system2("echo", args = "Output that would normally be lost")
#require library
required_packages <- c("GGally", "naniar", "gridExtra", "scales", "ggplot2",
"dplyr", "tidyr", "corrplot", "ggcorrplot", "caret",
"naivebayes", "pROC", "car", "DataExplorer", "knitr")
for (pkg in required_packages) {
if (!require(pkg, character.only = TRUE)) {
install.packages(pkg)
library(pkg, character.only = TRUE)
}
}
#;-) Loading required package: GGally
#;-) Loading required package: ggplot2
#;-) Registered S3 method overwritten by 'GGally':
#;-) method from
#;-) +.gg ggplot2
#;-) Loading required package: naniar
#;-) Loading required package: gridExtra
#;-) Loading required package: scales
#;-) Loading required package: dplyr
#;-)
#;-) Attaching package: 'dplyr'
#;-) The following object is masked from 'package:gridExtra':
#;-)
#;-) combine
#;-) The following objects are masked from 'package:stats':
#;-)
#;-) filter, lag
#;-) The following objects are masked from 'package:base':
#;-)
#;-) intersect, setdiff, setequal, union
#;-) Loading required package: tidyr
#;-) Loading required package: corrplot
#;-) corrplot 0.95 loaded
#;-) Loading required package: ggcorrplot
#;-) Loading required package: caret
#;-) Loading required package: lattice
#;-) Loading required package: naivebayes
#;-) naivebayes 1.0.0 loaded
#;-) For more information please visit:
#;-) https://majkamichal.github.io/naivebayes/
#;-) Loading required package: pROC
#;-) Type 'citation("pROC")' for a citation.
#;-)
#;-) Attaching package: 'pROC'
#;-) The following objects are masked from 'package:stats':
#;-)
#;-) cov, smooth, var
#;-) Loading required package: car
#;-) Loading required package: carData
#;-)
#;-) Attaching package: 'car'
#;-) The following object is masked from 'package:dplyr':
#;-)
#;-) recode
#;-) Loading required package: DataExplorer
#;-) Loading required package: knitr
#install.packages("rmarkdown")
#install.packages("knitr")
#install.packages("ggplot2") # Install other missing libraries if needed
library(rmarkdown)
library(knitr)
library(ggplot2)
#loding date and overview
#data_path <- "Google Drive/Hunter /ML Big data 622/assignment 1/bank-additional-full.csv"
data_path <- "/Users/ahmhamza/Google Drive/Hunter /ML Big data 622/assignment 1/bank-additional-full.csv"
df <- read.csv(data_path, sep = ";", stringsAsFactors = TRUE)
# Overview of the dataset
str(df)
#;-) 'data.frame': 41188 obs. of 21 variables:
#;-) $ age : int 56 57 37 40 56 45 59 41 24 25 ...
#;-) $ job : Factor w/ 12 levels "admin.","blue-collar",..: 4 8 8 1 8 8 1 2 10 8 ...
#;-) $ marital : Factor w/ 4 levels "divorced","married",..: 2 2 2 2 2 2 2 2 3 3 ...
#;-) $ education : Factor w/ 8 levels "basic.4y","basic.6y",..: 1 4 4 2 4 3 6 8 6 4 ...
#;-) $ default : Factor w/ 3 levels "no","unknown",..: 1 2 1 1 1 2 1 2 1 1 ...
#;-) $ housing : Factor w/ 3 levels "no","unknown",..: 1 1 3 1 1 1 1 1 3 3 ...
#;-) $ loan : Factor w/ 3 levels "no","unknown",..: 1 1 1 1 3 1 1 1 1 1 ...
#;-) $ contact : Factor w/ 2 levels "cellular","telephone": 2 2 2 2 2 2 2 2 2 2 ...
#;-) $ month : Factor w/ 10 levels "apr","aug","dec",..: 7 7 7 7 7 7 7 7 7 7 ...
