Scribd
Upload
64 views

Project

The document discusses building a logistic regression model to predict customer satisfaction from flight data. It loads necessary packages, splits the data into training and validation sets, and fits a logistic regression model to the training data with satisfaction as the outcome. It examines the model coefficients, plots residuals against predictions, and evaluates the model's performance on the validation data using ROC curves and a confusion matrix.

Uploaded by

api-554183287
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
64 views

Project

The document discusses building a logistic regression model to predict customer satisfaction from flight data. It loads necessary packages, splits the data into training and validation sets, and fits a logistic regression model to the training data with satisfaction as the outcome. It examines the model coefficients, plots residuals against predictions, and evaluates the model's performance on the validation data using ROC curves and a confusion matrix.

Uploaded by

api-554183287
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 16

MATH445 Project

setwd("C:/Users/Ryan/Desktop/spring 2021/MATH445/project due may 5th")


library(MASS)
library(caret)

## Warning: package ’caret’ was built under R version 3.6.3

## Loading required package: lattice

## Loading required package: ggplot2

## Warning: package ’ggplot2’ was built under R version 3.6.3

library(pROC)

## Warning: package ’pROC’ was built under R version 3.6.3

## Type ’citation("pROC")’ for a citation.

##
## Attaching package: ’pROC’

## The following objects are masked from ’package:stats’:


##
## cov, smooth, var

train.full <- read.csv("train.csv")


train <- train.full[1:round(0.7*nrow(train.full)),]
val <- train.full[round(0.7*nrow(train.full)):nrow(train.full),]
test <- read.csv("test.csv")
summary(train)

## X id Gender Customer.Type
## Min. : 0 Min. : 2 Female:36949 disloyal Customer:13371
## 1st Qu.:18183 1st Qu.: 32441 Male :35784 Loyal Customer :59362
## Median :36366 Median : 64717
## Mean :36366 Mean : 64825
## 3rd Qu.:54549 3rd Qu.: 97240
## Max. :72732 Max. :129880
##
## Age Type.of.Travel Class Flight.Distance
## Min. : 7.00 Business travel:50228 Business:34777 Min. : 31
## 1st Qu.:27.00 Personal Travel:22505 Eco :32719 1st Qu.: 413

1
## Median :40.00 Eco Plus: 5237 Median : 842
## Mean :39.37 Mean :1188
## 3rd Qu.:51.00 3rd Qu.:1741
## Max. :85.00 Max. :4983
##
## Inflight.wifi.service Departure.Arrival.time.convenient Ease.of.Online.booking
## Min. :0.000 Min. :0.000 Min. :0.000
## 1st Qu.:2.000 1st Qu.:2.000 1st Qu.:2.000
## Median :3.000 Median :3.000 Median :3.000
## Mean :2.732 Mean :3.059 Mean :2.756
## 3rd Qu.:4.000 3rd Qu.:4.000 3rd Qu.:4.000
## Max. :5.000 Max. :5.000 Max. :5.000
##
## Gate.location Food.and.drink Online.boarding Seat.comfort
## Min. :0.000 Min. :0.000 Min. :0.000 Min. :0.000
## 1st Qu.:2.000 1st Qu.:2.000 1st Qu.:2.000 1st Qu.:2.000
## Median :3.000 Median :3.000 Median :3.000 Median :4.000
## Mean :2.973 Mean :3.206 Mean :3.252 Mean :3.443
## 3rd Qu.:4.000 3rd Qu.:4.000 3rd Qu.:4.000 3rd Qu.:5.000
## Max. :5.000 Max. :5.000 Max. :5.000 Max. :5.000
##
## Inflight.entertainment On.board.service Leg.room.service Baggage.handling
## Min. :0.000 Min. :0.000 Min. :0.000 Min. :1.000
## 1st Qu.:2.000 1st Qu.:2.000 1st Qu.:2.000 1st Qu.:3.000
## Median :4.000 Median :4.000 Median :4.000 Median :4.000
## Mean :3.359 Mean :3.381 Mean :3.348 Mean :3.633
## 3rd Qu.:4.000 3rd Qu.:4.000 3rd Qu.:4.000 3rd Qu.:5.000
## Max. :5.000 Max. :5.000 Max. :5.000 Max. :5.000
##
## Checkin.service Inflight.service Cleanliness Departure.Delay.in.Minutes
## Min. :0.000 Min. :0.000 Min. :0.000 Min. : 0.0
## 1st Qu.:3.000 1st Qu.:3.000 1st Qu.:2.000 1st Qu.: 0.0
## Median :3.000 Median :4.000 Median :3.000 Median : 0.0
## Mean :3.307 Mean :3.641 Mean :3.289 Mean : 14.8
## 3rd Qu.:4.000 3rd Qu.:5.000 3rd Qu.:4.000 3rd Qu.: 12.0
## Max. :5.000 Max. :5.000 Max. :5.000 Max. :1305.0
##
## Arrival.Delay.in.Minutes satisfaction
## Min. : 0.00 neutral or dissatisfied:41133
## 1st Qu.: 0.00 satisfied :31600
## Median : 0.00
## Mean : 15.14
## 3rd Qu.: 13.00
## Max. :1280.00
## NA’s :220

