Pipe operator

Description

See magrittr::%>% for details.

Usage

lhs %>% rhs

lhs %>% rhs

Arguments

Value

The result of applying rhs to lhs.

Augment Data with DBSCAN Cluster Assignments

Description

Augment Data with DBSCAN Cluster Assignments

Usage

augment_dbscan(dbscan_obj, data)

Arguments

Value

A tibble containing the original data with additional columns cluster (factor), is_noise (logical), and is_core (logical).

Examples

db <- tidy_dbscan(iris[, 1:4], eps = 0.5, minPts = 5)
augmented <- augment_dbscan(db, iris)

Augment Data with Hierarchical Cluster Assignments

Description

Add cluster assignments to original data

Usage

augment_hclust(hclust_obj, data, k = NULL, h = NULL)

Arguments

Value

A tibble containing the original data with an additional cluster integer column indicating cluster assignments.

Examples

hc <- tidy_hclust(USArrests, method = "ward.D2")
augmented <- augment_hclust(hc, USArrests, k = 3)

Augment Data with K-Means Cluster Assignments

Description

Augment Data with K-Means Cluster Assignments

Usage

augment_kmeans(kmeans_obj, data)

Arguments

Value

A tibble containing the original data with an additional cluster factor column indicating cluster assignments.

Examples

km <- tidy_kmeans(iris[, 1:4], k = 3)
augmented <- augment_kmeans(km, iris)

Augment Data with PAM Cluster Assignments

Description

Augment Data with PAM Cluster Assignments

Usage

augment_pam(pam_obj, data)

Arguments

Value

A tibble containing the original data with an additional cluster factor column indicating cluster assignments.

Examples

pm <- tidy_pam(iris[, 1:4], k = 3)
augmented <- augment_pam(pm, iris)

Augment Original Data with PCA Scores

Description

Add PC scores to the original dataset

Usage

augment_pca(pca_obj, data, n_components = NULL)

Arguments

Value

A tibble containing the original data with additional columns for each principal component score (named PC1, PC2, etc.).

Examples

pca <- tidy_pca(USArrests)
augmented <- augment_pca(pca, USArrests, n_components = 2)

Calculate Cluster Validation Metrics

Description

Comprehensive validation metrics for a clustering result

Usage

calc_validation_metrics(clusters, data = NULL, dist_mat = NULL)

Arguments

Value

A single-row tibble with columns k, min_size, max_size, avg_size, and optionally avg_silhouette, min_silhouette (if dist_mat provided), and total_wss (if data provided).

Examples

km <- kmeans(iris[, 1:4], centers = 3, nstart = 25)
d <- dist(iris[, 1:4])
metrics <- calc_validation_metrics(km$cluster, iris[, 1:4], d)

Calculate Within-Cluster Sum of Squares for Different k

Description

Used for elbow method to determine optimal k

Usage

calc_wss(data, max_k = 10, nstart = 25)

Arguments

Value

A tibble with columns k (number of clusters) and tot_withinss (total within-cluster sum of squares).

Examples

wss <- calc_wss(iris[, 1:4], max_k = 6)
plot(wss$k, wss$tot_withinss, type = "b")

Compare Multiple Clustering Results

Description

Compare Multiple Clustering Results

Usage

compare_clusterings(cluster_list, data, dist_mat = NULL)

Arguments

Value

A tibble with one row per clustering method and columns for each validation metric (see calc_validation_metrics), plus a method column identifying the clustering.

Examples

km3 <- kmeans(iris[, 1:4], 3, nstart = 25)$cluster
km4 <- kmeans(iris[, 1:4], 4, nstart = 25)$cluster
compare_clusterings(list(k3 = km3, k4 = km4), iris[, 1:4])

Compare Distance Methods

Description

Compute distances using multiple methods for comparison

Usage

compare_distances(data, methods = c("euclidean", "manhattan", "maximum"))

Arguments

Value

A named list of dist objects, one per method.

Examples

dists <- compare_distances(iris[, 1:4], methods = c("euclidean", "manhattan"))

Create Summary Dashboard

Description

Generate a multi-panel summary of clustering results

Usage

create_cluster_dashboard(
  data,
  cluster_col = "cluster",
  validation_metrics = NULL
)

Arguments

Value

Invisibly returns a list of ggplot objects. The combined plot grid is drawn as a side effect via grid.arrange.

Examples

df <- iris[, 1:4]
df$cluster <- kmeans(df, 3)$cluster
create_cluster_dashboard(df)

Explore DBSCAN Parameters

Description

Test multiple eps and minPts combinations

Usage

explore_dbscan_params(data, eps_values, minPts_values)

Arguments

Value

A tibble with columns eps, minPts, n_clusters, n_noise, and prop_noise for each parameter combination.

Examples

params <- explore_dbscan_params(iris[, 1:4],
  eps_values = c(0.3, 0.5, 0.8), minPts_values = c(3, 5))

Filter Rules by Item

Description

Subset rules containing specific items

Usage

filter_rules_by_item(rules_obj, item, where = "both")

Arguments

Value

A tibble of rules containing the specified item in the requested position.

Examples

if (requireNamespace("arules", quietly = TRUE)) {
  data("Groceries", package = "arules")
  res <- tidy_apriori(Groceries, support = 0.001, confidence = 0.5)
  filter_rules_by_item(res, "whole milk", where = "rhs")
}

Find Related Items

Description

Find items frequently purchased with a given item

Usage

find_related_items(rules_obj, item, min_lift = 1.5, top_n = 10)

Arguments

Value

A tibble of rules involving the specified item, filtered by min_lift and sorted by lift in descending order.

Examples

if (requireNamespace("arules", quietly = TRUE)) {
  data("Groceries", package = "arules")
  res <- tidy_apriori(Groceries, support = 0.001, confidence = 0.5)
  find_related_items(res, "whole milk", min_lift = 1.5)
}

Get PCA Loadings in Wide Format

Description

Get PCA Loadings in Wide Format

Usage

get_pca_loadings(pca_obj, n_components = NULL)

Arguments

Value

A tibble with one row per variable and one column per principal component, containing the loading values.

Examples

pca <- tidy_pca(USArrests)
get_pca_loadings(pca, n_components = 2)

Get Variance Explained Summary

Description

Get Variance Explained Summary

Usage

get_pca_variance(pca_obj)

Arguments

Value

A tibble with columns component, sdev, variance, prop_variance, and cum_variance.

Examples

pca <- tidy_pca(USArrests)
get_pca_variance(pca)

Inspect Association Rules

Description

View rules sorted by various quality measures

Usage

inspect_rules(rules_obj, by = "lift", n = 10, decreasing = TRUE)

Arguments

Value

A tibble of the top n rules sorted by the specified quality measure.

Examples

if (requireNamespace("arules", quietly = TRUE)) {
  data("Groceries", package = "arules")
  res <- tidy_apriori(Groceries, support = 0.001, confidence = 0.5)
  inspect_rules(res, by = "lift", n = 5)
}

Find Optimal Number of Clusters

Description

Use multiple methods to suggest optimal k

Usage

optimal_clusters(data, max_k = 10, methods = c("silhouette", "gap", "wss"))

Arguments

Value

A list of class "optimal_k_results" containing one or more of:

• wss: tibble from calc_wss (if "wss" method used)

• silhouette: tibble from tidy_silhouette_analysis (if "silhouette" method used)

• gap: a tidy_gap object from tidy_gap_stat (if "gap" method used)

Examples

opt <- optimal_clusters(iris[, 1:4], max_k = 6, methods = "wss")

Determine Optimal Number of Clusters for Hierarchical Clustering

Description

Use silhouette or gap statistic to find optimal k

Usage

optimal_hclust_k(hclust_obj, method = "silhouette", max_k = 10)

Arguments

Value

A list containing:

• optimal_k: the recommended number of clusters

• method: the evaluation method used

• values: numeric vector of evaluation scores (for silhouette)

• k_range: integer vector of k values tested (for silhouette)

If method = "gap", returns a tidy_gap object instead.

Examples

hc <- tidy_hclust(USArrests, method = "ward.D2")
opt <- optimal_hclust_k(hc, method = "silhouette", max_k = 6)

Plot EDA results

Description

Plot EDA results

Usage

## S3 method for class 'tidylearn_eda'
plot(x, ...)

Arguments

Value

The input object x, returned invisibly. Called for its side effect of plotting a PCA scatter plot coloured by cluster.

Examples

eda <- tl_explore(iris, response = "Species")
plot(eda)

Plot method for tidylearn models

Description

Plot method for tidylearn models

Usage

## S3 method for class 'tidylearn_model'
plot(x, type = "auto", ...)

Arguments

Value

A ggplot object. The specific plot depends on the model paradigm and type argument.

Examples

model <- tl_model(mtcars, mpg ~ wt + hp, method = "linear")
plot(model, type = "actual_predicted")

Create Cluster Comparison Plot

Description

Compare multiple clustering results side-by-side

Usage

plot_cluster_comparison(data, cluster_cols, x_col, y_col)

Arguments

Value

The return value of grid.arrange, a gtable drawn as a side effect.

Examples

df <- iris[, 1:4]
df$km3 <- kmeans(df, 3)$cluster
df$km4 <- kmeans(df, 4)$cluster
plot_cluster_comparison(df, c("km3", "km4"), "Sepal.Length", "Sepal.Width")

Plot Cluster Size Distribution

Description

Create bar plot of cluster sizes

Usage

plot_cluster_sizes(clusters, title = "Cluster Size Distribution")

Arguments

Value

A ggplot object.

Examples

clusters <- kmeans(iris[, 1:4], 3)$cluster
plot_cluster_sizes(clusters)

Plot Clusters in 2D Space

Description

Visualize clustering results using first two dimensions or specified dimensions

Usage

plot_clusters(
  data,
  cluster_col = "cluster",
  x_col = NULL,
  y_col = NULL,
  centers = NULL,
  title = "Cluster Plot",
  color_noise_black = TRUE
)

Arguments

Value

A ggplot object.

Examples

km <- tidy_kmeans(iris[, 1:4], k = 3)
clustered <- augment_kmeans(km, iris[, 1:4])
plot_clusters(clustered)

Plot Dendrogram with Cluster Highlights

Description

Enhanced dendrogram with colored cluster rectangles

Usage

plot_dendrogram(
  hclust_obj,
  k = NULL,
  title = "Hierarchical Clustering Dendrogram"
)

Arguments

Value

Invisibly returns the hclust object. The dendrogram is drawn as a side effect.

