Bar Plot for Categorical Data with Optional Grouping

Description

Creates a publication-quality bar plot for a categorical variable, with optional grouping by another variable. Automatically calculates counts and percentages and can display them on the bars. Also performs Chi-square or Fisher exact test if by is provided.

Usage

plot_bar(
  data,
  var,
  by = NULL,
  vjust = -0.3,
  hjust = 0.5,
  axis.label.angle = 45,
  label = NULL,
  border.color = NULL,
  label.color = "black",
  x.lab = "Group",
  y.lab = "Percentage (%)",
  fill.lab = "Variable",
  text.size = 3,
  color.bar = NULL,
  theme_fun = ggthemes::theme_stata,
  bar.width = 0.8,
  y.expand = 1.12
)

Arguments

Value

A ggplot2 object representing the bar plot.

Examples

# Example using CO2 dataset
plot_bar(
  CO2,
  var = "Type",
  by = "Treatment",
  fill.lab = "Plant Type",
  color.bar = c("lightblue","lightgreen"),
  border.color = "black",
  bar.width = 0.5,
  text.size = 3,
  label = c("Quebec","Mississippi")
)

# Example using diamonds dataset
plot_bar(
  ggplot2::diamonds,
  var = "cut",
  by = "color",
  y.lab = "Distribution (%)",
  fill.lab = "Cut",
  text.size = 2,
  bar.width = 0.9,
  color.bar = c("#a465db","steelblue","darkgreen","darkred","#fcba03")
)

# Simple bar plot without grouping
plot_bar(ggplot2::diamonds, var = "cut")

Correlation Heatmap Plot

Description

Creates a publication-ready correlation heatmap for numeric variables in a data frame. Each tile shows the correlation coefficient, with optional significance stars.

Usage

plot_cor(
  data,
  method = "pearson",
  conf.level = 0.95,
  stars = TRUE,
  plot.title = NULL,
  var.labels = NULL
)

Arguments

Value

A ggplot object showing the correlation heatmap with correlation coefficients and significance stars.

Examples

plot_cor(mtcars)
plot_cor(mtcars, var.labels = colnames(mtcars))
plot_cor(mtcars, method = "spearman", stars = FALSE)

Plot Mean with Error Bars

Description

This function creates a line plot with points and customizable error bars (standard deviation, standard error, or confidence interval) for a numeric variable grouped by a categorical variable. Mean values can optionally be displayed above the points.

Usage

plot_errorbar(
  data,
  var,
  by,
  error = c("sd", "se", "ci"),
  err.mult = 1.5,
  point.shape = 19,
  point.size = 3,
  line.color = "blue",
  line.size = 1,
  color.point = "black",
  color.error = "black",
  show.mean = TRUE,
  text.size = 3.5,
  err.width = 0.05,
  x.lab = "Group",
  y.lab = NULL,
  title = NULL,
  rotate = FALSE,
  theme_fun = ggthemes::theme_stata
)

Arguments

Value

A ggplot2 object displaying the line plot with points and error bars.

Examples

plot_errorbar(
  data = iris,
  var = Sepal.Length,
  by = Species,
  error = "se",
  err.mult = 1,
  point.shape = 19,
  point.size = 3,
  line.color = "red",
  line.size = 0.5,
  color.point = "blue",
  color.error = "blue",
  show.mean = TRUE,
  text.size = 3,
  err.width = 0.05,
  title = "Mean Sepal Length by Species",
  rotate = TRUE
)

Line Plot with Error Bars by Group and Time

Description

This function creates a line plot showing the mean of a numeric variable over time for different groups, with optional error bars (standard deviation, standard error, or 95% confidence interval). Multiple groups are displayed on the same plot with customizable colors, point shapes, and line thickness.

Usage

plot_line(
  data,
  var,
  time,
  group,
  error = c("sd", "se", "ci"),
  err.mult = 1.5,
  point.shape = 19,
  point.size = 3,
  line.size = 1,
  color.lines = c("red", "blue"),
  show.mean = FALSE,
  text.size = 3.5,
  err.width = 0.05,
  x.lab = "Time",
  y.lab = NULL,
  title = NULL,
  theme_fun = ggthemes::theme_stata
)

Arguments

Value

A ggplot object displaying the line plot with optional error bars for multiple groups.

