library(ISLR)
## Warning: package 'ISLR' was built under R version 4.2.2
library(e1071)
## Warning: package 'e1071' was built under R version 4.2.2
5 A
set.seed(1)
x1 <- runif(500) - 0.5
x2 <- runif(500) - 0.5
y <- 1 * (x1^2 - x2^2 > 0)
B
plot(x1[y == 0], x2[y == 0], col = "red", xlab = "X1", ylab = "X2", pch = "+")
points(x1[y == 1], x2[y == 1], col = "blue", pch = 4)
C
lm.fit <- glm(y~ x1 + x2, family = binomial)
summary(lm.fit)
##
## Call:
## glm(formula = y ~ x1 + x2, family = binomial)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -1.179 -1.139 -1.112 1.206 1.257
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -0.087260 0.089579 -0.974 0.330
## x1 0.196199 0.316864 0.619 0.536
## x2 -0.002854 0.305712 -0.009 0.993
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 692.18 on 499 degrees of freedom
## Residual deviance: 691.79 on 497 degrees of freedom
## AIC: 697.79
##
## Number of Fisher Scoring iterations: 3
I had issues past this point and got too frustrated to continue. Thanks for everything this semester, I will say this class is intense and I relied a decent amount in the internet, but I did learn a decent amount about some of the core concepts. It is actually pretty nice understanding the concepts behind testing/training data and some of the different approaches. NOw when speaking with my data analyttics team at work, I am not as intimidated!
7 A
gas.med = median(Auto$mpg)
new.var = ifelse(Auto$mpg > gas.med, 1, 0)
Auto$mpglevel = as.factor(new.var)
B
set.seed(1)
tune.out = tune(svm, mpglevel ~ ., data = Auto, kernel = "linear", ranges = list(cost = c(0.01, 0.1, 1, 5, 10, 100)))
summary(tune.out)
##
## Parameter tuning of 'svm':
##
## - sampling method: 10-fold cross validation
##
## - best parameters:
## cost
## 1
##
## - best performance: 0.01025641
##
## - Detailed performance results:
## cost error dispersion
## 1 1e-02 0.07653846 0.03617137
## 2 1e-01 0.04596154 0.03378238
## 3 1e+00 0.01025641 0.01792836
## 4 5e+00 0.02051282 0.02648194
## 5 1e+01 0.02051282 0.02648194
## 6 1e+02 0.03076923 0.03151981
C
set.seed(1)
tune.out = tune(svm, mpglevel ~ ., data = Auto, kernel = "polynomial", ranges = list(cost = c(0.1, 1, 5, 10), degree = c(2, 3, 4)))
summary(tune.out)
##
## Parameter tuning of 'svm':
##
## - sampling method: 10-fold cross validation
##
## - best parameters:
## cost degree
## 10 2
##
## - best performance: 0.5130128
##
## - Detailed performance results:
## cost degree error dispersion
## 1 0.1 2 0.5511538 0.04366593
## 2 1.0 2 0.5511538 0.04366593
## 3 5.0 2 0.5511538 0.04366593
## 4 10.0 2 0.5130128 0.08963366
## 5 0.1 3 0.5511538 0.04366593
## 6 1.0 3 0.5511538 0.04366593
## 7 5.0 3 0.5511538 0.04366593
## 8 10.0 3 0.5511538 0.04366593
## 9 0.1 4 0.5511538 0.04366593
## 10 1.0 4 0.5511538 0.04366593
## 11 5.0 4 0.5511538 0.04366593
## 12 10.0 4 0.5511538 0.04366593
set.seed(3)
tune.out = tune(svm, mpglevel ~ ., data = Auto, kernel = "radial", ranges = list(cost = c(0.1, 1, 5, 10), gamma = c(0.01, 0.1, 1, 5, 10, 100)))
summary(tune.out)