Examples

hc <- hclust(dist(iris[, 1:4]))
plot_dendrogram(hc, k = 3)

Create Distance Heatmap

Description

Visualize distance matrix as heatmap

Usage

plot_distance_heatmap(
  dist_mat,
  cluster_order = NULL,
  title = "Distance Heatmap"
)

Arguments

Value

A ggplot object.

Examples

d <- dist(iris[1:20, 1:4])
plot_distance_heatmap(d)

Create Elbow Plot for K-Means

Description

Plot total within-cluster sum of squares vs number of clusters

Usage

plot_elbow(wss_data, add_line = FALSE, suggested_k = NULL)

Arguments

Value

A ggplot object.

Examples

wss <- data.frame(k = 2:6, tot_withinss = c(150, 90, 60, 50, 45))
plot_elbow(wss)

Plot Gap Statistic

Description

Plot Gap Statistic

Usage

plot_gap_stat(gap_obj, show_methods = FALSE)

Arguments

Value

A ggplot object.

Examples

gap <- tidy_gap_stat(iris[, 1:4], max_k = 6, B = 10)
plot_gap_stat(gap)

Plot k-NN Distance Plot

Description

Visualize k-NN distances to help choose eps

Usage

plot_knn_dist(data, k = 4, add_suggestion = TRUE, percentile = 0.95)

Arguments

Value

A ggplot object.

Examples

plot_knn_dist(iris[, 1:4], k = 5)

Plot MDS Configuration

Description

Visualize MDS results

Usage

plot_mds(mds_obj, color_by = NULL, label_points = TRUE, dim_x = 1, dim_y = 2)

Arguments

Value

A ggplot object.

Examples

mds <- tidy_mds(USArrests, method = "classical")
plot_mds(mds)

Plot Silhouette Analysis

Description

Plot Silhouette Analysis

Usage

plot_silhouette(sil_obj)

Arguments

Value

A ggplot object.

Examples

km <- kmeans(iris[, 1:4], centers = 3, nstart = 25)
d <- dist(iris[, 1:4])
sil <- tidy_silhouette(km$cluster, d)
plot_silhouette(sil)

Plot Variance Explained (PCA)

Description

Create combined scree plot showing individual and cumulative variance

Usage

plot_variance_explained(variance_tbl, threshold = 0.8)

Arguments

Value

A ggplot object.

Examples

model <- tl_model(iris[, 1:4], method = "pca")
plot_variance_explained(model$fit$variance_explained)

Predict using a tidylearn model

Description

Unified prediction interface for both supervised and unsupervised models

Usage

## S3 method for class 'tidylearn_model'
predict(object, new_data = NULL, type = "response", ...)

Arguments

Value

A tibble with a .pred column containing predictions. For classification with type = "prob", returns columns for each class probability.

Examples

model <- tl_model(mtcars, mpg ~ wt + hp, method = "linear")
predict(model)
predict(model, new_data = mtcars[1:5, ])

Predict from stratified models

Description

Predict from stratified models

Usage

## S3 method for class 'tidylearn_stratified'
predict(object, new_data = NULL, ...)

Arguments

Value

A tibble with a .pred column containing predictions and a .cluster column with cluster assignments.

Examples

models <- tl_stratified_models(mtcars, mpg ~ .,
  cluster_method = "kmeans", k = 2, supervised_method = "linear")
preds <- predict(models)

Predict with transfer learning model

Description

Predict with transfer learning model

Usage

## S3 method for class 'tidylearn_transfer'
predict(object, new_data, ...)

Arguments

Value

A tibble with a .pred column containing predictions.

Examples

model <- tl_transfer_learning(iris, Species ~ .,
  pretrain_method = "pca", supervised_method = "logistic")
preds <- predict(model, iris[1:5, ])

Print Method for tidy_apriori

Description

Print Method for tidy_apriori

Usage

## S3 method for class 'tidy_apriori'
print(x, ...)

Arguments

Value

The input object x, returned invisibly.

Examples

if (requireNamespace("arules", quietly = TRUE)) {
  data("Groceries", package = "arules")
  res <- tidy_apriori(Groceries, support = 0.001, confidence = 0.5)
  print(res)
}

Print Method for tidy_dbscan

Description

Print Method for tidy_dbscan

Usage

## S3 method for class 'tidy_dbscan'
print(x, ...)

Arguments

Value

The input object x, returned invisibly.

Examples

db <- tidy_dbscan(iris[, 1:4], eps = 0.5, minPts = 5)
print(db)

Print Method for tidy_gap

Description

Print Method for tidy_gap

Usage

## S3 method for class 'tidy_gap'
print(x, ...)

Arguments

Value

The input object x, returned invisibly.

Examples

gap <- tidy_gap_stat(iris[, 1:4], max_k = 6, B = 10)
print(gap)

Print Method for tidy_hclust

Description

Print Method for tidy_hclust

Usage

## S3 method for class 'tidy_hclust'
print(x, ...)

Arguments

Value

The input object x, returned invisibly.

Examples

hc <- tidy_hclust(USArrests, method = "ward.D2")
print(hc)

Print Method for tidy_kmeans

Description

Print Method for tidy_kmeans

Usage

## S3 method for class 'tidy_kmeans'
print(x, ...)

Arguments

Value

The input object x, returned invisibly.

Examples

km <- tidy_kmeans(iris[, 1:4], k = 3)
print(km)

Print Method for tidy_mds

Description

Print Method for tidy_mds

Usage

## S3 method for class 'tidy_mds'
print(x, ...)

Arguments

Value

The input object x, returned invisibly.

Examples

mds <- tidy_mds(USArrests, method = "classical")
print(mds)

Print Method for tidy_pam

Description

Print Method for tidy_pam

Usage

## S3 method for class 'tidy_pam'
print(x, ...)

Arguments

Value

The input object x, returned invisibly.

Examples

pm <- tidy_pam(iris[, 1:4], k = 3)
print(pm)

Print Method for tidy_pca

Description

Print Method for tidy_pca

Usage

## S3 method for class 'tidy_pca'
print(x, ...)

Arguments

Value

The input object x, returned invisibly.

Examples

pca <- tidy_pca(USArrests)
print(pca)

Print Method for tidy_silhouette

Description

Print Method for tidy_silhouette

Usage

## S3 method for class 'tidy_silhouette'
print(x, ...)

Arguments

Value

The input object x, returned invisibly.

Examples

km <- kmeans(iris[, 1:4], centers = 3, nstart = 25)
d <- dist(iris[, 1:4])
sil <- tidy_silhouette(km$cluster, d)
print(sil)

Print auto ML results

Description

Print auto ML results

Usage

## S3 method for class 'tidylearn_automl'
print(x, ...)

Arguments

Value

The input object x, returned invisibly.

Print a tidylearn_data object

Description

Print a tidylearn_data object

Usage

## S3 method for class 'tidylearn_data'
print(x, ...)

Arguments

Value

The input object x, returned invisibly.

Examples

f <- tempfile(fileext = ".csv")
write.csv(iris, f, row.names = FALSE)
d <- tl_read(f)
print(d)

Print EDA results

Description

Print EDA results

Usage

## S3 method for class 'tidylearn_eda'
print(x, ...)

Arguments

Value

The input object x, returned invisibly.

Examples

eda <- tl_explore(iris, response = "Species")
print(eda)

Print method for tidylearn models

Description

Print method for tidylearn models

Usage

## S3 method for class 'tidylearn_model'
print(x, ...)

Arguments

Value

The input object x, returned invisibly.

Examples

model <- tl_model(mtcars, mpg ~ wt + hp, method = "linear")
print(model)

Print a tidylearn pipeline

Description

Print a tidylearn pipeline

Usage

## S3 method for class 'tidylearn_pipeline'
print(x, ...)

Arguments

Value

The input pipeline object x, returned invisibly.

Examples

pipe <- tl_pipeline(iris, Species ~ .)
print(pipe)

Generate Product Recommendations

Description

Get product recommendations based on basket contents

Usage

recommend_products(rules_obj, basket, top_n = 5, min_confidence = 0.5)

Arguments

Value

A tibble with columns rhs (recommended item), confidence, lift, and support, sorted by lift in descending order.

Examples

if (requireNamespace("arules", quietly = TRUE)) {
  data("Groceries", package = "arules")
  res <- tidy_apriori(Groceries, support = 0.001, confidence = 0.5)
  recommend_products(res, basket = c("whole milk", "butter"))
}

Standardize Data

Description

Center and/or scale numeric variables

Usage

standardize_data(data, center = TRUE, scale = TRUE)

Arguments

Value

A tibble with numeric variables centered and/or scaled as specified; non-numeric columns are returned unchanged.

Examples

std <- standardize_data(iris[, 1:4])

Suggest eps Parameter for DBSCAN

Description

Use k-NN distance plot to suggest eps value

Usage

suggest_eps(data, minPts = 5, method = "percentile", percentile = 0.95)

Arguments

Value

A list containing:

• eps: suggested epsilon value

• knn_distances: full tibble of k-NN distances

• method: method used

Examples

eps_info <- suggest_eps(iris, minPts = 5)
eps_info$eps

Summarize Association Rules

Description

Get summary statistics about rules

Usage

summarize_rules(rules_obj)

Arguments

Value

A list with n_rules and summary statistics (min, max, mean, median) for support, confidence, and lift.

Examples

if (requireNamespace("arules", quietly = TRUE)) {
  data("Groceries", package = "arules")
  res <- tidy_apriori(Groceries, support = 0.001, confidence = 0.5)
  summarize_rules(res)
}

Summary method for tidylearn models

Description

Summary method for tidylearn models

Usage

## S3 method for class 'tidylearn_model'
summary(object, ...)

Arguments

Value

The input object, returned invisibly. Called for its side effect of printing model summary and training performance.

Examples

model <- tl_model(mtcars, mpg ~ wt + hp, method = "linear")
summary(model)

Summarize a tidylearn pipeline

Description

Summarize a tidylearn pipeline

Usage

## S3 method for class 'tidylearn_pipeline'
summary(object, ...)

Arguments

Value

The input pipeline object, returned invisibly. Called for its side effect of printing detailed pipeline and model results.