#;-) $ day_of_week : Factor w/ 5 levels "fri","mon","thu",..: 2 2 2 2 2 2 2 2 2 2 ...
#;-) $ duration : int 261 149 226 151 307 198 139 217 380 50 ...
#;-) $ campaign : int 1 1 1 1 1 1 1 1 1 1 ...
#;-) $ pdays : int 999 999 999 999 999 999 999 999 999 999 ...
#;-) $ previous : int 0 0 0 0 0 0 0 0 0 0 ...
#;-) $ poutcome : Factor w/ 3 levels "failure","nonexistent",..: 2 2 2 2 2 2 2 2 2 2 ...
#;-) $ emp.var.rate : num 1.1 1.1 1.1 1.1 1.1 1.1 1.1 1.1 1.1 1.1 ...
#;-) $ cons.price.idx: num 94 94 94 94 94 ...
#;-) $ cons.conf.idx : num -36.4 -36.4 -36.4 -36.4 -36.4 -36.4 -36.4 -36.4 -36.4 -36.4 ...
#;-) $ euribor3m : num 4.86 4.86 4.86 4.86 4.86 ...
#;-) $ nr.employed : num 5191 5191 5191 5191 5191 ...
#;-) $ y : Factor w/ 2 levels "no","yes": 1 1 1 1 1 1 1 1 1 1 ...
summary(df)
#;-) age job marital
#;-) Min. :17.00 admin. :10422 divorced: 4612
#;-) 1st Qu.:32.00 blue-collar: 9254 married :24928
#;-) Median :38.00 technician : 6743 single :11568
#;-) Mean :40.02 services : 3969 unknown : 80
#;-) 3rd Qu.:47.00 management : 2924
#;-) Max. :98.00 retired : 1720
#;-) (Other) : 6156
#;-) education default housing loan
#;-) university.degree :12168 no :32588 no :18622 no :33950
#;-) high.school : 9515 unknown: 8597 unknown: 990 unknown: 990
#;-) basic.9y : 6045 yes : 3 yes :21576 yes : 6248
#;-) professional.course: 5243
#;-) basic.4y : 4176
#;-) basic.6y : 2292
#;-) (Other) : 1749
#;-) contact month day_of_week duration
#;-) cellular :26144 may :13769 fri:7827 Min. : 0.0
#;-) telephone:15044 jul : 7174 mon:8514 1st Qu.: 102.0
#;-) aug : 6178 thu:8623 Median : 180.0
#;-) jun : 5318 tue:8090 Mean : 258.3
#;-) nov : 4101 wed:8134 3rd Qu.: 319.0
#;-) apr : 2632 Max. :4918.0
#;-) (Other): 2016
#;-) campaign pdays previous poutcome
#;-) Min. : 1.000 Min. : 0.0 Min. :0.000 failure : 4252
#;-) 1st Qu.: 1.000 1st Qu.:999.0 1st Qu.:0.000 nonexistent:35563
#;-) Median : 2.000 Median :999.0 Median :0.000 success : 1373
#;-) Mean : 2.568 Mean :962.5 Mean :0.173
#;-) 3rd Qu.: 3.000 3rd Qu.:999.0 3rd Qu.:0.000
#;-) Max. :56.000 Max. :999.0 Max. :7.000
#;-)
#;-) emp.var.rate cons.price.idx cons.conf.idx euribor3m
#;-) Min. :-3.40000 Min. :92.20 Min. :-50.8 Min. :0.634
#;-) 1st Qu.:-1.80000 1st Qu.:93.08 1st Qu.:-42.7 1st Qu.:1.344
#;-) Median : 1.10000 Median :93.75 Median :-41.8 Median :4.857
#;-) Mean : 0.08189 Mean :93.58 Mean :-40.5 Mean :3.621
#;-) 3rd Qu.: 1.40000 3rd Qu.:93.99 3rd Qu.:-36.4 3rd Qu.:4.961
#;-) Max. : 1.40000 Max. :94.77 Max. :-26.9 Max. :5.045
#;-)
#;-) nr.employed y
#;-) Min. :4964 no :36548
#;-) 1st Qu.:5099 yes: 4640
#;-) Median :5191
#;-) Mean :5167
#;-) 3rd Qu.:5228
#;-) Max. :5228
#;-)
#auto data report
create_report(df)
#;-) processing file: report.rmd
#;-) output file: /Users/ahmhamza/Downloads/report.knit.md
