Source code for pyml_datasets.datasets.wine
"""Wine: chemical analysis of 178 Italian wines from three cultivars."""
from typing import Final
from .._loader import load_npz
from .._types import Dataset, DatasetInfo
INFO: Final = DatasetInfo(
name="wine",
title="Wine",
task="classification",
summary=(
"Results of a chemical analysis of wines grown in the same region of Italy but "
"derived from three different cultivars. 13 constituents were measured in each wine."
),
license="CC-BY-4.0",
license_url="https://creativecommons.org/licenses/by/4.0/",
source="UCI Machine Learning Repository",
source_url="https://archive.ics.uci.edu/dataset/109/wine",
doi="10.24432/C5PC7J",
creators=("Stefan Aeberhard", "M. Forina"),
citation=(
"Aeberhard, S. & Forina, M. (1992). Wine [Dataset]. UCI Machine Learning Repository. "
"https://doi.org/10.24432/C5PC7J"
),
obtained_from=(
"scikit-learn (sklearn.datasets.load_wine), which redistributes a copy of the data. "
"The scikit-learn version is recorded in the file."
),
changes=(
"Converted to the NumPy NPZ format. Values are stored as float64 and the cultivar as "
"int64 labels.",
"The cultivar labels are 0, 1 and 2 (the UCI file numbers them 1, 2 and 3).",
"Feature and class names follow scikit-learn.",
),
verified_on="2026-10-17",
references=(
"Forina, M. et al. PARVUS: an extendable package of programs for data exploration, "
"classification and correlation. Institute of Pharmaceutical and Food Analysis and "
"Technologies, Genoa, Italy.",
),
)
[docs]
def load_wine() -> Dataset:
"""Load the Wine dataset (classification, 178 samples, 13 features).
Returns
-------
Dataset
Dataset with 3 classes of wine cultivars. ``Dataset.info`` holds the license, the
source and the citation.
Examples
--------
>>> from pyml_datasets import load_wine
>>> X, y = load_wine()
>>> X.shape, y.shape
((178, 13), (178,))
"""
return load_npz(INFO)