Examples

pipe <- tl_pipeline(iris, Species ~ .)
summary(pipe)

Tidy Apriori Algorithm

Description

Mine association rules using the Apriori algorithm with tidy output

Usage

tidy_apriori(
  transactions,
  support = 0.01,
  confidence = 0.5,
  minlen = 2,
  maxlen = 10,
  target = "rules"
)

Arguments

Value

A list of class "tidy_rules" containing:

• rules_tbl: tibble of rules with lhs, rhs, and quality measures

• rules: original rules object

• parameters: parameters used

Examples

if (requireNamespace("arules", quietly = TRUE)) {
data("Groceries", package = "arules")

# Basic apriori
rules <- tidy_apriori(Groceries, support = 0.001, confidence = 0.5)

# Access rules
rules$rules_tbl
}

Tidy CLARA (Clustering Large Applications)

Description

Performs CLARA clustering (scalable version of PAM)

Usage

tidy_clara(data, k, metric = "euclidean", samples = 50, sampsize = NULL)

Arguments

Value

A list of class "tidy_clara" containing:

• clusters: tibble with observation IDs and cluster assignments

• medoids: tibble of medoid values

• silhouette_avg: average silhouette width

• model: original clara object

Examples

# CLARA for large datasets
large_data <- iris[rep(1:nrow(iris), 10), 1:4]
clara_result <- tidy_clara(large_data, k = 3, samples = 50)
print(clara_result)

Cut Hierarchical Clustering Tree

Description

Cut dendrogram to obtain cluster assignments

Usage

tidy_cutree(hclust_obj, k = NULL, h = NULL)

Arguments

Value

A tibble with columns .obs_id (observation identifier) and cluster (integer cluster assignment).

Examples

hc <- tidy_hclust(USArrests, method = "ward.D2")
clusters <- tidy_cutree(hc, k = 3)

Tidy DBSCAN Clustering

Description

Performs density-based clustering with tidy output

Usage

tidy_dbscan(data, eps, minPts = 5, cols = NULL, distance = "euclidean")

Arguments

Value

A list of class "tidy_dbscan" containing:

• clusters: tibble with observation IDs and cluster assignments (0 = noise)

• core_points: logical vector indicating core points

• n_clusters: number of clusters (excluding noise)

• n_noise: number of noise points

• model: original dbscan object

Examples

# Basic DBSCAN
db_result <- tidy_dbscan(iris, eps = 0.5, minPts = 5)

# With suggested eps from k-NN distance plot
eps_suggestion <- suggest_eps(iris, minPts = 5)
db_result <- tidy_dbscan(iris, eps = eps_suggestion$eps, minPts = 5)

Plot Dendrogram

Description

Create dendrogram visualization

Usage

tidy_dendrogram(hclust_obj, k = NULL, hang = 0.01, cex = 0.7)

Arguments

Value

The hclust object, returned invisibly. The dendrogram is plotted as a side effect.

Examples

hc <- tidy_hclust(USArrests, method = "ward.D2")
tidy_dendrogram(hc, k = 3)

Tidy Distance Matrix Computation

Description

Compute distance matrices with tidy output

Usage

tidy_dist(data, method = "euclidean", cols = NULL, ...)

Arguments

Value

A dist object containing the computed distance matrix.

Examples

d <- tidy_dist(iris[, 1:4], method = "euclidean")

Tidy Gap Statistic

Description

Compute gap statistic for determining optimal number of clusters

Usage

tidy_gap_stat(data, FUN_cluster = NULL, max_k = 10, B = 50, nstart = 25)

Arguments

Value

A list of class "tidy_gap" containing:

• gap_data: tibble with gap statistics for each k

• k_firstSEmax: optimal k via firstSEmax method (most conservative)

• k_globalmax: optimal k via globalmax method

• k_firstmax: optimal k via firstmax method

• recommended_k: recommended k (uses firstSEmax)

• model: the clusGap result

Examples

gap <- tidy_gap_stat(iris[, 1:4], max_k = 6, B = 10)
gap$recommended_k

Gower Distance Calculation

Description

Computes Gower distance for mixed data types (numeric, factor, ordered)

Usage

tidy_gower(data, weights = NULL)

Arguments

Details

Gower distance handles mixed data types:

• Numeric: range-normalized Manhattan distance

• Factor/Character: 0 if same, 1 if different

• Ordered: treated as numeric ranks

Formula: d_ij = sum(w_k * d_ijk) / sum(w_k) where d_ijk is the dissimilarity for variable k between obs i and j

Value

A dist object containing Gower distances, with the method attribute set to "gower".

Examples

# Create example data with mixed types
car_data <- data.frame(
  horsepower = c(130, 250, 180),
  weight = c(1200, 1650, 1420),
  color = factor(c("red", "black", "blue"))
)

# Compute Gower distance
gower_dist <- tidy_gower(car_data)

Tidy Hierarchical Clustering

Description

Performs hierarchical clustering with tidy output

Usage

tidy_hclust(data, method = "average", distance = "euclidean", cols = NULL)

Arguments

Value

A list of class "tidy_hclust" containing:

• model: hclust object

• dist: distance matrix used

• method: linkage method used

• data: original data (for plotting)

Examples

# Basic hierarchical clustering
hc_result <- tidy_hclust(USArrests, method = "average")

# With specific distance
hc_result <- tidy_hclust(mtcars, method = "complete", distance = "manhattan")

Tidy K-Means Clustering

Description

Performs k-means clustering with tidy output

Usage

tidy_kmeans(
  data,
  k,
  cols = NULL,
  nstart = 25,
  iter_max = 100,
  algorithm = "Hartigan-Wong"
)

Arguments

Value

A list of class "tidy_kmeans" containing:

• clusters: tibble with observation IDs and cluster assignments

• centers: tibble of cluster centers

• metrics: tibble with clustering quality metrics

• model: original kmeans object

Examples

# Basic k-means
km_result <- tidy_kmeans(iris, k = 3)

Compute k-NN Distances

Description

Calculate distances to k-th nearest neighbor for each point

Usage

tidy_knn_dist(data, k = 4, cols = NULL)

Arguments

Value

A tibble with columns .obs_id (observation identifier), knn_dist (distance to k-th nearest neighbor), and rank (rank of the k-NN distance).

Examples

knn <- tidy_knn_dist(iris[, 1:4], k = 5)

Tidy Multidimensional Scaling

Description

Unified interface for MDS methods with tidy output

Usage

tidy_mds(data, method = "classical", ndim = 2, distance = "euclidean", ...)

Arguments

Value

A list of class "tidy_mds" containing:

• config: tibble of MDS configuration (coordinates)

• stress: goodness-of-fit measure (if applicable)

• method: character string of method used

• model: original model object

Examples

# Classical MDS
mds_result <- tidy_mds(eurodist, method = "classical")
print(mds_result)

Classical (Metric) MDS

Description

Performs classical multidimensional scaling using cmdscale()

Usage

tidy_mds_classical(dist_mat, ndim = 2, add_rownames = TRUE)

Arguments

Value

A list of class "tidy_mds" containing:

• config: tibble of MDS coordinates

• stress: NA (not applicable for classical MDS)

• gof: goodness-of-fit (proportion of variance retained)

• eigenvalues: numeric vector of eigenvalues

• method: "Classical MDS"

• model: the cmdscale result

Examples

d <- dist(USArrests)
mds <- tidy_mds_classical(d)
print(mds)

Kruskal's Non-metric MDS

Description

Performs Kruskal's isoMDS

Usage

tidy_mds_kruskal(dist_mat, ndim = 2, ...)

Arguments

Value

A list of class "tidy_mds" containing:

• config: tibble of MDS coordinates

• stress: Kruskal stress value

• method: "Kruskal's isoMDS"

• model: the isoMDS result

Examples

d <- dist(USArrests)
mds <- tidy_mds_kruskal(d)

Sammon Mapping

Description

Performs Sammon's non-linear mapping

Usage

tidy_mds_sammon(dist_mat, ndim = 2, ...)

Arguments

Value

A list of class "tidy_mds" containing:

• config: tibble of MDS coordinates

• stress: Sammon stress value

• method: "Sammon Mapping"

• model: the sammon result

Examples

d <- dist(USArrests)
mds <- tidy_mds_sammon(d)

SMACOF MDS (Metric or Non-metric)

Description

Performs MDS using SMACOF algorithm from the smacof package

Usage

tidy_mds_smacof(dist_mat, ndim = 2, type = "ratio", ...)

Arguments

Value

A list of class "tidy_mds" containing:

• config: tibble of MDS coordinates

• stress: stress value from the SMACOF algorithm

• method: character string describing the MDS type

• model: the mds result

Examples

d <- dist(USArrests)
mds <- tidy_mds_smacof(d, type = "ratio")

Tidy PAM (Partitioning Around Medoids)

Description

Performs PAM clustering with tidy output

Usage

tidy_pam(data, k, metric = "euclidean", cols = NULL)

Arguments

Value

A list of class "tidy_pam" containing:

• clusters: tibble with observation IDs and cluster assignments

• medoids: tibble of medoid indices and values

• silhouette: average silhouette width

• model: original pam object

Examples

# PAM with Euclidean distance
pam_result <- tidy_pam(iris, k = 3)

# PAM with Gower distance for mixed data
pam_result <- tidy_pam(mtcars, k = 3, metric = "gower")

Tidy Principal Component Analysis

Description

Performs PCA on a dataset using tidyverse principles. Returns a tidy list containing scores, loadings, variance explained, and the original model.

Usage

tidy_pca(data, cols = NULL, scale = TRUE, center = TRUE, method = "prcomp")

Arguments

Value

A list of class "tidy_pca" containing:

• scores: tibble of PC scores with observation identifiers

• loadings: tibble of variable loadings in long format

• variance: tibble of variance explained by each PC

• model: the original prcomp/princomp object

• settings: list of scale, center, method used

Examples

# Basic PCA
pca_result <- tidy_pca(USArrests)


# Access components
pca_result$scores
pca_result$loadings
pca_result$variance

Create PCA Biplot

Description

Visualize both observations and variables in PC space

Usage

tidy_pca_biplot(
  pca_obj,
  pc_x = 1,
  pc_y = 2,
  color_by = NULL,
  arrow_scale = 1,
  label_obs = FALSE,
  label_vars = TRUE
)

Arguments

Value

A ggplot object.

Examples

pca <- tidy_pca(USArrests)
tidy_pca_biplot(pca)

Create PCA Scree Plot

Description

Visualize variance explained by each principal component

Usage

tidy_pca_screeplot(pca_obj, type = "proportion", add_line = TRUE)

Arguments

Value

A ggplot object.