model.LR <- glm(satisfaction~.,data = train[,3:25], family = "binomial")


summary(model.LR)

##
## Call:
## glm(formula = satisfaction ~ ., family = "binomial", data = train[,
## 3:25])
##

2
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -2.8399 -0.4966 -0.1781 0.3931 4.0168
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -7.800e+00 9.363e-02 -83.305 < 2e-16 ***
## GenderMale 6.586e-02 2.318e-02 2.841 0.00450 **
## Customer.TypeLoyal Customer 2.030e+00 3.566e-02 56.944 < 2e-16 ***
## Age -8.651e-03 8.469e-04 -10.215 < 2e-16 ***
## Type.of.TravelPersonal Travel -2.729e+00 3.748e-02 -72.801 < 2e-16 ***
## ClassEco -7.087e-01 3.049e-02 -23.242 < 2e-16 ***
## ClassEco Plus -8.450e-01 4.951e-02 -17.068 < 2e-16 ***
## Flight.Distance -2.133e-05 1.349e-05 -1.581 0.11388
## Inflight.wifi.service 3.897e-01 1.362e-02 28.612 < 2e-16 ***
## Departure.Arrival.time.convenient -1.290e-01 9.747e-03 -13.236 < 2e-16 ***
## Ease.of.Online.booking -1.448e-01 1.345e-02 -10.770 < 2e-16 ***
## Gate.location 3.079e-02 1.089e-02 2.827 0.00469 **
## Food.and.drink -2.466e-02 1.275e-02 -1.935 0.05305 .
## Online.boarding 6.122e-01 1.221e-02 50.147 < 2e-16 ***
## Seat.comfort 6.755e-02 1.331e-02 5.076 3.86e-07 ***
## Inflight.entertainment 5.335e-02 1.698e-02 3.142 0.00168 **
## On.board.service 3.033e-01 1.211e-02 25.051 < 2e-16 ***
## Leg.room.service 2.543e-01 1.014e-02 25.083 < 2e-16 ***
## Baggage.handling 1.332e-01 1.356e-02 9.825 < 2e-16 ***
## Checkin.service 3.173e-01 1.018e-02 31.152 < 2e-16 ***
## Inflight.service 1.244e-01 1.435e-02 8.667 < 2e-16 ***
## Cleanliness 2.201e-01 1.446e-02 15.220 < 2e-16 ***
## Departure.Delay.in.Minutes 4.876e-03 1.180e-03 4.133 3.58e-05 ***
## Arrival.Delay.in.Minutes -9.301e-03 1.165e-03 -7.987 1.39e-15 ***
## ---
## Signif. codes: 0 ’***’ 0.001 ’**’ 0.01 ’*’ 0.05 ’.’ 0.1 ’ ’ 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 99276 on 72512 degrees of freedom
## Residual deviance: 48864 on 72489 degrees of freedom
## (220 observations deleted due to missingness)
## AIC: 48912
##
## Number of Fisher Scoring iterations: 5

plot(density(train$Flight.Distance))

3
density.default(x = train$Flight.Distance)
0e+00 2e−04 4e−04 6e−04 8e−04
Density

0 1000 2000 3000 4000 5000

N = 72733 Bandwidth = 95.06

plot(table(train$Food.and.drink, train$satisfaction))

4
table(train$Food.and.drink, train$satisfaction)

neutral or dissatisfied
satisfied 0 1 2 3 4 5

Looking at the summary for the logistic regression, the two main predictors struggling with significance are
flight distance and Food and Drink satisfaction. Quickly looking at the density of flight distance, it looks
like there is a lot of good data and it may just be a weak predictor in this model. The stacked bar chart
of Food and Drink ratings looks like a similar number are in each container where a rank of 1 on food and
drink seems good at being related to dissatisfaction and 2,3 are roughly the same but slightly higher levels
of satisfaction and then 4,5 improve slightly more on those two, it seems like a good predictor as well so
there may be something else going on.

