Enkhjin/ex4
2025-04-24
library(tidymodels)## ── Attaching packages ────────────────────────────────────── tidymodels 1.3.0 ──## ✔ broom 1.0.8 ✔ recipes 1.3.0
## ✔ dials 1.4.0 ✔ rsample 1.3.0
## ✔ dplyr 1.1.4 ✔ tibble 3.2.1
## ✔ ggplot2 3.5.2 ✔ tidyr 1.3.1
## ✔ infer 1.0.8 ✔ tune 1.3.0
## ✔ modeldata 1.4.0 ✔ workflows 1.2.0
## ✔ parsnip 1.3.1 ✔ workflowsets 1.1.0
## ✔ purrr 1.0.4 ✔ yardstick 1.3.2## ── Conflicts ───────────────────────────────────────── tidymodels_conflicts() ──
## ✖ purrr::discard() masks scales::discard()
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ✖ recipes::step() masks stats::step()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, Creditlibrary(discrim)##
## Attaching package: 'discrim'## The following object is masked from 'package:dials':
##
## smoothnesslibrary(poissonreg)library(corrr)
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"))
ggplot(Smarket, aes(Year, Volume)) +
geom_jitter(height = 0)
lr_spec <- logistic_reg() %>%
set_engine("glm") %>%
set_mode("classification")lr_fit <- lr_spec %>%
fit(
Direction ~ Lag1 + Lag2 + Lag3 + Lag4 + Lag5 + Volume,
data = Smarket
)
lr_fit## parsnip model object
##
##
## Call: stats::glm(formula = Direction ~ Lag1 + Lag2 + Lag3 + Lag4 +
## Lag5 + Volume, family = stats::binomial, data = data)
##
## Coefficients:
## (Intercept) Lag1 Lag2 Lag3 Lag4 Lag5
## -0.126000 -0.073074 -0.042301 0.011085 0.009359 0.010313
## Volume
## 0.135441
##
## Degrees of Freedom: 1249 Total (i.e. Null); 1243 Residual
## Null Deviance: 1731
## Residual Deviance: 1728 AIC: 1742lr_fit %>%
pluck("fit") %>%
summary()##
## 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: 3tidy(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 0.392predict(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 rowspredict(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 rowsaugment(lr_fit, new_data = Smarket) %>%
conf_mat(truth = Direction, estimate = .pred_class)## Truth
## Prediction Down Up
## Down 145 141
## Up 457 507augment(lr_fit, new_data = Smarket) %>%
accuracy(truth = Direction, estimate = .pred_class)## # A tibble: 1 × 3
## .metric .estimator .estimate
## <chr> <chr> <dbl>
## 1 accuracy binary 0.522Smarket_train <- Smarket %>%
filter(Year != 2005)
Smarket_test <- Smarket %>%
filter(Year == 2005)lr_fit2 <- lr_spec %>%
fit(
Direction ~ Lag1 + Lag2 + Lag3 + Lag4 + Lag5 + Volume,
data = Smarket_train
)augment(lr_fit2, new_data = Smarket_test) %>%
conf_mat(truth = Direction, estimate = .pred_class) ## Truth
## Prediction Down Up
## Down 77 97
## Up 34 44augment(lr_fit2, new_data = Smarket_test) %>%
accuracy(truth = Direction, estimate = .pred_class) ## # A tibble: 1 × 3
## .metric .estimator .estimate
## <chr> <chr> <dbl>
## 1 accuracy binary 0.480lr_fit3 <- lr_spec %>%
fit(
Direction ~ Lag1 + Lag2,
data = Smarket_train
)
augment(lr_fit3, new_data = Smarket_test) %>%
conf_mat(truth = Direction, estimate = .pred_class) ## Truth
## Prediction Down Up
## Down 35 35
## Up 76 106augment(lr_fit3, new_data = Smarket_test) %>%
accuracy(truth = Direction, estimate = .pred_class)## # A tibble: 1 × 3
## .metric .estimator .estimate
## <chr> <chr> <dbl>
## 1 accuracy binary 0.560Smarket_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#4.3 Linear Discriminant Analysis
lda_spec <- discrim_linear() %>%
set_mode("classification") %>%
set_engine("MASS")
lda_fit <- lda_spec %>%
fit(Direction ~ Lag1 + Lag2, data = Smarket_train)
lda_fit## parsnip model object
##
## Call:
## lda(Direction ~ Lag1 + Lag2, data = data)
##
## Prior probabilities of groups:
## Down Up
## 0.491984 0.508016
##
## Group means:
## Lag1 Lag2
## Down 0.04279022 0.03389409
## Up -0.03954635 -0.03132544
##
## Coefficients of linear discriminants:
## LD1
## Lag1 -0.6420190
## Lag2 -0.5135293