Examples

pca <- tidy_pca(USArrests)
tidy_pca_screeplot(pca)

Convert Association Rules to Tidy Tibble

Description

Convert Association Rules to Tidy Tibble

Usage

tidy_rules(rules)

Arguments

Value

A tibble with columns rule_id, lhs, rhs, and quality measures (e.g., support, confidence, lift).

Examples

if (requireNamespace("arules", quietly = TRUE)) {
  data("Groceries", package = "arules")
  rules_obj <- arules::apriori(Groceries,
    parameter = list(supp = 0.001, conf = 0.5))
  rules_tbl <- tidy_rules(rules_obj)
}

Tidy Silhouette Analysis

Description

Compute silhouette statistics for cluster validation

Usage

tidy_silhouette(clusters, dist_mat)

Arguments

Value

A list of class "tidy_silhouette" containing:

• silhouette_data: tibble with silhouette values for each observation

• avg_width: average silhouette width

• cluster_avg: average silhouette width by cluster

Examples

km <- kmeans(iris[, 1:4], centers = 3, nstart = 25)
d <- dist(iris[, 1:4])
sil <- tidy_silhouette(km$cluster, d)

Silhouette Analysis Across Multiple k Values

Description

Silhouette Analysis Across Multiple k Values

Usage

tidy_silhouette_analysis(
  data,
  max_k = 10,
  method = "kmeans",
  nstart = 25,
  dist_method = "euclidean",
  linkage_method = "average"
)

Arguments

Value

A tibble with columns k and avg_sil_width. The "optimal_k" attribute contains the k with the highest average silhouette width.

Examples

sil_analysis <- tidy_silhouette_analysis(iris[, 1:4], max_k = 6)

Classification Functions for tidylearn

Description

Logistic regression and classification metrics functionality

tidylearn: A Unified Tidy Interface to R's Machine Learning Ecosystem

Description

Core functionality for tidylearn. This package provides a unified tidyverse-compatible interface to established R machine learning packages including glmnet, randomForest, xgboost, e1071, rpart, gbm, nnet, cluster, and dbscan. The underlying algorithms are unchanged - tidylearn wraps them with consistent function signatures, tidy tibble output, and unified ggplot2-based visualization. Access raw model objects via model$fit.

Deep Learning for tidylearn

Description

Deep learning functionality using Keras/TensorFlow

Advanced Diagnostics Functions for tidylearn

Description

Functions for advanced model diagnostics, assumption checking, and outlier detection

Interaction Analysis Functions for tidylearn

Description

Functions for testing, visualizing, and analyzing interactions

Metrics Functionality for tidylearn

Description

Functions for calculating model evaluation metrics

Model Selection Functions for tidylearn

Description

Functions for stepwise model selection, cross-validation, and hyperparameter tuning

Neural Networks for tidylearn

Description

Neural network functionality for classification and regression

Model Pipeline Functions for tidylearn

Description

Functions for creating end-to-end model pipelines

Data Reading Functions for tidylearn

Description

Functions for reading data from diverse sources into tidy tidylearn_data objects. The main dispatcher tl_read() auto-detects the format from the file extension and routes to the appropriate reader. All readers return a tidylearn_data object, which is a tibble subclass carrying metadata about the data source.

Details

Supported file formats:

• CSV: .csv files via readr (with base R fallback)

• TSV: .tsv files via readr (with base R fallback)

• Excel: .xls, .xlsx, .xlsm files via readxl

• Parquet: .parquet files via nanoparquet

• JSON: .json files via jsonlite

• RDS: .rds files via base readRDS()

• RData: .rdata, .rda files via base load()

Supported databases (via DBI):

• SQLite: .sqlite, .db files via RSQLite

• PostgreSQL: via RPostgres

• MySQL/MariaDB: via RMariaDB

• BigQuery: via bigrquery

Supported cloud/API sources:

• S3: s3:// URIs via paws.storage

• GitHub: raw file download from repositories

• Kaggle: dataset download via Kaggle CLI

Multi-file reading:

• Multiple paths: pass a character vector to tl_read()

• Directories: tl_read_dir() scans for data files with optional pattern/format filtering and recursive scanning

• Zip archives: tl_read_zip() extracts and reads from .zip files

When combining multiple files, a source_file column is added to identify the origin of each row.

Data Reading Backends for tidylearn

Description

Backend readers for databases and cloud/API sources. All backends are optional dependencies checked at call time via tl_check_packages().

Details

Database backends (via DBI):

• SQLite: via RSQLite

• PostgreSQL: via RPostgres

• MySQL/MariaDB: via RMariaDB

• BigQuery: via bigrquery

Cloud/API backends:

• S3: via paws.storage

• GitHub: via base download.file()

• Kaggle: via Kaggle CLI

Regression Functions for tidylearn

Description

Linear and polynomial regression functionality

Regularization Functions for tidylearn

Description

Ridge, Lasso, and Elastic Net regularization functionality

Support Vector Machines for tidylearn

Description

SVM functionality for classification and regression

Table Functions for tidylearn

Description

Functions for producing formatted gt tables from tidylearn models. Provides a parallel interface to the plot functions: tl_table(model, type) dispatches to the appropriate table formatter based on model type. Requires the gt package (suggested dependency).

Tree-based Methods for tidylearn

Description

Decision trees, random forests, and boosting functionality

Hyperparameter Tuning Functions for tidylearn

Description

Functions for automatic hyperparameter tuning and selection

Visualization Functions for tidylearn

Description

General visualization functions for tidylearn models

High-Level Workflows for Common Machine Learning Patterns

Description

Functions providing end-to-end workflows that showcase tidylearn's ability to seamlessly combine multiple learning paradigms

XGBoost Functions for tidylearn

Description

XGBoost-specific implementation for gradient boosting

Cluster-Based Features

Description

Add cluster assignments as features for supervised learning. This semi-supervised approach can capture non-linear patterns.

Usage

tl_add_cluster_features(data, response = NULL, method = "kmeans", ...)

Arguments

Value

The original data frame with an additional factor column named cluster_<method> containing cluster assignments. The fitted cluster model is stored as an attribute "cluster_model".

Examples

# Add cluster features before supervised learning
data_with_clusters <- tl_add_cluster_features(iris, response = "Species",
                                                method = "kmeans", k = 3)
model <- tl_model(data_with_clusters, Species ~ ., method = "forest")

Anomaly-Aware Supervised Learning

Description

Detect outliers using DBSCAN or other methods, then optionally remove them or down-weight them before supervised learning.

Usage

tl_anomaly_aware(
  data,
  formula,
  response,
  anomaly_method = "dbscan",
  action = "flag",
  supervised_method = "logistic",
  ...
)

Arguments

Value

A tidylearn model object with additional class "tidylearn_anomaly_aware". The model includes an anomaly_info element with anomaly_model, is_anomaly (logical vector), n_anomalies, and action.

Examples

model <- tl_anomaly_aware(iris, Species ~ ., response = "Species",
                           anomaly_method = "dbscan", action = "flag")

Find important interactions automatically

Description

Find important interactions automatically

Usage

tl_auto_interactions(
  data,
  formula,
  top_n = 3,
  min_r2_change = 0.01,
  max_p_value = 0.05,
  exclude_vars = NULL
)

Arguments

Value

A tidylearn model object (class "tidylearn_model") fitted with the top significant interaction terms added to the formula. The interaction test results and selected interactions are stored as attributes "interaction_tests" and "selected_interactions".

Examples

model <- tl_auto_interactions(mtcars, mpg ~ wt + hp + cyl, top_n = 2)

Auto ML: Automated Machine Learning Workflow

Description

Automatically explores multiple modeling approaches including dimensionality reduction, clustering, and various supervised methods. Returns the best performing model based on cross-validation.

Usage

tl_auto_ml(
  data,
  formula,
  task = "auto",
  use_reduction = TRUE,
  use_clustering = TRUE,
  time_budget = 300,
  cv_folds = 5,
  metric = NULL
)

Arguments

Value

A list with class "tidylearn_automl" containing:

best_model

The best tidylearn model object

models

Named list of all successfully trained models

leaderboard

Tibble ranking models by the chosen metric

task

Detected or specified task type

metric

Metric used for ranking

runtime

Total elapsed time as a difftime object

Examples

# Quick run with fast models only (< 30s budget skips forest/SVM/XGBoost)
result <- tl_auto_ml(iris, Species ~ .,
  time_budget = 10,
  use_reduction = FALSE,
  use_clustering = FALSE,
  cv_folds = 2)
result$leaderboard

Calculate classification metrics

Description

Calculate classification metrics

Usage

tl_calc_classification_metrics(
  actuals,
  predicted,
  predicted_probs = NULL,
  metrics = c("accuracy", "precision", "recall", "f1", "auc"),
  thresholds = NULL,
  ...
)

Arguments

Value

A tibble with columns metric (character) and value (numeric) containing the requested classification metrics. When thresholds are supplied, additional rows are appended with threshold-specific metric names.

Examples

model <- tl_model(iris, Species ~ ., method = "forest")
preds <- predict(model)
tl_calc_classification_metrics(iris$Species, preds$.pred)

Calculate the area under the precision-recall curve

Description

Calculate the area under the precision-recall curve

Usage

tl_calculate_pr_auc(perf)

Arguments

Value

The area under the PR curve

Check model assumptions

Description

Check model assumptions

Usage

tl_check_assumptions(model, test = TRUE, verbose = TRUE)

Arguments

Value

A named list with one element per assumption checked (linearity, independence, homoscedasticity, normality, multicollinearity, outliers), each containing assumption (character label), check (logical or NULL), details (character), and recommendation (character). An additional overall element summarises the number of assumptions checked, violated, and satisfied.

Examples

model <- tl_model(mtcars, mpg ~ wt + hp, method = "linear")
tl_check_assumptions(model)

Compare models using cross-validation

Description

Compare models using cross-validation

Usage

tl_compare_cv(data, models, folds = 5, metrics = NULL, ...)

Arguments

Value

A list with two elements:

$fold_metrics

A data frame with columns metric, value, fold, and model containing per-fold results for every model.

$summary

A data frame with columns model, metric, mean_value, sd_value, min_value, and max_value summarizing cross-validation performance.

