Loading and preprocessing the data
library(rpart) # R package for decision Tree
library(caret) # R package for decision Tree
## Loading required package: lattice
## Loading required package: ggplot2
setwd("D:/Users/gkokate/Desktop/Markdown")
build <- read.csv(file = "Build .csv",sep = ",", header = TRUE)
test1 <- read.csv(file = "test.csv", sep = "," , header = TRUE)
# Sample observations
head(build)
## gponOntAniOpInfoOpticalSignalLevel gponOntAniOpInfoTxOpticalSignalLevel
## 1 -7711 1142
## 2 -7703 1288
## 3 -7703 1081
## 4 -7703 1207
## 5 -7688 1276
## 6 -7688 1282
## gponOntOltsideOpInfoRxOpticalSignalLevel X15MinDnFwdByteCounter
## 1 -171 8.888281
## 2 -170 9.544178
## 3 -170 8.915710
## 4 -171 7.555582
## 5 -170 7.475159
## 6 -169 7.236687
## X15MinUpFwdByteCounter bponOntOpInfoDistance ifOperStatus
## 1 7.245204 38 up
## 2 7.764763 38 up
## 3 7.648214 38 up
## 4 6.976296 38 up
## 5 6.646812 38 up
## 6 6.449259 38 up
#dependent variable as a factor (categorical)
build$ifOperStatus <- as.factor(build$ifOperStatus)
# Split data into training (70%) and validation (30%)
split <- sample(nrow(build),floor(nrow(build)*0.7))
train <- build[split,]
val <- build[-split,]
Decision Tree Model
mtree <- rpart(ifOperStatus~ .,data=train,method = "class",parms = list(prior = c(0.3, 0.7)))
#parms = list(prior = c(0.5, 0.5)
#Confusion matrix
rpartpred <- predict(mtree,val,type="class")
confusionMatrix(rpartpred,val$ifOperStatus)
## Confusion Matrix and Statistics
##
## Reference
## Prediction down up
## down 215 300
## up 54 3995
##
## Accuracy : 0.9224
## 95% CI : (0.9143, 0.93)
## No Information Rate : 0.9411
## P-Value [Acc > NIR] : 1
##
## Kappa : 0.5106
## Mcnemar's Test P-Value : <2e-16
##
## Sensitivity : 0.79926
## Specificity : 0.93015
## Pos Pred Value : 0.41748
## Neg Pred Value : 0.98666
## Prevalence : 0.05894
## Detection Rate : 0.04711
## Detection Prevalence : 0.11284
## Balanced Accuracy : 0.86470
##
## 'Positive' Class : down
##
#Plot tree
plot(mtree)
#Lable on Decision Tree
text(mtree)
library(rattle)
## Rattle: A free graphical interface for data mining with R.
## Version 4.1.0 Copyright (c) 2006-2015 Togaware Pty Ltd.
## Type 'rattle()' to shake, rattle, and roll your data.
library(rpart.plot)
library(RColorBrewer)
#plot
prp(mtree, faclen = 0, cex = 0.8, extra = 1)
tot_count <- function(x, labs, digits, varlen)
{paste(labs, "\n\nn =", x$frame$n)}
## Decision Tree
prp(mtree, faclen = 0, cex = 0.8, node.fun=tot_count)
printcp(mtree)
##
## Classification tree:
## rpart(formula = ifOperStatus ~ ., data = train, method = "class",
## parms = list(prior = c(0.3, 0.7)))
##
## Variables actually used in tree construction:
## [1] bponOntOpInfoDistance
## [2] gponOntOltsideOpInfoRxOpticalSignalLevel
## [3] X15MinDnFwdByteCounter
## [4] X15MinUpFwdByteCounter
##
## Root node error: 3194.4/10648 = 0.3
##
## n= 10648
##
## CP nsplit rel error xerror xstd
## 1 0.620251 0 1.00000 1.00000 0.037639
## 2 0.014403 1 0.37975 0.37975 0.021782
## 3 0.010304 4 0.33654 0.35330 0.017771
## 4 0.010000 5 0.32624 0.34084 0.017437
bestcp <- mtree$cptable[which.min(mtree$cptable[,"xerror"]),"CP"]