Examples

set.seed(123)
n_subj <- 10
time_points <- c("T1","T2","T3")
groups <- c("DrugA","DrugB")

df <- expand.grid(
  id = 1:n_subj,
  time = time_points,
  group = groups
)

# Arrange by group, id, time
df <- dplyr::arrange(df, group, id, time)

# Add BMI column
df <- dplyr::mutate(df,
  BMI = dplyr::case_when(
    time == "T1" & group == "DrugA" ~ 29 + stats::rnorm(dplyr::n(), 0, 0.3),
    time == "T2" & group == "DrugA" ~ 26 + stats::rnorm(dplyr::n(), 0, 0.3),
    time == "T3" & group == "DrugA" ~ 22 + stats::rnorm(dplyr::n(), 0, 0.3),
    time == "T1" & group == "DrugB" ~ 28 + stats::rnorm(dplyr::n(), 0, 0.3),
    time == "T2" & group == "DrugB" ~ 25 + stats::rnorm(dplyr::n(), 0, 0.2),
    time == "T3" & group == "DrugB" ~ 21 + stats::rnorm(dplyr::n(), 0, 0.2)
  )
)

Plot Linear Regression Estimates with Confidence Intervals

Description

This function fits univariate and multivariate linear regression models for a given outcome and a set of predictors. It returns a ggplot showing point estimates and 95% confidence intervals for each predictor. Reference levels of factors can optionally be added, and univariate and multivariate results are plotted side by side.

Usage

plot_lm(
  data,
  outcome,
  predictors,
  label_vjust = -0.8,
  label_hjust = 0.4,
  label_size = 3.5,
  label_color = "black",
  point_color = c("steelblue", "firebrick"),
  point_shape = 15,
  ref = TRUE
)

Arguments

Value

A ggplot object showing regression estimates with 95% confidence intervals for both univariate and multivariate models. @import broom

Examples

mtcars2 <- dplyr::mutate(
  mtcars,
  cyl = factor(cyl),
  am = factor(am, labels = c("Automatic", "Manual")),
  gear = factor(gear)
)

plot_lm(
  data = mtcars2,
  outcome = "mpg",
  predictors = c("cyl", "hp", "wt", "am", "gear"),
  point_shape = 18
)

plot_lm(
  data = mtcars2,
  outcome = "mpg",
  predictors = c("cyl", "hp", "wt", "am", "gear"),
  point_shape = 18
)

Normality Assessment Plot with Shapiro-Wilk and Kolmogorov–Smirnov Tests

Description

This function visualizes the distribution of multiple numeric variables using boxplots or histograms with overlaid normal distribution curves. It automatically selects the appropriate normality test based on sample size: the Shapiro–Wilk test is applied when sample size is <= 5000, while the Kolmogorov–Smirnov test is used for larger samples (> 5000). The resulting p-values are displayed directly on the plots.

Usage

plot_norm(
  data,
  vars,
  geom = c("box", "hist"),
  color_bar = "#377eb8",
  color_line = "darkred",
  xlab = NULL,
  ylab = NULL,
  bins = 20,
  label_color = "black",
  label_size = 3.5,
  label_vjust = 0,
  label_hjust = 0,
  alpha_bar = 0.5,
  sample_size = 5000,
  label_fraction = 0.05,
  position = NULL,
  p.ypos = NULL
)

Arguments

Value

A ggplot object displaying the selected normality plots with test p-values.

Examples

## Load example dataset safely
data(diamonds, package = "ggplot2")
## Example 1: Boxplots with Shapiro-Wilk test (n <= 5000)
plot_norm(
  data = diamonds[1:4000, ],
  vars = c("carat", "x", "y"),
  geom = "box"
)

## Example 2: Histograms with Shapiro-Wilk test (n <= 5000)
plot_norm(
  data = diamonds[1:4000, ],
  vars = c("carat", "x", "y"),
  geom = "hist",
  bins = 20,
  p.ypos = 0.6
)

## Example 3: Kolmogorov-Smirnov test automatically applied (n > 5000)
plot_norm(
  data = diamonds[1:6000, ],
  vars = c("carat", "x"),
  geom = "hist",
  bins = 25
)

## Example 4: CO2 dataset (base R)
plot_norm(
  data = CO2,
  vars = c("uptake", "conc"),
  geom = "hist",
  bins = 3
)

Publication-Quality Numeric Plot with Optional Grouping and Statistical Tests

Description

Creates a publication-ready plot for numeric variables, including bar plots, violin plots, boxplots, and combinations (violin + box, violin + jitter, box + jitter). Supports error bars (SD, SE, CI), group comparisons, and automatic or specified statistical tests with optional post-hoc annotations.