Examples

m1 <- tl_model(mtcars, mpg ~ wt, method = "linear")
m2 <- tl_model(mtcars, mpg ~ wt + hp, method = "linear")
cv <- tl_compare_cv(mtcars, list(simple = m1, full = m2), folds = 3)
cv$summary

Compare models from a pipeline

Description

Compare models from a pipeline

Usage

tl_compare_pipeline_models(pipeline, metrics = NULL)

Arguments

Value

A ggplot object showing a faceted bar chart comparing metric values across models, with the best model highlighted.

Cross-validation for tidylearn models

Description

Cross-validation for tidylearn models

Usage

tl_cv(data, formula, method, folds = 5, ...)

Arguments

Value

A list with two elements:

$folds

A list of per-fold evaluation tibbles, each with metric and value columns.

$summary

A tibble with columns metric, mean, and sd summarizing performance across folds.

Examples

cv <- tl_cv(mtcars, mpg ~ wt + hp, method = "linear", folds = 3)
cv$summary

Create interactive visualization dashboard for a model

Description

Create interactive visualization dashboard for a model

Usage

tl_dashboard(model, new_data = NULL, ...)

Arguments

Value

A shinyApp object.

Examples

if (requireNamespace("shiny")) {
  model <- tl_model(mtcars, mpg ~ wt + hp, method = "linear")
  app <- tl_dashboard(model)
}

Create pre-defined parameter grids for common models

Description

Create pre-defined parameter grids for common models

Usage

tl_default_param_grid(method, size = "medium", is_classification = TRUE)

Arguments

Value

A named list of parameter values suitable for passing to tl_tune_grid or tl_tune_random. Each element is a numeric or character vector of candidate values for that hyperparameter.

Examples

grid <- tl_default_param_grid("tree", size = "small")
grid <- tl_default_param_grid("forest", size = "medium")

Detect outliers in the data

Description

Detect outliers in the data

Usage

tl_detect_outliers(
  data,
  variables = NULL,
  method = "iqr",
  threshold = NULL,
  plot = TRUE
)

Arguments

Value

A list with outlier detection results:

method

The detection method used (character).

method_name

Human-readable method name (character).

threshold

The threshold value used (numeric).

threshold_label

Formatted threshold description (character).

outlier_flags

A logical matrix (observations x variables).

any_outlier

Logical vector indicating if each observation is an outlier in any variable.

outlier_counts

List with total, by_variable, and by_observation counts.

outlier_indices

Integer vector of outlier row indices.

plot

A ggplot object, or NULL if plot = FALSE.

Examples

tl_detect_outliers(mtcars, variables = c("mpg", "wt"), method = "iqr")

Create a comprehensive diagnostic dashboard

Description

Create a comprehensive diagnostic dashboard

Usage

tl_diagnostic_dashboard(
  model,
  include_influence = TRUE,
  include_assumptions = TRUE,
  include_performance = TRUE,
  arrange_plots = "grid"
)

Arguments

Value

A grid.arrange object (a grob) containing the arranged diagnostic plots.

Examples

if (requireNamespace("gridExtra")) {
  model <- tl_model(mtcars, mpg ~ wt + hp, method = "linear")
  tl_diagnostic_dashboard(model)
}

Evaluate a tidylearn model

Description

Evaluate a tidylearn model

Usage

tl_evaluate(object, new_data = NULL, ...)

Arguments

Value

A tibble with columns metric (character) and value (numeric). For regression models, includes rmse, mae, and rsq. For classification models, includes accuracy.

Examples

model <- tl_model(mtcars, mpg ~ wt + hp, method = "linear")
tl_evaluate(model)

Evaluate metrics at different thresholds

Description

Evaluate metrics at different thresholds

Usage

tl_evaluate_thresholds(actuals, probs, thresholds, pos_class)

Arguments

Value

A tibble of metrics at different thresholds

Exploratory Data Analysis Workflow

Description

Comprehensive EDA combining unsupervised learning techniques to understand data structure before modeling

Usage

tl_explore(data, response = NULL, max_components = 5, k_range = 2:6)

Arguments

Value

A list with class "tidylearn_eda" containing:

data

The original data frame.

response

The response variable name, or NULL.

pca

The fitted PCA model.

optimal_k

List with optimal cluster count results.

kmeans

The fitted k-means model.

hclust

The fitted hierarchical clustering model.

summary

List with n_obs, n_vars, n_components, and best_k.

Examples

eda <- tl_explore(iris, response = "Species")
plot(eda)

Extract importance from a tree-based model

Description

Extract importance from a tree-based model

Usage

tl_extract_importance(model)

Arguments

Value

A data frame with feature importance values

Extract importance from a regularized regression model

Description

Extract importance from a regularized regression model

Usage

tl_extract_importance_regularized(model, lambda = "1se")

Arguments

Value

A data frame with feature importance values

Fit a gradient boosting model

Description

Fit a gradient boosting model

Usage

tl_fit_boost(
  data,
  formula,
  is_classification = FALSE,
  n.trees = 100,
  interaction.depth = 3,
  shrinkage = 0.1,
  n.minobsinnode = 10,
  cv.folds = 0,
  ...
)

Arguments

Value

A fitted gradient boosting model

Fit a deep learning model

Description

Fit a deep learning model

Usage

tl_fit_deep(
  data,
  formula,
  is_classification = FALSE,
  hidden_layers = c(32, 16),
  activation = "relu",
  dropout = 0.2,
  epochs = 30,
  batch_size = 32,
  validation_split = 0.2,
  verbose = 0,
  ...
)

Arguments

Value

A fitted deep learning model

Fit an Elastic Net regression model

Description

Fit an Elastic Net regression model

Usage

tl_fit_elastic_net(
  data,
  formula,
  is_classification = FALSE,
  alpha = 0.5,
  lambda = NULL,
  cv_folds = 5,
  ...
)

Arguments

Value

A fitted Elastic Net regression model

Fit a random forest model

Description

Fit a random forest model

Usage

tl_fit_forest(
  data,
  formula,
  is_classification = FALSE,
  ntree = 500,
  mtry = NULL,
  importance = TRUE,
  ...
)

Arguments

Value

A fitted random forest model

Fit a Lasso regression model

Description

Fit a Lasso regression model

Usage

tl_fit_lasso(
  data,
  formula,
  is_classification = FALSE,
  alpha = 1,
  lambda = NULL,
  cv_folds = 5,
  ...
)

Arguments

Value

A fitted Lasso regression model

Fit a linear regression model

Description

Fit a linear regression model

Usage

tl_fit_linear(data, formula, ...)

Arguments

Value

A fitted linear regression model

Fit a logistic regression model

Description

Fit a logistic regression model

Usage

tl_fit_logistic(data, formula, ...)

Arguments

Value

A fitted logistic regression model

Fit a neural network model

Description

Fit a neural network model

Usage

tl_fit_nn(
  data,
  formula,
  is_classification = FALSE,
  size = 5,
  decay = 0,
  maxit = 100,
  trace = FALSE,
  ...
)

Arguments

Value

A fitted neural network model

Fit a polynomial regression model

Description

Fit a polynomial regression model

Usage

tl_fit_polynomial(data, formula, degree = 2, ...)

Arguments

Value

A fitted polynomial regression model

Fit a regularized regression model

Description

Fits Ridge, Lasso, or Elastic Net regularization.

Usage

tl_fit_regularized(
  data,
  formula,
  is_classification = FALSE,
  alpha = 0,
  lambda = NULL,
  cv_folds = 5,
  ...
)

Arguments

Value

A fitted regularized regression model

Fit a Ridge regression model

Description

Fit a Ridge regression model

Usage

tl_fit_ridge(
  data,
  formula,
  is_classification = FALSE,
  alpha = 0,
  lambda = NULL,
  cv_folds = 5,
  ...
)

Arguments

Value

A fitted Ridge regression model

Fit a support vector machine model

Description

Fit a support vector machine model

Usage

tl_fit_svm(
  data,
  formula,
  is_classification = FALSE,
  kernel = "radial",
  cost = 1,
  gamma = NULL,
  degree = 3,
  tune = FALSE,
  tune_folds = 5,
  ...
)

Arguments

Value

A fitted SVM model

Fit a decision tree model

Description

Fit a decision tree model

Usage

tl_fit_tree(
  data,
  formula,
  is_classification = FALSE,
  cp = 0.01,
  minsplit = 20,
  maxdepth = 30,
  ...
)

Arguments

Value

A fitted decision tree model

Fit an XGBoost model

Description

Fit an XGBoost model

Usage

tl_fit_xgboost(
  data,
  formula,
  is_classification = FALSE,
  nrounds = 100,
  max_depth = 6,
  eta = 0.3,
  subsample = 1,
  colsample_bytree = 1,
  min_child_weight = 1,
  gamma = 0,
  alpha = 0,
  lambda = 1,
  early_stopping_rounds = NULL,
  nthread = NULL,
  verbose = 0,
  ...
)

Arguments

Value

A fitted XGBoost model

Get the best model from a pipeline

Description

Get the best model from a pipeline

Usage

tl_get_best_model(pipeline)

Arguments

Value

The best tidylearn_model object from the pipeline, selected by the metric specified in evaluation$best_metric.

Examples

pipe <- tl_pipeline(iris, Species ~ .,
  models = list(tree = list(method = "tree")),
  evaluation = list(metrics = "accuracy", validation = "cv",
    cv_folds = 2, best_metric = "accuracy"))
pipe <- tl_run_pipeline(pipe, verbose = FALSE)
best <- tl_get_best_model(pipe)

Calculate influence measures for a linear model

Description

Calculate influence measures for a linear model

Usage

tl_influence_measures(
  model,
  threshold_cook = NULL,
  threshold_leverage = NULL,
  threshold_dffits = NULL
)

Arguments

Value

A data frame with one row per observation containing influence measures: cooks_distance, leverage, dffits, std_residual, stud_residual, boolean flags for each threshold (is_cook_influential, is_leverage_influential, is_dffits_influential, is_outlier), per-coefficient dfbetas_* columns, and an overall is_influential flag. Threshold values are stored as attributes.

Examples

model <- tl_model(mtcars, mpg ~ wt + hp, method = "linear")
tl_influence_measures(model)

Calculate partial effects based on a model with interactions

Description

Calculate partial effects based on a model with interactions

Usage

tl_interaction_effects(model, var, by_var, at_values = NULL, intervals = TRUE)

Arguments

Value

For numeric var: a list with effects (data frame of predicted values across the variable range for each level of by_var) and slopes (data frame with estimated slopes and standard errors per level). For categorical var: a data frame of predicted values at each factor level for each level of by_var.

