Airlines: Subsampled Classification Dataset with 10 Classes and 100 Features

Airlines_seed_3_nrows_2000_nclasses_10_ncols_100_stratify_True is a subsampled version of the original airlines dataset from OpenML. It was generated by Eddie Bergman using a script to uniformly sample rows, columns, and classes. The resulting dataset likely contains 2000 rows, 100 columns, and 10 target classes for classification tasks.

Use Cases

• Benchmarking classification model performance based on the described 10 target classes.
• Feature selection experiments based on the described 100 sampled columns.
• Training models on a controlled, stratified subset of airline operational data.

Strengths

• Subsampling parameters are explicitly defined: seed=3, nrows_max=2000, ncols_max=100, nclasses_max=10.
• Stratified sampling was applied, which likely preserves the original class distribution in the subset.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• Last update date is unknown; freshness unverified.

Provenance

Source

OpenML dataset 1169 (airlines), subsampled by Eddie Bergman.

Collection Method

Algorithmic subsampling of rows, columns, and target classes using a Python script with a specified random seed.