hist(ploan$AMT_BR_CSH_WDL_DR ,main="AMT_BR_CSH_WDL_DR ", xlab=NA, ylab=NA)
plot(ploan$OCCUPATION,main="OCCUPATION", xlab=NA, ylab=NA)
plot(ploan$AGE_BKT,main="AGE_BKT", xlab=NA, ylab=NA)
plot(ploan$FLG_HAS_CC,main="FLG_HAS_CC", xlab=NA, ylab=NA)
plot(ploan$GENDER,main="GENDER", xlab=NA, ylab=NA)
Bivariate analysis
library(corrplot)## Warning: package 'corrplot' was built under R version 3.4.2## corrplot 0.84 loadedpl1 <- subset(ploan[c(1,2,4,6,7,10,11,21,28,38,39,41,42)])
pl2 <- subset(ploan[-c(1,2,4,6,7,10,11,21,28,38,39,41,42)])
corx <- cor(pl2)
corrplot(corx,method="circle",tl.cex=0.5)
corx## AGE BALANCE SCR
## AGE 1.0000000000 -0.1225868887 -0.0058707849
## BALANCE -0.1225868887 1.0000000000 -0.0652999838
## SCR -0.0058707849 -0.0652999838 1.0000000000
## HOLDING_PERIOD -0.0120598801 0.0392406960 -0.0251743685
## LEN_OF_RLTN_IN_MNTH -0.0082792784 -0.0008551526 0.0090335800
## NO_OF_L_CR_TXNS 0.0301702109 -0.0476523126 -0.0131789419
## NO_OF_L_DR_TXNS 0.0196022896 -0.0434309712 0.0093894768
## TOT_NO_OF_L_TXNS 0.0289320084 -0.0512985219 -0.0049522451
## NO_OF_BR_CSH_WDL_DR_TXNS 0.0242658282 -0.0348138188 0.0048274515
## NO_OF_ATM_DR_TXNS 0.0067570308 -0.0305791491 0.0149096786
## NO_OF_NET_DR_TXNS 0.0122679435 -0.0370182529 0.0064761681
## NO_OF_MOB_DR_TXNS 0.0019572951 -0.0210124259 0.0012361580
## NO_OF_CHQ_DR_TXNS 0.0217996747 -0.0325159849 0.0087075107
## AMT_ATM_DR 0.0197021581 -0.0359871389 0.0097440989
## AMT_BR_CSH_WDL_DR 0.0103506920 -0.0209013013 -0.0198408171
## AMT_CHQ_DR 0.0121892929 -0.0125106170 0.0045193167
## AMT_NET_DR 0.0043899298 -0.0293345016 0.0236541198
## AMT_MOB_DR 0.0289084717 -0.0266942619 -0.0125878255
## AMT_L_DR 0.0167245204 -0.0331931481 0.0034849587
## AMT_OTH_BK_ATM_USG_CHGS -0.0079800174 -0.0109486772 0.0079019189
## AMT_MIN_BAL_NMC_CHGS 0.0164369225 -0.0618186605 0.0086818985
## NO_OF_IW_CHQ_BNC_TXNS -0.0144121792 -0.0099343663 0.0008638097
## NO_OF_OW_CHQ_BNC_TXNS -0.0058303195 -0.0143641666 0.0065411505
## AVG_AMT_PER_ATM_TXN 0.0186923009 -0.0353602872 0.0194400547
## AVG_AMT_PER_CSH_WDL_TXN -0.0050775478 0.0058067710 -0.0225312148
## AVG_AMT_PER_CHQ_TXN 0.0144561895 -0.0237323732 0.0082671172
## AVG_AMT_PER_NET_TXN 0.0000790903 -0.0191491203 0.0257306992
## AVG_AMT_PER_MOB_TXN 0.0282875621 -0.0287271783 -0.0152461010
## random -0.0045172819 -0.0040261584 0.0081308782
## HOLDING_PERIOD LEN_OF_RLTN_IN_MNTH
## AGE -0.012059880 -8.279278e-03
## BALANCE 0.039240696 -8.551526e-04
## SCR -0.025174369 9.033580e-03
## HOLDING_PERIOD 1.000000000 1.144767e-02
## LEN_OF_RLTN_IN_MNTH 0.011447673 1.000000e+00
## NO_OF_L_CR_TXNS -0.008474285 2.171897e-02
## NO_OF_L_DR_TXNS -0.347855164 1.878054e-03
## TOT_NO_OF_L_TXNS -0.156350280 1.577737e-02
## NO_OF_BR_CSH_WDL_DR_TXNS -0.196454853 -3.073078e-03
## NO_OF_ATM_DR_TXNS -0.181790415 -4.713136e-05
## NO_OF_NET_DR_TXNS -0.250650046 5.920794e-03
## NO_OF_MOB_DR_TXNS -0.109956056 -3.159358e-03
## NO_OF_CHQ_DR_TXNS -0.473639299 5.684616e-03
## AMT_ATM_DR -0.173627031 -1.001416e-02
## AMT_BR_CSH_WDL_DR -0.048038366 -1.698567e-03
## AMT_CHQ_DR -0.173118109 1.379614e-02
## AMT_NET_DR -0.198319400 1.535660e-03
## AMT_MOB_DR -0.104096870 4.805786e-03
## AMT_L_DR -0.228820720 8.522072e-03
## AMT_OTH_BK_ATM_USG_CHGS -0.077077830 -6.432491e-03
## AMT_MIN_BAL_NMC_CHGS -0.006945401 -8.238740e-03
## NO_OF_IW_CHQ_BNC_TXNS -0.040949546 1.704724e-03
## NO_OF_OW_CHQ_BNC_TXNS -0.066336851 1.299358e-03
## AVG_AMT_PER_ATM_TXN -0.167648137 -1.890459e-02
## AVG_AMT_PER_CSH_WDL_TXN 0.053489719 7.646441e-03
## AVG_AMT_PER_CHQ_TXN -0.209996056 1.290957e-02
## AVG_AMT_PER_NET_TXN -0.107639295 -2.317134e-03
## AVG_AMT_PER_MOB_TXN -0.080624988 7.677896e-04
## random -0.002089157 3.608765e-03
## NO_OF_L_CR_TXNS NO_OF_L_DR_TXNS TOT_NO_OF_L_TXNS
## AGE 0.030170211 0.019602290 0.028932008
## BALANCE -0.047652313 -0.043430971 -0.051298522
## SCR -0.013178942 0.009389477 -0.004952245
## HOLDING_PERIOD -0.008474285 -0.347855164 -0.156350280
## LEN_OF_RLTN_IN_MNTH 0.021718966 0.001878054 0.015777365
## NO_OF_L_CR_TXNS 1.000000000 0.582878327 0.936225572
## NO_OF_L_DR_TXNS 0.582878327 1.000000000 0.831203457
## TOT_NO_OF_L_TXNS 0.936225572 0.831203457 1.000000000
## NO_OF_BR_CSH_WDL_DR_TXNS 0.376076032 0.566710618 0.502432910
## NO_OF_ATM_DR_TXNS 0.478080796 0.806728473 0.675687477
## NO_OF_NET_DR_TXNS 0.543464462 0.915082176 0.767502156
## NO_OF_MOB_DR_TXNS 0.456308736 0.763747602 0.642399104
## NO_OF_CHQ_DR_TXNS 0.286492245 0.608017630 0.459061809
## AMT_ATM_DR 0.436094319 0.699706523 0.601077738
## AMT_BR_CSH_WDL_DR 0.086326741 0.115308142 0.108965340
## AMT_CHQ_DR 0.288798124 0.466685679 0.399406743
## AMT_NET_DR 0.146707618 0.303860430 0.231834834
## AMT_MOB_DR 0.394123020 0.551017942 0.507941092
## AMT_L_DR 0.320615158 0.530681849 0.448896195
## AMT_OTH_BK_ATM_USG_CHGS 0.320124519 0.564558279 0.463085674
## AMT_MIN_BAL_NMC_CHGS 0.026631556 0.009876822 0.022458196
## NO_OF_IW_CHQ_BNC_TXNS 0.002825437 0.059746413 0.027804172
## NO_OF_OW_CHQ_BNC_TXNS 0.036371862 0.085200056 0.061762124
## AVG_AMT_PER_ATM_TXN 0.196087423 0.320450157 0.273037974
## AVG_AMT_PER_CSH_WDL_TXN -0.072480645 -0.138213687 -0.109383160
## AVG_AMT_PER_CHQ_TXN 0.296118646 0.496140739 0.417130807
## AVG_AMT_PER_NET_TXN -0.070979834 -0.040286627 -0.065890212
## AVG_AMT_PER_MOB_TXN 0.331735967 0.409491099 0.404072540
## random -0.006646545 -0.005100748 -0.006643155
## NO_OF_BR_CSH_WDL_DR_TXNS NO_OF_ATM_DR_TXNS
## AGE 0.024265828 6.757031e-03
## BALANCE -0.034813819 -3.057915e-02
## SCR 0.004827451 1.490968e-02
## HOLDING_PERIOD -0.196454853 -1.817904e-01
## LEN_OF_RLTN_IN_MNTH -0.003073078 -4.713136e-05
## NO_OF_L_CR_TXNS 0.376076032 4.780808e-01
## NO_OF_L_DR_TXNS 0.566710618 8.067285e-01
## TOT_NO_OF_L_TXNS 0.502432910 6.756875e-01
## NO_OF_BR_CSH_WDL_DR_TXNS 1.000000000 2.528161e-01
## NO_OF_ATM_DR_TXNS 0.252816060 1.000000e+00
## NO_OF_NET_DR_TXNS 0.414579011 7.587912e-01
## NO_OF_MOB_DR_TXNS 0.168559933 7.737012e-01
## NO_OF_CHQ_DR_TXNS 0.156116651 3.117335e-01
## AMT_ATM_DR 0.344833802 7.083088e-01
## AMT_BR_CSH_WDL_DR 0.320712863 1.054877e-02
## AMT_CHQ_DR 0.085462604 2.523575e-01
## AMT_NET_DR 0.173491510 2.288784e-01
## AMT_MOB_DR 0.464860671 3.326339e-01
## AMT_L_DR 0.319194885 3.012735e-01
## AMT_OTH_BK_ATM_USG_CHGS -0.014458881 8.409783e-01
## AMT_MIN_BAL_NMC_CHGS 0.010882111 3.306876e-03
## NO_OF_IW_CHQ_BNC_TXNS 0.045698356 3.112818e-02
## NO_OF_OW_CHQ_BNC_TXNS 0.049474952 5.866894e-02
## AVG_AMT_PER_ATM_TXN 0.239661040 3.119639e-01
## AVG_AMT_PER_CSH_WDL_TXN -0.127145035 -1.026635e-01
## AVG_AMT_PER_CHQ_TXN 0.137317211 2.842338e-01