##
## Parameter tuning of 'svm':
##
## - sampling method: 10-fold cross validation
##
## - best parameters:
## cost gamma
## 10 0.01
##
## - best performance: 0.02551282
##
## - Detailed performance results:
## cost gamma error dispersion
## 1 0.1 1e-02 0.08935897 0.05024613
## 2 1.0 1e-02 0.07397436 0.03896185
## 3 5.0 1e-02 0.05358974 0.03718096
## 4 10.0 1e-02 0.02551282 0.02417610
## 5 0.1 1e-01 0.07653846 0.04350608
## 6 1.0 1e-01 0.05358974 0.03718096
## 7 5.0 1e-01 0.03320513 0.02720447
## 8 10.0 1e-01 0.02807692 0.01894083
## 9 0.1 1e+00 0.55346154 0.04319433
## 10 1.0 1e+00 0.06384615 0.04400278
## 11 5.0 1e+00 0.06391026 0.04047896
## 12 10.0 1e+00 0.06391026 0.04047896
## 13 0.1 5e+00 0.55346154 0.04319433
## 14 1.0 5e+00 0.49230769 0.05344444
## 15 5.0 5e+00 0.48980769 0.05628746
## 16 10.0 5e+00 0.48980769 0.05628746
## 17 0.1 1e+01 0.55346154 0.04319433
## 18 1.0 1e+01 0.52019231 0.06053102
## 19 5.0 1e+01 0.51006410 0.04925670
## 20 10.0 1e+01 0.51006410 0.04925670
## 21 0.1 1e+02 0.55346154 0.04319433
## 22 1.0 1e+02 0.55346154 0.04319433
## 23 5.0 1e+02 0.55346154 0.04319433
## 24 10.0 1e+02 0.55346154 0.04319433
D
svm.linear = svm(mpglevel ~ ., data = Auto, kernel = "linear", cost = 1)
svm.poly = svm(mpglevel ~ ., data = Auto, kernel = "polynomial", cost = 10,
degree = 2)
svm.radial = svm(mpglevel ~ ., data = Auto, kernel = "radial", cost = 10, gamma = 0.01)
plotpairs = function(fit) {
for (name in names(Auto)[!(names(Auto) %in% c("mpg", "mpglevel", "name"))]) {
plot(fit, Auto, as.formula(paste("mpg~", name, sep = "")))
}
}
plotpairs(svm.linear)
8 A
attach(OJ)
set.seed(1)
train<-sample(dim(OJ)[1], 800)
OJtraining<-OJ[train,]
OJtesting<-OJ[-train,]
B
OJsvm.lin <- svm(Purchase ~ ., kernel='linear', data=OJtraining, cost=0.01)
summary(OJsvm.lin)
##
## Call:
## svm(formula = Purchase ~ ., data = OJtraining, kernel = "linear",
## cost = 0.01)
##
##
## Parameters:
## SVM-Type: C-classification
## SVM-Kernel: linear
## cost: 0.01
##
## Number of Support Vectors: 435
##
## ( 219 216 )
##
##
## Number of Classes: 2
##
## Levels:
## CH MM
C
train.pred<-predict(OJsvm.lin, OJtraining)
table(OJtraining$Purchase, train.pred)
## train.pred
## CH MM
## CH 420 65
## MM 75 240
The error rate is 17.5%
test.pred<-predict(OJsvm.lin, OJtesting)
table(OJtesting$Purchase, test.pred)
## test.pred
## CH MM
## CH 153 15
## MM 33 69
The error rate is 17.8%
D
tune.out = tune(svm, Purchase ~ ., data = OJtraining, kernel = "linear", ranges = list(cost = 10^seq(-2, 1, by = 0.25)))
summary(tune.out)
##
## Parameter tuning of 'svm':
##
## - sampling method: 10-fold cross validation
##
## - best parameters:
## cost
## 10
##
## - best performance: 0.17125
##
## - Detailed performance results:
## cost error dispersion
## 1 0.01000000 0.17375 0.03884174
## 2 0.01778279 0.17500 0.03996526
## 3 0.03162278 0.17750 0.03717451
## 4 0.05623413 0.18000 0.03073181
## 5 0.10000000 0.17875 0.03064696
## 6 0.17782794 0.17875 0.03537988
## 7 0.31622777 0.17875 0.03438447
## 8 0.56234133 0.17625 0.03197764
## 9 1.00000000 0.17500 0.03061862
## 10 1.77827941 0.17375 0.02972676
## 11 3.16227766 0.17250 0.03270236
## 12 5.62341325 0.17250 0.03322900
## 13 10.00000000 0.17125 0.03488573
svm.linear = svm(Purchase ~ ., kernel = "linear", data = OJtraining, cost = tune.out$best.parameters$cost)
train.pred = predict(svm.linear, OJtraining)
table(OJtraining$Purchase, train.pred)
## train.pred
## CH MM
## CH 423 62
## MM 69 246
test.pred = predict(svm.linear, OJtesting)
table(OJtesting$Purchase, test.pred)
## test.pred
## CH MM
## CH 156 12
## MM 28 74
E The error rates have reduced to 16.4% and 14.8% respectively
F
svm.radial = svm(Purchase ~ ., data = OJtraining, kernel = "radial")
summary(svm.radial)
##
## Call:
## svm(formula = Purchase ~ ., data = OJtraining, kernel = "radial")
##
##
## Parameters:
## SVM-Type: C-classification
## SVM-Kernel: radial
## cost: 1
##
## Number of Support Vectors: 373
##
## ( 188 185 )
##
##
## Number of Classes: 2
##
## Levels:
## CH MM
train.pred = predict(svm.radial, OJtraining)
