Weekly
data set, which is part of the ISLR2 package. This data is similar in
nature to the Smarket data from this chapter’s lab, except that it
contains 1, 089 weekly returns for 21 years, from the beginning of 1990
to the end of 2010.library(ISLR2)
(a) Produce some numerical and graphical summaries of the Weekly data. Do there appear to be any patterns?
summary(Weekly)
## Year Lag1 Lag2 Lag3
## Min. :1990 Min. :-18.1950 Min. :-18.1950 Min. :-18.1950
## 1st Qu.:1995 1st Qu.: -1.1540 1st Qu.: -1.1540 1st Qu.: -1.1580
## Median :2000 Median : 0.2410 Median : 0.2410 Median : 0.2410
## Mean :2000 Mean : 0.1506 Mean : 0.1511 Mean : 0.1472
## 3rd Qu.:2005 3rd Qu.: 1.4050 3rd Qu.: 1.4090 3rd Qu.: 1.4090
## Max. :2010 Max. : 12.0260 Max. : 12.0260 Max. : 12.0260
## Lag4 Lag5 Volume Today
## Min. :-18.1950 Min. :-18.1950 Min. :0.08747 Min. :-18.1950
## 1st Qu.: -1.1580 1st Qu.: -1.1660 1st Qu.:0.33202 1st Qu.: -1.1540
## Median : 0.2380 Median : 0.2340 Median :1.00268 Median : 0.2410
## Mean : 0.1458 Mean : 0.1399 Mean :1.57462 Mean : 0.1499
## 3rd Qu.: 1.4090 3rd Qu.: 1.4050 3rd Qu.:2.05373 3rd Qu.: 1.4050
## Max. : 12.0260 Max. : 12.0260 Max. :9.32821 Max. : 12.0260
## Direction
## Down:484
## Up :605
##
##
##
##
pairs(Weekly)
plot(Weekly$Volume, ylab = "Shares traded (in billions)")
cor(Weekly[,-9])
## Year Lag1 Lag2 Lag3 Lag4
## Year 1.00000000 -0.032289274 -0.03339001 -0.03000649 -0.031127923
## Lag1 -0.03228927 1.000000000 -0.07485305 0.05863568 -0.071273876
## Lag2 -0.03339001 -0.074853051 1.00000000 -0.07572091 0.058381535
## Lag3 -0.03000649 0.058635682 -0.07572091 1.00000000 -0.075395865
## Lag4 -0.03112792 -0.071273876 0.05838153 -0.07539587 1.000000000
## Lag5 -0.03051910 -0.008183096 -0.07249948 0.06065717 -0.075675027
## Volume 0.84194162 -0.064951313 -0.08551314 -0.06928771 -0.061074617
## Today -0.03245989 -0.075031842 0.05916672 -0.07124364 -0.007825873
## Lag5 Volume Today
## Year -0.030519101 0.84194162 -0.032459894
## Lag1 -0.008183096 -0.06495131 -0.075031842
## Lag2 -0.072499482 -0.08551314 0.059166717
## Lag3 0.060657175 -0.06928771 -0.071243639
## Lag4 -0.075675027 -0.06107462 -0.007825873
## Lag5 1.000000000 -0.05851741 0.011012698
## Volume -0.058517414 1.00000000 -0.033077783
## Today 0.011012698 -0.03307778 1.000000000
With the exception of year and volume, the scatterplot shown above
does not appear to show any relationship between the covariants. I
attempted to calculate the increase in share volume over a 21-year
period using the plot function. I made an effort to quantitatively find
the collinear correlations between year and volume using the corelation
matrix. Volume and Year’s lone significant value of 0.842 fits with the
strong link shown in the scatterplot and correlation matrix above.