## AVG_AMT_PER_NET_TXN -0.045247021 -1.114357e-02
## AVG_AMT_PER_MOB_TXN 0.432036996 1.966421e-01
## random 0.001383773 -2.728814e-03
## NO_OF_NET_DR_TXNS NO_OF_MOB_DR_TXNS
## AGE 0.012267943 0.001957295
## BALANCE -0.037018253 -0.021012426
## SCR 0.006476168 0.001236158
## HOLDING_PERIOD -0.250650046 -0.109956056
## LEN_OF_RLTN_IN_MNTH 0.005920794 -0.003159358
## NO_OF_L_CR_TXNS 0.543464462 0.456308736
## NO_OF_L_DR_TXNS 0.915082176 0.763747602
## TOT_NO_OF_L_TXNS 0.767502156 0.642399104
## NO_OF_BR_CSH_WDL_DR_TXNS 0.414579011 0.168559933
## NO_OF_ATM_DR_TXNS 0.758791239 0.773701233
## NO_OF_NET_DR_TXNS 1.000000000 0.753339568
## NO_OF_MOB_DR_TXNS 0.753339568 1.000000000
## NO_OF_CHQ_DR_TXNS 0.432361300 0.210224038
## AMT_ATM_DR 0.640036786 0.537395811
## AMT_BR_CSH_WDL_DR 0.060027161 -0.031144375
## AMT_CHQ_DR 0.452952997 0.216940442
## AMT_NET_DR 0.413677540 0.111040021
## AMT_MOB_DR 0.474324695 0.319453846
## AMT_L_DR 0.539066983 0.202704988
## AMT_OTH_BK_ATM_USG_CHGS 0.569358116 0.805864033
## AMT_MIN_BAL_NMC_CHGS 0.006654306 0.014441666
## NO_OF_IW_CHQ_BNC_TXNS 0.037649370 0.010777148
## NO_OF_OW_CHQ_BNC_TXNS 0.062208664 0.046850773
## AVG_AMT_PER_ATM_TXN 0.226788266 0.063536037
## AVG_AMT_PER_CSH_WDL_TXN -0.125559398 -0.093861111
## AVG_AMT_PER_CHQ_TXN 0.486431759 0.232384892
## AVG_AMT_PER_NET_TXN 0.040412931 -0.086132463
## AVG_AMT_PER_MOB_TXN 0.320204432 0.150585721
## random -0.002216460 -0.001283732
## NO_OF_CHQ_DR_TXNS AMT_ATM_DR AMT_BR_CSH_WDL_DR
## AGE 0.0217996747 0.019702158 0.010350692
## BALANCE -0.0325159849 -0.035987139 -0.020901301
## SCR 0.0087075107 0.009744099 -0.019840817
## HOLDING_PERIOD -0.4736392990 -0.173627031 -0.048038366
## LEN_OF_RLTN_IN_MNTH 0.0056846161 -0.010014162 -0.001698567
## NO_OF_L_CR_TXNS 0.2864922454 0.436094319 0.086326741
## NO_OF_L_DR_TXNS 0.6080176296 0.699706523 0.115308142
## TOT_NO_OF_L_TXNS 0.4590618093 0.601077738 0.108965340
## NO_OF_BR_CSH_WDL_DR_TXNS 0.1561166514 0.344833802 0.320712863
## NO_OF_ATM_DR_TXNS 0.3117334639 0.708308791 0.010548774
## NO_OF_NET_DR_TXNS 0.4323613005 0.640036786 0.060027161
## NO_OF_MOB_DR_TXNS 0.2102240375 0.537395811 -0.031144375
## NO_OF_CHQ_DR_TXNS 1.0000000000 0.381930517 0.025830464
## AMT_ATM_DR 0.3819305171 1.000000000 0.041550639
## AMT_BR_CSH_WDL_DR 0.0258304639 0.041550639 1.000000000
## AMT_CHQ_DR 0.6230378798 0.309998601 0.024670558
## AMT_NET_DR 0.1590108697 0.221944553 0.104824900
## AMT_MOB_DR 0.3760261233 0.377971600 0.074122864
## AMT_L_DR 0.5016408908 0.357536594 0.533224860
## AMT_OTH_BK_ATM_USG_CHGS 0.0496839455 0.431459258 -0.054181965
## AMT_MIN_BAL_NMC_CHGS 0.0005051339 0.003875363 0.001265182
## NO_OF_IW_CHQ_BNC_TXNS 0.0823414499 0.037500737 0.042927667
## NO_OF_OW_CHQ_BNC_TXNS 0.0882304908 0.032538929 0.031696090
## AVG_AMT_PER_ATM_TXN 0.3258795124 0.724982307 0.087367371
## AVG_AMT_PER_CSH_WDL_TXN -0.0540339181 -0.106329710 0.776706032
## AVG_AMT_PER_CHQ_TXN 0.6018441917 0.326789870 0.031137620
## AVG_AMT_PER_NET_TXN -0.0478749757 -0.017963262 0.080935912
## AVG_AMT_PER_MOB_TXN 0.3347324610 0.281797857 0.082373510
## random -0.0127008050 -0.003748107 -0.002808173
## AMT_CHQ_DR AMT_NET_DR AMT_MOB_DR
## AGE 0.012189293 0.0043899298 0.0289084717
## BALANCE -0.012510617 -0.0293345016 -0.0266942619
## SCR 0.004519317 0.0236541198 -0.0125878255
## HOLDING_PERIOD -0.173118109 -0.1983193996 -0.1040968699
## LEN_OF_RLTN_IN_MNTH 0.013796138 0.0015356605 0.0048057857
## NO_OF_L_CR_TXNS 0.288798124 0.1467076180 0.3941230204
## NO_OF_L_DR_TXNS 0.466685679 0.3038604305 0.5510179422
## TOT_NO_OF_L_TXNS 0.399406743 0.2318348343 0.5079410924
## NO_OF_BR_CSH_WDL_DR_TXNS 0.085462604 0.1734915098 0.4648606706
## NO_OF_ATM_DR_TXNS 0.252357473 0.2288783616 0.3326338702
## NO_OF_NET_DR_TXNS 0.452952997 0.4136775398 0.4743246955
## NO_OF_MOB_DR_TXNS 0.216940442 0.1110400208 0.3194538462
## NO_OF_CHQ_DR_TXNS 0.623037880 0.1590108697 0.3760261233
## AMT_ATM_DR 0.309998601 0.2219445527 0.3779716004
## AMT_BR_CSH_WDL_DR 0.024670558 0.1048249003 0.0741228636
## AMT_CHQ_DR 1.000000000 0.1547845811 0.3293078035
## AMT_NET_DR 0.154784581 1.0000000000 0.1161647353
## AMT_MOB_DR 0.329307803 0.1161647353 1.0000000000
## AMT_L_DR 0.726831006 0.6047251144 0.3670629404
## AMT_OTH_BK_ATM_USG_CHGS 0.064480153 0.0779602866 0.1145090322
## AMT_MIN_BAL_NMC_CHGS -0.006257877 -0.0006234766 0.0188714317
## NO_OF_IW_CHQ_BNC_TXNS 0.027038765 0.0446767607 -0.0002489512
## NO_OF_OW_CHQ_BNC_TXNS 0.036334694 0.0393407230 0.0268431976
## AVG_AMT_PER_ATM_TXN 0.156373325 0.2338513188 0.1911939468
## AVG_AMT_PER_CSH_WDL_TXN -0.036469233 -0.0029777271 -0.1402926321
## AVG_AMT_PER_CHQ_TXN 0.904118428 0.1956416760 0.3437716019
## AVG_AMT_PER_NET_TXN -0.058813641 0.8567920886 -0.1600936064
## AVG_AMT_PER_MOB_TXN 0.268764198 0.0882360434 0.9641983995
## random -0.014588125 0.0059192938 -0.0025768599
## AMT_L_DR AMT_OTH_BK_ATM_USG_CHGS
## AGE 0.016724520 -0.0079800174
## BALANCE -0.033193148 -0.0109486772
## SCR 0.003484959 0.0079019189
## HOLDING_PERIOD -0.228820720 -0.0770778303
## LEN_OF_RLTN_IN_MNTH 0.008522072 -0.0064324907
## NO_OF_L_CR_TXNS 0.320615158 0.3201245188
## NO_OF_L_DR_TXNS 0.530681849 0.5645582793
## TOT_NO_OF_L_TXNS 0.448896195 0.4630856743
## NO_OF_BR_CSH_WDL_DR_TXNS 0.319194885 -0.0144588805
## NO_OF_ATM_DR_TXNS 0.301273547 0.8409783281
## NO_OF_NET_DR_TXNS 0.539066983 0.5693581163
## NO_OF_MOB_DR_TXNS 0.202704988 0.8058640332
## NO_OF_CHQ_DR_TXNS 0.501640891 0.0496839455
## AMT_ATM_DR 0.357536594 0.4314592577
## AMT_BR_CSH_WDL_DR 0.533224860 -0.0541819645
## AMT_CHQ_DR 0.726831006 0.0644801529
## AMT_NET_DR 0.604725114 0.0779602866
## AMT_MOB_DR 0.367062940 0.1145090322
## AMT_L_DR 1.000000000 0.0666782928
## AMT_OTH_BK_ATM_USG_CHGS 0.066678293 1.0000000000
## AMT_MIN_BAL_NMC_CHGS -0.002155378 0.0074047711
## NO_OF_IW_CHQ_BNC_TXNS 0.057424091 0.0065801985
## NO_OF_OW_CHQ_BNC_TXNS 0.057317799 0.0420089960
## AVG_AMT_PER_ATM_TXN 0.270583341 -0.0122208608
## AVG_AMT_PER_CSH_WDL_TXN 0.325359596 -0.0490491974
## AVG_AMT_PER_CHQ_TXN 0.690381328 0.0927150459
## AVG_AMT_PER_NET_TXN 0.373473913 -0.0402883178
## AVG_AMT_PER_MOB_TXN 0.316517155 -0.0212487487
## random -0.007909288 -0.0002576055
## AMT_MIN_BAL_NMC_CHGS NO_OF_IW_CHQ_BNC_TXNS
## AGE 0.0164369225 -0.0144121792
## BALANCE -0.0618186605 -0.0099343663
## SCR 0.0086818985 0.0008638097
## HOLDING_PERIOD -0.0069454006 -0.0409495460
## LEN_OF_RLTN_IN_MNTH -0.0082387403 0.0017047238
## NO_OF_L_CR_TXNS 0.0266315558 0.0028254367
## NO_OF_L_DR_TXNS 0.0098768220 0.0597464134
## TOT_NO_OF_L_TXNS 0.0224581958 0.0278041719
## NO_OF_BR_CSH_WDL_DR_TXNS 