Load a pipeline from disk

Description

Load a pipeline from disk

Usage

tl_load_pipeline(file)

Arguments

Value

A tidylearn_pipeline object previously saved with tl_save_pipeline.

Examples

pipe <- tl_pipeline(iris, Species ~ .)
f <- tempfile(fileext = ".rds")
tl_save_pipeline(pipe, f)
pipe2 <- tl_load_pipeline(f)

Create a tidylearn model

Description

Unified interface for creating machine learning models by wrapping established R packages. This function dispatches to the appropriate underlying package based on the method.

Usage

tl_model(data, formula = NULL, method = "linear", ...)

Arguments

Details

The wrapped packages include: stats (lm, glm, prcomp, kmeans, hclust), glmnet, randomForest, xgboost, gbm, e1071, nnet, rpart, cluster, and dbscan. The underlying algorithms are unchanged - this function provides a consistent interface and returns tidy output.

Access the raw model object from the underlying package via model$fit.

Value

A tidylearn_model object (S3) containing the fitted model ($fit), model specification ($spec), and training data ($data). The object also inherits from a method-specific class (e.g., tidylearn_linear) and a paradigm class (tidylearn_supervised or tidylearn_unsupervised).

Examples

# Classification -> wraps randomForest::randomForest()
model <- tl_model(iris, Species ~ ., method = "forest")
model$fit  # Access the raw randomForest object

# Regression -> wraps stats::lm()
model <- tl_model(mtcars, mpg ~ wt + hp, method = "linear")
model$fit  # Access the raw lm object

# PCA -> wraps stats::prcomp()
model <- tl_model(iris, ~ ., method = "pca")
model$fit  # Access the raw prcomp object

# Clustering -> wraps stats::kmeans()
model <- tl_model(iris, method = "kmeans", k = 3)
model$fit  # Access the raw kmeans object

Create a modeling pipeline

Description

Create a modeling pipeline

Usage

tl_pipeline(
  data,
  formula,
  preprocessing = NULL,
  models = NULL,
  evaluation = NULL,
  ...
)

Arguments

Value

A tidylearn_pipeline object (S3 list) with components $formula, $data, $preprocessing, $models, $evaluation, and $results (initially NULL; populated after tl_run_pipeline).

Examples

pipe <- tl_pipeline(iris, Species ~ .,
  models = list(tree = list(method = "tree")))
print(pipe)

Plot actual vs predicted values for a regression model

Description

Plot actual vs predicted values for a regression model

Usage

tl_plot_actual_predicted(model, new_data = NULL, ...)

Arguments

Value

A ggplot object

Plot calibration curve for a classification model

Description

Plot calibration curve for a classification model

Usage

tl_plot_calibration(model, new_data = NULL, bins = 10, ...)

Arguments

Value

A ggplot object with calibration curve

Plot confusion matrix for a classification model

Description

Plot confusion matrix for a classification model

Usage

tl_plot_confusion(model, new_data = NULL, ...)

Arguments

Value

A ggplot object with confusion matrix

Plot comparison of cross-validation results

Description

Plot comparison of cross-validation results

Usage

tl_plot_cv_comparison(cv_results, metrics = NULL)

Arguments

Value

A ggplot object showing boxplots of cross-validation metric distributions for each model.

Examples

m1 <- tl_model(mtcars, mpg ~ wt, method = "linear")
m2 <- tl_model(mtcars, mpg ~ wt + hp, method = "linear")
cv <- tl_compare_cv(mtcars, list(simple = m1, full = m2), folds = 3)
tl_plot_cv_comparison(cv)

Plot cross-validation results

Description

Plot cross-validation results

Usage

tl_plot_cv_results(cv_results, metrics = NULL)

Arguments

Value

A ggplot object.

Plot deep learning model architecture

Description

Plot deep learning model architecture

Usage

tl_plot_deep_architecture(model, ...)

Arguments

Value

The return value of keras::plot_model(), an architecture diagram of the Keras model.

Examples

## Not run: 
if (requireNamespace("keras", quietly = TRUE)) {
  model <- tl_model(iris, Species ~ ., method = "deep", epochs = 5)
  tl_plot_deep_architecture(model)
}

## End(Not run)

Plot deep learning model training history

Description

Plot deep learning model training history

Usage

tl_plot_deep_history(model, metrics = c("loss", "val_loss"), ...)

Arguments

Value

A ggplot object.

Examples

## Not run: 
if (requireNamespace("keras", quietly = TRUE)) {
  model <- tl_model(iris, Species ~ ., method = "deep", epochs = 5)
  tl_plot_deep_history(model)
}

## End(Not run)

Plot diagnostics for a regression model

Description

Plot diagnostics for a regression model

Usage

tl_plot_diagnostics(model, which = 1:4, ...)

Arguments

Value

A ggplot object (or list of ggplot objects)

Plot gain chart for a classification model

Description

Plot gain chart for a classification model

Usage

tl_plot_gain(model, new_data = NULL, bins = 10, ...)

Arguments

Value

A ggplot object.

Examples

iris_bin <- iris[iris$Species != "setosa", ]
iris_bin$Species <- factor(iris_bin$Species)
model <- tl_model(iris_bin, Species ~ ., method = "logistic")
tl_plot_gain(model)

Plot variable importance for tree-based models

Description

Plot variable importance for tree-based models

Usage

tl_plot_importance(model, top_n = 20, ...)

Arguments

Value

A ggplot object

Plot feature importance across multiple models

Description

Plot feature importance across multiple models

Usage

tl_plot_importance_comparison(..., top_n = 10, names = NULL)

Arguments

Value

A ggplot object.

Examples

m1 <- tl_model(iris, Species ~ ., method = "forest")
m2 <- tl_model(iris, Species ~ ., method = "boost")
tl_plot_importance_comparison(m1, m2, names = c("Forest", "Boost"))

Plot variable importance for a regularized model

Description

Plot variable importance for a regularized model

Usage

tl_plot_importance_regularized(model, lambda = "1se", top_n = 20, ...)

Arguments

Value

A ggplot object.

Examples

model <- tl_model(mtcars, mpg ~ ., method = "lasso")
tl_plot_importance_regularized(model)

Plot influence diagnostics

Description

Plot influence diagnostics

Usage

tl_plot_influence(
  model,
  plot_type = "cook",
  threshold_cook = NULL,
  threshold_leverage = NULL,
  threshold_dffits = NULL,
  n_labels = 3,
  label_size = 3
)

Arguments

Value

A ggplot object.

Examples

model <- tl_model(mtcars, mpg ~ wt + hp, method = "linear")
tl_plot_influence(model, plot_type = "cook")

Plot interaction effects

Description

Plot interaction effects

Usage

tl_plot_interaction(
  model,
  var1,
  var2,
  n_points = 100,
  fixed_values = NULL,
  confidence = TRUE,
  ...
)

Arguments

Value

A ggplot object.

Create confidence and prediction interval plots

Description

Create confidence and prediction interval plots

Usage

tl_plot_intervals(model, new_data = NULL, level = 0.95, ...)

Arguments

Value

A ggplot object.

Examples

model <- tl_model(mtcars, mpg ~ wt, method = "linear")
tl_plot_intervals(model)

Plot lift chart for a classification model

Description

Plot lift chart for a classification model

Usage

tl_plot_lift(model, new_data = NULL, bins = 10, ...)

Arguments

Value

A ggplot object.

Examples

iris_bin <- iris[iris$Species != "setosa", ]
iris_bin$Species <- factor(iris_bin$Species)
model <- tl_model(iris_bin, Species ~ ., method = "logistic")
tl_plot_lift(model)

Plot a supervised tidylearn model

Description

Dispatches to the appropriate plotting function based on model type and requested plot type.

Usage

tl_plot_model(model, type = "auto", ...)

Arguments

Value

A ggplot2 object (invisibly for base-graphics plots)

Plot model comparison

Description

Plot model comparison

Usage

tl_plot_model_comparison(..., new_data = NULL, metrics = NULL, names = NULL)

Arguments

Value

A ggplot object.

Examples

m1 <- tl_model(mtcars, mpg ~ wt + hp, method = "linear")
m2 <- tl_model(mtcars, mpg ~ wt + hp, method = "lasso")
tl_plot_model_comparison(m1, m2, names = c("Linear", "Lasso"))

Plot neural network architecture

Description

Plot neural network architecture

Usage

tl_plot_nn_architecture(model, ...)

Arguments

Value

The return value of plotnet, called for its side effect of drawing the network diagram, or NULL if the NeuralNetTools package is not installed.

Examples

if (requireNamespace("NeuralNetTools", quietly = TRUE)) {
  model <- tl_model(iris, Species ~ ., method = "nn", size = 3)
  tl_plot_nn_architecture(model)
}

Plot neural network training history

Description

Plot neural network training history

Usage

tl_plot_nn_tuning(model, ...)

Arguments

Value

A ggplot object.

Plot partial dependence for tree-based models

Description

Plot partial dependence for tree-based models

Usage

tl_plot_partial_dependence(model, var, n.pts = 20, ...)

Arguments

Value

A ggplot object.

Examples

model <- tl_model(mtcars, mpg ~ ., method = "forest")
tl_plot_partial_dependence(model, var = "wt")

Plot precision-recall curve for a classification model

Description

Plot precision-recall curve for a classification model

Usage

tl_plot_precision_recall(model, new_data = NULL, ...)

Arguments

Value

A ggplot object with precision-recall curve

Plot cross-validation results for a regularized model

Description

Shows the cross-validation error as a function of lambda for ridge, lasso, or elastic net models fitted with cv.glmnet.

Usage

tl_plot_regularization_cv(model, ...)

Arguments

Value

A ggplot object.

Examples

model <- tl_model(mtcars, mpg ~ ., method = "ridge")
tl_plot_regularization_cv(model)

Plot regularization path for a regularized model

Description

Plot regularization path for a regularized model

Usage

tl_plot_regularization_path(model, label_n = 5, ...)

Arguments

Value

A ggplot object.

Examples

model <- tl_model(mtcars, mpg ~ ., method = "lasso")
tl_plot_regularization_path(model)

Plot residuals for a regression model

Description

Plot residuals for a regression model

Usage

tl_plot_residuals(model, type = "fitted", ...)

Arguments

Value

A ggplot object

Plot ROC curve for a classification model

Description

Plot ROC curve for a classification model

Usage

tl_plot_roc(model, new_data = NULL, ...)