#;-) /Applications/RStudio.app/Contents/Resources/app/quarto/bin/tools/x86_64/pandoc +RTS -K512m -RTS /Users/ahmhamza/Downloads/report.knit.md --to html4 --from markdown+autolink_bare_uris+tex_math_single_backslash --output /Users/ahmhamza/Downloads/report.html --lua-filter /Library/Frameworks/R.framework/Versions/4.3-x86_64/Resources/library/rmarkdown/rmarkdown/lua/pagebreak.lua --lua-filter /Library/Frameworks/R.framework/Versions/4.3-x86_64/Resources/library/rmarkdown/rmarkdown/lua/latex-div.lua --embed-resources --standalone --variable bs3=TRUE --section-divs --table-of-contents --toc-depth 6 --template /Library/Frameworks/R.framework/Versions/4.3-x86_64/Resources/library/rmarkdown/rmd/h/default.html --no-highlight --variable highlightjs=1 --variable theme=yeti --mathjax --variable 'mathjax-url=https://mathjax.rstudio.com/latest/MathJax.js?config=TeX-AMS-MML_HTMLorMML' --include-in-header /var/folders/m9/w8sx54nj2jz7d6t1yldp4qmc0000gn/T//Rtmp4Zwh16/rmarkdown-str33cc2709940f.html
#;-)
#;-) Output created: report.html
#checking for missing values
missing_vals <- colSums(is.na(df))
print("Missing values in each column:")
#;-) [1] "Missing values in each column:"
print(missing_vals)
#;-) age job marital education default
#;-) 0 0 0 0 0
#;-) housing loan contact month day_of_week
#;-) 0 0 0 0 0
#;-) duration campaign pdays previous poutcome
#;-) 0 0 0 0 0
#;-) emp.var.rate cons.price.idx cons.conf.idx euribor3m nr.employed
#;-) 0 0 0 0 0
#;-) y
#;-) 0
#summary stat
numerical_vars <- c("age", "duration", "campaign", "pdays", "previous",
"emp.var.rate", "cons.price.idx", "euribor3m", "nr.employed")
summary(df[, numerical_vars])
#;-) age duration campaign pdays
#;-) Min. :17.00 Min. : 0.0 Min. : 1.000 Min. : 0.0
#;-) 1st Qu.:32.00 1st Qu.: 102.0 1st Qu.: 1.000 1st Qu.:999.0
#;-) Median :38.00 Median : 180.0 Median : 2.000 Median :999.0
#;-) Mean :40.02 Mean : 258.3 Mean : 2.568 Mean :962.5
#;-) 3rd Qu.:47.00 3rd Qu.: 319.0 3rd Qu.: 3.000 3rd Qu.:999.0
#;-) Max. :98.00 Max. :4918.0 Max. :56.000 Max. :999.0
#;-) previous emp.var.rate cons.price.idx euribor3m
#;-) Min. :0.000 Min. :-3.40000 Min. :92.20 Min. :0.634
#;-) 1st Qu.:0.000 1st Qu.:-1.80000 1st Qu.:93.08 1st Qu.:1.344
#;-) Median :0.000 Median : 1.10000 Median :93.75 Median :4.857
#;-) Mean :0.173 Mean : 0.08189 Mean :93.58 Mean :3.621
#;-) 3rd Qu.:0.000 3rd Qu.: 1.40000 3rd Qu.:93.99 3rd Qu.:4.961
#;-) Max. :7.000 Max. : 1.40000 Max. :94.77 Max. :5.045
#;-) nr.employed
#;-) Min. :4964
#;-) 1st Qu.:5099
#;-) Median :5191
#;-) Mean :5167
#;-) 3rd Qu.:5228
#;-) Max. :5228
## cor for numerical feauters
numeric_cols <- df %>% select_if(is.numeric)
cor_matrix <- cor(numeric_cols, use = "pairwise.complete.obs")
corrplot(cor_matrix, method = "circle", type = "upper", tl.col = "black",
tl.srt = 60, col = colorRampPalette(c("blue", "white", "red"))(200),
addCoef.col = "black", number.cex = 0.6)
#distri of numeric vars