(b) Use the full data set to perform a logistic regression with
Direction as the response and the five lag variables plus Volume as
predictors. Use the summary function to print the results. Do any of the
predictors appear to be statistically significant? If so, which
ones?
glm.fit=glm(Direction~Lag1+Lag2+Lag3+Lag4+Lag5+Volume,data=Weekly, family=binomial)
summary(glm.fit)
##
## Call:
## glm(formula = Direction ~ Lag1 + Lag2 + Lag3 + Lag4 + Lag5 +
## Volume, family = binomial, data = Weekly)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -1.6949 -1.2565 0.9913 1.0849 1.4579
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 0.26686 0.08593 3.106 0.0019 **
## Lag1 -0.04127 0.02641 -1.563 0.1181
## Lag2 0.05844 0.02686 2.175 0.0296 *
## Lag3 -0.01606 0.02666 -0.602 0.5469
## Lag4 -0.02779 0.02646 -1.050 0.2937
## Lag5 -0.01447 0.02638 -0.549 0.5833
## Volume -0.02274 0.03690 -0.616 0.5377
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 1496.2 on 1088 degrees of freedom
## Residual deviance: 1486.4 on 1082 degrees of freedom
## AIC: 1500.4
##
## Number of Fisher Scoring iterations: 4
With the “glm” function, we can calculate the logistic regression.
Lag2 is the statistically significant predictor; p-value of 0.0296
provides evidence at the 5% significance level to reject the null
hypothesis that it is unrelated to the response Direction.
(c) Compute the confusion matrix and overall fraction of correct
predictions. Explain what the confusion matrix is telling you about the
types of mistakes made by logistic regression.
glm.probs=predict(glm.fit,type='response')
glm.pred=rep("Down",1089)
glm.pred[glm.probs>0.5]="Up"
table(glm.pred,Weekly$Direction)
##
## glm.pred Down Up
## Down 54 48
## Up 430 557
mean(glm.pred==Weekly$Direction)
## [1] 0.5610652
This shows that the model properly forecasted the weekly market
movement 56.11% of the time. Differentiating between how the model
correctly forecasts the upward and downward trends. The model was 92.07%
accurate in predicting the weekly uptrends (557/(48+557)=0.9207; up). On
the other hand, just 11.15% of down weekly trends were accurately
anticipated, or 54/(430+54)=0.1115.
(d) Now fit the logistic regression model using a training data
period from 1990 to 2008, with Lag2 as the only predictor. Compute the
confusion matrix and the overall fraction of correct predictions for the
held out data (that is, the data from 2009 and 2010).
train=(Weekly$Year<2009)
head(train)
## [1] TRUE TRUE TRUE TRUE TRUE TRUE
tail(train)
## [1] FALSE FALSE FALSE FALSE FALSE FALSE
Weekly.test=Weekly[!train,]
dim(Weekly)
## [1] 1089 9
dim(Weekly.test)
## [1] 104 9
Direction.test=Weekly$Direction[!train]
glm.fits=glm(Direction~Lag2, data=Weekly, subset=train, family=binomial)
glm.probs=predict(glm.fits, Weekly.test,type='response')
glm.pred=rep('Down',104)
glm.pred[glm.probs>0.5]='Up'
table(glm.pred,Direction.test)
## Direction.test
## glm.pred Down Up
## Down 9 5
## Up 34 56
mean(glm.pred==Direction.test)
## [1] 0.625
The model successfully predicted weekly trends at a rate of 62.5%
after dividing the entire Weekly dataset into a training and test
dataset, which is a marginal improvement over the model that used the
entire dataset. Although this model was able to slightly improve on
correctly forecasting downward trends, it also performed better at
predicting upward trends (56/(56+5)= 0.918: 91.80%) than downward ones
(9/(34+9)=0.2093: 20.93%).
(e) Repeat (d) using LDA.
library(MASS)
lda.fit=lda(Direction~Lag2, data=Weekly, subset=train)
lda.fit
## Call:
## lda(Direction ~ Lag2, data = Weekly, subset = train)
##
## Prior probabilities of groups:
## Down Up
## 0.4477157 0.5522843
##
## Group means:
## Lag2
## Down -0.03568254
## Up 0.26036581
##
## Coefficients of linear discriminants:
## LD1
## Lag2 0.4414162
lda.pred=predict(lda.fit, Weekly.test)
table(lda.pred$class, Direction.test)
## Direction.test
## Down Up
## Down 9 5
## Up 34 56
mean(lda.pred$class==Direction.test)
## [1] 0.625
Similar outcomes were obtained when a classifying model was developed
using linear discriminant analysis as compared to the logistic
regression model developed in above section.