Arguments

Value

A ggplot object with ROC curve

Plot SVM decision boundary

Description

Plot SVM decision boundary

Usage

tl_plot_svm_boundary(model, x_var = NULL, y_var = NULL, grid_size = 100, ...)

Arguments

Value

A ggplot object.

Examples

if (requireNamespace("e1071", quietly = TRUE)) {
  model <- tl_model(iris, Species ~ ., method = "svm")
  tl_plot_svm_boundary(model,
    x_var = "Sepal.Length", y_var = "Sepal.Width")
}

Plot SVM tuning results

Description

Plot SVM tuning results

Usage

tl_plot_svm_tuning(model, ...)

Arguments

Value

A ggplot object.

Examples

if (requireNamespace("e1071", quietly = TRUE)) {
  model <- tl_model(iris, Species ~ ., method = "svm",
    kernel = "linear", tune = TRUE, tune_folds = 2)
  tl_plot_svm_tuning(model)
}

Plot a decision tree

Description

Plot a decision tree

Usage

tl_plot_tree(model, ...)

Arguments

Value

The return value of rpart.plot, called for its side effect of drawing the tree.

Examples

model <- tl_model(iris, Species ~ ., method = "tree")
tl_plot_tree(model)

Plot hyperparameter tuning results

Description

Plot hyperparameter tuning results

Usage

tl_plot_tuning_results(
  model,
  top_n = 5,
  param1 = NULL,
  param2 = NULL,
  plot_type = "scatter"
)

Arguments

Value

A ggplot object.

Examples

model <- tl_tune_grid(iris, Species ~ ., method = "tree",
  param_grid = list(cp = c(0.01, 0.1), minsplit = c(10, 20)),
  folds = 2, verbose = FALSE)
tl_plot_tuning_results(model)

Plot an unsupervised tidylearn model

Description

Dispatches to the appropriate plotting function based on the unsupervised model method.

Usage

tl_plot_unsupervised(model, type = "auto", ...)

Arguments

Value

A ggplot2 object or invisible result

Plot feature importance for an XGBoost model

Description

Plot feature importance for an XGBoost model

Usage

tl_plot_xgboost_importance(model, top_n = 10, importance_type = "gain", ...)

Arguments

Value

A ggplot object.

Examples

if (requireNamespace("xgboost", quietly = TRUE)) {
  model <- tl_model(mtcars, mpg ~ ., method = "xgboost")
  tl_plot_xgboost_importance(model)
}

Plot SHAP dependence for a specific feature

Description

Plot SHAP dependence for a specific feature

Usage

tl_plot_xgboost_shap_dependence(
  model,
  feature,
  interaction_feature = NULL,
  data = NULL,
  n_samples = 100
)

Arguments

Value

A ggplot object.

Plot SHAP summary for XGBoost model

Description

Plot SHAP summary for XGBoost model

Usage

tl_plot_xgboost_shap_summary(model, data = NULL, top_n = 10, n_samples = 100)

Arguments

Value

A ggplot object.

Examples

if (requireNamespace("xgboost", quietly = TRUE)) {
  model <- tl_model(mtcars, mpg ~ ., method = "xgboost")
  tl_plot_xgboost_shap_summary(model, n_samples = 20)
}

Plot XGBoost tree visualization

Description

Plot XGBoost tree visualization

Usage

tl_plot_xgboost_tree(model, tree_index = 0, ...)

Arguments

Value

The return value of xgb.plot.tree, a tree diagram rendered via the DiagrammeR package.

Predict using a gradient boosting model

Description

Predict using a gradient boosting model

Usage

tl_predict_boost(model, new_data, type = "response", n.trees = NULL, ...)

Arguments

Value

Predictions

Predict using a deep learning model

Description

Predict using a deep learning model

Usage

tl_predict_deep(model, new_data, type = "response", ...)

Arguments

Value

Predictions

Predict using an Elastic Net regression model

Description

Predict using an Elastic Net regression model

Usage

tl_predict_elastic_net(model, new_data, type = "response", ...)

Arguments

Value

Predictions

Predict using a random forest model

Description

Predict using a random forest model

Usage

tl_predict_forest(model, new_data, type = "response", ...)

Arguments

Value

Predictions

Predict using a Lasso regression model

Description

Predict using a Lasso regression model

Usage

tl_predict_lasso(model, new_data, type = "response", ...)

Arguments

Value

Predictions

Predict using a linear regression model

Description

Predict using a linear regression model

Usage

tl_predict_linear(model, new_data, type = "response", level = 0.95, ...)

Arguments

Value

Predictions

Predict using a logistic regression model

Description

Predict using a logistic regression model

Usage

tl_predict_logistic(model, new_data, type = "prob", ...)

Arguments

Value

Predictions

Predict using a neural network model

Description

Predict using a neural network model

Usage

tl_predict_nn(model, new_data, type = "response", ...)

Arguments

Value

Predictions

Make predictions using a pipeline

Description

Make predictions using a pipeline

Usage

tl_predict_pipeline(
  pipeline,
  new_data,
  type = "response",
  model_name = NULL,
  ...
)

Arguments

Value

A tibble with a .pred column containing predictions from the selected (or best) pipeline model, after applying the same preprocessing steps used during training.

Predict using a polynomial regression model

Description

Predict using a polynomial regression model

Usage

tl_predict_polynomial(model, new_data, type = "response", level = 0.95, ...)

Arguments

Value

Predictions

Predict using a regularized regression model

Description

Predict using a regularized regression model

Usage

tl_predict_regularized(model, new_data, type = "response", lambda = "1se", ...)

Arguments

Value

Predictions

Predict using a Ridge regression model

Description

Predict using a Ridge regression model

Usage

tl_predict_ridge(model, new_data, type = "response", ...)

Arguments

Value

Predictions

Predict using a support vector machine model

Description

Predict using a support vector machine model

Usage

tl_predict_svm(model, new_data, type = "response", ...)

Arguments

Value

Predictions

Predict using a decision tree model

Description

Predict using a decision tree model

Usage

tl_predict_tree(model, new_data, type = "response", ...)

Arguments

Value

Predictions

Predict using an XGBoost model

Description

Predict using an XGBoost model

Usage

tl_predict_xgboost(model, new_data, type = "response", ntreelimit = NULL, ...)

Arguments

Value

Predictions

Data Preprocessing for tidylearn

Description

Unified preprocessing functions that work with both supervised and unsupervised workflows Prepare Data for Machine Learning

Usage

tl_prepare_data(
  data,
  formula = NULL,
  impute_method = "mean",
  scale_method = "standardize",
  encode_categorical = TRUE,
  remove_zero_variance = TRUE,
  remove_correlated = FALSE,
  correlation_cutoff = 0.95
)

Arguments

Details

Comprehensive preprocessing pipeline including imputation, scaling, encoding, and feature engineering

Value

A list with components:

data

The processed data frame.

original_data

The original unprocessed data frame.

preprocessing_steps

A list of metadata for each preprocessing step applied (imputation values, encoding maps, scaling parameters, etc.).

formula

The formula passed in (or NULL).

Examples

processed <- tl_prepare_data(iris, Species ~ ., scale_method = "standardize")
model <- tl_model(processed$data, Species ~ ., method = "tree")

Read data from diverse sources

Description

Auto-detects the data format from the file extension or source pattern and dispatches to the appropriate reader. All readers return a tidylearn_data object, which is a tibble subclass carrying metadata about the data source.

Usage

tl_read(source, ..., format = NULL, .quiet = FALSE)

Arguments

Details

When source is a character vector of multiple paths, each file is read and row-bound into a single result with a source_file column. When source is a directory path, it is equivalent to calling tl_read_dir(). When source is a .zip file, it is equivalent to calling tl_read_zip().

Value

A tidylearn_data object (a tibble subclass) with attributes tl_source, tl_format, and tl_timestamp.

Examples

# Read a single CSV file
# data <- tl_read("path/to/data.csv")

# Read multiple files and row-bind
# data <- tl_read(c("jan.csv", "feb.csv", "mar.csv"))

# Read all CSVs from a directory
# data <- tl_read("data/")

# Read from a zip archive
# data <- tl_read("data.zip")

# Explicit format override
# data <- tl_read("path/to/data.txt", format = "tsv")

Read from Google BigQuery

Description

Executes a SQL query against Google BigQuery and returns the result as a tidylearn_data object. Requires the bigrquery package and valid Google Cloud authentication.

Usage

tl_read_bigquery(project, query, dataset = NULL, ...)

Arguments

Value

A tidylearn_data object containing the query results.

Examples

# data <- tl_read_bigquery(
#   project = "my-project",
#   query = "SELECT * FROM `my_dataset.my_table` LIMIT 1000"
# )

Read a CSV file

Description

Reads a CSV file into a tidylearn_data object. Uses readr when available for faster parsing, with a base R fallback.

Usage

tl_read_csv(path, ...)

Arguments

Value

A tidylearn_data object (a tibble subclass) with attributes tl_source, tl_format, and tl_timestamp.

Examples

# data <- tl_read_csv("path/to/data.csv")

Read from a DBI database connection

Description

Executes a SQL query against an existing DBI connection and returns the result as a tidylearn_data object. The connection is not closed by this function — the caller is responsible for managing the connection lifecycle.

Usage

tl_read_db(conn, query, ...)

Arguments

Value

A tidylearn_data object containing the query results.

Examples

# conn <- DBI::dbConnect(RSQLite::SQLite(), "my_database.sqlite")
# data <- tl_read_db(conn, "SELECT * FROM my_table")
# DBI::dbDisconnect(conn)

Read all matching files from a directory

Description

Scans a directory for files matching a pattern or format, reads each one, and row-binds them into a single tidylearn_data object with a source_file column identifying the origin of each row.

Usage

tl_read_dir(
  path,
  pattern = NULL,
  format = NULL,
  recursive = FALSE,
  .quiet = FALSE,
  ...
)

Arguments

Value

A tidylearn_data object with an additional source_file column identifying the origin of each row.

Examples

# Read all CSVs from a directory
# data <- tl_read_dir("data/", format = "csv")

# Read with pattern matching
# data <- tl_read_dir("data/", pattern = "^sales_.*\.csv$")

# Read all recognized data files recursively
# data <- tl_read_dir("data/", recursive = TRUE)

Read an Excel file

Description

Reads an Excel file (.xls, .xlsx, or .xlsm) into a tidylearn_data object. Requires the readxl package.

