1 datasets-uci

1.1 abalone🔗ℹ

4177 rows × 9 columns. Continuous measurements as distributed, scaled by 1/200 by the donors; rows with missing values were removed upstream.

Nash, W., Sellers, T., Talbot, S., Cawthorn, A. and Ford, W. (1994). Abalone. UCI Machine Learning Repository. doi:10.24432/C55C7W. https://archive.ics.uci.edu/dataset/1/abalone Described in: Nash, W. J., Sellers, T. L., Talbot, S. R., Cawthorn, A. J. and Ford, W. B. (1994). The Population Biology of Abalone (Haliotis species) in Tasmania. I. Blacklip Abalone (H. rubra) from the North Coast and Islands of Bass Strait. Sea Fisheries Division, Technical Report No. 48.

UCI snapshot 2026-10-23 (hash pinned); CC-BY-4.0

Column	Original	Type	Description / unit / levels
sex	Sex	categorical	M, F or I (infant); #f; (M F I)
length	Length	real	Longest shell measurement; mm / 200; ()
diameter	Diameter	real	Perpendicular to length; mm / 200; ()
height	Height	real	With meat in shell; mm / 200; ()
whole-weight	Whole weight	real	Whole abalone; grams / 200; ()
shucked-weight	Shucked weight	real	Weight of meat; grams / 200; ()
viscera-weight	Viscera weight	real	Gut weight (after bleeding); grams / 200; ()
shell-weight	Shell weight	real	After being dried; grams / 200; ()
rings	Rings	integer	Rings; +1.5 gives the age in years; #f; ()

1.2 adult🔗ℹ

48842 rows × 16 columns. 1994 US Census extract: the 32,561 adult.data rows, then the 16,281 adult.test rows, told apart by split. The trailing period on test income labels is removed. ? is rendered as missing (workclass, occupation, native-country).

Becker, B. and Kohavi, R. (1996). Adult. UCI Machine Learning Repository. doi:10.24432/C5XW20. https://archive.ics.uci.edu/dataset/2/adult

UCI snapshot 2026-10-23 (hash pinned); CC-BY-4.0

Column	Original	Type	Description / unit / levels
age	age	integer	age; #f; ()
workclass	workclass	categorical	workclass; #f; (Private Self-emp-not-inc Self-emp-inc Federal-gov Local-gov State-gov Without-pay Never-worked)
fnlwgt	fnlwgt	integer	Final sampling weight; #f; ()
education	education	categorical	education; #f; (Bachelors Some-college 11th HS-grad Prof-school Assoc-acdm Assoc-voc 9th 7th-8th 12th Masters 1st-4th 10th Doctorate 5th-6th Preschool)
education-num	education-num	integer	Education, as a number; #f; ()
marital-status	marital-status	categorical	marital-status; #f; (Married-civ-spouse Divorced Never-married Separated Widowed Married-spouse-absent Married-AF-spouse)
occupation	occupation	categorical	occupation; #f; (Tech-support Craft-repair Other-service Sales Exec-managerial Prof-specialty Handlers-cleaners Machine-op-inspct Adm-clerical Farming-fishing Transport-moving Priv-house-serv Protective-serv Armed-Forces)
relationship	relationship	categorical	relationship; #f; (Wife Own-child Husband Not-in-family Other-relative Unmarried)
race	race	categorical	race; #f; (White Asian-Pac-Islander Amer-Indian-Eskimo Other Black)
sex	sex	categorical	sex; #f; (Female Male)
capital-gain	capital-gain	integer	capital-gain; #f; ()
capital-loss	capital-loss	integer	capital-loss; #f; ()
hours-per-week	hours-per-week	integer	hours-per-week; #f; ()
native-country	native-country	categorical	native-country; #f; (United-States Cambodia England Puerto-Rico Canada Germany Outlying-US(Guam-USVI-etc) India Japan Greece South China Cuba Iran Honduras Philippines Italy Poland Jamaica Vietnam Mexico Portugal Ireland France Dominican-Republic Laos Ecuador Taiwan Haiti Columbia Hungary Guatemala Nicaragua Scotland Thailand Yugoslavia El-Salvador Trinadad&Tobago Peru Hong Holand-Netherlands)
income	income	categorical	Whether income exceeds $50K/yr; #f; (<=50K >50K)
split	split	categorical	Source file: train (adult.data) or test (adult.test); #f; (train test)

1.3 auto-mpg🔗ℹ

398 rows × 9 columns. auto-mpg.data: the StatLib cars with the 8 unknown-mpg rows removed. The 6 ? horsepower values are rendered as missing. Integral values written with a decimal point are stored as integers.