0.0108821107 0.0456983559
## NO_OF_ATM_DR_TXNS 0.0033068757 0.0311281767
## NO_OF_NET_DR_TXNS 0.0066543062 0.0376493698
## NO_OF_MOB_DR_TXNS 0.0144416658 0.0107771477
## NO_OF_CHQ_DR_TXNS 0.0005051339 0.0823414499
## AMT_ATM_DR 0.0038753628 0.0375007374
## AMT_BR_CSH_WDL_DR 0.0012651818 0.0429276667
## AMT_CHQ_DR -0.0062578775 0.0270387654
## AMT_NET_DR -0.0006234766 0.0446767607
## AMT_MOB_DR 0.0188714317 -0.0002489512
## AMT_L_DR -0.0021553778 0.0574240912
## AMT_OTH_BK_ATM_USG_CHGS 0.0074047711 0.0065801985
## AMT_MIN_BAL_NMC_CHGS 1.0000000000 0.0241087169
## NO_OF_IW_CHQ_BNC_TXNS 0.0241087169 1.0000000000
## NO_OF_OW_CHQ_BNC_TXNS -0.0076740076 0.0060161767
## AVG_AMT_PER_ATM_TXN -0.0010541073 0.0495007799
## AVG_AMT_PER_CSH_WDL_TXN -0.0089700934 0.0130782914
## AVG_AMT_PER_CHQ_TXN -0.0107249969 0.0465097592
## AVG_AMT_PER_NET_TXN -0.0055692355 0.0401768417
## AVG_AMT_PER_MOB_TXN 0.0191151141 -0.0030758287
## random 0.0031265951 -0.0048168358
## NO_OF_OW_CHQ_BNC_TXNS AVG_AMT_PER_ATM_TXN
## AGE -0.0058303195 0.018692301
## BALANCE -0.0143641666 -0.035360287
## SCR 0.0065411505 0.019440055
## HOLDING_PERIOD -0.0663368508 -0.167648137
## LEN_OF_RLTN_IN_MNTH 0.0012993584 -0.018904591
## NO_OF_L_CR_TXNS 0.0363718620 0.196087423
## NO_OF_L_DR_TXNS 0.0852000564 0.320450157
## TOT_NO_OF_L_TXNS 0.0617621242 0.273037974
## NO_OF_BR_CSH_WDL_DR_TXNS 0.0494749522 0.239661040
## NO_OF_ATM_DR_TXNS 0.0586689437 0.311963910
## NO_OF_NET_DR_TXNS 0.0622086641 0.226788266
## NO_OF_MOB_DR_TXNS 0.0468507732 0.063536037
## NO_OF_CHQ_DR_TXNS 0.0882304908 0.325879512
## AMT_ATM_DR 0.0325389289 0.724982307
## AMT_BR_CSH_WDL_DR 0.0316960899 0.087367371
## AMT_CHQ_DR 0.0363346938 0.156373325
## AMT_NET_DR 0.0393407230 0.233851319
## AMT_MOB_DR 0.0268431976 0.191193947
## AMT_L_DR 0.0573177987 0.270583341
## AMT_OTH_BK_ATM_USG_CHGS 0.0420089960 -0.012220861
## AMT_MIN_BAL_NMC_CHGS -0.0076740076 -0.001054107
## NO_OF_IW_CHQ_BNC_TXNS 0.0060161767 0.049500780
## NO_OF_OW_CHQ_BNC_TXNS 1.0000000000 0.030366280
## AVG_AMT_PER_ATM_TXN 0.0303662799 1.000000000
## AVG_AMT_PER_CSH_WDL_TXN 0.0113525559 -0.023336905
## AVG_AMT_PER_CHQ_TXN 0.0729911230 0.176683964
## AVG_AMT_PER_NET_TXN 0.0215107302 0.143489591
## AVG_AMT_PER_MOB_TXN 0.0199930200 0.189097228
## random -0.0001959959 -0.007888469
## AVG_AMT_PER_CSH_WDL_TXN AVG_AMT_PER_CHQ_TXN
## AGE -0.005077548 0.014456189
## BALANCE 0.005806771 -0.023732373
## SCR -0.022531215 0.008267117
## HOLDING_PERIOD 0.053489719 -0.209996056
## LEN_OF_RLTN_IN_MNTH 0.007646441 0.012909573
## NO_OF_L_CR_TXNS -0.072480645 0.296118646
## NO_OF_L_DR_TXNS -0.138213687 0.496140739
## TOT_NO_OF_L_TXNS -0.109383160 0.417130807
## NO_OF_BR_CSH_WDL_DR_TXNS -0.127145035 0.137317211
## NO_OF_ATM_DR_TXNS -0.102663537 0.284233850
## NO_OF_NET_DR_TXNS -0.125559398 0.486431759
## NO_OF_MOB_DR_TXNS -0.093861111 0.232384892
## NO_OF_CHQ_DR_TXNS -0.054033918 0.601844192
## AMT_ATM_DR -0.106329710 0.326789870
## AMT_BR_CSH_WDL_DR 0.776706032 0.031137620
## AMT_CHQ_DR -0.036469233 0.904118428
## AMT_NET_DR -0.002977727 0.195641676
## AMT_MOB_DR -0.140292632 0.343771602
## AMT_L_DR 0.325359596 0.690381328
## AMT_OTH_BK_ATM_USG_CHGS -0.049049197 0.092715046
## AMT_MIN_BAL_NMC_CHGS -0.008970093 -0.010724997
## NO_OF_IW_CHQ_BNC_TXNS 0.013078291 0.046509759
## NO_OF_OW_CHQ_BNC_TXNS 0.011352556 0.072991123
## AVG_AMT_PER_ATM_TXN -0.023336905 0.176683964
## AVG_AMT_PER_CSH_WDL_TXN 1.000000000 -0.043675627
## AVG_AMT_PER_CHQ_TXN -0.043675627 1.000000000
## AVG_AMT_PER_NET_TXN 0.069843066 -0.033329317
## AVG_AMT_PER_MOB_TXN -0.125600515 0.289496096
## random 0.002993618 -0.010437338
## AVG_AMT_PER_NET_TXN AVG_AMT_PER_MOB_TXN
## AGE 0.0000790903 0.0282875621
## BALANCE -0.0191491203 -0.0287271783
## SCR 0.0257306992 -0.0152461010
## HOLDING_PERIOD -0.1076392949 -0.0806249880
## LEN_OF_RLTN_IN_MNTH -0.0023171340 0.0007677896
## NO_OF_L_CR_TXNS -0.0709798339 0.3317359670
## NO_OF_L_DR_TXNS -0.0402866267 0.4094910991
## TOT_NO_OF_L_TXNS -0.0658902116 0.4040725404
## NO_OF_BR_CSH_WDL_DR_TXNS -0.0452470211 0.4320369958
## NO_OF_ATM_DR_TXNS -0.0111435684 0.1966421056
## NO_OF_NET_DR_TXNS 0.0404129313 0.3202044323
## NO_OF_MOB_DR_TXNS -0.0861324629 0.1505857210
## NO_OF_CHQ_DR_TXNS -0.0478749757 0.3347324610
## AMT_ATM_DR -0.0179632619 0.2817978566
## AMT_BR_CSH_WDL_DR 0.0809359115 0.0823735098
## AMT_CHQ_DR -0.0588136412 0.2687641979
## AMT_NET_DR 0.8567920886 0.0882360434
## AMT_MOB_DR -0.1600936064 0.9641983995
## AMT_L_DR 0.3734739128 0.3165171552
## AMT_OTH_BK_ATM_USG_CHGS -0.0402883178 -0.0212487487
## AMT_MIN_BAL_NMC_CHGS -0.0055692355 0.0191151141
## NO_OF_IW_CHQ_BNC_TXNS 0.0401768417 -0.0030758287
## NO_OF_OW_CHQ_BNC_TXNS 0.0215107302 0.0199930200
## AVG_AMT_PER_ATM_TXN 0.1434895914 0.1890972281
## AVG_AMT_PER_CSH_WDL_TXN 0.0698430660 -0.1256005147
## AVG_AMT_PER_CHQ_TXN -0.0333293167 0.2894960959
## AVG_AMT_PER_NET_TXN 1.0000000000 -0.1518724649
## AVG_AMT_PER_MOB_TXN -0.1518724649 1.0000000000
## random 0.0064117100 -0.0021431760
## random
## AGE -0.0045172819
## BALANCE -0.0040261584
## SCR 0.0081308782
## HOLDING_PERIOD -0.0020891571
## LEN_OF_RLTN_IN_MNTH 0.0036087650
## NO_OF_L_CR_TXNS -0.0066465453
## NO_OF_L_DR_TXNS -0.0051007475
## TOT_NO_OF_L_TXNS -0.0066431547
## NO_OF_BR_CSH_WDL_DR_TXNS 0.0013837732
## NO_OF_ATM_DR_TXNS -0.0027288136
## NO_OF_NET_DR_TXNS -0.0022164604
## NO_OF_MOB_DR_TXNS -0.0012837317
## NO_OF_CHQ_DR_TXNS -0.0127008050
## AMT_ATM_DR -0.0037481072
## AMT_BR_CSH_WDL_DR -0.0028081725
## AMT_CHQ_DR -0.0145881249
## AMT_NET_DR 0.0059192938
## AMT_MOB_DR -0.0025768599
## AMT_L_DR -0.0079092875
## AMT_OTH_BK_ATM_USG_CHGS -0.0002576055
## AMT_MIN_BAL_NMC_CHGS 0.0031265951
## NO_OF_IW_CHQ_BNC_TXNS -0.0048168358
## NO_OF_OW_CHQ_BNC_TXNS -0.0001959959
## AVG_AMT_PER_ATM_TXN -0.0078884687
## AVG_AMT_PER_CSH_WDL_TXN 0.0029936185
## AVG_AMT_PER_CHQ_TXN -0.0104373377
## AVG_AMT_PER_NET_TXN 0.0064117100
## AVG_AMT_PER_MOB_TXN -0.0021431760
## random 1.0000000000Splittting the data into 70% and 30%
library(caret)## Warning: package 'caret' was built under R version 3.4.3## Loading required package: lattice## Loading required package: ggplot2##
## Attaching package: 'ggplot2'## The following objects are masked from 'package:psych':
##
## %+%, alphaindex <- createDataPartition(ploan$TARGET, p=0.70, list=FALSE)
train <- ploan[ index,]
test <- ploan[-index,]Node size should be 1-2% of the development sample
library(randomForest)## Warning: package 'randomForest' was built under R version 3.4.2## randomForest 4.6-12## Type rfNews() to see new features/changes/bug fixes.##