#Pruning & classification matrix of Pruning
pruned <- prune(mtree, cp = bestcp)
prp(pruned, faclen = 0, cex = 0.8, extra = 1)
predictions <- predict(pruned, val, type="class")
confusionMatrix(predictions,val$ifOperStatus)
## Confusion Matrix and Statistics
##
## Reference
## Prediction down up
## down 215 300
## up 54 3995
##
## Accuracy : 0.9224
## 95% CI : (0.9143, 0.93)
## No Information Rate : 0.9411
## P-Value [Acc > NIR] : 1
##
## Kappa : 0.5106
## Mcnemar's Test P-Value : <2e-16
##
## Sensitivity : 0.79926
## Specificity : 0.93015
## Pos Pred Value : 0.41748
## Neg Pred Value : 0.98666
## Prevalence : 0.05894
## Detection Rate : 0.04711
## Detection Prevalence : 0.11284
## Balanced Accuracy : 0.86470
##
## 'Positive' Class : down
##
##Scoring
library(ROCR)
## Loading required package: gplots
##
## Attaching package: 'gplots'
## The following object is masked from 'package:stats':
##
## lowess
val1 = predict(pruned, val, type = "prob")
pred_val <-prediction(val1[,2],val$ifOperStatus)
perf_val <- performance(pred_val,"auc")
perf_val
## An object of class "performance"
## Slot "x.name":
## [1] "None"
##
## Slot "y.name":
## [1] "Area under the ROC curve"
##
## Slot "alpha.name":
## [1] "none"
##
## Slot "x.values":
## list()
##
## Slot "y.values":
## [[1]]
## [1] 0.8938214
##
##
## Slot "alpha.values":
## list()
plot(performance(pred_val, measure="lift", x.measure="rpp"), colorize=TRUE)
# Calculating True Positive and False Positive Rate
perf_val <- performance(pred_val, "tpr", "fpr")
#Plot the ROC curve
plot(perf_val, col = "green", lwd = 1.5)
#Calculating KS statistics
ks1.tree <- max(attr(perf_val, "y.values")[[1]] - (attr(perf_val, "x.values")[[1]]))
ks1.tree
## [1] 0.733552
## Cross Validation Method1
library(ROSE)
## Loaded ROSE 0.0-3
ROSE.BOOT <- ROSE.eval(ifOperStatus ~ ., data = train, learner = rpart,method.assess = "BOOT", extr.pred = function(obj)obj[,2], seed = 1)
# Cross Validation Method2
library(caret)
tc <- trainControl("cv",10)
rpart.grid <- expand.grid(.cp=0.2)
(train.rpart <- train(ifOperStatus ~., data= train, method="rpart",trControl=tc,tuneGrid=rpart.grid))
## CART
##
## 10648 samples
## 6 predictor
## 2 classes: 'down', 'up'
##
## No pre-processing
## Resampling: Cross-Validated (10 fold)
## Summary of sample sizes: 9583, 9583, 9584, 9582, 9584, 9583, ...
## Resampling results
##
## Accuracy Kappa Accuracy SD Kappa SD
## 0.9536065 0.6241365 0.006786997 0.0476512
##
## Tuning parameter 'cp' was held constant at a value of 0.2
##
# Model Perfomance on test data
ptest <- predict(mtree, test1)
answers <- as.vector(ptest)
pml_write_files = function(x) {
n = length(x)
for (i in 1:n) {
filename = paste0("problem_id_", i, ".txt")
write.table(x[i], file = filename, quote = FALSE, row.names = FALSE,
col.names = FALSE)
}
}
pml_write_files(answers)
## Prediction of probabilites new data
ptest
