.. _auto_curve_get_fit_slopes:

*GET FIT SLOPES*
================

Segments an input curve into piecewise linear regions and extracts the best-fit slope for each segment using a sliding-window linear regression. Use this worker to identify dominant slope regimes in stress-strain, force-displacement, or similar engineering curves, with optional filtering to a target slope value.

When to use
-----------

Classification: **process**.

Tagged: ``curve``, ``digitization``, ``fit_slopes``, ``linear_fit``, ``piecewise``, ``r2``, ``regression``, ``segmentation``.

Inputs
------

.. list-table::
   :header-rows: 1
   :widths: 20 20 20 20 20 20

   * - Label
     - ID
     - Type
     - Default
     - Required
     - Description
   * - Input Curve
     - input_curve
     - vector
     - —
     - 
     - The XY curve to analyse (e.g. force-displacement or stress-strain); supplied as a two-column vector — leave empty only when chaining from an upstream curve output.
   * - Num Dig
     - num_dig
     - integer
     - 1000
     - 
     - Number of uniformly spaced points used to re-digitize the input curve before segmentation; default 1000 — increase for high-frequency curves, decrease for speed.
   * - Segment Length Ratio
     - segment_length_ratio
     - integer
     - 0.01
     - 
     - Fraction of the total re-digitized point count that defines the sliding-window width for local linear fitting (e.g. 0.01 = 1 %); smaller values yield finer slope resolution.
   * - Min R2
     - r2_limit
     - integer
     - 0.95
     - 
     - Minimum R² goodness-of-fit threshold (0–1) a segment must meet to be retained; default 0.95 — lower to accept noisier linear regions.
   * - Merge Ratio
     - merge_ratio
     - integer
     - 0.025
     - 
     - Relative tolerance used to merge adjacent segments whose slopes differ by less than this fraction (e.g. 0.025 = 2.5 %); reduces duplicate near-identical slope entries.
   * - Target Slope
     - target_slope
     - integer
     - 0
     - 
     - Reference slope value around which results are filtered; set to 0 (default) to disable target filtering and return all detected slopes.
   * - Target Percentage
     - target_percentage
     - integer
     - 0.05
     - 
     - Fractional tolerance around target_slope — only slopes within ±target_percentage of target_slope are returned (e.g. 0.05 = ±5 %); ignored when target_slope is 0.
   * - Maximize Params
     - maximize_params
     - scalar
     - slope,r2
     - 
     - 

Outputs
-------

.. list-table::
   :header-rows: 1
   :widths: 20 20 20 20

   * - Label
     - ID
     - Type
     - Description
   * - curve_get_fit_slopes_output_1
     - curve_get_fit_slopes_output_1
     - dataset
     - Dataset table of detected piecewise linear segments, each row containing the x-start, x-end, fitted slope, and R² value for that segment, sorted by descending slope·R² score.

Disciplines
-----------

- ai_ml.supervised.regression
- data.curve.transform
- data.statistics
- engineering.material.characterization

Runnable example
----------------

A runnable example is registered for this worker. Open the example workflow on the d3VIEW canvas: `/api/workflow/example?id=curve_get_fit_slopes <https://www.d3view.com/api/workflow/example?id=curve_get_fit_slopes>`_

.. raw:: html

   <hr style="margin-top:2em">
   <p style="font-size:11px;color:#888">
   Auto-generated from <code>transformation</code> schema. Worker id: <code>curve_get_fit_slopes</code>. Schema hash: <code>f1e365ee47b4</code>. Hand-curated docs in <code>workerexamples/</code> override this page when present.
   </p>