Create a plotnine visualization from data.

This tool allows you to create highly customizable plots using the grammar of graphics. You can specify data sources (file, URL, or inline), aesthetic mappings, geometries, scales, themes, facets, labels, and coordinate systems.

NEW: Multi-layer plots! Use 'geoms' array to combine multiple geometries in one plot.

Example usage:

• Simple scatter plot: provide data_source, aes (x, y), and geom (type: "point")

• Multi-layer plot: use geoms array with multiple geometries (e.g., point + smooth)

• Line plot with custom theme: add theme config with base and customizations

• Faceted plot: include facet config to split by categorical variables

• Multiple scales: provide list of scale configs for x, y, color, etc.

All parameters support extensive customization through nested objects.

List all available geometry types that can be used in plots

Preview and inspect data before creating plots.

Returns a comprehensive summary including:

• Dataset shape (rows and columns)

• Column names and data types

• First few rows of data

• Basic statistics for numeric columns

• Missing value counts

This helps verify data loaded correctly and understand its structure.

List all available themes for plot styling

Export plot configuration to a JSON file for reuse.

This saves the exact configuration used to create a plot, allowing you to:

• Recreate the same plot later

• Share configurations with others

• Version control your visualizations

• Use as templates for similar plots

Import and use a saved plot configuration.

Load a previously exported plot configuration and create a plot from it. You can optionally override specific parameters (like data_source) while keeping the rest of the configuration intact.

List all available plot templates with descriptions. Templates provide preset configurations for common visualization patterns like time series, scatter with trend, distribution comparison, etc.

Create a plot using a predefined template.

Templates provide optimized configurations for common plot types:

• time_series: Line plot with date formatting

• scatter_with_trend: Points with regression line

• distribution_comparison: Violin + jitter for group comparison

• category_breakdown: Bar chart with categories

• correlation_heatmap: Tile plot for correlations

• boxplot_comparison: Boxplot with points overlay

• multi_line: Multiple lines for trend comparison

• histogram_with_density: Histogram with density curve

• before_after: Side-by-side comparison

You only need to provide data and aesthetics; the template handles the rest. You can override any template settings if needed.

Analyze data and suggest appropriate plot templates.

Examines data characteristics (number of numeric/categorical columns, presence of time data) and optionally a user goal to recommend suitable templates.

List available color palettes with preview colors.

Palettes are organized by category:

• colorblind_safe: Accessible palettes (Okabe-Ito, Tol)

• scientific: Perceptually uniform (viridis, plasma, inferno, magma)

• categorical: Distinct colors for categories

• corporate: Professional business colors

• sequential: Gradual scales for ordered data

• diverging: Two-tone scales for data with midpoints

Use these palettes by adding a scale configuration to your plot.

Create multiple plots in one batch operation.

Useful for:

• Creating plots for all numeric columns in a dataset

• Generating pairwise scatter plots

• Creating plots for each category separately

• Comparing different plot types

Each plot configuration is processed independently, and all plots are created in sequence.