Reporting with tidylearn • tidylearn

Overview

Two families turn a fitted model into something publishable. plot() and the tl_plot_*() functions return ggplot2 objects, with the exceptions listed under Interactive Reporting with plotly; tl_table() and the tl_table_*() functions return gt tables. Both dispatch on model type, so the same call covers a forest and a lasso fit, and both hand back an object you can keep editing rather than printed output you cannot.

library(tidylearn)
library(dplyr)
library(ggplot2)
library(gt)

Plots

plot() picks the visualisation from the model type, and type narrows it further where a model supports more than one view.

Regression

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

# Actual vs predicted — one call
plot(model_reg, type = "actual_predicted")

Classification

split <- tl_split(iris, prop = 0.7, stratify = "Species", seed = 42)
model_clf <- tl_model(split$train, Species ~ ., method = "forest")

plot(model_clf, type = "confusion")

PCA

pca <- tidy_pca(USArrests, scale = TRUE)

tidy_pca_screeplot(pca)

tidy_pca_biplot(pca, label_obs = TRUE)

Regularisation

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

tl_plot_regularization_path(model_lasso)

tl_plot_regularization_cv(model_lasso)

Tables

tl_table() mirrors the plot interface, dispatching on model type and an optional type:

tl_table(model)                       # auto-selects the best table type
tl_table(model, type = "coefficients") # specific type

Evaluation Metrics

tl_table_metrics(model_reg)

Metric	Value
Model Evaluation Metrics
Rmse	2.4689
Mae	1.9015
Rsq	0.8268
tidylearn \| linear (regression) \| mpg ~ wt + hp \| n = 32

Coefficients

For linear and logistic models, the table includes standard errors, test statistics, and p-values, with significant terms highlighted:

tl_table_coefficients(model_reg)

Term	Estimate	Std. Error	t value	p
Linear Model Coefficients
(Intercept)	37.2273	1.5988	23.2847	2.57 × 10⁻²⁰	*
wt	−3.8778	0.6327	−6.1287	1.12 × 10⁻⁶	*
hp	−0.0318	0.0090	−3.5187	1.45 × 10⁻³	*
tidylearn \| linear (regression) \| mpg ~ wt + hp \| n = 32

conf_int = TRUE adds a confidence interval, and level sets its width:

tl_table_coefficients(model_reg, conf_int = TRUE, level = 0.9)

Term	Estimate	Std. Error	Lower 90%	Upper 90%	t value	p
Linear Model Coefficients
Wald 90% intervals
(Intercept)	37.2273	1.5988	34.5107	39.9438	23.2847	2.57 × 10⁻²⁰	*
wt	−3.8778	0.6327	−4.9529	−2.8027	−6.1287	1.12 × 10⁻⁶	*
hp	−0.0318	0.0090	−0.0471	−0.0164	−3.5187	1.45 × 10⁻³	*
tidylearn \| linear (regression) \| mpg ~ wt + hp \| n = 32

These are Wald intervals, built from the standard errors in the column beside them, so the interval and the p-value in a row always agree about whether zero is excluded. For a logistic model, exponentiate = TRUE reports odds ratios instead of log odds.

For regularised models, coefficients are sorted by magnitude and zero coefficients are greyed out. There is no interval to add — glmnet reports no standard errors, and conf_int = TRUE is an error here rather than a column of NA:

tl_table_coefficients(model_lasso)

Term	Coefficient	\|Coefficient\|
Lasso Coefficients
lambda = 1.399 (1se)
(Intercept)	33.9405	33.9405
wt	−2.3659	2.3659
cyl	−0.8430	0.8430
hp	−0.0070	0.0070
disp	0.0000	0.0000
drat	0.0000	0.0000
qsec	0.0000	0.0000
vs	0.0000	0.0000
am	0.0000	0.0000
gear	0.0000	0.0000
carb	0.0000	0.0000
tidylearn \| lasso (regression) \| mpg ~ . \| n = 32

The numbers behind these tables come from tl_coefficients(), which takes the same arguments, returns a tibble, and does not need gt installed:

tl_coefficients(model_reg, conf_int = TRUE)
#> # A tibble: 3 × 7
#>   term        estimate std_error conf_low conf_high statistic  p_value
#>   <chr>          <dbl>     <dbl>    <dbl>     <dbl>     <dbl>    <dbl>
#> 1 (Intercept)  37.2      1.60     34.0      40.5        23.3  2.57e-20
#> 2 wt           -3.88     0.633    -5.17     -2.58       -6.13 1.12e- 6
#> 3 hp           -0.0318   0.00903  -0.0502   -0.0133     -3.52 1.45e- 3

Confusion Matrix

A formatted confusion matrix with correct predictions highlighted on the diagonal:

tl_table_confusion(model_clf, new_data = split$test)