Usage

tl_read_excel(path, sheet = 1, ...)

Arguments

Value

A tidylearn_data object (a tibble subclass) with attributes tl_source, tl_format, and tl_timestamp.

Examples

# data <- tl_read_excel("path/to/data.xlsx")
# data <- tl_read_excel("path/to/data.xlsx", sheet = "Sheet2")

Read from GitHub

Description

Downloads a raw file from a GitHub repository and reads it into a tidylearn_data object. Accepts either a full GitHub URL or a owner/repo shorthand with a file path.

Usage

tl_read_github(source, path = NULL, ref = "main", ...)

Arguments

Value

A tidylearn_data object containing the downloaded data.

Examples

# data <- tl_read_github("user/repo", path = "data/file.csv")
# data <- tl_read_github(
#   "https://github.com/user/repo/blob/main/data/file.csv"
# )

Read a JSON file

Description

Reads a JSON file into a tidylearn_data object. Expects the JSON to represent tabular data (array of objects or similar). Requires the jsonlite package.

Usage

tl_read_json(path, flatten = TRUE, ...)

Arguments

Value

A tidylearn_data object (a tibble subclass) with attributes tl_source, tl_format, and tl_timestamp.

Examples

# data <- tl_read_json("path/to/data.json")

Read from Kaggle

Description

Downloads a dataset file from Kaggle using the Kaggle CLI and reads it into a tidylearn_data object. Requires the Kaggle CLI to be installed and configured (pip install kaggle).

Usage

tl_read_kaggle(source, file = NULL, dest = tempdir(), type = "dataset", ...)

Arguments

Value

A tidylearn_data object containing the downloaded data.

Examples

# data <- tl_read_kaggle("zillow/zecon", file = "Zip_time_series.csv")
# data <- tl_read_kaggle("titanic", file = "train.csv", type = "competition")

Read from a MySQL/MariaDB database

Description

Connects to a MySQL or MariaDB database, executes a SQL query, and returns the result as a tidylearn_data object. Accepts either a connection string or individual connection parameters. Requires DBI and RMariaDB.

Usage

tl_read_mysql(
  dsn,
  query,
  dbname = NULL,
  user = NULL,
  password = NULL,
  port = 3306,
  ...
)

Arguments

Value

A tidylearn_data object containing the query results.

Examples

# data <- tl_read_mysql(
#   dsn = "localhost",
#   query = "SELECT * FROM my_table",
#   dbname = "mydb",
#   user = "myuser",
#   password = "mypass"
# )

Read a Parquet file

Description

Reads a Parquet file into a tidylearn_data object. Requires the nanoparquet package.

Usage

tl_read_parquet(path, ...)

Arguments

Value

A tidylearn_data object (a tibble subclass) with attributes tl_source, tl_format, and tl_timestamp.

Examples

# data <- tl_read_parquet("path/to/data.parquet")

Read from a PostgreSQL database

Description

Connects to a PostgreSQL database, executes a SQL query, and returns the result as a tidylearn_data object. Accepts either a connection string or individual connection parameters. Requires DBI and RPostgres.

Usage

tl_read_postgres(
  dsn,
  query,
  dbname = NULL,
  user = NULL,
  password = NULL,
  port = 5432,
  ...
)

Arguments

Value

A tidylearn_data object containing the query results.

Examples

# data <- tl_read_postgres(
#   dsn = "localhost",
#   query = "SELECT * FROM my_table",
#   dbname = "mydb",
#   user = "myuser",
#   password = "mypass"
# )

Read an RData file

Description

Reads an RData (.rdata or .rda) file into a tidylearn_data object. Since RData files can contain multiple objects, use the name argument to specify which object to extract. If name is NULL and the file contains exactly one data frame, it is returned automatically.

Usage

tl_read_rdata(path, name = NULL, ...)

Arguments

Value

A tidylearn_data object (a tibble subclass) with attributes tl_source, tl_format, and tl_timestamp.

Examples

# data <- tl_read_rdata("path/to/data.rdata")
# data <- tl_read_rdata("path/to/data.rdata", name = "my_data")

Read an RDS file

Description

Reads an RDS file into a tidylearn_data object. Uses base R readRDS() — no additional packages required.

Usage

tl_read_rds(path)

Arguments

Value

A tidylearn_data object (a tibble subclass) with attributes tl_source, tl_format, and tl_timestamp.

Examples

# data <- tl_read_rds("path/to/data.rds")

Read from Amazon S3

Description

Downloads a file from an S3 bucket and reads it into a tidylearn_data object. The file format is auto-detected from the key's extension, or can be specified explicitly. Requires the paws.storage package and valid AWS credentials.

Usage

tl_read_s3(source, format = NULL, region = NULL, ...)

Arguments

Value

A tidylearn_data object containing the downloaded data.

Examples

# data <- tl_read_s3("s3://my-bucket/data/sales.csv")
# data <- tl_read_s3("s3://my-bucket/data/results.parquet")

Read from a SQLite database

Description

Opens a SQLite database file, executes a SQL query, and returns the result as a tidylearn_data object. The connection is automatically closed when done. Requires DBI and RSQLite.

Usage

tl_read_sqlite(path, query, ...)

Arguments

Value

A tidylearn_data object containing the query results.

Examples

# data <- tl_read_sqlite("my_database.sqlite", "SELECT * FROM my_table")

Read a TSV file

Description

Reads a tab-separated file into a tidylearn_data object. Uses readr when available for faster parsing, with a base R fallback.

Usage

tl_read_tsv(path, ...)

Arguments

Value

A tidylearn_data object (a tibble subclass) with attributes tl_source, tl_format, and tl_timestamp.

Examples

# data <- tl_read_tsv("path/to/data.tsv")

Read data from a zip archive

Description

Extracts a zip archive to a temporary directory and reads the contents. If the archive contains a single data file, it is read directly. If multiple data files are found, they are row-bound with a source_file column. Use the file argument to select a specific file from the archive.

Usage

tl_read_zip(path, file = NULL, format = NULL, .quiet = FALSE, ...)

Arguments

Value

A tidylearn_data object (a tibble subclass) with attributes tl_source, tl_format, and tl_timestamp. The archive is extracted to a temporary directory that is cleaned up automatically. If multiple data files are found, a source_file column identifies the origin of each row.

Examples

# Read from a zip archive
# data <- tl_read_zip("data.zip")

# Read a specific file from the archive
# data <- tl_read_zip("data.zip", file = "train.csv")

Integration Functions: Combining Supervised and Unsupervised Learning

Description

These functions demonstrate the power of tidylearn's unified approach by seamlessly integrating supervised and unsupervised learning techniques. Feature Engineering via Dimensionality Reduction

Usage

tl_reduce_dimensions(
  data,
  response = NULL,
  method = "pca",
  n_components = NULL,
  ...
)

Arguments

Details

Use PCA, MDS, or other dimensionality reduction as a preprocessing step for supervised learning. This can improve model performance and interpretability.

Value

A list with components:

data

The transformed data frame with reduced-dimension columns and the response variable (if provided).

reduction_model

The fitted tidylearn dimensionality reduction model.

original_data

The original input data frame.

response

The response variable name, or NULL.

Examples

# Reduce dimensions before classification
reduced <- tl_reduce_dimensions(
  iris, response = "Species",
  method = "pca", n_components = 3
)
model <- tl_model(reduced$data, Species ~ ., method = "tree")

Run a tidylearn pipeline

Description

Run a tidylearn pipeline

Usage

tl_run_pipeline(pipeline, verbose = TRUE)

Arguments

Value

The input tidylearn_pipeline object with its $results component populated. Results include $processed_data, $model_results (a named list of per-model fits and metrics), $best_model_name, $best_model (the winning tidylearn_model), and $metric_values.

Examples

pipe <- tl_pipeline(iris, Species ~ .,
  models = list(tree = list(method = "tree")),
  evaluation = list(metrics = "accuracy", validation = "cv",
    cv_folds = 2, best_metric = "accuracy"))
pipe <- tl_run_pipeline(pipe, verbose = FALSE)

Save a pipeline to disk

Description

Save a pipeline to disk

Usage

tl_save_pipeline(pipeline, file)

Arguments

Value

Called for its side effect of saving to disk; returns NULL invisibly.

Examples

pipe <- tl_pipeline(iris, Species ~ .)
tl_save_pipeline(pipe, tempfile(fileext = ".rds"))

Semi-Supervised Learning via Clustering

Description

Train a supervised model with limited labels by first clustering the data and propagating labels within clusters.

Usage

tl_semisupervised(
  data,
  formula,
  labeled_indices,
  cluster_method = "kmeans",
  supervised_method = "logistic",
  ...
)

Arguments

Value

A tidylearn model object with additional class "tidylearn_semisupervised", trained on pseudo-labeled data. The model includes a semisupervised_info element with labeled_indices, cluster_model, and label_mapping.

Examples

# Use only 10% of labels
labeled_idx <- sample(nrow(iris), size = 15)
model <- tl_semisupervised(iris, Species ~ ., labeled_indices = labeled_idx,
  cluster_method = "kmeans",
  supervised_method = "tree"
)

Split data into train and test sets

Description

Split data into train and test sets

Usage

tl_split(data, prop = 0.8, stratify = NULL, seed = NULL)

Arguments

Value

A list with two elements:

$train

A data frame containing the training subset.

$test

A data frame containing the test subset.

Examples

split_data <- tl_split(iris, prop = 0.7, stratify = "Species")
train <- split_data$train
test <- split_data$test

Perform stepwise selection on a linear model

Description

Perform stepwise selection on a linear model

Usage

tl_step_selection(
  data,
  formula,
  direction = "backward",
  criterion = "AIC",
  trace = FALSE,
  steps = 1000,
  ...
)

Arguments

Value

A tidylearn_model object of class tidylearn_linear wrapping the selected lm model. Access the underlying model via $fit and the selected formula via $spec$formula.

Examples

model <- tl_step_selection(mtcars, mpg ~ ., direction = "backward")
summary(model)

Stratified Features via Clustering

Description

Create cluster-specific supervised models for heterogeneous data

Usage

tl_stratified_models(
  data,
  formula,
  cluster_method = "kmeans",
  k = 3,
  supervised_method = "linear",
  ...
)

Arguments

Value

A list with class "tidylearn_stratified" containing:

cluster_model

The fitted clustering model.

supervised_models

Named list of tidylearn models, one per cluster.

formula

The model formula.

data

The original training data.