Usage

plot_numeric(
  data,
  var,
  by,
  geom_type = c("bar", "violin", "box", "violin_box", "violin_jitter", "box_jitter"),
  error = c("sd", "se", "ci"),
  test.type = c("auto", "parametric", "nonparametric"),
  vjust = 0,
  rotate = FALSE,
  x.lab = "Group",
  y.lab = NULL,
  text.size = 3.5,
  color.violin = NULL,
  color.box = NULL,
  box.color = "black",
  color.jitter = "black",
  jitter.size = 1.5,
  ptext.size = 3,
  theme_fun = ggthemes::theme_stata,
  bar.width = 0.85,
  box.width = 0.2,
  show.posthoc = TRUE,
  err.mult = 1.5,
  position.p = NULL,
  jitter.width = 0.1
)

Arguments

Value

A ggplot2 object representing the numeric variable plot.

Examples

# Violin + Box plot for iris dataset
plot_numeric(
  data = iris,
  var = Sepal.Length,
  by = Species,
  geom_type = "violin_box",
  box.width = 0.1,
  color.violin = c("#377eb8", "#ff7f00", "#4daf4a"),
  color.box = c("darkgreen", "#a65628", "#f781bf"),
  box.color = "black",
  color.jitter = "red",
  position.p = c(1,9),
  jitter.size = 2,
  ptext.size = 4,
  show.posthoc = TRUE
)

# Simple bar plot with error bars
plot_numeric(
  data = iris,
  var = Sepal.Length,
  by = Species,
  geom_type = "bar",
  error = "se"
)

# Violin plot with jitter points
plot_numeric(
  data = iris,
  var = Sepal.Length,
  by = Species,
  geom_type = "violin_jitter"
)

Plot Odds Ratios from Logistic Regression

Description

This function fits univariate and multivariate logistic regression models and plots odds ratios with 95% confidence intervals. Reference levels can optionally be displayed.

Usage

plot_or(
  data,
  outcome,
  predictors,
  label_vjust = -0.8,
  label_hjust = 0.5,
  label_size = 3.5,
  label_color = "black",
  point_color = c("steelblue", "firebrick"),
  ref = TRUE
)

Arguments

Value

A ggplot object showing odds ratios with confidence intervals.

Examples

# Load built-in infertility dataset
infert1 <- datasets::infert
infert$case <- factor(infert$case, levels = c(0,1), labels = c("Control","Infertile"))
infert$induced <- factor(infert$induced, levels = c(0,1), labels = c("No","Yes"))
infert$spontaneous <- factor(infert$spontaneous, levels = c(0,1), labels = c("No","Yes"))

# Plot with reference levels
plot_or(
  data = infert1,
  outcome = "case",
  predictors = c("parity","induced","spontaneous","age"),
  ref = TRUE
)

# Plot without reference levels
plot_or(
  data = infert1,
  outcome = "case",
  predictors = c("parity","induced","spontaneous","age"),
  ref = FALSE
)

Scatter Plot with Linear Regression and Equation Annotation

Description

This function creates a scatter plot of a numeric outcome against a numeric predictor, optionally grouped by a factor (by). A linear regression line is added with optional standard error (SE) shading, and the regression equation and R² value are displayed on the plot.

Usage

plot_scatter(
  data,
  outcome,
  predictor,
  by = NULL,
  point_color = "#377eb8",
  line_color = "#e41a1c",
  se_fill = "#e41a1c55",
  line_size = 1,
  se = TRUE,
  facet_scales = "free",
  eq_position = c(0.05, 0.95),
  ncol_by = NULL
)

Arguments

Value

A ggplot2 object of the scatter plot with regression line and annotated equation.

Examples

# Basic scatter plot with regression line and equation
plot_scatter(mtcars, "mpg", "wt")

# Scatter plot grouped by cylinder
plot_scatter(mtcars, "mpg", "wt", by = "cyl",
           point_color = "blue",
           line_color = "red",
           se_fill = "#ff000055",
           line_size = 0.9,
           se = TRUE,
           eq_position = c(0.5, 0.95),
           ncol_by = 2)