# Install the required package
install.packages("kknn")
## Installing package into '/cloud/lib/x86_64-pc-linux-gnu-library/4.4'
## (as 'lib' is unspecified)
# Load required libraries
library(tidymodels)
## ── Attaching packages ────────────────────────────────────── tidymodels 1.2.0 ──
## ✔ broom 1.0.5 ✔ recipes 1.0.10
## ✔ dials 1.2.1 ✔ rsample 1.2.1
## ✔ dplyr 1.1.4 ✔ tibble 3.2.1
## ✔ ggplot2 3.5.1 ✔ tidyr 1.3.1
## ✔ infer 1.0.7 ✔ tune 1.2.1
## ✔ modeldata 1.3.0 ✔ workflows 1.1.4
## ✔ parsnip 1.2.1 ✔ workflowsets 1.1.0
## ✔ purrr 1.0.2 ✔ yardstick 1.3.1
## ── Conflicts ───────────────────────────────────────── tidymodels_conflicts() ──
## ✖ purrr::discard() masks scales::discard()
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ✖ recipes::step() masks stats::step()
## • Dig deeper into tidy modeling with R at https://www.tmwr.org
library(dplyr) # For data manipulation
library(ggplot2) # For plotting
library(ISLR) # For the Smarket data set
library(ISLR2) # For the Bikeshare data set
##
## Attaching package: 'ISLR2'
## The following objects are masked from 'package:ISLR':
##
## Auto, Credit
library(discrim)
##
## Attaching package: 'discrim'
## The following object is masked from 'package:dials':
##
## smoothness
library(poissonreg)
library(corrr)
library(paletteer)
# Correlation plot for Smarket dataset
cor_Smarket <- Smarket %>%
select(-Direction) %>%
correlate()
## Correlation computed with
## • Method: 'pearson'
## • Missing treated using: 'pairwise.complete.obs'
rplot(cor_Smarket, colours = c("indianred2", "black", "skyblue1"))
cor_Smarket %>%
stretch() %>%
ggplot(aes(x, y, fill = r)) +
geom_tile() +
geom_text(aes(label = as.character(fashion(r)))) +
scale_fill_paletteer_c("scico::roma", limits = c(-1, 1), direction = -1)
ggplot(Smarket, aes(Year, Volume)) +
geom_jitter(height = 0)
# Logistic Regression Model
lr_spec <- logistic_reg() %>%
set_engine("glm") %>%
set_mode("classification")
lr_fit <- lr_spec %>%
fit(Direction ~ Lag1 + Lag2 + Lag3 + Lag4 + Lag5 + Volume, data = Smarket)
summary(lr_fit$fit)
##
## Call:
## stats::glm(formula = Direction ~ Lag1 + Lag2 + Lag3 + Lag4 +
## Lag5 + Volume, family = stats::binomial, data = data)
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -0.126000 0.240736 -0.523 0.601
## Lag1 -0.073074 0.050167 -1.457 0.145
## Lag2 -0.042301 0.050086 -0.845 0.398
## Lag3 0.011085 0.049939 0.222 0.824
## Lag4 0.009359 0.049974 0.187 0.851
## Lag5 0.010313 0.049511 0.208 0.835
## Volume 0.135441 0.158360 0.855 0.392
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 1731.2 on 1249 degrees of freedom
## Residual deviance: 1727.6 on 1243 degrees of freedom
## AIC: 1741.6
##
## Number of Fisher Scoring iterations: 3
tidy(lr_fit)
## # A tibble: 7 × 5
## term estimate std.error statistic p.value
## <chr> <dbl> <dbl> <dbl> <dbl>
## 1 (Intercept) -0.126 0.241 -0.523 0.601
## 2 Lag1 -0.0731 0.0502 -1.46 0.145
## 3 Lag2 -0.0423 0.0501 -0.845 0.398
## 4 Lag3 0.0111 0.0499 0.222 0.824
## 5 Lag4 0.00936 0.0500 0.187 0.851
## 6 Lag5 0.0103 0.0495 0.208 0.835
## 7 Volume 0.135 0.158 0.855 0.392
predict(lr_fit, new_data = Smarket)
## # A tibble: 1,250 × 1
## .pred_class
## <fct>
## 1 Up
## 2 Down
## 3 Down
## 4 Up
## 5 Up
## 6 Up
## 7 Down
## 8 Up
## 9 Up
## 10 Down
## # ℹ 1,240 more rows
predict(lr_fit, new_data = Smarket, type = "prob")