table(OJtraining$Purchase, train.pred)
## train.pred
## CH MM
## CH 441 44
## MM 77 238
test.pred = predict(svm.radial, OJtesting)
table(OJtesting$Purchase, test.pred)
## test.pred
## CH MM
## CH 151 17
## MM 33 69
tune.out = tune(svm, Purchase ~ ., data = OJtesting, kernel = "radial", ranges = list(cost = 10^seq(-2, 1, by = 0.25)))
summary(tune.out)
##
## Parameter tuning of 'svm':
##
## - sampling method: 10-fold cross validation
##
## - best parameters:
## cost
## 1
##
## - best performance: 0.1703704
##
## - Detailed performance results:
## cost error dispersion
## 1 0.01000000 0.3777778 0.08151888
## 2 0.01778279 0.3777778 0.08151888
## 3 0.03162278 0.3777778 0.08151888
## 4 0.05623413 0.3777778 0.08151888
## 5 0.10000000 0.3740741 0.10395326
## 6 0.17782794 0.2259259 0.10966132
## 7 0.31622777 0.1888889 0.08454762
## 8 0.56234133 0.1777778 0.08868289
## 9 1.00000000 0.1703704 0.08936771
## 10 1.77827941 0.1888889 0.09634377
## 11 3.16227766 0.2037037 0.08597771
## 12 5.62341325 0.2074074 0.08038924
## 13 10.00000000 0.2185185 0.07499428
svm.radial = svm(Purchase ~ ., data = OJtraining, kernel = "radial", cost = tune.out$best.parameters$cost)
train.pred = predict(svm.radial, OJtraining)
table(OJtraining$Purchase, train.pred)
## train.pred
## CH MM
## CH 441 44
## MM 77 238
test.pred = predict(svm.radial, OJtesting)
table(OJtesting$Purchase, test.pred)
## test.pred
## CH MM
## CH 151 17
## MM 33 69
G
svm.poly = svm(Purchase ~ ., data = OJtraining, kernel = "poly", degree = 2)
summary(svm.poly)
##
## Call:
## svm(formula = Purchase ~ ., data = OJtraining, kernel = "poly", degree = 2)
##
##
## Parameters:
## SVM-Type: C-classification
## SVM-Kernel: polynomial
## cost: 1
## degree: 2
## coef.0: 0
##
## Number of Support Vectors: 447
##
## ( 225 222 )
##
##
## Number of Classes: 2
##
## Levels:
## CH MM
train.pred = predict(svm.poly, OJtraining)
table(OJtraining$Purchase, train.pred)
## train.pred
## CH MM
## CH 449 36
## MM 110 205
test.pred = predict(svm.poly, OJtesting)
table(OJtesting$Purchase, test.pred)
## test.pred
## CH MM
## CH 153 15
## MM 45 57
tune.out = tune(svm, Purchase ~ ., data = OJtraining, kernel = "poly", degree = 2, ranges = list(cost = 10^seq(-2, 1, by = 0.25)))
summary(tune.out)
##
## Parameter tuning of 'svm':
##
## - sampling method: 10-fold cross validation
##
## - best parameters:
## cost
## 5.623413
##
## - best performance: 0.18625
##
## - Detailed performance results:
## cost error dispersion
## 1 0.01000000 0.39000 0.04281744
## 2 0.01778279 0.37000 0.04048319
## 3 0.03162278 0.36625 0.03998698
## 4 0.05623413 0.34000 0.03987829
## 5 0.10000000 0.32375 0.04427267
## 6 0.17782794 0.24500 0.06241661
## 7 0.31622777 0.21250 0.06038074
## 8 0.56234133 0.20625 0.05408648
## 9 1.00000000 0.19375 0.05628857
## 10 1.77827941 0.19250 0.05109903
## 11 3.16227766 0.18750 0.05464532
## 12 5.62341325 0.18625 0.05015601
## 13 10.00000000 0.18625 0.04387878
svm.poly = svm(Purchase ~ ., data = OJtraining, kernel = "poly", degree = 2, cost = tune.out$best.parameters$cost)
train.pred = predict(svm.poly, OJtraining)
table(OJtraining$Purchase, train.pred)
## train.pred
## CH MM
## CH 447 38
## MM 88 227
test.pred = predict(svm.poly, OJtesting)
table(OJtesting$Purchase, test.pred)
## test.pred
## CH MM
## CH 154 14
## MM 36 66
H Sted D/E had the best rate