Quinlan, R. (1993). Auto MPG. UCI Machine Learning Repository. doi:10.24432/C5859H. https://archive.ics.uci.edu/dataset/9/auto+mpg

UCI snapshot 2026-10-23 (hash pinned); CC-BY-4.0

Column	Original	Type	Description / unit / levels
mpg	mpg	real	mpg; #f; ()
cylinders	cylinders	integer	Number of cylinders; #f; ()
displacement	displacement	real	displacement; #f; ()
horsepower	horsepower	integer	horsepower; #f; ()
weight	weight	integer	weight; #f; ()
acceleration	acceleration	real	acceleration; #f; ()
model-year	model year	integer	Model year (19xx); #f; ()
origin	origin	integer	Origin code (1, 2 or 3); #f; ()
car-name	car name	string	Car name; not unique across rows; #f; ()

1.4 bank-marketing🔗ℹ

41188 rows × 21 columns. bank-additional-full.csv: 41,188 calls, May 2008 to November 2010, ordered by date, with five social and economic context attributes; the file analysed by Moro et al. (2014), chosen over the older bank-full.csv (45,211 rows, no context attributes). The documented unknown label is rendered as missing; pdays 999 is kept.

Moro, S., Rita, P. and Cortez, P. (2014). Bank Marketing. UCI Machine Learning Repository. doi:10.24432/C5K306. https://archive.ics.uci.edu/dataset/222/bank+marketing Described in: Moro, S., Cortez, P. and Rita, P. (2014). A data-driven approach to predict the success of bank telemarketing. Decision Support Systems. doi:10.1016/j.dss.2014.03.001

UCI snapshot 2026-10-23 (hash pinned); CC-BY-4.0

Column	Original	Type	Description / unit / levels
age	age	integer	age; #f; ()
job	job	categorical	job; #f; (admin. blue-collar entrepreneur housemaid management retired self-employed services student technician unemployed)
marital	marital	categorical	marital; #f; (divorced married single)
education	education	categorical	education; #f; (basic.4y basic.6y basic.9y high.school illiterate professional.course university.degree)
default	default	categorical	default; #f; (no yes)
housing	housing	categorical	housing; #f; (no yes)
loan	loan	categorical	loan; #f; (no yes)
contact	contact	categorical	contact; #f; (cellular telephone)
month	month	categorical	month; #f; (mar apr may jun jul aug sep oct nov dec)
day-of-week	day_of_week	categorical	day_of_week; #f; (mon tue wed thu fri)
duration	duration	integer	Last contact duration; known only after the call, so for benchmarking only; seconds; ()
campaign	campaign	integer	campaign; #f; ()
pdays	pdays	integer	Days since last contact in a previous campaign; 999 = not previously contacted; #f; ()
previous	previous	integer	previous; #f; ()
poutcome	poutcome	categorical	poutcome; #f; (failure nonexistent success)
emp-var-rate	emp.var.rate	real	emp.var.rate; #f; ()
cons-price-idx	cons.price.idx	real	cons.price.idx; #f; ()
cons-conf-idx	cons.conf.idx	real	cons.conf.idx; #f; ()
euribor3m	euribor3m	real	euribor3m; #f; ()
nr-employed	nr.employed	real	nr.employed; #f; ()
y	y	categorical	Whether the client subscribed a term deposit; #f; (no yes)

1.5 banknote-authentication🔗ℹ

1372 rows × 5 columns. Wavelet features of images of genuine and forged banknote-like specimens. The archive carries no documentation file; names and descriptions follow the UCI dataset page.

Lohweg, V. (2012). Banknote Authentication. UCI Machine Learning Repository. doi:10.24432/C55P57. https://archive.ics.uci.edu/dataset/267/banknote+authentication

UCI snapshot 2026-10-23 (hash pinned); CC-BY-4.0

Column	Original	Type	Description / unit / levels
variance	variance	real	Variance of the wavelet transformed image; #f; ()
skewness	skewness	real	Skewness of the wavelet transformed image; #f; ()
curtosis	curtosis	real	Curtosis of the wavelet transformed image; #f; ()
entropy	entropy	real	Entropy of the image; #f; ()
class	class	integer	Class (0 or 1); #f; ()

1.6 bike-sharing-daily🔗ℹ

731 rows × 16 columns. Capital Bikeshare (Washington, D.C.) rentals per day, 2011-2012, with weather and calendar attributes (day.csv). casual + registered = cnt, so leave casual and registered out when predicting cnt. Descriptions follow the UCI dataset page, which corrects the bundled Readme.txt (season 1:springer, temp divided by 41, atemp by 50); season 1 is winter, which matches the January rows.