(f) Repeat (d) using QDA.
qda.fit=qda(Direction~Lag2, data=Weekly, subset=train)
qda.fit
## Call:
## qda(Direction ~ Lag2, data = Weekly, subset = train)
##
## Prior probabilities of groups:
## Down Up
## 0.4477157 0.5522843
##
## Group means:
## Lag2
## Down -0.03568254
## Up 0.26036581
qda.class=predict(qda.fit, Weekly.test)$class
table(qda.class, Direction.test)
## Direction.test
## qda.class Down Up
## Down 0 0
## Up 43 61
mean(qda.class==Direction.test)
## [1] 0.5865385
Compared to the earlier methods, quadratic linear analysis produced a
model with a lower accuracy of 58.65%. Furthermore, this model only
evaluated estimating the accuracy of weekly upward trends, degrading the
weekly downward trends.
(g) Repeat (d) using KNN with K = 1.
library(class)
attach(Weekly)
train.X=as.matrix(Lag2[train])
test.X=as.matrix(Lag2[!train])
train.Direction=Direction[train]
dim(train.X)
## [1] 985 1
dim(test.X)
## [1] 104 1
set.seed(1)
knn.pred=knn(train.X,test.X,train.Direction,k=1)
table(knn.pred, Direction.test)
## Direction.test
## knn.pred Down Up
## Down 21 30
## Up 22 31
mean(knn.pred==Direction.test)
## [1] 0.5
A classification model created using K-Nearest Neighbors seemed to
have an accuracy rate of 50%, which is the same as pure guessing.
(h) Repeat (d) using naive Bayes.
library(e1071)
nbayes=naiveBayes(Direction~Lag2, data=Weekly, subset=train)
nbayes
##
## Naive Bayes Classifier for Discrete Predictors
##
## Call:
## naiveBayes.default(x = X, y = Y, laplace = laplace)
##
## A-priori probabilities:
## Y
## Down Up
## 0.4477157 0.5522843
##
## Conditional probabilities:
## Lag2
## Y [,1] [,2]
## Down -0.03568254 2.199504
## Up 0.26036581 2.317485
nbayes.class=predict(nbayes,Weekly.test)
table(nbayes.class, Direction.test)
## Direction.test
## nbayes.class Down Up
## Down 0 0
## Up 43 61
mean(nbayes.class==Direction.test)
## [1] 0.5865385
A classification model created using Naive Bayes seemed to have an
accuracy rate of 58.65%, which is the same as Quadratic Linear Analysis
model.
(i) Which of these methods appears to provide the best results
on this data?
It seems that the models that performed the best on this data were
linear discriminant analysis and logistic regression, both of which were
equally effective.
**(j) Experiment with different combinations of predictors, including
possible transformations and interactions, for each of the methods.
Report the variables, method, and associated confusion matrix that
appears to provide the best results on the held out data. Note that you
should also experiment with values for K in the KNN classifier.
