Nesting Tasks Dataset for 2D-Nesting Efficiency Estimation

Nesting efficiency dataset This is the raw dataset associated with the paper “Graph Neural Networks Comparison for 2D-Nesting Efficiency Estimation”, by C.Lallier, L. Vézard, B. Pinaud and G. Blin, 2022. Consisting of 100,000 nesting tasks. <strong>Usage:</strong> The files are: <em>tasks.gz, parts.gz, constraints.gz, </em>and<em> shapes.gz</em>. They are in PICKLE file format version 5 with a gzip compression. Example to load a file : <pre><code class="language-python">import pandas as pd tasks = pd.read_pickle('tasks.gz')</code></pre> <strong>Description:</strong> <em>Tasks.gz</em> file contains nestings high-level descriptors. It is composed of the following columns: Column Type Description efficiency float The variable to predict (label). Given in % duration integer input data. The nesting algorithm convergence time. Given in s. sheet_width integer input data. The width of the nesting area. Given in m^-4 sheet_length integer input data. Facultative. The height of the nesting area. Given in m^-4 sheet_type integer input data. Kind of the nesting. tasks_index integer Generated data. Join key between tables. is_train, is_val, is_test boolean Generated data. Can be used as mask for the train, val and test subsets. <em>Parts.gz</em> contains description of the parts to be nested : Column Type Description <strong>tasks_index</strong> integer Reference to the join key from the <em>Task</em> table. <strong>parts_id</strong> integer Generated part id. <strong>shape_hash</strong> integer Reference to the hash of the part's shape, join key from the <em>Shape </em>table. <em>Shapes.gz</em> is the description of the shapes of the parts to be nested : Column Type Description <strong>shape_hash</strong> integer Generated data. Join key between tables. <strong>raw</strong> list of integers List of x, y tuples for each point. Unit is m^-4 <strong>sizes</strong> list of integers List of sub-shapes sizes. <em>Constraints.gz</em> describes constraints and their parameters: Column Type Description <strong>type</strong> string Generated constraint type. <strong>tasks_index</strong> integer Reference to the join key from the <em>Task</em> table. <strong>parts_1, parts_2</strong> list of integers References to the <em>parts_id</em> from the <em>Parts</em> table. <strong>p1_x, p1_y and p2_x, p2_y</strong> list of floats Input data. Origin position (x, y) of the constraint on parts. For each part of the constraint. <strong>r1_start, r1_end, r1_flip_x</strong> list of floats Input data. Rotation (start, end, and flip_x) parameters of the constraint. Multiple ranges accepted. <strong>y_min, y_max</strong> list of floats Input data. Range from (y_min, y_max). Multiple ranges accepted. <strong>x_offset, y_offset, motif_order, x_alignment_type, y_alignment_type, proximity_type, max_distance, groups_relative_orientation, is_frozen</strong> float Input data. Other constraint parameters.