Fanaee-T, H. (2013). Bike Sharing. UCI Machine Learning Repository. doi:10.24432/C5W894. https://archive.ics.uci.edu/dataset/275/bike+sharing+dataset Described in: Fanaee-T, H. and Gama, J. (2013). Event labeling combining ensemble detectors and background knowledge. Progress in Artificial Intelligence, 1-15. doi:10.1007/s13748-013-0040-3

UCI snapshot 2026-10-23 (hash pinned); CC-BY-4.0

Column	Original	Type	Description / unit / levels
instant	instant	identifier	Record index; #f; ()
dteday	dteday	string	Date (ISO 8601); #f; ()
season	season	integer	Season: 1 winter, 2 spring, 3 summer, 4 fall; #f; ()
yr	yr	integer	Year: 0 = 2011, 1 = 2012; #f; ()
mnth	mnth	integer	Month (1 to 12); #f; ()
holiday	holiday	integer	Whether the day is a holiday; #f; ()
weekday	weekday	integer	Day of the week; #f; ()
workingday	workingday	integer	1 if the day is neither weekend nor holiday, otherwise 0; #f; ()
weathersit	weathersit	integer	Weather: 1 clear or partly cloudy; 2 mist; 3 light snow or rain; 4 heavy rain, ice, snow or fog; #f; ()
temp	temp	real	Normalized temperature in Celsius: (t - t_min)/(t_max - t_min), t_min = -8, t_max = +39; #f; ()
atemp	atemp	real	Normalized feeling temperature in Celsius: (t - t_min)/(t_max - t_min), t_min = -16, t_max = +50; #f; ()
hum	hum	real	Normalized humidity, divided by 100; #f; ()
windspeed	windspeed	real	Normalized wind speed, divided by 67; #f; ()
casual	casual	integer	Count of casual users; #f; ()
registered	registered	integer	Count of registered users; #f; ()
cnt	cnt	integer	Count of total rental bikes, casual and registered; #f; ()

1.7 bike-sharing-hourly🔗ℹ

17379 rows × 17 columns. Capital Bikeshare (Washington, D.C.) rentals per hour, 2011-2012, with weather and calendar attributes (hour.csv); hours without rentals are absent. casual + registered = cnt, so leave casual and registered out when predicting cnt. Descriptions follow the UCI dataset page, which corrects the bundled Readme.txt (season 1:springer, temp divided by 41, atemp by 50); season 1 is winter, which matches the January rows.

Fanaee-T, H. (2013). Bike Sharing. UCI Machine Learning Repository. doi:10.24432/C5W894. https://archive.ics.uci.edu/dataset/275/bike+sharing+dataset Described in: Fanaee-T, H. and Gama, J. (2013). Event labeling combining ensemble detectors and background knowledge. Progress in Artificial Intelligence, 1-15. doi:10.1007/s13748-013-0040-3

UCI snapshot 2026-10-23 (hash pinned); CC-BY-4.0

Column	Original	Type	Description / unit / levels
instant	instant	identifier	Record index; #f; ()
dteday	dteday	string	Date (ISO 8601); #f; ()
season	season	integer	Season: 1 winter, 2 spring, 3 summer, 4 fall; #f; ()
yr	yr	integer	Year: 0 = 2011, 1 = 2012; #f; ()
mnth	mnth	integer	Month (1 to 12); #f; ()
hr	hr	integer	Hour (0 to 23); #f; ()
holiday	holiday	integer	Whether the day is a holiday; #f; ()
weekday	weekday	integer	Day of the week; #f; ()
workingday	workingday	integer	1 if the day is neither weekend nor holiday, otherwise 0; #f; ()
weathersit	weathersit	integer	Weather: 1 clear or partly cloudy; 2 mist; 3 light snow or rain; 4 heavy rain, ice, snow or fog; #f; ()
temp	temp	real	Normalized temperature in Celsius: (t - t_min)/(t_max - t_min), t_min = -8, t_max = +39; #f; ()
atemp	atemp	real	Normalized feeling temperature in Celsius: (t - t_min)/(t_max - t_min), t_min = -16, t_max = +50; #f; ()
hum	hum	real	Normalized humidity, divided by 100; #f; ()
windspeed	windspeed	real	Normalized wind speed, divided by 67; #f; ()
casual	casual	integer	Count of casual users; #f; ()
registered	registered	integer	Count of registered users; #f; ()
cnt	cnt	integer	Count of total rental bikes, casual and registered; #f; ()

1.8 car-evaluation🔗ℹ

1728 rows × 7 columns. All 1,728 combinations of the six attributes with their acceptability class.

Bohanec, M. (1988). Car Evaluation. UCI Machine Learning Repository. doi:10.24432/C5JP48. https://archive.ics.uci.edu/dataset/19/car+evaluation Described in: Bohanec, M. and Rajkovic, V. (1988). Knowledge acquisition and explanation for multi-attribute decision making. 8th International Workshop on Expert Systems and their Applications, Avignon, 59-78.

