hw 3 Emmanuel
Emmanuel Ferdinand Anggawirja
2023-04-27
library(ISLR2)
library(class)
library(ggplot2)
library(gmodels)
library(scales)
library(caret)## Loading required package: latticelibrary(tidyverse)## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.0 ✔ readr 2.1.4
## ✔ forcats 1.0.0 ✔ stringr 1.5.0
## ✔ lubridate 1.9.2 ✔ tibble 3.1.8
## ✔ purrr 1.0.1 ✔ tidyr 1.3.0## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ readr::col_factor() masks scales::col_factor()
## ✖ purrr::discard() masks scales::discard()
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ✖ purrr::lift() masks caret::lift()
## ℹ Use the ]8;;http://conflicted.r-lib.org/conflicted package]8;; to force all conflicts to become errorslibrary(pROC)## Type 'citation("pROC")' for a citation.
##
## Attaching package: 'pROC'
##
## The following object is masked from 'package:gmodels':
##
## ci
##
## The following objects are masked from 'package:stats':
##
## cov, smooth, varlibrary(tidymodels)## ── Attaching packages ────────────────────────────────────── tidymodels 1.0.0 ──
## ✔ broom 1.0.3 ✔ rsample 1.1.1
## ✔ dials 1.2.0 ✔ tune 1.1.0
## ✔ infer 1.0.4 ✔ workflows 1.1.3
## ✔ modeldata 1.1.0 ✔ workflowsets 1.0.0
## ✔ parsnip 1.0.4 ✔ yardstick 1.1.0
## ✔ recipes 1.0.5
## ── Conflicts ───────────────────────────────────────── tidymodels_conflicts() ──
## ✖ purrr::discard() masks scales::discard()
## ✖ dplyr::filter() masks stats::filter()
## ✖ recipes::fixed() masks stringr::fixed()
## ✖ dplyr::lag() masks stats::lag()
## ✖ purrr::lift() masks caret::lift()
## ✖ yardstick::precision() masks caret::precision()
## ✖ yardstick::recall() masks caret::recall()
## ✖ yardstick::sensitivity() masks caret::sensitivity()
## ✖ yardstick::spec() masks readr::spec()
## ✖ yardstick::specificity() masks caret::specificity()
## ✖ recipes::step() masks stats::step()
## • Use tidymodels_prefer() to resolve common conflicts.dataset = Default
df <- dataset %>% mutate_if(is.ordered, factor, ordered = FALSE)
set.seed(123)
churn_split <- initial_split(df, prop = .7, strata = default)
churn_train <- training(churn_split)
churn_test <- testing(churn_split)
cv_mod1 <- caret::train(
default ~ balance,
data = churn_train,
method = "glm",
family = "binomial",
trControl = trainControl(method = "cv", number = 10)
)
pred_class <- predict(cv_mod1, churn_train)
confusionMatrix(
data = relevel(pred_class, ref = "Yes"),
reference = relevel(churn_train$default, ref = "Yes")
)## Confusion Matrix and Statistics
##
## Reference
## Prediction Yes No
## Yes 71 30
## No 159 6740
##
## Accuracy : 0.973
## 95% CI : (0.9689, 0.9767)
## No Information Rate : 0.9671
## P-Value [Acc > NIR] : 0.002652
##
## Kappa : 0.4173
##
## Mcnemar's Test P-Value : < 2.2e-16
##
## Sensitivity : 0.30870
## Specificity : 0.99557
## Pos Pred Value : 0.70297
## Neg Pred Value : 0.97695
## Prevalence : 0.03286
## Detection Rate : 0.01014
## Detection Prevalence : 0.01443
## Balanced Accuracy : 0.65213
##
## 'Positive' Class : Yes
## cv_mod2 <- caret::train(
default ~ balance + student,
data = churn_train,
method = "glm",
family = "binomial",
trControl = trainControl(method = "cv", number = 10)
)