## down up
## 1 0.06152869 0.9384713
## 2 0.60895045 0.3910496
## 3 0.06152869 0.9384713
## 4 0.07471066 0.9252893
## 5 0.06152869 0.9384713
## 6 0.41645011 0.5835499
## 7 0.06152869 0.9384713
## 8 0.07471066 0.9252893
## 9 0.06152869 0.9384713
## 10 0.07471066 0.9252893
## 11 0.06152869 0.9384713
## 12 0.60895045 0.3910496
## 13 0.06152869 0.9384713
## 14 0.60895045 0.3910496
## 15 0.06152869 0.9384713
## 16 0.60895045 0.3910496
## 17 0.06152869 0.9384713
## 18 0.60895045 0.3910496
## 19 0.06152869 0.9384713
## 20 0.60895045 0.3910496
## 21 0.06152869 0.9384713
## 22 0.60895045 0.3910496
## 23 0.06152869 0.9384713
## 24 0.60895045 0.3910496
## 25 0.06152869 0.9384713
## 26 0.60895045 0.3910496
## 27 0.06152869 0.9384713
## 28 0.60895045 0.3910496
## 29 0.06152869 0.9384713
## 30 0.60895045 0.3910496
## 31 0.06152869 0.9384713
## 32 0.60895045 0.3910496
## 33 0.06152869 0.9384713
## 34 0.60895045 0.3910496
## 35 0.06152869 0.9384713
## 36 0.60895045 0.3910496
## 37 0.06152869 0.9384713
## 38 0.60895045 0.3910496
## 39 0.06152869 0.9384713
## 40 0.60895045 0.3910496
## 41 0.06152869 0.9384713
## 42 0.60895045 0.3910496
## 43 0.06152869 0.9384713
## 44 0.60895045 0.3910496
## 45 0.06152869 0.9384713
## 46 0.41645011 0.5835499
## 47 0.06152869 0.9384713
## 48 0.06152869 0.9384713
## 49 0.06152869 0.9384713
## 50 0.60895045 0.3910496
## 51 0.06152869 0.9384713
## 52 0.60895045 0.3910496
## 53 0.06152869 0.9384713
## 54 0.60895045 0.3910496
## 55 0.06152869 0.9384713
## 56 0.60895045 0.3910496
## 57 0.06152869 0.9384713
## 58 0.60895045 0.3910496
## 59 0.06152869 0.9384713
## 60 0.60895045 0.3910496
## 61 0.06152869 0.9384713
## 62 0.60895045 0.3910496
## 63 0.06152869 0.9384713
## 64 0.60895045 0.3910496
## 65 0.06152869 0.9384713
## 66 0.07471066 0.9252893
## 67 0.06152869 0.9384713
## 68 0.60895045 0.3910496
## 69 0.06152869 0.9384713
## 70 0.60895045 0.3910496
## 71 0.06152869 0.9384713
## 72 0.60895045 0.3910496
## 73 0.06152869 0.9384713
## 74 0.60895045 0.3910496
## 75 0.06152869 0.9384713
## 76 0.07471066 0.9252893
## 77 0.06152869 0.9384713
## 78 0.60895045 0.3910496
## 79 0.06152869 0.9384713
## 80 0.60895045 0.3910496
## 81 0.06152869 0.9384713
## 82 0.07471066 0.9252893
## 83 0.06152869 0.9384713
## 84 0.60895045 0.3910496
## 85 0.06152869 0.9384713
## 86 0.60895045 0.3910496
## 87 0.06152869 0.9384713
## 88 0.60895045 0.3910496
## 89 0.06152869 0.9384713
## 90 0.60895045 0.3910496
## 91 0.06152869 0.9384713
## 92 0.60895045 0.3910496
## 93 0.06152869 0.9384713
## 94 0.41645011 0.5835499
## 95 0.06152869 0.9384713
## 96 0.41645011 0.5835499
## 97 0.06152869 0.9384713
## 98 0.60895045 0.3910496
## 99 0.06152869 0.9384713
## 100 0.60895045 0.3910496
## 101 0.06152869 0.9384713
## 102 0.60895045 0.3910496
## 103 0.06152869 0.9384713
## 104 0.41645011 0.5835499
## 105 0.06152869 0.9384713
## 106 0.60895045 0.3910496
## 107 0.60895045 0.3910496
## 108 0.06152869 0.9384713
## 109 0.60895045 0.3910496
## 110 0.06152869 0.9384713
## 111 0.60895045 0.3910496
## 112 0.06152869 0.9384713
## 113 0.60895045 0.3910496
## 114 0.06152869 0.9384713
## 115 0.60895045 0.3910496
## 116 0.06152869 0.9384713
## 117 0.60895045 0.3910496
## 118 0.06152869 0.9384713
## 119 0.07471066 0.9252893
## 120 0.06152869 0.9384713