UCI snapshot 2026-10-23 (hash pinned); CC-BY-4.0

Column	Original	Type	Description / unit / levels
buying	buying	categorical	Buying price; #f; (vhigh high med low)
maint	maint	categorical	Price of the maintenance; #f; (vhigh high med low)
doors	doors	categorical	Number of doors; #f; (2 3 4 5more)
persons	persons	categorical	Capacity in terms of persons to carry; #f; (2 4 more)
lug-boot	lug_boot	categorical	Size of luggage boot; #f; (small med big)
safety	safety	categorical	Estimated safety of the car; #f; (low med high)
class	class	categorical	Car acceptability; #f; (unacc acc good vgood)

1.9 concrete-strength🔗ℹ

1030 rows × 9 columns. Concrete_Data.xls in raw, unscaled form; cell values as stored in the workbook. Column names shortened from the workbook headers (kept as original names).

Yeh, I.-C. (1998). Concrete Compressive Strength. UCI Machine Learning Repository. doi:10.24432/C5PK67. https://archive.ics.uci.edu/dataset/165/concrete+compressive+strength Described in: Yeh, I.-C. (1998). Modeling of strength of high performance concrete using artificial neural networks. Cement and Concrete Research 28(12), 1797-1808. doi:10.1016/S0008-8846(98)00165-3. Copyright Prof. I-Cheng Yeh.

UCI snapshot 2026-10-23 (hash pinned); CC-BY-4.0

Column	Original	Type	Description / unit / levels
cement	Cement (component 1)(kg in a m^3 mixture)	real	Cement (component 1)(kg in a m^3 mixture); kg/m^3 of mixture; ()
blast-furnace-slag	Blast Furnace Slag (component 2)(kg in a m^3 mixture)	real	Blast Furnace Slag (component 2)(kg in a m^3 mixture); kg/m^3 of mixture; ()
fly-ash	Fly Ash (component 3)(kg in a m^3 mixture)	real	Fly Ash (component 3)(kg in a m^3 mixture); kg/m^3 of mixture; ()
water	Water (component 4)(kg in a m^3 mixture)	real	Water (component 4)(kg in a m^3 mixture); kg/m^3 of mixture; ()
superplasticizer	Superplasticizer (component 5)(kg in a m^3 mixture)	real	Superplasticizer (component 5)(kg in a m^3 mixture); kg/m^3 of mixture; ()
coarse-aggregate	Coarse Aggregate (component 6)(kg in a m^3 mixture)	real	Coarse Aggregate (component 6)(kg in a m^3 mixture); kg/m^3 of mixture; ()
fine-aggregate	Fine Aggregate (component 7)(kg in a m^3 mixture)	real	Fine Aggregate (component 7)(kg in a m^3 mixture); kg/m^3 of mixture; ()
age	Age (day)	integer	Age (day); days; ()
concrete-compressive-strength	Concrete compressive strength(MPa, megapascals)	real	Concrete compressive strength(MPa, megapascals) ; MPa; ()

1.10 digits🔗ℹ

1797 rows × 65 columns. The 1,797-row optdigits.tes test portion, identical row for row to the data of scikit-learn load_digits (checked against scikit-learn 1.8.0): 64 pixel counts (0-16) of an 8x8 grid in row-major order, then the digit class. Pixel names follow scikit-learn (pixel_ROW_COL; the source names no attributes). The full 5,620-row set is optdigits.

Alpaydin, E. and Kaynak, C. (1998). Optical Recognition of Handwritten Digits. UCI Machine Learning Repository. doi:10.24432/C50P49. https://archive.ics.uci.edu/dataset/80/optical+recognition+of+handwritten+digits