#Logistic regression
attach(Weekly)
Weekly.fit=glm(Direction~Lag2:Lag4+Lag2, data=Weekly,family=binomial, subset=train)
logWeekly.prob= predict(Weekly.fit, Weekly.test, type = "response")
logWeekly.pred = rep("Down", length(logWeekly.prob))
logWeekly.pred[logWeekly.prob > 0.5] = "Up"
Direction.test=Direction[!train]
table(logWeekly.pred, Direction.test)
## Direction.test
## logWeekly.pred Down Up
## Down 3 4
## Up 40 57
mean(logWeekly.pred == Direction.test)
## [1] 0.5769231
#Linear Discriminant Analysis
Weeklylda.fit=lda(Direction~Lag2:Lag4+Lag2, data=Weekly,family=binomial, subset=train)
Weeklylda.pred=predict(Weeklylda.fit, Weekly.test)
table(Weeklylda.pred$class, Direction.test)
## Direction.test
## Down Up
## Down 3 3
## Up 40 58
mean(Weeklylda.pred$class==Direction.test)
## [1] 0.5865385
#Quadratic Discriminant Analysis
Weeklyqda.fit = qda(Direction ~ poly(Lag2,2), data = Weekly, subset = train)
Weeklyqda.pred = predict(Weeklyqda.fit, Weekly.test)$class
table(Weeklyqda.pred, Direction.test)
## Direction.test
## Weeklyqda.pred Down Up
## Down 7 3
## Up 36 58
mean(Weeklyqda.pred==Direction.test)
## [1] 0.625
#KNN Neighbors for K=4
Week.train=as.matrix(Lag2[train])
Week.test=as.matrix(Lag2[!train])
train.Direction =Direction[train]
set.seed(1)
Weekknn.pred=knn(Week.train,Week.test,train.Direction,k=4)
table(Weekknn.pred,Direction.test)
## Direction.test
## Weekknn.pred Down Up
## Down 20 17
## Up 23 44
mean(Weekknn.pred==Direction.test)
## [1] 0.6153846
#K=10
Week.train=as.matrix(Lag2[train])
Week.test=as.matrix(Lag2[!train])
train.Direction =Direction[train]
set.seed(1)
Weekknn.pred=knn(Week.train,Week.test,train.Direction,k=10)
table(Weekknn.pred,Direction.test)
## Direction.test
## Weekknn.pred Down Up
## Down 17 21
## Up 26 40
mean(Weekknn.pred==Direction.test)
## [1] 0.5480769
detach(Weekly)
After trying different transformations for the different methods, the
Quadratic Discriminant Analysis shows the best accuracy rate i.e. 62.5%.
In the case of KNN Neighbors method for K=4 shows the next best
prediction rate.
##Problem 14: In this problem, you will develop a model to predict
whether a given car gets high or low gas mileage based on the Auto
data set.
library(ISLR2)
library(MASS)
Auto=na.omit(Auto)
summary(Auto)
## mpg cylinders displacement horsepower weight
## Min. : 9.00 Min. :3.000 Min. : 68.0 Min. : 46.0 Min. :1613
## 1st Qu.:17.00 1st Qu.:4.000 1st Qu.:105.0 1st Qu.: 75.0 1st Qu.:2225
## Median :22.75 Median :4.000 Median :151.0 Median : 93.5 Median :2804
## Mean :23.45 Mean :5.472 Mean :194.4 Mean :104.5 Mean :2978
## 3rd Qu.:29.00 3rd Qu.:8.000 3rd Qu.:275.8 3rd Qu.:126.0 3rd Qu.:3615
## Max. :46.60 Max. :8.000 Max. :455.0 Max. :230.0 Max. :5140
##
## acceleration year origin name
## Min. : 8.00 Min. :70.00 Min. :1.000 amc matador : 5
## 1st Qu.:13.78 1st Qu.:73.00 1st Qu.:1.000 ford pinto : 5
## Median :15.50 Median :76.00 Median :1.000 toyota corolla : 5
## Mean :15.54 Mean :75.98 Mean :1.577 amc gremlin : 4
## 3rd Qu.:17.02 3rd Qu.:79.00 3rd Qu.:2.000 amc hornet : 4
## Max. :24.80 Max. :82.00 Max. :3.000 chevrolet chevette: 4
## (Other) :365
(a) Create a binary variable, mpg01, that contains a 1 if mpg contains a value above its median, and a 0 if mpg contains a value below its median. You can compute the median using the median() function. Note you may find it helpful to use the data.frame() function to create a single data set containing both mpg01 and the other Auto variables.
attach(Auto)
mpg01=rep(0, length(mpg))
mpg01[mpg > median(mpg)]=1
Auto = data.frame(Auto, mpg01)
head(Auto)
## mpg cylinders displacement horsepower weight acceleration year origin
## 1 18 8 307 130 3504 12.0 70 1
## 2 15 8 350 165 3693 11.5 70 1
## 3 18 8 318 150 3436 11.0 70 1
## 4 16 8 304 150 3433 12.0 70 1
## 5 17 8 302 140 3449 10.5 70 1
## 6 15 8 429 198 4341 10.0 70 1
## name mpg01
## 1 chevrolet chevelle malibu 0
## 2 buick skylark 320 0
## 3 plymouth satellite 0
## 4 amc rebel sst 0
## 5 ford torino 0
## 6 ford galaxie 500 0
(b) Explore the data graphically in order to investigate the association between mpg01 and the other features. Which of the other features seem most likely to be useful in predicting mpg01? Scatterplots and boxplots may be useful tools to answer this question. Describe your findings.
