"""Real Estate Valuation: 414 house sales in Taiwan, price of unit area from 6 features."""
from typing import Final
from .._loader import load_npz
from .._types import Dataset, DatasetInfo
INFO: Final = DatasetInfo(
name="real_estate_valuation",
title="Real Estate Valuation",
task="regression",
summary=(
"Market historical data of real estate valuation, collected from the Sindian District "
"of New Taipei City, Taiwan. Each of the 414 samples is a house sale described by 6 "
"features: the transaction date, the house age, the distance to the nearest MRT "
"station, the number of convenience stores in the living circle on foot and the "
"latitude and the longitude. The goal is to predict the house price of unit area."
),
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/477/real+estate+valuation+data+set",
doi="10.24432/C5J30W",
creators=("I-Cheng Yeh",),
citation=(
"Yeh, I. (2018). Real Estate Valuation [Dataset]. UCI Machine Learning Repository. "
"https://doi.org/10.24432/C5J30W"
),
obtained_from=(
"UCI Machine Learning Repository, dataset 477, downloaded with the ucimlrepo package: "
"all 414 examples with 6 inputs and the target. The ucimlrepo version is recorded in "
"the file."
),
changes=(
"Converted to the NumPy NPZ format. The features and the target are stored as float64.",
"The identifier column No, the numbers 1 to 414, is not stored, because it is not a "
"feature.",
"The column names are written in lowercase with underscores, and the prefixes X1 to X6 "
"and Y are dropped, for example X3 distance to the nearest MRT station becomes "
"distance_to_nearest_mrt_station.",
),
verified_on="2026-11-09",
references=(
"Yeh, I., & Hsu, T.-K. (2018). Building real estate valuation models with comparative "
"approach through case-based reasoning. Applied Soft Computing.",
),
notes=(
"The source says that the data set was randomly split into a training part (2/3 of the "
"samples) and a testing part (1/3), but its file has no column that tells which sample "
"belongs to which part. All 414 samples are stored and the split is not provided.",
"The transaction date is a number: 2013.250 is March 2013 and 2013.500 is June 2013, "
"as the source describes. Only 12 different dates occur, from 2012.667 to 2013.583. "
"ucimlrepo gives the dates rounded to three decimals, while the xlsx file of the UCI "
"page has seven (the first sale: 2012.9166667), so the stored dates differ from that "
"file by 0.0004 at most.",
"The target is the house price of unit area in 10000 New Taiwan Dollar per Ping, where "
"a Ping is a local unit of area, 1 Ping = 3.3 square meters, as the source gives.",
),
)
[docs]
def load_real_estate_valuation() -> Dataset:
"""Load the Real Estate Valuation dataset (regression, 414 samples, 6 features).
Returns
-------
Dataset
Dataset with the transaction date, the age and the surroundings of a house, and the
house price of unit area (10000 New Taiwan Dollar per Ping) as the target.
``Dataset.info`` holds the license, the source and the citation.
Examples
--------
>>> from pyml_datasets import load_real_estate_valuation
>>> X, y = load_real_estate_valuation()
>>> X.shape, y.shape
((414, 6), (414,))
"""
return load_npz(INFO)