numeric_cols %>%
pivot_longer(cols = everything(), names_to = "variable", values_to = "value") %>%
ggplot(aes(x = value)) +
facet_wrap(~ variable, scales = "free") +
geom_histogram(bins = 30, fill = "steelblue", color = "black") +
theme_minimal() +
labs(title = "Distribution of Numeric Variables")
#boxplot outliers
ggplot(stack(df[, numerical_vars]), aes(x = ind, y = values)) +
geom_boxplot(fill = "lightgreen") +
coord_flip() +
ggtitle("Outlier Detection for Numeric Features")
#central tendency stat
df %>%
select(all_of(numerical_vars)) %>%
summarise(across(everything(), list(mean = mean, sd = sd, median = median), na.rm = TRUE)) %>%
pivot_longer(everything(), names_to = "stat", values_to = "value") %>%
separate(stat, into = c("variable", "stat"), sep = "_") %>%
pivot_wider(names_from = stat, values_from = value) %>%
knitr::kable()
#;-) Warning: There was 1 warning in `summarise()`.
#;-) ℹ In argument: `across(...)`.
#;-) Caused by warning:
#;-) ! The `...` argument of `across()` is deprecated as of dplyr 1.1.0.
#;-) Supply arguments directly to `.fns` through an anonymous function instead.
#;-)
#;-) # Previously
#;-) across(a:b, mean, na.rm = TRUE)
#;-)
#;-) # Now
#;-) across(a:b, \(x) mean(x, na.rm = TRUE))| variable | mean | sd | median |
|---|---|---|---|
| age | 40.0240604 | 10.4212500 | 38.000 |
| duration | 258.2850102 | 259.2792488 | 180.000 |
| campaign | 2.5675925 | 2.7700135 | 2.000 |
| pdays | 962.4754540 | 186.9109073 | 999.000 |
| previous | 0.1729630 | 0.4949011 | 0.000 |
| emp.var.rate | 0.0818855 | 1.5709597 | 1.100 |
| cons.price.idx | 93.5756644 | 0.5788400 | 93.749 |
| euribor3m | 3.6212908 | 1.7344474 | 4.857 |
| nr.employed | 5167.0359109 | 72.2515277 | 5191.000 |
#categorical vars
categorical_vars <- c("job", "marital", "education", "default", "housing",
"loan", "contact", "month", "day_of_week", "poutcome")
df_cat <- df %>%
select(all_of(categorical_vars)) %>%
pivot_longer(cols = everything(), names_to = "variable", values_to = "value")
df_summary <- df_cat %>%
group_by(variable, value) %>%
summarise(count = n(), .groups = 'drop') %>%
group_by(variable) %>%
mutate(percent = count / sum(count)) %>%
ungroup()
# Bar chart for categorical variables
ggplot(df_summary, aes(x = value, y = count)) +
geom_bar(stat = "identity", fill = "dodgerblue", color = "black") +
geom_text(aes(label = scales::percent(percent, accuracy = 1)),
vjust = -0.5, size = 2) +
facet_wrap(~ variable, scales = "free_x") +
theme_minimal() +
theme(axis.text.x = element_text(angle = 45, hjust = 1)) +
labs(title = "Frequency Distribution of Categorical Variables",
x = "Category", y = "Frequency")
#data preprocessing
unknown_vars <- c("job", "marital", "education", "default", "housing", "loan", "contact")
df <- df %>%
mutate(across(all_of(unknown_vars), ~ ifelse(. == "unknown", NA, .)))