pred_class <- predict(cv_mod2, churn_train)
confusionMatrix(
data = relevel(pred_class, ref = "Yes"),
reference = relevel(churn_train$default, ref = "Yes")
)## Confusion Matrix and Statistics
##
## Reference
## Prediction Yes No
## Yes 76 30
## No 154 6740
##
## Accuracy : 0.9737
## 95% CI : (0.9697, 0.9773)
## No Information Rate : 0.9671
## P-Value [Acc > NIR] : 0.0008272
##
## Kappa : 0.4408
##
## Mcnemar's Test P-Value : < 2.2e-16
##
## Sensitivity : 0.33043
## Specificity : 0.99557
## Pos Pred Value : 0.71698
## Neg Pred Value : 0.97766
## Prevalence : 0.03286
## Detection Rate : 0.01086
## Detection Prevalence : 0.01514
## Balanced Accuracy : 0.66300
##
## 'Positive' Class : Yes
## cv_mod3 <- caret::train(
default ~ balance + income + student,
data = churn_train,
method = "glm",
family = "binomial",
trControl = trainControl(method = "cv", number = 10)
)
pred_class <- predict(cv_mod3, churn_train)
confusionMatrix(
data = relevel(pred_class, ref = "Yes"),
reference = relevel(churn_train$default, ref = "Yes")
)## Confusion Matrix and Statistics
##
## Reference
## Prediction Yes No
## Yes 76 30
## No 154 6740
##
## Accuracy : 0.9737
## 95% CI : (0.9697, 0.9773)
## No Information Rate : 0.9671
## P-Value [Acc > NIR] : 0.0008272
##
## Kappa : 0.4408
##
## Mcnemar's Test P-Value : < 2.2e-16
##
## Sensitivity : 0.33043
## Specificity : 0.99557
## Pos Pred Value : 0.71698
## Neg Pred Value : 0.97766
## Prevalence : 0.03286
## Detection Rate : 0.01086
## Detection Prevalence : 0.01514
## Balanced Accuracy : 0.66300
##
## 'Positive' Class : Yes
## summary(
resamples(
list(
Table_1 = cv_mod1,
Table_2 = cv_mod2,
Table_3 = cv_mod3
)
)
)##
## Call:
## summary.resamples(object = resamples(list(Table_1 = cv_mod1, Table_2 =
## cv_mod2, Table_3 = cv_mod3)))
##
## Models: Table_1, Table_2, Table_3
## Number of resamples: 10
##
## Accuracy
## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## Table_1 0.9642857 0.9717857 0.9735714 0.9731429 0.9753571 0.9800000 0
## Table_2 0.9671429 0.9714286 0.9735714 0.9737143 0.9757143 0.9800000 0
## Table_3 0.9685714 0.9717857 0.9728571 0.9735714 0.9764286 0.9785714 0
##
## Kappa
## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## Table_1 0.1796362 0.3665542 0.4385241 0.4177551 0.4844803 0.5542618 0
## Table_2 0.2452653 0.4023762 0.4305530 0.4367752 0.5071568 0.6016584 0
## Table_3 0.3108944 0.3482950 0.4176434 0.4326191 0.5323200 0.5677345 0R Markdown
This is an R Markdown document. Markdown is a simple formatting syntax for authoring HTML, PDF, and MS Word documents. For more details on using R Markdown see http://rmarkdown.rstudio.com.
When you click the Knit button a document will be generated that includes both content as well as the output of any embedded R code chunks within the document. You can embed an R code chunk like this:
summary(cars)## speed dist
## Min. : 4.0 Min. : 2.00
## 1st Qu.:12.0 1st Qu.: 26.00
## Median :15.0 Median : 36.00
## Mean :15.4 Mean : 42.98
## 3rd Qu.:19.0 3rd Qu.: 56.00
## Max. :25.0 Max. :120.00Including Plots
You can also embed plots, for example:
Note that the echo = FALSE parameter was added to the
code chunk to prevent printing of the R code that generated the
plot.