## Attaching package: 'randomForest'## The following object is masked from 'package:ggplot2':
##
## margin## The following object is masked from 'package:psych':
##
## outlierOptimal number of trees is 25
Tuning Random Forest, finding the optimal number of m
tRF2 <- tuneRF(x = train[,-c(1,2)],
y=as.factor(train$TARGET),
mtryStart = 3,
ntreeTry=25,
stepFactor = 1.5,
improve = 0.001,
trace=TRUE,
plot = TRUE,
doBest = TRUE,
nodesize = 100,
importance=TRUE
)## mtry = 3 OOB error = 12.22%
## Searching left ...
## mtry = 2 OOB error = 12.29%
## -0.005260082 0.001
## Searching right ...
## mtry = 4 OOB error = 12.12%
## 0.00818235 0.001
## mtry = 6 OOB error = 11.96%
## 0.01296405 0.001
## mtry = 9 OOB error = 11.87%
## 0.007761194 0.001
## mtry = 13 OOB error = 11.75%
## 0.01015794 0.001
## mtry = 19 OOB error = 11.74%
## 0.001287147 0.001
## mtry = 28 OOB error = 11.66%
## 0.00669507 0.001
## mtry = 40 OOB error = 11.61%
## 0.004218088 0.001
using tuneRF found m as 13
print(tRF2)##
## Call:
## randomForest(x = x, y = y, mtry = res[which.min(res[, 2]), 1], nodesize = 100, importance = TRUE)
## Type of random forest: classification
## Number of trees: 500
## No. of variables tried at each split: 40
##
## OOB estimate of error rate: 11.61%
## Confusion matrix:
## 0 1 class.error
## 0 12237 31 0.002526899
## 1 1595 137 0.920900693plot(tRF2, main="")
legend("topright", c("OOB", "0", "1"), text.col=1:6, lty=1:3, col=1:3)
title(main="Error Rates Random Forest RFDF.dev")
tRF2$importance## 0 1 MeanDecreaseAccuracy
## AGE 1.018293e-03 4.892221e-03 1.496210e-03
## GENDER 1.147883e-03 3.202941e-03 1.401051e-03
## BALANCE 2.498618e-03 3.135466e-02 6.063722e-03
## OCCUPATION 3.482819e-03 2.556256e-02 6.210751e-03
## AGE_BKT 1.502607e-03 1.252907e-02 2.866081e-03
## SCR 3.393084e-03 3.035856e-02 6.724208e-03
## HOLDING_PERIOD 1.946641e-02 1.921907e-02 1.943840e-02
## ACC_TYPE 7.344651e-04 1.489373e-04 6.609152e-04
## ACC_OP_DATE 4.107715e-03 5.072407e-03 4.223463e-03
## LEN_OF_RLTN_IN_MNTH 3.224285e-03 -4.805475e-04 2.764136e-03
## NO_OF_L_CR_TXNS 3.243441e-02 -8.949877e-03 2.731652e-02
## NO_OF_L_DR_TXNS 9.381195e-02 -2.663333e-02 7.893805e-02
## TOT_NO_OF_L_TXNS 3.703274e-02 -2.177546e-02 2.978365e-02
## NO_OF_BR_CSH_WDL_DR_TXNS 2.199687e-03 1.799596e-03 2.150081e-03
## NO_OF_ATM_DR_TXNS 2.587951e-02 -1.456011e-02 2.088901e-02
## NO_OF_NET_DR_TXNS 8.486262e-04 -3.548047e-04 7.001810e-04
## NO_OF_MOB_DR_TXNS 5.493343e-04 -3.115659e-04 4.424556e-04
## NO_OF_CHQ_DR_TXNS 4.281624e-03 -2.150697e-04 3.724991e-03
## FLG_HAS_CC 2.614018e-03 1.944593e-02 4.694556e-03
## AMT_ATM_DR 1.160043e-02 1.138020e-04 1.016776e-02
## AMT_BR_CSH_WDL_DR 6.027803e-03 3.678128e-03 5.734477e-03
## AMT_CHQ_DR 6.691233e-03 -3.370808e-04 5.825329e-03
## AMT_NET_DR 2.092071e-03 7.649549e-04 1.925363e-03
## AMT_MOB_DR 2.915398e-03 -7.366642e-04 2.458838e-03
## AMT_L_DR 2.086338e-02 -8.752214e-03 1.720980e-02
## FLG_HAS_ANY_CHGS 1.067064e-04 2.379925e-04 1.231093e-04
## AMT_OTH_BK_ATM_USG_CHGS -7.595654e-06 5.837013e-05 8.010807e-07
## AMT_MIN_BAL_NMC_CHGS 3.107518e-06 5.064522e-05 8.980494e-06
## NO_OF_IW_CHQ_BNC_TXNS 6.920842e-05 3.899875e-04 1.091865e-04
## NO_OF_OW_CHQ_BNC_TXNS 2.495608e-05 4.244435e-04 7.433764e-05
## AVG_AMT_PER_ATM_TXN 9.080786e-03 -8.552783e-04 7.847931e-03
## AVG_AMT_PER_CSH_WDL_TXN 5.559868e-03 9.484557e-04 4.991598e-03
## AVG_AMT_PER_CHQ_TXN 8.952852e-03 -2.280435e-03 7.567514e-03
## AVG_AMT_PER_NET_TXN 2.644861e-03 5.786227e-04 2.386537e-03
## AVG_AMT_PER_MOB_TXN 1.706737e-03 4.234294e-03 2.014644e-03
## FLG_HAS_NOMINEE 5.001393e-05 1.374494e-04 6.097462e-05
## FLG_HAS_OLD_LOAN 6.692224e-06 1.583228e-04 2.527735e-05
## random 3.352413e-05 7.559321e-04 1.230970e-04
## LOW_BAL 0.000000e+00 0.000000e+00 0.000000e+00
## LOW_HOLD 0.000000e+00 0.000000e+00 0.000000e+00
## MeanDecreaseGini
## AGE 22.6424421
## GENDER 14.4373147
## BALANCE 77.3519660
## OCCUPATION 40.9323883
## AGE_BKT 37.9694162
## SCR 78.4414355
## HOLDING_PERIOD 56.5717561
## ACC_TYPE 3.1901887
## ACC_OP_DATE 43.6354960
## LEN_OF_RLTN_IN_MNTH 15.5469130
## NO_OF_L_CR_TXNS 55.8492979
## NO_OF_L_DR_TXNS 49.1277270
## TOT_NO_OF_L_TXNS 48.0896195
## NO_OF_BR_CSH_WDL_DR_TXNS 13.3763557
## NO_OF_ATM_DR_TXNS 17.9420072
## NO_OF_NET_DR_TXNS 2.1800071
## NO_OF_MOB_DR_TXNS 1.3794476
## NO_OF_CHQ_DR_TXNS 10.3413527
## FLG_HAS_CC 21.7606289
## AMT_ATM_DR 29.7490316
## AMT_BR_CSH_WDL_DR 34.5492091
## AMT_CHQ_DR 21.0375430
## AMT_NET_DR 14.2695808
## AMT_MOB_DR 10.5347242
## AMT_L_DR 35.7047485
## FLG_HAS_ANY_CHGS 2.8727688
## AMT_OTH_BK_ATM_USG_CHGS 0.2697427
## AMT_MIN_BAL_NMC_CHGS 0.3414494
## NO_OF_IW_CHQ_BNC_TXNS 3.2658671
## NO_OF_OW_CHQ_BNC_TXNS 2.5520463
## AVG_AMT_PER_ATM_TXN 28.0863935
## AVG_AMT_PER_CSH_WDL_TXN 28.2169823
## AVG_AMT_PER_CHQ_TXN 22.0183368
## AVG_AMT_PER_NET_TXN 18.7041979
## AVG_AMT_PER_MOB_TXN 20.0389305
## FLG_HAS_NOMINEE 1.2584349
## FLG_HAS_OLD_LOAN 1.5522024
## random 23.0425189
## LOW_BAL 0.0000000
## LOW_HOLD 0.0000000List the importance of the variables
impVar <- round(randomForest::importance(tRF2), 2)
impVar[order(impVar[,4], decreasing=TRUE),]## 0 1 MeanDecreaseAccuracy
## SCR 27.76 43.17 42.69
## BALANCE 21.38 41.49 39.35
## HOLDING_PERIOD 27.25 21.93 32.67
## NO_OF_L_CR_TXNS 25.84 -7.01 27.76
## NO_OF_L_DR_TXNS 35.08 -13.86 36.03
## TOT_NO_OF_L_TXNS 23.03 -11.31 24.61
## ACC_OP_DATE 12.86 10.92 16.46
## OCCUPATION 25.86 34.25 36.67
## AGE_BKT 16.36 25.63 26.51
## AMT_L_DR 33.54 -15.04 34.68
## AMT_BR_CSH_WDL_DR 15.37 8.77 17.59
## AMT_ATM_DR 18.36 0.15 19.94
## AVG_AMT_PER_CSH_WDL_TXN 14.72 2.68 16.19
## AVG_AMT_PER_ATM_TXN 17.87 -1.49 19.53
## random 1.01 6.35 3.83
## AGE 13.69 15.36 18.71
## AVG_AMT_PER_CHQ_TXN 21.61 -5.70 22.48
## FLG_HAS_CC 28.08 36.80 38.79
## AMT_CHQ_DR 14.87 -0.78 15.81
## AVG_AMT_PER_MOB_TXN 5.60 11.04 8.23
## AVG_AMT_PER_NET_TXN 9.27 2.47 10.00
## NO_OF_ATM_DR_TXNS 26.71 -21.80 26.57
## LEN_OF_RLTN_IN_MNTH 10.35 -1.31 11.46
## GENDER 17.17 20.48 22.67
## AMT_NET_DR 8.46 3.08 9.59
## NO_OF_BR_CSH_WDL_DR_TXNS 12.36 6.09 14.68
## AMT_MOB_DR 6.86 -1.34 7.82
## NO_OF_CHQ_DR_TXNS 12.17 -0.53 13.16
## NO_OF_IW_CHQ_BNC_TXNS 4.49 6.61 6.68
## ACC_TYPE 5.87 1.33 6.31
## FLG_HAS_ANY_CHGS 6.52 4.65 7.32
## NO_OF_OW_CHQ_BNC_TXNS 1.55 5.95 4.65
## NO_OF_NET_DR_TXNS 8.50 -2.93 8.97
## FLG_HAS_OLD_LOAN 0.76 3.02 2.52
## NO_OF_MOB_DR_TXNS 3.75 -1.82 4.06
## FLG_HAS_NOMINEE 3.54 3.00 4.07
## AMT_MIN_BAL_NMC_CHGS 1.09 2.65 2.80
## AMT_OTH_BK_ATM_USG_CHGS -2.62 2.91 0.33
## LOW_BAL 0.00 0.00 0.00
## LOW_HOLD 0.00 0.00 0.00
## MeanDecreaseGini
## SCR 78.44
## BALANCE 77.35
## HOLDING_PERIOD 56.57
## NO_OF_L_CR_TXNS 55.85
## NO_OF_L_DR_TXNS 49.13
## TOT_NO_OF_L_TXNS 48.09
## ACC_OP_DATE 43.64
## OCCUPATION 40.93
## AGE_BKT 37.97
## AMT_L_DR 35.70
## AMT_BR_CSH_WDL_DR 34.55
## AMT_ATM_DR 29.75
## AVG_AMT_PER_CSH_WDL_TXN 28.22
## AVG_AMT_PER_ATM_TXN 28.09
## random 23.04
## AGE 22.64
## AVG_AMT_PER_CHQ_TXN 22.02
## FLG_HAS_CC 21.76
## AMT_CHQ_DR 21.04
## AVG_AMT_PER_MOB_TXN 20.04
## AVG_AMT_PER_NET_TXN 18.70
## NO_OF_ATM_DR_TXNS 17.94
## LEN_OF_RLTN_IN_MNTH 15.55
## GENDER 14.44
## AMT_NET_DR 14.27
## NO_OF_BR_CSH_WDL_DR_TXNS 13.38
## AMT_MOB_DR 10.53
## NO_OF_CHQ_DR_TXNS 10.34
## NO_OF_IW_CHQ_BNC_TXNS 3.27
## ACC_TYPE 3.19
## FLG_HAS_ANY_CHGS 2.87
## NO_OF_OW_CHQ_BNC_TXNS 2.55
## NO_OF_NET_DR_TXNS 2.18
## FLG_HAS_OLD_LOAN 1.55
## NO_OF_MOB_DR_TXNS 1.38
## FLG_HAS_NOMINEE 1.26
## AMT_MIN_BAL_NMC_CHGS 0.34
## AMT_OTH_BK_ATM_USG_CHGS 0.27
## LOW_BAL 0.00
## LOW_HOLD 0.00varImpPlot(tRF2,
sort = T,
