Electricity Consumption Data: 2,000-Row Subsampled Classification Dataset

A 2,000-row, 100-column subsample of a larger electricity dataset, created with a random seed of 1. It was generated by Eddie Bergman using a Python script that performed stratified sampling to maintain class distribution across 10 target classes. The original dataset is from OpenML and is in the public domain (us-pd).

Use Cases

• Training classification models to predict electricity-related outcomes based on 100 sampled features.
• Benchmarking model performance on a stratified, medium-scale tabular dataset.
• Analyzing feature importance within a controlled subset of electricity consumption variables.

Strengths

• Controlled creation with a specific random seed (1), ensuring reproducibility.
• Stratified sampling was used, which likely preserves the original class distribution for the 10 target classes.
• Subsampling parameters are explicitly documented: 2,000 rows, 100 columns, and 10 classes.

Limitations

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

Provenance

Source

OpenML (dataset ID 44120), subsampled by Eddie Bergman.

Collection Method

Algorithmic subsampling via a custom Python function using numpy and scikit-learn's train_test_split.