par(mfrow = c(2, 3))
plot(factor(Auto$mpg01), Auto$cylinders, ylab = "Number of engine cylinders")
plot(factor(Auto$mpg01), Auto$displacement, ylab = "Engine displacement (cubic inches)")
plot(factor(Auto$mpg01), Auto$horsepower, ylab = "Horsepower")
plot(factor(Auto$mpg01), Auto$weight, ylab = "Weight (pounds)")
plot(factor(Auto$mpg01), Auto$acceleration, ylab = "Time to reach 60mpg (seconds)")
plot(factor(Auto$mpg01), Auto$year, ylab = "Manufacture year")
mtext("Boxplots for cars with above(1) and below(0) median mpg", outer = TRUE, line = -1)
As we can see in the box plot for manufacturing year and time there is a
lot of overlap between the two categories of car based on median mpg.
But with the other predictors there are no overlaps between the two
categories. This suggest that cylinders, displacement, horsepower and
weight would be the most useful in predicting mpg01.
par(mfrow = c(3, 2))
plot(Auto$cylinders, Auto$mpg01, xlab = "Number of engine cylinders")
plot(Auto$displacement, Auto$mpg01, xlab = "Engine displacement (cubic inches)")
plot(Auto$horsepower, Auto$mpg01, xlab = "Horsepower")
plot(Auto$weight, Auto$mpg01, xlab = "Weight (pounds)")
plot(Auto$acceleration, Auto$mpg01, xlab = "Time to reach 60mpg (seconds)")
plot(Auto$year, Auto$mpg01, xlab = "Manufacture year")
mtext("Scatterplots for cars with above(1) and below(0) median mpg", outer = TRUE, line = -1)
Further evidence that horsepower and weight will be helpful in
predicting mpg01 can be found in scatterplots with mpg01 on the y-axis
and the various quantitative variables on the x-axis. These scatterplots
show clusters of above-median mpgs at the low ends and clusters of
below-median mpgs at the high ends of each variable’s range. Cylinders
and discplacement appear to be less useful on their own, at least for
logistic regression, according to the scatterplots that show them.
(c) Split the data into a training set and a test
set.
train = (year %% 2 == 0)
train.auto = Auto[train,]
test.auto = Auto[-train,]
(d) Perform LDA on the training data in order to predict mpg01 using the variables that seemed most associated with mpg01 in (b). What is the test error of the model obtained?
autolda.fit = lda(mpg01~displacement+horsepower+weight+cylinders, data=train.auto)
autolda.pred = predict(autolda.fit, test.auto)
table(autolda.pred$class, test.auto$mpg01)
##
## 0 1
## 0 169 13
## 1 26 183
mean(autolda.pred$class != test.auto$mpg01)
## [1] 0.09974425
Using LDA method to create a classifying model using the variable
that was most associated with the mpg01 in (b) resulted in a test error
rate of 11.2%.
(e) Perform QDA on the training data in order to predict mpg01
using the variables that seemed most associated with mpg01 in (b). What
is the test error of the model obtained?
autoqda.fit <- qda(mpg01~displacement+horsepower+weight+cylinders, data=train.auto)
autoqda.pred <- predict(autoqda.fit, test.auto)
table(autoqda.pred$class, test.auto$mpg01)
##
## 0 1
## 0 174 19
## 1 21 177
mean(autoqda.pred$class != test.auto$mpg01)
## [1] 0.1023018
Using QDA method to create a classifying model using the variable
that was most associated with the mpg01 in (b) resulted in a test error
rate of 11.5%.