## # A tibble: 1,250 × 2
## .pred_Down .pred_Up
## <dbl> <dbl>
## 1 0.493 0.507
## 2 0.519 0.481
## 3 0.519 0.481
## 4 0.485 0.515
## 5 0.489 0.511
## 6 0.493 0.507
## 7 0.507 0.493
## 8 0.491 0.509
## 9 0.482 0.518
## 10 0.511 0.489
## # ℹ 1,240 more rows
# Evaluate logistic regression model on full data
augmented_lr <- augment(lr_fit, new_data = Smarket)
conf_mat(augmented_lr, truth = Direction, estimate = .pred_class) %>%
autoplot(type = "heatmap")
accuracy(augmented_lr, truth = Direction, estimate = .pred_class)
## # A tibble: 1 × 3
## .metric .estimator .estimate
## <chr> <chr> <dbl>
## 1 accuracy binary 0.522
# Split data into training and testing sets
Smarket_train <- Smarket %>%
filter(Year != 2005)
Smarket_test <- Smarket %>%
filter(Year == 2005)
# Logistic Regression with training data
lr_fit2 <- lr_spec %>%
fit(Direction ~ Lag1 + Lag2 + Lag3 + Lag4 + Lag5 + Volume, data = Smarket_train)
augmented_lr2 <- augment(lr_fit2, new_data = Smarket_test)
conf_mat(augmented_lr2, truth = Direction, estimate = .pred_class) %>%
autoplot(type = "heatmap")
accuracy(augmented_lr2, truth = Direction, estimate = .pred_class)
## # A tibble: 1 × 3
## .metric .estimator .estimate
## <chr> <chr> <dbl>
## 1 accuracy binary 0.480
# Logistic Regression with fewer predictors
lr_fit3 <- lr_spec %>%
fit(Direction ~ Lag1 + Lag2, data = Smarket_train)
augmented_lr3 <- augment(lr_fit3, new_data = Smarket_test)
conf_mat(augmented_lr3, truth = Direction, estimate = .pred_class) %>%
autoplot(type = "heatmap")
accuracy(augmented_lr3, truth = Direction, estimate = .pred_class)
## # A tibble: 1 × 3
## .metric .estimator .estimate
## <chr> <chr> <dbl>
## 1 accuracy binary 0.560
# Predictions for new data
Smarket_new <- tibble(
Lag1 = c(1.2, 1.5),
Lag2 = c(1.1, -0.8)
)
predict(lr_fit3, new_data = Smarket_new, type = "prob")
## # A tibble: 2 × 2
## .pred_Down .pred_Up
## <dbl> <dbl>
## 1 0.521 0.479
## 2 0.504 0.496
# Linear Discriminant Analysis (LDA)
lda_spec <- discrim_linear() %>%
set_mode("classification") %>%
set_engine("MASS")
lda_fit <- lda_spec %>%
fit(Direction ~ Lag1 + Lag2, data = Smarket_train)
predict(lda_fit, new_data = Smarket_test)
## # A tibble: 252 × 1
## .pred_class
## <fct>
## 1 Up
## 2 Up
## 3 Up
## 4 Up
## 5 Up
## 6 Up
## 7 Up
## 8 Up
## 9 Up
## 10 Up
## # ℹ 242 more rows
predict(lda_fit, new_data = Smarket_test, type = "prob")
## # A tibble: 252 × 2
## .pred_Down .pred_Up
## <dbl> <dbl>
## 1 0.490 0.510
## 2 0.479 0.521
## 3 0.467 0.533
## 4 0.474 0.526
## 5 0.493 0.507
## 6 0.494 0.506
## 7 0.495 0.505
## 8 0.487 0.513
## 9 0.491 0.509
## 10 0.484 0.516
## # ℹ 242 more rows
augmented_lda <- augment(lda_fit, new_data = Smarket_test)
conf_mat(augmented_lda, truth = Direction, estimate = .pred_class) %>%
autoplot(type = "heatmap")
accuracy(augmented_lda, truth = Direction, estimate = .pred_class)
## # A tibble: 1 × 3
## .metric .estimator .estimate
## <chr> <chr> <dbl>
## 1 accuracy binary 0.560
# Quadratic Discriminant Analysis (QDA)
qda_spec <- discrim_quad() %>%
set_mode("classification") %>%
set_engine("MASS")
qda_fit <- qda_spec %>%
fit(Direction ~ Lag1 + Lag2, data = Smarket_train)
augmented_qda <- augment(qda_fit, new_data = Smarket_test)
