library(tidymodels)
## ── Attaching packages ────────────────────────────────────── tidymodels 1.1.1 ──
## ✔ broom 1.0.5 ✔ recipes 1.0.8
## ✔ dials 1.2.0 ✔ rsample 1.2.0
## ✔ dplyr 1.1.3 ✔ tibble 3.2.1
## ✔ ggplot2 3.4.3 ✔ tidyr 1.3.0
## ✔ infer 1.0.5 ✔ tune 1.1.2
## ✔ modeldata 1.2.0 ✔ workflows 1.1.3
## ✔ parsnip 1.1.1 ✔ workflowsets 1.0.1
## ✔ purrr 1.0.2 ✔ yardstick 1.2.0
## ── Conflicts ───────────────────────────────────────── tidymodels_conflicts() ──
## ✖ purrr::discard() masks scales::discard()
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ✖ recipes::step() masks stats::step()
## • Use tidymodels_prefer() to resolve common conflicts.
library(tidyverse)
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ forcats 1.0.0 ✔ readr 2.1.4
## ✔ lubridate 1.9.2 ✔ stringr 1.5.0
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ readr::col_factor() masks scales::col_factor()
## ✖ purrr::discard() masks scales::discard()
## ✖ dplyr::filter() masks stats::filter()
## ✖ stringr::fixed() masks recipes::fixed()
## ✖ dplyr::lag() masks stats::lag()
## ✖ readr::spec() masks yardstick::spec()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
library(here)
## here() starts at C:/Users/vishe/Downloads
boston <- readr::read_csv("boston.csv")
## Rows: 506 Columns: 16
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## dbl (16): lon, lat, cmedv, crim, zn, indus, chas, nox, rm, age, dis, rad, ta...
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
set.seed(123)
split <- initial_split(boston, prop = 0.7, strata = cmedv)
train <- training(split)
test <- testing(split)
cor_mat <- cor(train)
cor_mat["cmedv",]
## lon lat cmedv crim zn indus
## -0.315456520 -0.002024587 1.000000000 -0.384298342 0.344272023 -0.489537963
## chas nox rm age dis rad
## 0.164575979 -0.439021014 0.708152619 -0.398915864 0.271455846 -0.396999035
## tax ptratio b lstat
## -0.479383777 -0.500927283 0.358302318 -0.742823016
cor_cmedv <- cor_mat["cmedv",]
which.max(cor_cmedv)
## cmedv
## 3
which.min(cor_mat["cmedv",])
## lstat
## 16
ggplot(train, aes(x = rm, y = cmedv)) +
geom_point() +
geom_smooth(method = "lm")
## `geom_smooth()` using formula = 'y ~ x'
model1 <- linear_reg()%>%
fit(cmedv ~ rm, data = train)
tidy(model1)
## # A tibble: 2 × 5
## term estimate std.error statistic p.value
## <chr> <dbl> <dbl> <dbl> <dbl>
## 1 (Intercept) -35.4 3.11 -11.4 8.70e-26
## 2 rm 9.22 0.491 18.8 7.46e-55
model1 %>%
predict(test) %>%
bind_cols(test)%>%
rmse(truth = cmedv, estimate = .pred)
## # A tibble: 1 × 3
## .metric .estimator .estimate
## <chr> <chr> <dbl>
## 1 rmse standard 6.83
model11 <- linear_reg()%>%
fit(cmedv ~ ., data = train)
summary1 <- tidy(model11)
model12<- summary1 %>%
filter(p.value<0.05 & !is.na(term))%>%
pull(term)
model12
## [1] "crim" "zn" "chas" "nox" "rm" "dis" "rad"
## [8] "tax" "ptratio" "b" "lstat"
model2 <- linear_reg()%>%
fit(cmedv ~ ., data = train)
tidy(model2)
## # A tibble: 16 × 5
## term estimate std.error statistic p.value
## <chr> <dbl> <dbl> <dbl> <dbl>
## 1 (Intercept) -608. 342. -1.78 7.64e- 2
## 2 lon -5.65 3.86 -1.46 1.45e- 1
## 3 lat 5.54 4.24 1.31 1.93e- 1
## 4 crim -0.0830 0.0396 -2.10 3.65e- 2
## 5 zn 0.0332 0.0165 2.01 4.56e- 2
## 6 indus -0.0143 0.0738 -0.193 8.47e- 1
## 7 chas 2.28 1.05 2.17 3.06e- 2
## 8 nox -11.7 4.74 -2.46 1.44e- 2
## 9 rm 4.37 0.516 8.46 8.13e-16
## 10 age -0.00921 0.0156 -0.591 5.55e- 1
## 11 dis -1.26 0.244 -5.17 4.06e- 7
## 12 rad 0.272 0.0790 3.44 6.47e- 4
## 13 tax -0.0121 0.00436 -2.78 5.78e- 3
## 14 ptratio -0.874 0.163 -5.37 1.48e- 7
## 15 b 0.0123 0.00310 3.97 8.72e- 5
## 16 lstat -0.479 0.0637 -7.51 5.24e-13
model2 %>%
predict(test) %>%
bind_cols(test)%>%
rmse(truth = cmedv, estimate = .pred)
## # A tibble: 1 × 3
## .metric .estimator .estimate
## <chr> <chr> <dbl>
## 1 rmse standard 4.83
model3 <- tidy(model2) %>%
arrange(desc(abs(statistic))) %>%
slice_head(n = 5)
model3
## # A tibble: 5 × 5
## term estimate std.error statistic p.value
## <chr> <dbl> <dbl> <dbl> <dbl>
## 1 rm 4.37 0.516 8.46 8.13e-16
## 2 lstat -0.479 0.0637 -7.51 5.24e-13
## 3 ptratio -0.874 0.163 -5.37 1.48e- 7
## 4 dis -1.26 0.244 -5.17 4.06e- 7
## 5 b 0.0123 0.00310 3.97 8.72e- 5