The builder DSL was missing support for row-wise column transformations (mutations). Only aggregation operations like .summarize() and .aggregate() were available for creating derived columns.

Changes

Core implementation:

• Added mutate_specs field to SelectStmt AST node
• Implemented .mutate(**transformations) method on QueryBuilder
• Added _apply_mutate() executor function for row-wise transformation logic
• Updated post-processing pipeline to trigger when mutations are present

Mutation support:

• Lambda functions with access to all row attributes
• Constant values
• String expressions referencing other columns

Documentation:

• Added comprehensive RST documentation in docfiles/user_guide/dsl.rst with "MUTATE - Row-wise Transformations" section
• Added reference documentation in docfiles/reference/dsl_reference.rst
• Updated query builder method lists to include .mutate() in chainable operations
• Created examples/network_analysis/example_dsl_mutate.py with 6 comprehensive examples
• Updated examples/network_analysis/README.md with DSL section listing all examples
• Added mutate operator to flagship example in main README.md - demonstrates creating derived influence scores in a production-quality workflow

Example

from py3plex.dsl import Q

# Create derived columns using lambda transformations
result = Q.nodes().compute("degree", "clustering").mutate(
    hub_score=lambda row: row.get("degree", 0) * row.get("clustering", 0),
    is_hub=lambda row: row.get("degree", 0) > 2,
    normalized=lambda row: row.get("degree", 0) / 10.0
).execute(network)

# Chain with other DSL operations
result = (
    Q.nodes()
    .where(layer="social")
    .compute("degree", "betweenness_centrality")
    .mutate(
        influence=lambda row: (
            row.get("degree", 0) * 0.4 + 
            row.get("betweenness_centrality", 0) * 0.6
        )
    )
    .execute(network)
)

The five core DSL operations (node/edge selection, filtering, mutations, summary) are now all supported and documented.

• Fixes builder dsl #949

💬 We'd love your input! Share your thoughts on Copilot coding agent in our 2 minute survey.