UCI snapshot 2026-10-23 (hash pinned); CC-BY-4.0

Column	Original	Type	Description / unit / levels
pixel-0-0	pixel_0_0	integer	Count of on pixels in 4x4 block row 0, column 0 of the 32x32 bitmap (0-16); #f; ()
pixel-0-1	pixel_0_1	integer	Count of on pixels in 4x4 block row 0, column 1 of the 32x32 bitmap (0-16); #f; ()
pixel-0-2	pixel_0_2	integer	Count of on pixels in 4x4 block row 0, column 2 of the 32x32 bitmap (0-16); #f; ()
pixel-0-3	pixel_0_3	integer	Count of on pixels in 4x4 block row 0, column 3 of the 32x32 bitmap (0-16); #f; ()
pixel-0-4	pixel_0_4	integer	Count of on pixels in 4x4 block row 0, column 4 of the 32x32 bitmap (0-16); #f; ()
pixel-0-5	pixel_0_5	integer	Count of on pixels in 4x4 block row 0, column 5 of the 32x32 bitmap (0-16); #f; ()
pixel-0-6	pixel_0_6	integer	Count of on pixels in 4x4 block row 0, column 6 of the 32x32 bitmap (0-16); #f; ()
pixel-0-7	pixel_0_7	integer	Count of on pixels in 4x4 block row 0, column 7 of the 32x32 bitmap (0-16); #f; ()
pixel-1-0	pixel_1_0	integer	Count of on pixels in 4x4 block row 1, column 0 of the 32x32 bitmap (0-16); #f; ()
pixel-1-1	pixel_1_1	integer	Count of on pixels in 4x4 block row 1, column 1 of the 32x32 bitmap (0-16); #f; ()
pixel-1-2	pixel_1_2	integer	Count of on pixels in 4x4 block row 1, column 2 of the 32x32 bitmap (0-16); #f; ()
pixel-1-3	pixel_1_3	integer	Count of on pixels in 4x4 block row 1, column 3 of the 32x32 bitmap (0-16); #f; ()
pixel-1-4	pixel_1_4	integer	Count of on pixels in 4x4 block row 1, column 4 of the 32x32 bitmap (0-16); #f; ()
pixel-1-5	pixel_1_5	integer	Count of on pixels in 4x4 block row 1, column 5 of the 32x32 bitmap (0-16); #f; ()
pixel-1-6	pixel_1_6	integer	Count of on pixels in 4x4 block row 1, column 6 of the 32x32 bitmap (0-16); #f; ()
pixel-1-7	pixel_1_7	integer	Count of on pixels in 4x4 block row 1, column 7 of the 32x32 bitmap (0-16); #f; ()
pixel-2-0	pixel_2_0	integer	Count of on pixels in 4x4 block row 2, column 0 of the 32x32 bitmap (0-16); #f; ()
pixel-2-1	pixel_2_1	integer	Count of on pixels in 4x4 block row 2, column 1 of the 32x32 bitmap (0-16); #f; ()
pixel-2-2	pixel_2_2	integer	Count of on pixels in 4x4 block row 2, column 2 of the 32x32 bitmap (0-16); #f; ()
pixel-2-3	pixel_2_3	integer	Count of on pixels in 4x4 block row 2, column 3 of the 32x32 bitmap (0-16); #f; ()
pixel-2-4	pixel_2_4	integer	Count of on pixels in 4x4 block row 2, column 4 of the 32x32 bitmap (0-16); #f; ()
pixel-2-5	pixel_2_5	integer	Count of on pixels in 4x4 block row 2, column 5 of the 32x32 bitmap (0-16); #f; ()
pixel-2-6	pixel_2_6	integer	Count of on pixels in 4x4 block row 2, column 6 of the 32x32 bitmap (0-16); #f; ()
pixel-2-7	pixel_2_7	integer	Count of on pixels in 4x4 block row 2, column 7 of the 32x32 bitmap (0-16); #f; ()
pixel-3-0	pixel_3_0	integer	Count of on pixels in 4x4 block row 3, column 0 of the 32x32 bitmap (0-16); #f; ()
pixel-3-1	pixel_3_1	integer	Count of on pixels in 4x4 block row 3, column 1 of the 32x32 bitmap (0-16); #f; ()
pixel-3-2	pixel_3_2	integer	Count of on pixels in 4x4 block row 3, column 2 of the 32x32 bitmap (0-16); #f; ()
pixel-3-3	pixel_3_3	integer	Count of on pixels in 4x4 block row 3, column 3 of the 32x32 bitmap (0-16); #f; ()
pixel-3-4	pixel_3_4	integer	Count of on pixels in 4x4 block row 3, column 4 of the 32x32 bitmap (0-16); #f; ()
pixel-3-5	pixel_3_5	integer	Count of on pixels in 4x4 block row 3, column 5 of the 32x32 bitmap (0-16); #f; ()
pixel-3-6	pixel_3_6	integer	Count of on pixels in 4x4 block row 3, column 6 of the 32x32 bitmap (0-16); #f; ()
pixel-3-7	pixel_3_7	integer	Count of on pixels in 4x4 block row 3, column 7 of the 32x32 bitmap (0-16); #f; ()