conf_mat(augmented_qda, truth = Direction, estimate = .pred_class) %>%
autoplot(type = "heatmap")
accuracy(augmented_qda, truth = Direction, estimate = .pred_class)
## # A tibble: 1 × 3
## .metric .estimator .estimate
## <chr> <chr> <dbl>
## 1 accuracy binary 0.599
# Naive Bayes
nb_spec <- naive_Bayes() %>%
set_mode("classification") %>%
set_engine("klaR") %>%
set_args(usekernel = FALSE)
nb_fit <- nb_spec %>%
fit(Direction ~ Lag1 + Lag2, data = Smarket_train)
augmented_nb <- augment(nb_fit, new_data = Smarket_test)
conf_mat(augmented_nb, truth = Direction, estimate = .pred_class) %>%
autoplot(type = "heatmap")
accuracy(augmented_nb, truth = Direction, estimate = .pred_class)
## # A tibble: 1 × 3
## .metric .estimator .estimate
## <chr> <chr> <dbl>
## 1 accuracy binary 0.591
# K-Nearest Neighbors (KNN)
ggplot(Smarket, aes(Lag1, Lag2)) +
geom_point(alpha = 0.1, size = 2) +
geom_smooth(method = "lm", se = FALSE) +
labs(title = "No apparent correlation between Lag1 and Lag2")
## `geom_smooth()` using formula = 'y ~ x'
knn_spec <- nearest_neighbor(neighbors = 3) %>%
set_mode("classification") %>%
set_engine("kknn")
knn_fit <- knn_spec %>%
fit(Direction ~ Lag1 + Lag2, data = Smarket_train)
augmented_knn <- augment(knn_fit, new_data = Smarket_test)
conf_mat(augmented_knn, truth = Direction, estimate = .pred_class) %>%
autoplot(type = "heatmap")
accuracy(augmented_knn, truth = Direction, estimate = .pred_class)
## # A tibble: 1 × 3
## .metric .estimator .estimate
## <chr> <chr> <dbl>
## 1 accuracy binary 0.5
# Caravan dataset for KNN
Caravan_test <- Caravan[seq_len(1000), ]
Caravan_train <- Caravan[-seq_len(1000), ]
rec_spec <- recipe(Purchase ~ ., data = Caravan_train) %>%
step_normalize(all_numeric_predictors())
Caravan_wf <- workflow() %>%
add_recipe(rec_spec)
knn_spec <- nearest_neighbor() %>%
set_mode("classification") %>%
set_engine("kknn")
knn1_wf <- Caravan_wf %>%
add_model(knn_spec %>% set_args(neighbors = 1))
knn3_wf <- Caravan_wf %>%
add_model(knn_spec %>% set_args(neighbors = 3))
knn5_wf <- Caravan_wf %>%
add_model(knn_spec %>% set_args(neighbors = 5))
knn1_fit <- fit(knn1_wf, data = Caravan_train)
knn3_fit <- fit(knn3_wf, data = Caravan_train)
knn5_fit <- fit(knn5_wf, data = Caravan_train)
# Evaluate KNN models
augmented_knn1 <- augment(knn1_fit, new_data = Caravan_test)
augmented_knn3 <- augment(knn3_fit, new_data = Caravan_test)
augmented_knn5 <- augment(knn5_fit, new_data = Caravan_test)
conf_mat(augmented_knn1, truth = Purchase, estimate = .pred_class)
## Truth
## Prediction No Yes
## No 874 50
## Yes 67 9
accuracy(augmented_knn1, truth = Purchase, estimate = .pred_class)
## # A tibble: 1 × 3
## .metric .estimator .estimate
## <chr> <chr> <dbl>
## 1 accuracy binary 0.883
conf_mat(augmented_knn3, truth = Purchase, estimate = .pred_class)
## Truth
## Prediction No Yes
## No 875 50
## Yes 66 9
accuracy(augmented_knn3, truth = Purchase, estimate = .pred_class)
## # A tibble: 1 × 3
## .metric .estimator .estimate
## <chr> <chr> <dbl>
## 1 accuracy binary 0.884
conf_mat(augmented_knn5, truth = Purchase, estimate = .pred_class)
## Truth
## Prediction No Yes
## No 874 50
## Yes 67 9
accuracy(augmented_knn5, truth = Purchase, estimate = .pred_class)
## # A tibble: 1 × 3
## .metric .estimator .estimate
## <chr> <chr> <dbl>
## 1 accuracy binary 0.883