Actual	Predicted
Confusion Matrix
Actual	setosa	versicolor	virginica
setosa	15	0	0
versicolor	0	15	0
virginica	0	2	13
tidylearn \| forest (classification) \| Species ~ . \| n = 45

Feature Importance

A ranked importance table with a colour gradient:

tl_table_importance(model_clf)

Feature	Importance
Feature Importance
Top 4 features
Petal.Length	100.00
Petal.Width	88.23
Sepal.Length	29.63
Sepal.Width	15.77
tidylearn \| forest (classification) \| Species ~ . \| n = 105

PCA Variance Explained

Cumulative variance is coloured green to highlight how many components are needed:

pca_model <- tl_model(USArrests, method = "pca")
tl_table_variance(pca_model)

Component	Std. Dev.	Variance	Proportion	Cumulative
PCA Variance Explained
PC1	1.5749	2.4802	62.0%	62.0%
PC2	0.9949	0.9898	24.7%	86.8%
PC3	0.5971	0.3566	8.9%	95.7%
PC4	0.4164	0.1734	4.3%	100.0%
tidylearn \| pca \| n = 50

PCA Loadings

A diverging red–blue colour scale highlights strong positive and negative loadings:

tl_table_loadings(pca_model)

Variable	PC1	PC2	PC3	PC4
PCA Loadings
Murder	−0.536	−0.418	0.341	0.649
Assault	−0.583	−0.188	0.268	−0.743
UrbanPop	−0.278	0.873	0.378	0.134
Rape	−0.543	0.167	−0.818	0.089
tidylearn \| pca \| n = 50

Cluster Summary

Cluster sizes and mean feature values:

km <- tl_model(iris[, 1:4], method = "kmeans", k = 3)
tl_table_clusters(km)

Cluster	Size	Sepal.Length	Sepal.Width	Petal.Length	Petal.Width
Cluster Summary
kmeans \| 3 clusters
1	38	6.85	3.07	5.74	2.07
2	50	5.01	3.43	1.46	0.25
3	62	5.90	2.75	4.39	1.43
tidylearn \| kmeans \| n = 150

Model Comparison

Compare multiple models side-by-side:

m1 <- tl_model(split$train, Species ~ ., method = "svm")
m2 <- tl_model(split$train, Species ~ ., method = "forest")
m3 <- tl_model(split$train, Species ~ ., method = "tree")

tl_table_comparison(
  m1, m2, m3,
  new_data = split$test,
  names = c("SVM", "Random Forest", "Decision Tree")
)

Metric	SVM	Random Forest	Decision Tree
Model Comparison
3 models compared
Accuracy	0.9111	0.9333	0.8889
tidylearn \| n = 45

Interactive Reporting with plotly

Most plot functions return a ggplot2 object, and ggplotly() takes any of those without special handling:

library(plotly)

ggplotly(plot(model_reg, type = "actual_predicted"))
ggplotly(tidy_pca_biplot(pca, label_obs = TRUE))
ggplotly(tl_plot_regularization_path(model_lasso))

These do not return a single ggplot2 object:

plot_dendrogram(), which plot() uses for an hclust model, tl_plot_tree() and tl_plot_nn_architecture() draw with base graphics.
tl_plot_xgboost_tree() returns a DiagrammeR widget, tl_plot_deep_architecture() draws the keras model diagram, and visualize_rules(method = "paracoord") draws with grid.
tl_diagnostic_dashboard() and plot_cluster_comparison() return an arranged grid of panels. plot(model, type = "diagnostics") and create_cluster_dashboard() return a list of ggplot2 objects, which ggplotly() takes one at a time.
plot() on a tl_explore() result draws its plot and returns the exploration result, and tl_dashboard() returns a Shiny app.

Putting It Together

Fit, score, look, drill in — the four calls that make up most reporting sections:

# Fit
model <- tl_model(split$train, Species ~ ., method = "forest")

# Evaluate
tl_table_metrics(model, new_data = split$test)

Metric	Value
Model Evaluation Metrics
Accuracy	0.9333
tidylearn \| forest (classification) \| Species ~ . \| n = 45


# Visualise
plot(model, type = "confusion")


# Drill into feature importance
tl_table_importance(model, top_n = 4)

Feature	Importance
Feature Importance
Top 4 features
Petal.Length	100.00
Petal.Width	91.09
Sepal.Length	28.28
Sepal.Width	13.44
tidylearn \| forest (classification) \| Species ~ . \| n = 105

Swap method = "forest" for method = "tree" and the reporting code above works without modification. tl_table_importance() covers the tree-based and regularised methods only, so for a method such as "svm" or "nn", leave out the last call.