pixel-4-0	pixel_4_0	integer	Count of on pixels in 4x4 block row 4, column 0 of the 32x32 bitmap (0-16); #f; ()
pixel-4-1	pixel_4_1	integer	Count of on pixels in 4x4 block row 4, column 1 of the 32x32 bitmap (0-16); #f; ()
pixel-4-2	pixel_4_2	integer	Count of on pixels in 4x4 block row 4, column 2 of the 32x32 bitmap (0-16); #f; ()
pixel-4-3	pixel_4_3	integer	Count of on pixels in 4x4 block row 4, column 3 of the 32x32 bitmap (0-16); #f; ()
pixel-4-4	pixel_4_4	integer	Count of on pixels in 4x4 block row 4, column 4 of the 32x32 bitmap (0-16); #f; ()
pixel-4-5	pixel_4_5	integer	Count of on pixels in 4x4 block row 4, column 5 of the 32x32 bitmap (0-16); #f; ()
pixel-4-6	pixel_4_6	integer	Count of on pixels in 4x4 block row 4, column 6 of the 32x32 bitmap (0-16); #f; ()
pixel-4-7	pixel_4_7	integer	Count of on pixels in 4x4 block row 4, column 7 of the 32x32 bitmap (0-16); #f; ()
pixel-5-0	pixel_5_0	integer	Count of on pixels in 4x4 block row 5, column 0 of the 32x32 bitmap (0-16); #f; ()
pixel-5-1	pixel_5_1	integer	Count of on pixels in 4x4 block row 5, column 1 of the 32x32 bitmap (0-16); #f; ()
pixel-5-2	pixel_5_2	integer	Count of on pixels in 4x4 block row 5, column 2 of the 32x32 bitmap (0-16); #f; ()
pixel-5-3	pixel_5_3	integer	Count of on pixels in 4x4 block row 5, column 3 of the 32x32 bitmap (0-16); #f; ()
pixel-5-4	pixel_5_4	integer	Count of on pixels in 4x4 block row 5, column 4 of the 32x32 bitmap (0-16); #f; ()
pixel-5-5	pixel_5_5	integer	Count of on pixels in 4x4 block row 5, column 5 of the 32x32 bitmap (0-16); #f; ()
pixel-5-6	pixel_5_6	integer	Count of on pixels in 4x4 block row 5, column 6 of the 32x32 bitmap (0-16); #f; ()
pixel-5-7	pixel_5_7	integer	Count of on pixels in 4x4 block row 5, column 7 of the 32x32 bitmap (0-16); #f; ()
pixel-6-0	pixel_6_0	integer	Count of on pixels in 4x4 block row 6, column 0 of the 32x32 bitmap (0-16); #f; ()
pixel-6-1	pixel_6_1	integer	Count of on pixels in 4x4 block row 6, column 1 of the 32x32 bitmap (0-16); #f; ()
pixel-6-2	pixel_6_2	integer	Count of on pixels in 4x4 block row 6, column 2 of the 32x32 bitmap (0-16); #f; ()
pixel-6-3	pixel_6_3	integer	Count of on pixels in 4x4 block row 6, column 3 of the 32x32 bitmap (0-16); #f; ()
pixel-6-4	pixel_6_4	integer	Count of on pixels in 4x4 block row 6, column 4 of the 32x32 bitmap (0-16); #f; ()
pixel-6-5	pixel_6_5	integer	Count of on pixels in 4x4 block row 6, column 5 of the 32x32 bitmap (0-16); #f; ()
pixel-6-6	pixel_6_6	integer	Count of on pixels in 4x4 block row 6, column 6 of the 32x32 bitmap (0-16); #f; ()
pixel-6-7	pixel_6_7	integer	Count of on pixels in 4x4 block row 6, column 7 of the 32x32 bitmap (0-16); #f; ()
pixel-7-0	pixel_7_0	integer	Count of on pixels in 4x4 block row 7, column 0 of the 32x32 bitmap (0-16); #f; ()
pixel-7-1	pixel_7_1	integer	Count of on pixels in 4x4 block row 7, column 1 of the 32x32 bitmap (0-16); #f; ()
pixel-7-2	pixel_7_2	integer	Count of on pixels in 4x4 block row 7, column 2 of the 32x32 bitmap (0-16); #f; ()
pixel-7-3	pixel_7_3	integer	Count of on pixels in 4x4 block row 7, column 3 of the 32x32 bitmap (0-16); #f; ()
pixel-7-4	pixel_7_4	integer	Count of on pixels in 4x4 block row 7, column 4 of the 32x32 bitmap (0-16); #f; ()
pixel-7-5	pixel_7_5	integer	Count of on pixels in 4x4 block row 7, column 5 of the 32x32 bitmap (0-16); #f; ()
pixel-7-6	pixel_7_6	integer	Count of on pixels in 4x4 block row 7, column 6 of the 32x32 bitmap (0-16); #f; ()
pixel-7-7	pixel_7_7	integer	Count of on pixels in 4x4 block row 7, column 7 of the 32x32 bitmap (0-16); #f; ()
digit	class	integer	Digit class 0-9; #f; ()