# Function to calculate mode
getmode <- function(v) {
uniqv <- unique(v)
uniqv[which.max(tabulate(match(v, uniqv)))]
}
# Impute for numerical variables (using median)
for (var in numerical_vars) {
med_val <- median(df[[var]], na.rm = TRUE)
df[[var]][is.na(df[[var]])] <- med_val
}
# Impute for categorical variables (using mode)
for (var in categorical_vars) {
mode_val <- getmode(df[[var]])
df[[var]][is.na(df[[var]])] <- mode_val
}
# Convert categorical variables to factors
df[categorical_vars] <- lapply(df[categorical_vars], factor)
#splitting the data
set.seed(1234)
train_index <- createDataPartition(df$y, p = 0.8, list = FALSE)
train <- df[train_index, ]
test <- df[-train_index, ]
#building model ----------
#logistic reg
logit_model <- glm(y ~ ., data = train, family = binomial)
pred_logit_prob <- predict(logit_model, test, type = "response")
pred_logit_class <- ifelse(pred_logit_prob > 0.5, "yes", "no")
conf_matrix_logit <- table(Predicted = pred_logit_class, Actual = test$y)
print("Logistic Regression Confusion Matrix:")
#;-) [1] "Logistic Regression Confusion Matrix:"
print(conf_matrix_logit)
#;-) Actual
#;-) Predicted no yes
#;-) no 7111 515
#;-) yes 198 413
misclass_logit <- mean(pred_logit_class != test$y)
print(paste("Logistic Regression Misclassification Error:", misclass_logit))
#;-) [1] "Logistic Regression Misclassification Error: 0.0865606410100765"
# Check for multicollinearity
vif(logit_model)
#;-) GVIF Df GVIF^(1/(2*Df))
#;-) age 2.256226 1 1.502074
#;-) job 5.188047 10 1.085801
#;-) marital 1.461178 2 1.099451
#;-) education 2.843305 6 1.090985
#;-) default 1.000001 1 1.000000
#;-) housing 1.012374 1 1.006168
#;-) loan 1.006373 1 1.003181
#;-) contact 2.309911 1 1.519839
#;-) month 63.447258 9 1.259314
#;-) day_of_week 1.067990 4 1.008256
#;-) duration 1.233953 1 1.110834
#;-) campaign 1.053757 1 1.026527
#;-) pdays 11.159807 1 3.340630
#;-) previous 4.514174 1 2.124659
#;-) poutcome 24.842833 2 2.232545
#;-) emp.var.rate 144.022282 1 12.000928
#;-) cons.price.idx 67.940605 1 8.242609
#;-) cons.conf.idx 5.337276 1 2.310255
#;-) euribor3m 135.344539 1 11.633767
#;-) nr.employed 170.604033 1 13.061548
#naive bayes
nb_model <- naive_bayes(y ~ ., data = train)
#;-) Warning: naive_bayes(): Feature default - zero probabilities are present.
#;-) Consider Laplace smoothing.