main="Variable Importance",
n.var=13)
Scoring syntax
train$predict.class <- predict(tRF2,train, type="class")
train$predict.score <- predict(tRF2,train, type="prob")
class(train$predict.score)## [1] "matrix" "votes"deciling
decile <- function(x){
deciles <- vector(length=10)
for (i in seq(0.1,1,.1)){
deciles[i*10] <- quantile(x, i, na.rm=T)
}
return (
ifelse(x<deciles[1], 1,
ifelse(x<deciles[2], 2,
ifelse(x<deciles[3], 3,
ifelse(x<deciles[4], 4,
ifelse(x<deciles[5], 5,
ifelse(x<deciles[6], 6,
ifelse(x<deciles[7], 7,
ifelse(x<deciles[8], 8,
ifelse(x<deciles[9], 9, 10
))))))))))
}
train$deciles <- decile(train$predict.score[,2])Rank Ordering
library(data.table)
tmp_DT = data.table(train)
rank <- tmp_DT[, list(
cnt = length(TARGET),
cnt_resp = sum(TARGET),
cnt_non_resp = sum(TARGET == 0)) ,
by=deciles][order(-deciles)]
rank$rrate <- round (rank$cnt_resp / rank$cnt,2);
rank$cum_resp <- cumsum(rank$cnt_resp)
rank$cum_non_resp <- cumsum(rank$cnt_non_resp)
rank$cum_rel_resp <- round(rank$cum_resp / sum(rank$cnt_resp),2);
rank$cum_rel_non_resp <- round(rank$cum_non_resp / sum(rank$cnt_non_resp),2);
rank$ks <- abs(rank$cum_rel_resp - rank$cum_rel_non_resp);
library(scales)##
## Attaching package: 'scales'## The following objects are masked from 'package:psych':
##
## alpha, rescalerank$rrate <- percent(rank$rrate)
rank$cum_rel_resp <- percent(rank$cum_rel_resp)
rank$cum_rel_non_resp <- percent(rank$cum_rel_non_resp)
View(rank)
library(ROCR)## Warning: package 'ROCR' was built under R version 3.4.3## Loading required package: gplots## Warning: package 'gplots' was built under R version 3.4.3##
## Attaching package: 'gplots'## The following object is masked from 'package:stats':
##
## lowesspred <- prediction(train$predict.score[,2], train$TARGET)
perf <- performance(pred, "tpr", "fpr")
KS <- max(attr(perf, 'y.values')[[1]]-attr(perf, 'x.values')[[1]])
KS## [1] 0.7546218perf## An object of class "performance"
## Slot "x.name":
## [1] "False positive rate"
##
## Slot "y.name":
## [1] "True positive rate"
##
## Slot "alpha.name":
## [1] "Cutoff"
##
## Slot "x.values":
## [[1]]
## [1] 0.000000e+00 0.000000e+00 0.000000e+00 0.000000e+00 0.000000e+00
## [6] 0.000000e+00 0.000000e+00 0.000000e+00 0.000000e+00 0.000000e+00
## [11] 0.000000e+00 0.000000e+00 0.000000e+00 0.000000e+00 0.000000e+00
## [16] 0.000000e+00 0.000000e+00 0.000000e+00 0.000000e+00 0.000000e+00
## [21] 0.000000e+00 0.000000e+00 0.000000e+00 0.000000e+00 0.000000e+00
## [26] 0.000000e+00 0.000000e+00 0.000000e+00 0.000000e+00 0.000000e+00
## [31] 0.000000e+00 0.000000e+00 0.000000e+00 0.000000e+00 0.000000e+00
## [36] 0.000000e+00 0.000000e+00 0.000000e+00 8.151288e-05 8.151288e-05
## [41] 8.151288e-05 1.630258e-04 2.445386e-04 2.445386e-04 2.445386e-04
## [46] 2.445386e-04 2.445386e-04 2.445386e-04 3.260515e-04 4.075644e-04
## [51] 4.075644e-04 4.075644e-04 4.075644e-04 4.075644e-04 4.075644e-04
## [56] 4.890773e-04 4.890773e-04 4.890773e-04 5.705902e-04 5.705902e-04
## [61] 5.705902e-04 5.705902e-04 5.705902e-04 7.336159e-04 7.336159e-04
## [66] 8.151288e-04 8.151288e-04 8.151288e-04 8.151288e-04 8.151288e-04
## [71] 8.151288e-04 8.966417e-04 8.966417e-04 9.781545e-04 9.781545e-04
## [76] 1.141180e-03 1.141180e-03 1.141180e-03 1.141180e-03 1.141180e-03
## [81] 1.141180e-03 1.141180e-03 1.141180e-03 1.222693e-03 1.222693e-03
## [86] 1.222693e-03 1.304206e-03 1.385719e-03 1.385719e-03 1.385719e-03
## [91] 1.467232e-03 1.467232e-03 1.467232e-03 1.467232e-03 1.467232e-03
## [96] 1.467232e-03 1.467232e-03 1.467232e-03 1.467232e-03 1.467232e-03
## [101] 1.467232e-03 1.467232e-03 1.467232e-03 1.548745e-03 1.630258e-03
## [106] 1.630258e-03 1.630258e-03 1.630258e-03 1.630258e-03 1.630258e-03
## [111] 1.711770e-03 1.711770e-03 1.956309e-03 1.956309e-03 1.956309e-03
## [116] 1.956309e-03 2.119335e-03 2.119335e-03 2.119335e-03 2.119335e-03
## [121] 2.200848e-03 2.200848e-03 2.282361e-03 2.445386e-03 2.445386e-03
## [126] 2.445386e-03 2.526899e-03 2.526899e-03 2.689925e-03 2.852951e-03
## [131] 2.852951e-03 2.852951e-03 3.015977e-03 3.342028e-03 3.423541e-03
## [136] 3.505054e-03 3.505054e-03 3.505054e-03 3.505054e-03 3.505054e-03
## [141] 3.505054e-03 3.505054e-03 3.505054e-03 3.505054e-03 3.586567e-03
## [146] 3.668080e-03 3.668080e-03 3.668080e-03 3.668080e-03 3.668080e-03
## [151] 3.668080e-03 3.668080e-03 3.668080e-03 3.668080e-03 3.668080e-03
## [156] 3.831105e-03 3.831105e-03 3.831105e-03 3.831105e-03 3.831105e-03
## [161] 3.831105e-03 3.912618e-03 4.238670e-03 4.320183e-03 4.320183e-03
## [166] 4.320183e-03 4.483208e-03 4.564721e-03 4.564721e-03 4.646234e-03
## [171] 4.646234e-03 4.646234e-03 4.727747e-03 4.809260e-03 4.809260e-03
## [176] 4.809260e-03 4.890773e-03 4.972286e-03 5.135311e-03 5.298337e-03
## [181] 5.461363e-03 5.542876e-03 5.624389e-03 5.950440e-03 6.194979e-03
## [186] 6.602543e-03 6.602543e-03 6.684056e-03 6.928595e-03 7.254646e-03
## [191] 7.336159e-03 7.662211e-03 7.743724e-03 8.151288e-03 8.232801e-03
## [196] 8.640365e-03 8.721878e-03 8.803391e-03 8.966417e-03 9.047930e-03
## [201] 9.129442e-03 9.373981e-03 9.537007e-03 9.618520e-03 9.700033e-03
## [206] 9.781545e-03 9.863058e-03 9.863058e-03 9.944571e-03 1.018911e-02
## [211] 1.035214e-02 1.059667e-02 1.116726e-02 1.124878e-02 1.141180e-02
## [216] 1.149332e-02 1.190088e-02 1.198239e-02 1.238996e-02 1.263450e-02
## [221] 1.271601e-02 1.312357e-02 1.344963e-02 1.393870e-02 1.418324e-02
## [226] 1.459081e-02 1.483534e-02 1.507988e-02 1.532442e-02 1.565047e-02
## [231] 1.589501e-02 1.646560e-02 1.662863e-02 1.744376e-02 1.817737e-02
## [236] 1.866645e-02 1.923704e-02 1.948158e-02 1.980763e-02 2.037822e-02
## [241] 2.086730e-02 2.184545e-02 2.257907e-02 2.266058e-02 2.282361e-02
## [246] 2.314966e-02 2.461689e-02 2.486143e-02 2.535051e-02 2.608412e-02
## [251] 2.657320e-02 2.804043e-02 2.918161e-02 2.975220e-02 3.089338e-02
## [256] 3.179002e-02 3.325725e-02 3.382784e-02 3.439843e-02 3.594718e-02
## [261] 3.716987e-02 3.798500e-02 3.904467e-02 4.034888e-02 4.165308e-02
## [266] 4.295729e-02 4.401695e-02 4.475057e-02 4.572873e-02 4.703293e-02
## [271] 4.817411e-02 4.988588e-02 5.119009e-02 5.273883e-02 5.396153e-02
## [276] 5.510271e-02 5.640691e-02 5.803717e-02 5.901532e-02 6.048256e-02
## [281] 6.170525e-02 6.260189e-02 6.496576e-02 6.708510e-02 6.977502e-02
## [286] 7.140528e-02 7.311705e-02 7.458428e-02 7.548093e-02 7.800783e-02
## [291] 8.020867e-02 8.289860e-02 8.518096e-02 8.697424e-02 9.072383e-02
## [296] 9.341376e-02 9.553309e-02 9.765243e-02 1.000163e-01 1.032768e-01
## [301] 1.076785e-01 1.113466e-01 1.147701e-01 1.184382e-01 1.226769e-01
## [306] 1.270786e-01 1.305836e-01 1.354744e-01 1.411803e-01 1.460711e-01
## [311] 1.526736e-01 1.586241e-01 1.642485e-01 1.696283e-01 1.781872e-01
## [316] 1.847897e-01 1.924519e-01 2.014183e-01 2.123410e-01 2.208999e-01
## [321] 2.316596e-01 2.451907e-01 2.552983e-01 