1.11 energy-efficiency🔗ℹ

768 rows × 10 columns. 768 simulated building shapes from ENB2012_data.xlsx with two responses. The archive carries no documentation file; names X1-X8, Y1 and Y2 are replaced by the names on the UCI dataset page. Cell values as stored in the workbook.

Tsanas, A. and Xifara, A. (2012). Energy Efficiency. UCI Machine Learning Repository. doi:10.24432/C51307. https://archive.ics.uci.edu/dataset/242/energy+efficiency Described in: Tsanas, A. and Xifara, A. (2012). Accurate quantitative estimation of energy performance of residential buildings using statistical machine learning tools. Energy and Buildings 49.

UCI snapshot 2026-10-23 (hash pinned); CC-BY-4.0

Column	Original	Type	Description / unit / levels
relative-compactness	X1	real	Relative compactness; #f; ()
surface-area	X2	real	Surface area; #f; ()
wall-area	X3	real	Wall area; #f; ()
roof-area	X4	real	Roof area; #f; ()
overall-height	X5	real	Overall height; #f; ()
orientation	X6	integer	Orientation; #f; ()
glazing-area	X7	real	Glazing area; #f; ()
glazing-area-distribution	X8	integer	Glazing area distribution; #f; ()
heating-load	Y1	real	Heating load; #f; ()
cooling-load	Y2	real	Cooling load; #f; ()

1.12 heart-disease🔗ℹ

303 rows × 14 columns. processed.cleveland.data: the 303 Cleveland Clinic patients and the 14 attributes used in published experiments. ? is rendered as missing (ca, thal). Coded attributes stay numeric with their codes in the descriptions; integral values written with a decimal point are stored as integers.

Janosi, A., Steinbrunn, W., Pfisterer, M. and Detrano, R. (1989). Heart Disease. UCI Machine Learning Repository. doi:10.24432/C52P4X. https://archive.ics.uci.edu/dataset/45/heart+disease Described in: Detrano, R. et al. (1989). International application of a new probability algorithm for the diagnosis of coronary artery disease. American Journal of Cardiology 64, 304-310.

UCI snapshot 2026-10-23 (hash pinned); CC-BY-4.0

Column	Original	Type	Description / unit / levels
age	age	integer	Age; years; ()
sex	sex	integer	1 = male, 0 = female; #f; ()
cp	cp	integer	Chest pain type: 1 typical angina, 2 atypical angina, 3 non-anginal pain, 4 asymptomatic; #f; ()
trestbps	trestbps	integer	Resting blood pressure on admission; mm Hg; ()
chol	chol	integer	Serum cholesterol; mg/dl; ()
fbs	fbs	integer	Fasting blood sugar > 120 mg/dl: 1 true, 0 false; #f; ()
restecg	restecg	integer	Resting electrocardiographic results: 0 normal, 1 ST-T wave abnormality, 2 left ventricular hypertrophy; #f; ()
thalach	thalach	integer	Maximum heart rate achieved; #f; ()
exang	exang	integer	Exercise induced angina: 1 yes, 0 no; #f; ()
oldpeak	oldpeak	real	ST depression induced by exercise relative to rest; #f; ()
slope	slope	integer	Slope of the peak exercise ST segment: 1 upsloping, 2 flat, 3 downsloping; #f; ()
ca	ca	integer	Number of major vessels (0-3) colored by fluoroscopy; #f; ()
thal	thal	integer	3 normal, 6 fixed defect, 7 reversible defect; #f; ()
num	num	integer	Angiographic disease status: 0 absence, 1-4 presence; #f; ()

1.13 mushroom🔗ℹ

8124 rows × 23 columns. Hypothetical samples of 23 gilled mushroom species, keeping the source one-letter codes (decoded in each description) and the source column order with class first. bruises? is renamed bruises. The 2,480 ? stalk-root values are rendered as missing. Donated by J. Schlimmer (1987); the UCI page names no creator.

Mushroom [Dataset]. (1981). UCI Machine Learning Repository. doi:10.24432/C5959T. https://archive.ics.uci.edu/dataset/73/mushroom Described in: The Audubon Society Field Guide to North American Mushrooms (1981). G. H. Lincoff (Pres.), New York: Alfred A. Knopf.