print("Naive Bayes Model Summary:")
#;-) [1] "Naive Bayes Model Summary:"
print(nb_model)
#;-)
#;-) ================================= Naive Bayes ==================================
#;-)
#;-) Call:
#;-) naive_bayes.formula(formula = y ~ ., data = train)
#;-)
#;-) --------------------------------------------------------------------------------
#;-)
#;-) Laplace smoothing: 0
#;-)
#;-) --------------------------------------------------------------------------------
#;-)
#;-) A priori probabilities:
#;-)
#;-) no yes
#;-) 0.8873479 0.1126521
#;-)
#;-) --------------------------------------------------------------------------------
#;-)
#;-) Tables:
#;-)
#;-) --------------------------------------------------------------------------------
#;-) :: age (Gaussian)
#;-) --------------------------------------------------------------------------------
#;-)
#;-) age no yes
#;-) mean 39.912548 41.015625
#;-) sd 9.889584 13.897216
#;-)
#;-) --------------------------------------------------------------------------------
#;-) :: job (Categorical)
#;-) --------------------------------------------------------------------------------
#;-)
#;-) job no yes
#;-) 1 0.25459147 0.29391164
#;-) 2 0.23697801 0.13981681
#;-) 3 0.03591094 0.02532328
#;-) 4 0.02609528 0.02505388
#;-) 5 0.07127467 0.07219828
#;-) 6 0.03556893 0.09482759
#;-) 7 0.03444030 0.03286638
#;-) 8 0.10024283 0.07004310
#;-) 9 0.01583501 0.05818966
#;-) 10 0.16556654 0.15544181
#;-) 11 0.02349602 0.03232759
#;-)
#;-) --------------------------------------------------------------------------------
#;-) :: marital (Categorical)
#;-) --------------------------------------------------------------------------------
#;-)
#;-) marital no yes
#;-) 1 0.1128972 0.1066810
#;-) 2 0.6141113 0.5449892
#;-) 3 0.2729916 0.3483297
#;-)
#;-) --------------------------------------------------------------------------------
#;-) :: education (Categorical)
#;-) --------------------------------------------------------------------------------
#;-)
#;-) education no yes
#;-) 1 0.101645063 0.096174569
#;-) 2 0.058415130 0.040948276
#;-) 3 0.152741202 0.102370690
#;-) 4 0.232224084 0.221443966
#;-) 5 0.000342009 0.001077586
#;-) 6 0.127466740 0.127963362
#;-) 7 0.327165772 0.410021552
#;-)
#;-) --------------------------------------------------------------------------------
#;-) :: default (Bernoulli)
#;-) --------------------------------------------------------------------------------
#;-)
#;-) default no yes
#;-) 1 0.9998973973 1.0000000000
#;-) 3 0.0001026027 0.0000000000
#;-)
#;-) --------------------------------------------------------------------------------
#;-)
#;-) # ... and 15 more tables
#;-)
#;-) --------------------------------------------------------------------------------
pred_nb_prob <- predict(nb_model, test, type = "prob")
#;-) Warning: predict.naive_bayes(): more features in the newdata are provided as
#;-) there are probability tables in the object. Calculation is performed based on
#;-) features to be found in the tables.
head(pred_nb_prob)
#;-) no yes
#;-) [1,] 0.9999475 5.249120e-05
#;-) [2,] 0.9999710 2.902459e-05
#;-) [3,] 0.9998522 1.477800e-04
#;-) [4,] 0.9999676 3.243193e-05
#;-) [5,] 0.9999001 9.991972e-05
#;-) [6,] 0.9997024 2.975520e-04
pred_nb_class <- predict(nb_model, test)
#;-) Warning: predict.naive_bayes(): more features in the newdata are provided as
#;-) there are probability tables in the object. Calculation is performed based on
#;-) features to be found in the tables.
conf_matrix_nb <- table(Predicted = pred_nb_class, Actual = test$y)
print("Naive Bayes Confusion Matrix:")
#;-) [1] "Naive Bayes Confusion Matrix:"
print(conf_matrix_nb)
#;-) Actual
#;-) Predicted no yes
#;-) no 6514 357
#;-) yes 795 571
misclass_nb <- mean(pred_nb_class != test$y)
print(paste("Naive Bayes Misclassification Error:", misclass_nb))
#;-) [1] "Naive Bayes Misclassification Error: 0.13985674396018"Because session_info is TRUE, the rendered
result includes session info, even though no such code is included here
in the source document.