2.698076e-01 2.865178e-01
## [326] 3.042876e-01 3.218128e-01 3.420280e-01 3.672970e-01 3.937072e-01
## [331] 4.231334e-01 4.575318e-01 4.968210e-01 5.454842e-01 6.054777e-01
## [336] 6.755787e-01 7.791816e-01 1.000000e+00
##
##
## Slot "y.values":
## [[1]]
## [1] 0.000000000 0.002886836 0.003464203 0.005196305 0.008083141
## [6] 0.009237875 0.009815242 0.010392610 0.010969977 0.012124711
## [11] 0.013856813 0.014434180 0.015588915 0.016166282 0.018475751
## [16] 0.020785219 0.021362587 0.021939954 0.022517321 0.025981524
## [21] 0.026558891 0.027136259 0.029445727 0.030600462 0.031177829
## [26] 0.031755196 0.032332564 0.032909931 0.034064665 0.034642032
## [31] 0.035219400 0.037528868 0.040993072 0.041570439 0.042725173
## [36] 0.044457275 0.047921478 0.048498845 0.050808314 0.052540416
## [41] 0.054849885 0.054849885 0.056004619 0.056581986 0.057736721
## [46] 0.058314088 0.058891455 0.060046189 0.060623557 0.061778291
## [51] 0.062355658 0.062933025 0.063510393 0.064665127 0.065819861
## [56] 0.065819861 0.066397229 0.066974596 0.068706697 0.069284065
## [61] 0.069861432 0.071016166 0.071593533 0.073325635 0.074480370
## [66] 0.075057737 0.075635104 0.077367206 0.078521940 0.081408776
## [71] 0.081986143 0.083718245 0.084872979 0.088337182 0.089491917
## [76] 0.089491917 0.090646651 0.092956120 0.093533487 0.094688222
## [81] 0.095265589 0.095842956 0.097575058 0.098152425 0.098729792
## [86] 0.100461894 0.102771363 0.103348730 0.106235566 0.107967667
## [91] 0.107967667 0.112009238 0.113163972 0.117205543 0.117782910
## [96] 0.118937644 0.119515012 0.121247113 0.123556582 0.124711316
## [101] 0.125288684 0.126443418 0.127020785 0.128752887 0.131062356
## [106] 0.132217090 0.134526559 0.135681293 0.136258661 0.139722864
## [111] 0.140877598 0.142032333 0.142032333 0.142609700 0.144919169
## [116] 0.146651270 0.146651270 0.148960739 0.151270208 0.152424942
## [121] 0.152424942 0.153002309 0.155311778 0.157621247 0.158775982
## [126] 0.162240185 0.163394919 0.163972286 0.168591224 0.169745958
## [131] 0.171478060 0.176096998 0.178983834 0.181293303 0.184180139
## [136] 0.185334873 0.185912240 0.187644342 0.188221709 0.192263279
## [141] 0.195150115 0.196304850 0.197459584 0.198614319 0.199769053
## [146] 0.199769053 0.203233256 0.206120092 0.207852194 0.210161663
## [151] 0.211893764 0.214203233 0.217090069 0.218822171 0.219399538
## [156] 0.221709007 0.223441109 0.224595843 0.225173210 0.227482679
## [161] 0.232101617 0.233833718 0.236143187 0.237297921 0.239607390
## [166] 0.242494226 0.248845266 0.252309469 0.254618938 0.258083141
## [171] 0.261547344 0.267898383 0.270785219 0.273094688 0.276558891
## [176] 0.279445727 0.285796767 0.290993072 0.293879908 0.300230947
## [181] 0.306581986 0.308891455 0.313510393 0.316397229 0.318129330
## [186] 0.320438799 0.322748268 0.325635104 0.325635104 0.331408776
## [191] 0.337182448 0.340646651 0.341801386 0.343533487 0.344688222
## [196] 0.346997691 0.351039261 0.356235566 0.358545035 0.360277136
## [201] 0.361431871 0.362586605 0.367205543 0.370669746 0.375866051
## [206] 0.380484988 0.381639723 0.383949192 0.387413395 0.390877598
## [211] 0.392032333 0.397228637 0.400115473 0.404734411 0.406466513
## [216] 0.412817552 0.418013857 0.419745958 0.428406467 0.431293303
## [221] 0.433602771 0.438799076 0.442840647 0.443995381 0.448036952
## [226] 0.451501155 0.455542725 0.464780600 0.468244804 0.477482679
## [231] 0.483256351 0.487875289 0.491339492 0.495381062 0.499422633
## [236] 0.501154734 0.502886836 0.506351039 0.508660508 0.509237875
## [241] 0.513856813 0.515011547 0.521362587 0.525981524 0.531177829
## [246] 0.535796767 0.540993072 0.550230947 0.554849885 0.564087760
## [251] 0.568129330 0.575057737 0.577944573 0.581986143 0.587182448
## [256] 0.591801386 0.595265589 0.599307159 0.600461894 0.602771363
## [261] 0.608545035 0.613741339 0.623556582 0.631639723 0.636258661
## [266] 0.643187067 0.647806005 0.656466513 0.661085450 0.665704388
## [271] 0.670900693 0.678983834 0.686489607 0.691685912 0.699769053
## [276] 0.706697460 0.710739030 0.713048499 0.715935335 0.721131640
## [281] 0.725750577 0.732101617 0.737297921 0.742494226 0.749422633
## [286] 0.753464203 0.756351039 0.758660508 0.762702079 0.767898383
## [291] 0.772517321 0.777713626 0.782909931 0.790993072 0.798498845
## [296] 0.808314088 0.813510393 0.821016166 0.829099307 0.834872979
## [301] 0.840069284 0.851039261 0.859699769 0.867782910 0.871824480
## [306] 0.876443418 0.882794457 0.886258661 0.894919169 0.900692841
## [311] 0.904734411 0.909353349 0.911662818 0.919168591 0.924942263
## [316] 0.931870670 0.937066975 0.941685912 0.949769053 0.954387991
## [321] 0.960739030 0.963048499 0.966512702 0.974018476 0.976905312
## [326] 0.980946882 0.984411085 0.987875289 0.990762125 0.992494226
## [331] 0.994803695 0.995958430 0.997690531 0.997690531 0.998267898
## [336] 0.998845266 0.999422633 1.000000000
##
##
## Slot "alpha.values":
## [[1]]
## [1] Inf 0.950 0.876 0.874 0.856 0.852 0.838 0.836 0.808 0.802 0.800
## [12] 0.794 0.766 0.756 0.752 0.748 0.746 0.740 0.736 0.732 0.730 0.726
## [23] 0.724 0.722 0.720 0.718 0.714 0.712 0.710 0.708 0.706 0.704 0.702
## [34] 0.698 0.694 0.688 0.686 0.684 0.682 0.680 0.678 0.668 0.664 0.656
## [45] 0.652 0.646 0.644 0.640 0.638 0.636 0.634 0.628 0.624 0.622 0.620
## [56] 0.618 0.616 0.614 0.612 0.610 0.608 0.606 0.604 0.588 0.586 0.584
## [67] 0.582 0.580 0.578 0.576 0.574 0.572 0.570 0.566 0.564 0.562 0.560
## [78] 0.558 0.554 0.552 0.550 0.548 0.546 0.544 0.538 0.532 0.530 0.526
## [89] 0.522 0.520 0.518 0.512 0.510 0.508 0.504 0.502 0.500 0.498 0.496
## [100] 0.490 0.488 0.486 0.484 0.482 0.480 0.476 0.474 0.472 0.470 0.468
## [111] 0.466 0.462 0.460 0.458 0.456 0.454 0.452 0.448 0.446 0.442 0.440
## [122] 0.438 0.436 0.434 0.432 0.430 0.428 0.426 0.422 0.420 0.418 0.416
## [133] 0.414 0.412 0.410 0.408 0.406 0.404 0.402 0.400 0.398 0.396 0.394
## [144] 0.392 0.390 0.388 0.386 0.384 0.382 0.380 0.378 0.376 0.374 0.372
## [155] 0.370 0.368 0.366 0.364 0.362 0.360 0.358 0.356 0.354 0.352 0.346
## [166] 0.344 0.342 0.340 0.338 0.336 0.334 0.332 0.330 0.328 0.326 0.324
## [177] 0.322 0.320 0.318 0.316 0.314 0.312 0.310 0.308 0.306 0.304 0.302
## [188] 0.300 0.298 0.296 0.294 0.292 0.290 0.288 0.286 0.284 0.282 0.280
## [199] 0.278 0.276 0.274 0.272 0.270 0.268 0.266 0.264 0.262 0.260 0.258
## [210] 0.256 0.254 0.252 0.250 0.248 0.246 0.244 0.242 0.240 0.238 0.236
## [221] 0.234 0.232 0.230 0.228 0.226 0.224 0.222 0.220 0.218 0.216 0.214
## [232] 0.212 0.210 0.208 0.206 0.204 0.202 0.200 0.198 0.196 0.194 0.192
## [243] 0.190 0.188 0.186 0.184 0.182 0.180 0.178 0.176 0.174 0.172 0.170
## [254] 0.168 0.166 0.164 0.162 0.160 0.158 0.156 0.154 0.152 0.150 0.148
## [265] 0.146 0.144 0.142 0.140 0.138 0.136 0.134 0.132 0.130 0.128 0.126
## [276] 0.124 0.122 0.120 0.118 0.116 0.114 0.112 0.110 0.108 0.106 0.104
## [287] 0.102 0.100 0.098 0.096 0.094 0.092 0.090 0.088 0.086 0.084 0.082
## [298] 0.080 0.078 0.076 0.074 0.072 0.070 0.068 0.066 0.064 0.062 0.060
## [309] 0.058 0.056 0.054 0.052 0.050 0.048 0.046 0.044 0.042 0.040 0.038
## [320] 0.036 0.034 0.032 0.030 0.028 0.026 0.024 0.022 0.020 0.018 0.016
## [331] 0.014 0.012 0.010 0.008 0.006 0.004 0.002 0.000Lift chart
perf1 <- performance(pred,"lift","rpp")