plot(predict(model.LR), residuals(model.LR), col=train$satisfaction);abline(h=0,lty=2,col="grey");lines(

5
4
3
residuals(model.LR)

2
1
0
−1
−2
−3

−10 −5 0 5

predict(model.LR)

LR.valpredictions <- predict(model.LR, newdata = val, type = "response")


roc.curve.LR <- roc(val$satisfaction, LR.valpredictions, ci=T)

## Setting levels: control = neutral or dissatisfied, case = satisfied

## Setting direction: controls < cases

plot(roc.curve.LR, main="Logistic Regression ROC")

6
Logistic Regression ROC
1.0
0.8
0.6
Sensitivity
0.4
0.2
0.0

1.0 0.5 0.0


Specificity

LR.valpredictions <- ifelse(LR.valpredictions>0.5,"satisfied","neutral or dissatisfied")


caret::confusionMatrix(factor(LR.valpredictions), val$satisfaction)

## Confusion Matrix and Statistics


##
## Reference
## Prediction neutral or dissatisfied satisfied
## neutral or dissatisfied 16015 2128
## satisfied 1677 11262
##
## Accuracy : 0.8776
## 95% CI : (0.8739, 0.8812)
## No Information Rate : 0.5692
## P-Value [Acc > NIR] : < 2.2e-16
##
## Kappa : 0.7494
##
## Mcnemar’s Test P-Value : 2.983e-13
##
## Sensitivity : 0.9052
## Specificity : 0.8411
## Pos Pred Value : 0.8827
## Neg Pred Value : 0.8704
## Prevalence : 0.5692
## Detection Rate : 0.5152

7
## Detection Prevalence : 0.5837
## Balanced Accuracy : 0.8731
##
## ’Positive’ Class : neutral or dissatisfied
##

So the diagnostic plots are suspicions, there are clear patterns in the residuals (some of them are quiet pretty
as well). The ROC curve looks reasonable and the confusion matrix makes it more clear with accuracy CI
95% (0.8739, 0.8812).

model.lda <- lda(satisfaction~., data = train)


lda.valpredictions <- predict(model.lda, newdata = val, type = "response")

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

8
## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

9
## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

10
## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

caret::confusionMatrix(lda.valpredictions$class, val$satisfaction)

## Confusion Matrix and Statistics


##
## Reference
## Prediction neutral or dissatisfied satisfied
## neutral or dissatisfied 16007 2177
## satisfied 1685 11213
##
## Accuracy : 0.8757
## 95% CI : (0.872, 0.8794)
## No Information Rate : 0.5692
## P-Value [Acc > NIR] : < 2.2e-16
##
## Kappa : 0.7455
##
## Mcnemar’s Test P-Value : 2.769e-15
##
## Sensitivity : 0.9048
## Specificity : 0.8374
## Pos Pred Value : 0.8803
## Neg Pred Value : 0.8694

11
## Prevalence : 0.5692
## Detection Rate : 0.5150
## Detection Prevalence : 0.5850
## Balanced Accuracy : 0.8711
##
## ’Positive’ Class : neutral or dissatisfied
##

model.qda <- qda(satisfaction~., data = train)


qda.valpredictions <- predict(model.qda, newdata = val, type = "response")

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

12
## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

13
## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

14
## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf

caret::confusionMatrix(qda.valpredictions$class, val$satisfaction)

## Confusion Matrix and Statistics


##
## Reference
## Prediction neutral or dissatisfied satisfied
## neutral or dissatisfied 15897 2489
## satisfied 1795 10901
##
## Accuracy : 0.8622
## 95% CI : (0.8583, 0.866)
## No Information Rate : 0.5692
## P-Value [Acc > NIR] : < 2.2e-16
##
## Kappa : 0.7172
##
## Mcnemar’s Test P-Value : < 2.2e-16
##
## Sensitivity : 0.8985
## Specificity : 0.8141
## Pos Pred Value : 0.8646
## Neg Pred Value : 0.8586
## Prevalence : 0.5692
## Detection Rate : 0.5115
## Detection Prevalence : 0.5915

15
## Balanced Accuracy : 0.8563
##
## ’Positive’ Class : neutral or dissatisfied
##

16

You might also like