sessionInfo()
#;-) R version 4.3.3 (2024-02-29)
#;-) Platform: x86_64-apple-darwin20 (64-bit)
#;-) Running under: macOS 15.3.1
#;-)
#;-) Matrix products: default
#;-) BLAS: /Library/Frameworks/R.framework/Versions/4.3-x86_64/Resources/lib/libRblas.0.dylib
#;-) LAPACK: /Library/Frameworks/R.framework/Versions/4.3-x86_64/Resources/lib/libRlapack.dylib; LAPACK version 3.11.0
#;-)
#;-) locale:
#;-) [1] en_US.UTF-8/en_US.UTF-8/en_US.UTF-8/C/en_US.UTF-8/en_US.UTF-8
#;-)
#;-) time zone: America/New_York
#;-) tzcode source: internal
#;-)
#;-) attached base packages:
#;-) [1] stats graphics grDevices utils datasets methods base
#;-)
#;-) other attached packages:
#;-) [1] data.table_1.15.4 rmarkdown_2.29 knitr_1.49 DataExplorer_0.8.3
#;-) [5] car_3.1-3 carData_3.0-5 pROC_1.18.5 naivebayes_1.0.0
#;-) [9] caret_7.0-1 lattice_0.22-5 ggcorrplot_0.1.4.1 corrplot_0.95
#;-) [13] tidyr_1.3.1 dplyr_1.1.4 scales_1.3.0 gridExtra_2.3
#;-) [17] naniar_1.1.0 GGally_2.2.1 ggplot2_3.5.0
#;-)
#;-) loaded via a namespace (and not attached):
#;-) [1] tidyselect_1.2.1 timeDate_4041.110 farver_2.1.1
#;-) [4] fastmap_1.1.1 reprex_2.1.0 digest_0.6.35
#;-) [7] rpart_4.1.23 timechange_0.3.0 lifecycle_1.0.4
#;-) [10] survival_3.5-8 magrittr_2.0.3 compiler_4.3.3
#;-) [13] sass_0.4.9 rlang_1.1.3 tools_4.3.3
#;-) [16] igraph_2.1.4 utf8_1.2.4 yaml_2.3.8
#;-) [19] labeling_0.4.3 htmlwidgets_1.6.4 curl_5.2.1
#;-) [22] xml2_1.3.6 plyr_1.8.9 RColorBrewer_1.1-3
#;-) [25] abind_1.4-8 withr_3.0.0 purrr_1.0.2
#;-) [28] nnet_7.3-19 grid_4.3.3 stats4_4.3.3
#;-) [31] fansi_1.0.6 colorspace_2.1-0 future_1.34.0
#;-) [34] globals_0.16.3 iterators_1.0.14 MASS_7.3-60.0.1
#;-) [37] cli_3.6.2 generics_0.1.3 rstudioapi_0.16.0
#;-) [40] future.apply_1.11.3 reshape2_1.4.4 cachem_1.0.8
#;-) [43] stringr_1.5.1 splines_4.3.3 parallel_4.3.3
#;-) [46] vctrs_0.6.5 hardhat_1.4.1 Matrix_1.6-5
#;-) [49] jsonlite_1.8.8 visdat_0.6.0 Formula_1.2-5
#;-) [52] listenv_0.9.1 foreach_1.5.2 jquerylib_0.1.4
#;-) [55] gower_1.0.2 recipes_1.1.1 glue_1.7.0
#;-) [58] parallelly_1.42.0 ggstats_0.8.0 codetools_0.2-19
#;-) [61] lubridate_1.9.3 stringi_1.8.3 gtable_0.3.4
#;-) [64] munsell_0.5.1 tibble_3.2.1 pillar_1.9.0
#;-) [67] htmltools_0.5.8 ipred_0.9-15 lava_1.8.1
#;-) [70] R6_2.5.1 networkD3_0.4 evaluate_0.23
#;-) [73] bslib_0.7.0 class_7.3-23 Rcpp_1.0.12
#;-) [76] nlme_3.1-164 prodlim_2024.06.25 xfun_0.51
#;-) [79] fs_1.6.3 pkgconfig_2.0.3 ModelMetrics_1.2.2.2