(f) Perform logistic regression on the training data in order to
predict mpg01 using the variables that seemed most associated with mpg01
in (b). What is the test error of the model obtained?
auto.fit=glm(mpg01~displacement+horsepower+weight+cylinders, data=train.auto,family=binomial)
auto.probs = predict(auto.fit, test.auto, type = "response")
auto.pred = rep(0, length(auto.probs))
auto.pred[auto.probs > 0.5] = 1
table(auto.pred, test.auto$mpg01)
##
## auto.pred 0 1
## 0 176 15
## 1 19 181
mean(auto.pred != test.auto$mpg01)
## [1] 0.08695652
Using Logistic Regression method to create a classifying model using
the variable that was most associated with the mpg01 in (b) resulted in
a test error rate of 9.7%.
(g) Perform naive Bayes on the training data in order to predict
mpg01 using the variables that seemed most associated with mpg01 in (b).
What is the test error of the model obtained?
library(e1071)
nbayesauto=naiveBayes(mpg01~displacement+horsepower+weight+cylinders, data=train.auto)
nbayesauto
##
## Naive Bayes Classifier for Discrete Predictors
##
## Call:
## naiveBayes.default(x = X, y = Y, laplace = laplace)
##
## A-priori probabilities:
## Y
## 0 1
## 0.4571429 0.5428571
##
## Conditional probabilities:
## displacement
## Y [,1] [,2]
## 0 271.7396 89.15194
## 1 111.6623 28.27696
##
## horsepower
## Y [,1] [,2]
## 0 133.14583 38.49319
## 1 77.92105 15.19731
##
## weight
## Y [,1] [,2]
## 0 3604.823 624.9159
## 1 2314.763 334.7228
##
## cylinders
## Y [,1] [,2]
## 0 6.812500 1.4165377
## 1 4.070175 0.3928408
nbayesauto.class=predict(nbayesauto,test.auto)
table(nbayesauto.class, test.auto$mpg01)
##
## nbayesauto.class 0 1
## 0 171 15
## 1 24 181
mean(nbayesauto.class !=test.auto$mpg01)
## [1] 0.09974425
Using Naive Bayes method to create a classifying model using the
variable that was most associated with the mpg01 in (b) resulted in a
test error rate of 11.2% which is same as LDA method.
(h) Perform KNN on the training data, with several values of K,
in order to predict mpg01. Use only the variables that seemed most
associated with mpg01 in (b). What test errors do you obtain? Which
value of K seems to perform the best on this data set?
library(class)
#K=1
train.K= cbind(displacement,horsepower,weight,cylinders)[train,]
test.K=cbind(displacement,horsepower,weight,cylinders)[-train,]
set.seed(1)
autok.pred=knn(train.K,test.K,train.auto$mpg01,k=1)
table(autok.pred,test.auto$mpg01)
##
## autok.pred 0 1
## 0 178 11
## 1 17 185
mean(autok.pred != test.auto$mpg01)
## [1] 0.07161125
#K=8
train.K= cbind(displacement,horsepower,weight,cylinders)[train,]
test.K=cbind(displacement,horsepower,weight,cylinders)[-train,]
set.seed(1)
autok.pred=knn(train.K,test.K,train.auto$mpg01,k=8)
table(autok.pred,test.auto$mpg01)
##
## autok.pred 0 1
## 0 159 12
## 1 36 184
mean(autok.pred != test.auto$mpg01)
## [1] 0.1227621
#K=15
train.K= cbind(displacement,horsepower,weight,cylinders)[train,]
test.K=cbind(displacement,horsepower,weight,cylinders)[-train,]
set.seed(1)
autok.pred=knn(train.K,test.K,train.auto$mpg01,k=15)
table(autok.pred,test.auto$mpg01)
##
## autok.pred 0 1
## 0 157 15
## 1 38 181
mean(autok.pred != test.auto$mpg01)
## [1] 0.1355499
detach(Auto)
Looking into the results of the K-nearest neighbors, it seems that
K=1 has the lowest error rate of 6.9% and with the increase in K value
the error rate is also increasing.
#Problem 16: Using the Boston data set, fit classification models in
order to predict whether a given census tract has a crime rate above or
below the median. Explore logistic regression, LDA, naive Bayes, and KNN
models using various subsets of the predictors. Describe your findings.