plot(perf1, main="lift curve", colorize=T)
LC <- max(attr(perf1, 'y.values')[[1]]-attr(perf1, 'x.values')[[1]])
LC## [1] NaNArea Under Curve
auc <- performance(pred,"auc");
auc <- as.numeric(auc@y.values)
auc## [1] 0.947142plot(perf)
Scoring syntax
test$predict.class <- predict(tRF2,test, type="class")
test$predict.score <- predict(tRF2,test, type="prob")
class(train$predict.score)## [1] "matrix" "votes"Confusion matrix
pred1 <- predict(tRF2, test)
cm1 <- table(Predict = pred1, actual = test$TARGET)
cm1## actual
## Predict 0 1
## 0 5198 698
## 1 22 82Deciling the test data
decile <- function(x){
deciles <- vector(length=10)
for (i in seq(0.1,1,.1)){
deciles[i*10] <- quantile(x, i, na.rm=T)
}
return (
ifelse(x<deciles[1], 1,
ifelse(x<deciles[2], 2,
ifelse(x<deciles[3], 3,
ifelse(x<deciles[4], 4,
ifelse(x<deciles[5], 5,
ifelse(x<deciles[6], 6,
ifelse(x<deciles[7], 7,
ifelse(x<deciles[8], 8,
ifelse(x<deciles[9], 9, 10
))))))))))
}
test$deciles <- decile(test$predict.score[,2])Rank Ordering
library(data.table)
tmp_DT1 = data.table(test)
rank1 <- tmp_DT1[, list(
cnt = length(TARGET),
cnt_resp = sum(TARGET),
cnt_non_resp = sum(TARGET == 0)) ,
by=deciles][order(-deciles)]
rank1$rrate <- round (rank1$cnt_resp / rank1$cnt,2);
rank1$cum_resp <- cumsum(rank1$cnt_resp)
rank1$cum_non_resp <- cumsum(rank1$cnt_non_resp)
rank1$cum_rel_resp <- round(rank1$cum_resp / sum(rank1$cnt_resp),2);
rank1$cum_rel_non_resp <- round(rank1$cum_non_resp / sum(rank1$cnt_non_resp),2);
rank1$ks <- abs(rank1$cum_rel_resp - rank1$cum_rel_non_resp);
library(scales)
rank1$rrate <- percent(rank1$rrate)
rank1$cum_rel_resp <- percent(rank1$cum_rel_resp)
rank1$cum_rel_non_resp <- percent(rank1$cum_rel_non_resp)
View(rank1)KS
pred2 <- prediction(test$predict.score[,2], test$TARGET)
perf2 <- performance(pred2, "tpr", "fpr")
KS2 <- max(attr(perf2, 'y.values')[[1]]-attr(perf2, 'x.values')[[1]])
KS2## [1] 0.6102122perf## An object of class "performance"
## Slot "x.name":
## [1] "False positive rate"
##
## Slot "y.name":
## [1] "True positive rate"
##
## Slot "alpha.name":
## [1] "Cutoff"
##
## Slot "x.values":
## [[1]]
## [1] 0.000000e+00 0.000000e+00 0.000000e+00 0.000000e+00 0.000000e+00
## [6] 0.000000e+00 0.000000e+00 0.000000e+00 0.000000e+00 0.000000e+00
## [11] 0.000000e+00 0.000000e+00 0.000000e+00 0.000000e+00 0.000000e+00
## [16] 0.000000e+00 0.000000e+00 0.000000e+00 0.000000e+00 0.000000e+00
## [21] 0.000000e+00 0.000000e+00 0.000000e+00 0.000000e+00 0.000000e+00
## [26] 0.000000e+00 0.000000e+00 0.000000e+00 0.000000e+00 0.000000e+00
## [31] 0.000000e+00 0.000000e+00 0.000000e+00 0.000000e+00 0.000000e+00
## [36] 0.000000e+00 0.000000e+00 0.000000e+00 8.151288e-05 8.151288e-05
## [41] 8.151288e-05 1.630258e-04 2.445386e-04 2.445386e-04 2.445386e-04
## [46] 2.445386e-04 2.445386e-04 2.445386e-04 3.260515e-04 4.075644e-04
## [51] 4.075644e-04 4.075644e-04 4.075644e-04 4.075644e-04 4.075644e-04
## [56] 4.890773e-04 4.890773e-04 4.890773e-04 5.705902e-04 5.705902e-04
## [61] 5.705902e-04 5.705902e-04 5.705902e-04 7.336159e-04 7.336159e-04
## [66] 8.151288e-04 8.151288e-04 8.151288e-04 8.151288e-04 8.151288e-04
## [71] 8.151288e-04 8.966417e-04 8.966417e-04 9.781545e-04 9.781545e-04
## [76] 1.141180e-03 1.141180e-03 1.141180e-03 1.141180e-03 1.141180e-03
## [81] 1.141180e-03 1.141180e-03 1.141180e-03 1.222693e-03 1.222693e-03
## [86] 1.222693e-03 1.304206e-03 1.385719e-03 1.385719e-03 1.385719e-03
## [91] 1.467232e-03 1.467232e-03 1.467232e-03 1.467232e-03 1.467232e-03
## [96] 1.467232e-03 1.467232e-03 1.467232e-03 1.467232e-03 1.467232e-03
## [101] 1.467232e-03 1.467232e-03 1.467232e-03 1.548745e-03 1.630258e-03
## [106] 1.630258e-03 1.630258e-03 1.630258e-03 1.630258e-03 1.630258e-03
## [111] 1.711770e-03 1.711770e-03 1.956309e-03 1.956309e-03 1.956309e-03
## [116] 1.956309e-03 2.119335e-03 2.119335e-03 2.119335e-03 2.119335e-03
## [121] 2.200848e-03 2.200848e-03 2.282361e-03 2.445386e-03 2.445386e-03
## [126] 2.445386e-03 2.526899e-03 2.526899e-03 2.689925e-03 2.852951e-03
## [131] 2.852951e-03 2.852951e-03 3.015977e-03 3.342028e-03 3.423541e-03
## [136] 3.505054e-03 3.505054e-03 3.505054e-03 3.505054e-03 3.505054e-03
## [141] 3.505054e-03 3.505054e-03 3.505054e-03 3.505054e-03 3.586567e-03
## [146] 3.668080e-03 3.668080e-03 3.668080e-03 3.668080e-03 3.668080e-03
## [151] 3.668080e-03 3.668080e-03 3.668080e-03 3.668080e-03 3.668080e-03
## [156] 3.831105e-03 3.831105e-03 3.831105e-03 3.831105e-03 3.831105e-03
## [161] 3.831105e-03 3.912618e-03 4.238670e-03 4.320183e-03 4.320183e-03
## [166] 4.320183e-03 4.483208e-03 4.564721e-03 4.564721e-03 4.646234e-03
## [171] 4.646234e-03 4.646234e-03 4.727747e-03 4.809260e-03 4.809260e-03
## [176] 4.809260e-03 4.890773e-03 4.972286e-03 5.135311e-03 5.298337e-03
## [181] 5.461363e-03 5.542876e-03 5.624389e-03 5.950440e-03 6.194979e-03
## [186] 6.602543e-03 6.602543e-03 6.684056e-03 6.928595e-03 7.254646e-03
## [191] 7.336159e-03 7.662211e-03 7.743724e-03 8.151288e-03 8.232801e-03
## [196] 8.640365e-03 8.721878e-03 8.803391e-03 8.966417e-03 9.047930e-03
## [201] 9.129442e-03 9.373981e-03 9.537007e-03 9.618520e-03 9.700033e-03
## [206] 9.781545e-03 9.863058e-03 9.863058e-03 9.944571e-03 1.018911e-02
## [211] 1.035214e-02 1.059667e-02 1.116726e-02 1.124878e-02 1.141180e-02
## [216] 1.149332e-02 1.190088e-02 1.198239e-02 1.238996e-02 1.263450e-02
## [221] 1.271601e-02 1.312357e-02 1.344963e-02 1.393870e-02 1.418324e-02
## [226] 1.459081e-02 1.483534e-02 1.507988e-02 1.532442e-02 1.565047e-02
## [231] 1.589501e-02 1.646560e-02 1.662863e-02 1.744376e-02 1.817737e-02
## [236] 1.866645e-02 1.923704e-02 1.948158e-02 1.980763e-02 2.037822e-02
## [241] 2.086730e-02 2.184545e-02 2.257907e-02 2.266058e-02 2.282361e-02
## [246] 2.314966e-02 2.461689e-02 2.486143e-02 2.535051e-02 2.608412e-02
## [251] 2.657320e-02 2.804043e-02 2.918161e-02 2.975220e-02 3.089338e-02
## [256] 3.179002e-02 3.325725e-02 3.382784e-02 3.439843e-02 3.594718e-02
## [261] 3.716987e-02 3.798500e-02 3.904467e-02 4.034888e-02 4.165308e-02
## [266] 4.295729e-02 4.401695e-02 4.475057e-02 4.572873e-02 4.703293e-02
## [271] 4.817411e-02 4.988588e-02 5.119009e-02 5.273883e-02 5.396153e-02
## [276] 5.510271e-02 5.640691e-02 5.803717e-02 5.901532e-02 6.048256e-02
## [281] 6.170525e-02 6.260189e-02 6.496576e-02 6.708510e-02 6.977502e-02
## [286] 7.140528e-02 7.311705e-02 7.458428e-02 7.548093e-02 7.800783e-02
## [291] 8.020867e-02 8.289860e-02 8.518096e-02 8.697424e-02 9.072383e-02
## [296] 9.341376e-02 9.553309e-02 9.765243e-02 1.000163e-01 1.032768e-01
## [301] 1.076785e-01 1.113466e-01 1.147701e-01 1.184382e-01 1.226769e-01
## [306] 1.270786e-01 1.305836e-01 1.354744e-01 1.411803e-01 1.460711e-01
## [311] 1.526736e-01 1.586241e-01 1.642485e-01 1.696283e-01 1.781872e-01
## [316] 1.847897e-01 1.924519e-01 2.014183e-01 2.123410e-01 2.208999e-01
## [321] 2.316596e-01 2.451907e-01 2.552983e-01 2.698076e-01 2.865178e-01
## [326] 3.042876e-01 3.218128e-01 3.420280e-01 3.672970e-01 3.937072e-01
## [331] 4.231334e-01 4.575318e-01 4.968210e-01 5.454842e-01 6.054777e-01
## [336] 6.755787e-01 7.791816e-01 