Hint: You will have to create the response variable yourself, using the
variables that are contained in the Boston data set.
attach(Boston)
crime1 = rep(0, length(crim))
crime1[crim>median(crim)] = 1
Boston = data.frame(Boston, crime1)
train = 1:(dim(Boston)[1]/2)
test = (dim(Boston)[1]/2+1):dim(Boston)[1]
Boston.train = Boston[train,]
Boston.test = Boston[test,]
crime1.test = crime1[test]
plot(Boston)
from the above plot we can see a correlation between nox,tax,rad,indus,
and lstat.
#logistic Regression
set.seed(1)
Boston.fit = glm(crime1~nox + tax + rad + indus + lstat, data = Boston, family = binomial)
Boston.probs = predict(Boston.fit, Boston.test, type ="response")
Boston.pred = rep(0, length(Boston.probs))
Boston.pred[Boston.probs > 0.5] = 1
table(Boston.pred, crime1.test)
## crime1.test
## Boston.pred 0 1
## 0 82 16
## 1 8 147
mean(Boston.pred == crime1.test)
## [1] 0.9051383
Logistic Regression shows 90% of accuracy rate based on the associated predictors.
#Linear Discriminant Analysis
ldaBoston.fit = lda(crime1~nox + tax + rad + indus + lstat, data = Boston.train)
ldaBoston.pred = predict(ldaBoston.fit, Boston.test)
table(ldaBoston.pred$class, crime1.test)
## crime1.test
## 0 1
## 0 80 18
## 1 10 145
mean(ldaBoston.pred$class == crime1.test)
## [1] 0.8893281
Linear Discriminant Analysis shows 88.9% of accuracy rate based on the associated predictors.
#Naive Bayes
nbBoston.fit = naiveBayes(crime1~nox + tax + rad + indus + lstat, data = Boston, subset = train)
nbBoston.class = predict(nbBoston.fit, Boston.test)
table(nbBoston.class, crime1.test)
## crime1.test
## nbBoston.class 0 1
## 0 80 18
## 1 10 145
mean(nbBoston.class == crime1.test)
## [1] 0.8893281
Naive Bayes method shows similar accuracy rate as LDA i.e 88.9% based on the associated predictors.
#KNN for K=1
train.B = cbind(nox,tax,rad,indus,lstat)[train,]
test.B = cbind(nox,tax,rad,indus,lstat)[test,]
train.crime = crime1.test
set.seed(1)
Bostonknn.pred = knn(train.B, test.B, train.crime, k=1)
table(Bostonknn.pred, crime1.test)
## crime1.test
## Bostonknn.pred 0 1
## 0 34 140
## 1 56 23
mean(Bostonknn.pred == crime1.test)
## [1] 0.2252964
#KNN for K=6
train.B = cbind(nox,tax,rad,indus,lstat)[train,]
test.B = cbind(nox,tax,rad,indus,lstat)[test,]
train.crime = crime1.test
set.seed(1)
Bostonknn.pred = knn(train.B, test.B, train.crime, k=6)
table(Bostonknn.pred, crime1.test)
## crime1.test
## Bostonknn.pred 0 1
## 0 27 19
## 1 63 144
mean(Bostonknn.pred == crime1.test)
## [1] 0.6758893
#KNN for K=18
train.B = cbind(nox,tax,rad,indus,lstat)[train,]
test.B = cbind(nox,tax,rad,indus,lstat)[test,]
train.crime = crime1.test
set.seed(1)
Bostonknn.pred = knn(train.B, test.B, train.crime, k=18)
table(Bostonknn.pred, crime1.test)
## crime1.test
## Bostonknn.pred 0 1
## 0 51 23
## 1 39 140
mean(Bostonknn.pred == crime1.test)
## [1] 0.7549407
#KNN for K=22
train.B = cbind(nox,tax,rad,indus,lstat)[train,]
test.B = cbind(nox,tax,rad,indus,lstat)[test,]
train.crime = crime1.test
set.seed(1)
Bostonknn.pred = knn(train.B, test.B, train.crime, k=22)
table(Bostonknn.pred, crime1.test)
## crime1.test
## Bostonknn.pred 0 1
## 0 41 18
## 1 49 145
mean(Bostonknn.pred == crime1.test)
## [1] 0.7351779
In KNN method we can see for increasing value of K the accuracy rate tend to increase untill certain point and then it starts decreasing.