1.000000e+00
##
##
## Slot "y.values":
## [[1]]
## [1] 0.000000000 0.002886836 0.003464203 0.005196305 0.008083141
## [6] 0.009237875 0.009815242 0.010392610 0.010969977 0.012124711
## [11] 0.013856813 0.014434180 0.015588915 0.016166282 0.018475751
## [16] 0.020785219 0.021362587 0.021939954 0.022517321 0.025981524
## [21] 0.026558891 0.027136259 0.029445727 0.030600462 0.031177829
## [26] 0.031755196 0.032332564 0.032909931 0.034064665 0.034642032
## [31] 0.035219400 0.037528868 0.040993072 0.041570439 0.042725173
## [36] 0.044457275 0.047921478 0.048498845 0.050808314 0.052540416
## [41] 0.054849885 0.054849885 0.056004619 0.056581986 0.057736721
## [46] 0.058314088 0.058891455 0.060046189 0.060623557 0.061778291
## [51] 0.062355658 0.062933025 0.063510393 0.064665127 0.065819861
## [56] 0.065819861 0.066397229 0.066974596 0.068706697 0.069284065
## [61] 0.069861432 0.071016166 0.071593533 0.073325635 0.074480370
## [66] 0.075057737 0.075635104 0.077367206 0.078521940 0.081408776
## [71] 0.081986143 0.083718245 0.084872979 0.088337182 0.089491917
## [76] 0.089491917 0.090646651 0.092956120 0.093533487 0.094688222
## [81] 0.095265589 0.095842956 0.097575058 0.098152425 0.098729792
## [86] 0.100461894 0.102771363 0.103348730 0.106235566 0.107967667
## [91] 0.107967667 0.112009238 0.113163972 0.117205543 0.117782910
## [96] 0.118937644 0.119515012 0.121247113 0.123556582 0.124711316
## [101] 0.125288684 0.126443418 0.127020785 0.128752887 0.131062356
## [106] 0.132217090 0.134526559 0.135681293 0.136258661 0.139722864
## [111] 0.140877598 0.142032333 0.142032333 0.142609700 0.144919169
## [116] 0.146651270 0.146651270 0.148960739 0.151270208 0.152424942
## [121] 0.152424942 0.153002309 0.155311778 0.157621247 0.158775982
## [126] 0.162240185 0.163394919 0.163972286 0.168591224 0.169745958
## [131] 0.171478060 0.176096998 0.178983834 0.181293303 0.184180139
## [136] 0.185334873 0.185912240 0.187644342 0.188221709 0.192263279
## [141] 0.195150115 0.196304850 0.197459584 0.198614319 0.199769053
## [146] 0.199769053 0.203233256 0.206120092 0.207852194 0.210161663
## [151] 0.211893764 0.214203233 0.217090069 0.218822171 0.219399538
## [156] 0.221709007 0.223441109 0.224595843 0.225173210 0.227482679
## [161] 0.232101617 0.233833718 0.236143187 0.237297921 0.239607390
## [166] 0.242494226 0.248845266 0.252309469 0.254618938 0.258083141
## [171] 0.261547344 0.267898383 0.270785219 0.273094688 0.276558891
## [176] 0.279445727 0.285796767 0.290993072 0.293879908 0.300230947
## [181] 0.306581986 0.308891455 0.313510393 0.316397229 0.318129330
## [186] 0.320438799 0.322748268 0.325635104 0.325635104 0.331408776
## [191] 0.337182448 0.340646651 0.341801386 0.343533487 0.344688222
## [196] 0.346997691 0.351039261 0.356235566 0.358545035 0.360277136
## [201] 0.361431871 0.362586605 0.367205543 0.370669746 0.375866051
## [206] 0.380484988 0.381639723 0.383949192 0.387413395 0.390877598
## [211] 0.392032333 0.397228637 0.400115473 0.404734411 0.406466513
## [216] 0.412817552 0.418013857 0.419745958 0.428406467 0.431293303
## [221] 0.433602771 0.438799076 0.442840647 0.443995381 0.448036952
## [226] 0.451501155 0.455542725 0.464780600 0.468244804 0.477482679
## [231] 0.483256351 0.487875289 0.491339492 0.495381062 0.499422633
## [236] 0.501154734 0.502886836 0.506351039 0.508660508 0.509237875
## [241] 0.513856813 0.515011547 0.521362587 0.525981524 0.531177829
## [246] 0.535796767 0.540993072 0.550230947 0.554849885 0.564087760
## [251] 0.568129330 0.575057737 0.577944573 0.581986143 0.587182448
## [256] 0.591801386 0.595265589 0.599307159 0.600461894 0.602771363
## [261] 0.608545035 0.613741339 0.623556582 0.631639723 0.636258661
## [266] 0.643187067 0.647806005 0.656466513 0.661085450 0.665704388
## [271] 0.670900693 0.678983834 0.686489607 0.691685912 0.699769053
## [276] 0.706697460 0.710739030 0.713048499 0.715935335 0.721131640
## [281] 0.725750577 0.732101617 0.737297921 0.742494226 0.749422633
## [286] 0.753464203 0.756351039 0.758660508 0.762702079 0.767898383
## [291] 0.772517321 0.777713626 0.782909931 0.790993072 0.798498845
## [296] 0.808314088 0.813510393 0.821016166 0.829099307 0.834872979
## [301] 0.840069284 0.851039261 0.859699769 0.867782910 0.871824480
## [306] 0.876443418 0.882794457 0.886258661 0.894919169 0.900692841
## [311] 0.904734411 0.909353349 0.911662818 0.919168591 0.924942263
## [316] 0.931870670 0.937066975 0.941685912 0.949769053 0.954387991
## [321] 0.960739030 0.963048499 0.966512702 0.974018476 0.976905312
## [326] 0.980946882 0.984411085 0.987875289 0.990762125 0.992494226
## [331] 0.994803695 0.995958430 0.997690531 0.997690531 0.998267898
## [336] 0.998845266 0.999422633 1.000000000
##
##
## Slot "alpha.values":
## [[1]]
## [1] Inf 0.950 0.876 0.874 0.856 0.852 0.838 0.836 0.808 0.802 0.800
## [12] 0.794 0.766 0.756 0.752 0.748 0.746 0.740 0.736 0.732 0.730 0.726
## [23] 0.724 0.722 0.720 0.718 0.714 0.712 0.710 0.708 0.706 0.704 0.702
## [34] 0.698 0.694 0.688 0.686 0.684 0.682 0.680 0.678 0.668 0.664 0.656
## [45] 0.652 0.646 0.644 0.640 0.638 0.636 0.634 0.628 0.624 0.622 0.620
## [56] 0.618 0.616 0.614 0.612 0.610 0.608 0.606 0.604 0.588 0.586 0.584
## [67] 0.582 0.580 0.578 0.576 0.574 0.572 0.570 0.566 0.564 0.562 0.560
## [78] 0.558 0.554 0.552 0.550 0.548 0.546 0.544 0.538 0.532 0.530 0.526
## [89] 0.522 0.520 0.518 0.512 0.510 0.508 0.504 0.502 0.500 0.498 0.496
## [100] 0.490 0.488 0.486 0.484 0.482 0.480 0.476 0.474 0.472 0.470 0.468
## [111] 0.466 0.462 0.460 0.458 0.456 0.454 0.452 0.448 0.446 0.442 0.440
## [122] 0.438 0.436 0.434 0.432 0.430 0.428 0.426 0.422 0.420 0.418 0.416
## [133] 0.414 0.412 0.410 0.408 0.406 0.404 0.402 0.400 0.398 0.396 0.394
## [144] 0.392 0.390 0.388 0.386 0.384 0.382 0.380 0.378 0.376 0.374 0.372
## [155] 0.370 0.368 0.366 0.364 0.362 0.360 0.358 0.356 0.354 0.352 0.346
## [166] 0.344 0.342 0.340 0.338 0.336 0.334 0.332 0.330 0.328 0.326 0.324
## [177] 0.322 0.320 0.318 0.316 0.314 0.312 0.310 0.308 0.306 0.304 0.302
## [188] 0.300 0.298 0.296 0.294 0.292 0.290 0.288 0.286 0.284 0.282 0.280
## [199] 0.278 0.276 0.274 0.272 0.270 0.268 0.266 0.264 0.262 0.260 0.258
## [210] 0.256 0.254 0.252 0.250 0.248 0.246 0.244 0.242 0.240 0.238 0.236
## [221] 0.234 0.232 0.230 0.228 0.226 0.224 0.222 0.220 0.218 0.216 0.214
## [232] 0.212 0.210 0.208 0.206 0.204 0.202 0.200 0.198 0.196 0.194 0.192
## [243] 0.190 0.188 0.186 0.184 0.182 0.180 0.178 0.176 0.174 0.172 0.170
## [254] 0.168 0.166 0.164 0.162 0.160 0.158 0.156 0.154 0.152 0.150 0.148
## [265] 0.146 0.144 0.142 0.140 0.138 0.136 0.134 0.132 0.130 0.128 0.126
## [276] 0.124 0.122 0.120 0.118 0.116 0.114 0.112 0.110 0.108 0.106 0.104
## [287] 0.102 0.100 0.098 0.096 0.094 0.092 0.090 0.088 0.086 0.084 0.082
## [298] 0.080 0.078 0.076 0.074 0.072 0.070 0.068 0.066 0.064 0.062 0.060
## [309] 0.058 0.056 0.054 0.052 0.050 0.048 0.046 0.044 0.042 0.040 0.038
## [320] 0.036 0.034 0.032 0.030 0.028 0.026 0.024 0.022 0.020 0.018 0.016
## [331] 0.014 0.012 0.010 0.008 0.006 0.004 0.002 0.000Lift chart
perf3 <- performance(pred2,"lift","rpp")Area Under Curve
auc <- performance(pred2,"auc");
auc <- as.numeric(auc@y.values)
auc## [1] 0.8727702plot(perf2)