UCI snapshot 2026-10-23 (hash pinned); CC-BY-4.0

Column	Original	Type	Description / unit / levels
class	class	categorical	edible=e, poisonous=p; #f; (e p)
cap-shape	cap-shape	categorical	bell=b,conical=c,convex=x,flat=f, knobbed=k,sunken=s; #f; (b c x f k s)
cap-surface	cap-surface	categorical	fibrous=f,grooves=g,scaly=y,smooth=s; #f; (f g y s)
cap-color	cap-color	categorical	brown=n,buff=b,cinnamon=c,gray=g,green=r, pink=p,purple=u,red=e,white=w,yellow=y; #f; (n b c g r p u e w y)
bruises	bruises?	categorical	bruises=t,no=f; #f; (t f)
odor	odor	categorical	almond=a,anise=l,creosote=c,fishy=y,foul=f, musty=m,none=n,pungent=p,spicy=s; #f; (a l c y f m n p s)
gill-attachment	gill-attachment	categorical	attached=a,descending=d,free=f,notched=n; #f; (a f)
gill-spacing	gill-spacing	categorical	close=c,crowded=w,distant=d; #f; (c w)
gill-size	gill-size	categorical	broad=b,narrow=n; #f; (b n)
gill-color	gill-color	categorical	black=k,brown=n,buff=b,chocolate=h,gray=g, green=r,orange=o,pink=p,purple=u,red=e, white=w,yellow=y; #f; (k n b h g r o p u e w y)
stalk-shape	stalk-shape	categorical	enlarging=e,tapering=t; #f; (e t)
stalk-root	stalk-root	categorical	bulbous=b,club=c,cup=u,equal=e, rhizomorphs=z,rooted=r,missing=?; #f; (b c e r)
stalk-surface-above-ring	stalk-surface-above-ring	categorical	fibrous=f,scaly=y,silky=k,smooth=s; #f; (f y k s)
stalk-surface-below-ring	stalk-surface-below-ring	categorical	fibrous=f,scaly=y,silky=k,smooth=s; #f; (f y k s)
stalk-color-above-ring	stalk-color-above-ring	categorical	brown=n,buff=b,cinnamon=c,gray=g,orange=o, pink=p,red=e,white=w,yellow=y; #f; (n b c g o p e w y)
stalk-color-below-ring	stalk-color-below-ring	categorical	brown=n,buff=b,cinnamon=c,gray=g,orange=o, pink=p,red=e,white=w,yellow=y; #f; (n b c g o p e w y)
veil-type	veil-type	categorical	partial=p,universal=u; #f; (p)
veil-color	veil-color	categorical	brown=n,orange=o,white=w,yellow=y; #f; (n o w y)
ring-number	ring-number	categorical	none=n,one=o,two=t; #f; (n o t)
ring-type	ring-type	categorical	cobwebby=c,evanescent=e,flaring=f,large=l, none=n,pendant=p,sheathing=s,zone=z; #f; (e f l n p)
spore-print-color	spore-print-color	categorical	black=k,brown=n,buff=b,chocolate=h,green=r, orange=o,purple=u,white=w,yellow=y; #f; (k n b h r o u w y)
population	population	categorical	abundant=a,clustered=c,numerous=n, scattered=s,several=v,solitary=y; #f; (a c n s v y)
habitat	habitat	categorical	grasses=g,leaves=l,meadows=m,paths=p, urban=u,waste=w,woods=d; #f; (g l m p u w d)

1.14 optdigits🔗ℹ

5620 rows × 66 columns. All 5,620 rows: the 3,823 optdigits.tra rows, then the 1,797 optdigits.tes rows, told apart by split. Writers of the two splits do not overlap. Pixel names follow scikit-learn; digits is the test portion alone.

Alpaydin, E. and Kaynak, C. (1998). Optical Recognition of Handwritten Digits. UCI Machine Learning Repository. doi:10.24432/C50P49. https://archive.ics.uci.edu/dataset/80/optical+recognition+of+handwritten+digits

UCI snapshot 2026-10-23 (hash pinned); CC-BY-4.0

Column	Original	Type	Description / unit / levels
pixel-0-0	pixel_0_0	integer	Count of on pixels in 4x4 block row 0, column 0 of the 32x32 bitmap (0-16); #f; ()
pixel-0-1	pixel_0_1	integer	Count of on pixels in 4x4 block row 0, column 1 of the 32x32 bitmap (0-16); #f; ()
pixel-0-2	pixel_0_2	integer	Count of on pixels in 4x4 block row 0, column 2 of the 32x32 bitmap (0-16); #f; ()
pixel-0-3	pixel_0_3	integer	Count of on pixels in 4x4 block row 0, column 3 of the 32x32 bitmap (0-16); #f; ()
pixel-0-4	pixel_0_4	integer	Count of on pixels in 4x4 block row 0, column 4 of the 32x32 bitmap (0-16); #f; ()
pixel-0-5	pixel_0_5	integer	Count of on pixels in 4x4 block row 0, column 5 of the 32x32 bitmap (0-16); #f; ()
pixel-0-6	pixel_0_6	integer	Count of on pixels in 4x4 block row 0, column 6 of the 32x32 bitmap (0-16); #f; ()
pixel-0-7	pixel_0_7	integer	Count of on pixels in 4x4 block row 0, column 7 of the 32x32 bitmap (0-16); #f; ()
pixel-1-0	pixel_1_0	integer	Count of on pixels in 4x4 block row 1, column 0 of the 32x32 bitmap (0-16); #f; ()
pixel-1-1	pixel_1_1	integer	Count of on pixels in 4x4 block row 1, column 1 of the 32x32 bitmap (0-16); #f; ()
pixel-1-2	pixel_1_2	integer	Count of on pixels in 4x4 block row 1, column 2 of the 32x32 bitmap (0-16); #f; ()
pixel-1-3	pixel_1_3	integer	Count of on pixels in 4x4 block row 1, column 3 of the 32x32 bitmap (0-16); #f; ()
pixel-1-4	pixel_1_4	integer	Count of on pixels in 4x4 block row 1, column 4 of the 32x32 bitmap (0-16); #f; ()
pixel-1-5	pixel_1_5	integer	Count of on pixels in 4x4 block row 1, column 5 of the 32x32 bitmap (0-16); #f; ()
pixel-1-6	pixel_1_6	integer	Count of on pixels in 4x4 block row 1, column 6 of the 32x32 bitmap (0-16); #f; ()
pixel-1-7	pixel_1_7	integer	Count of on pixels in 4x4 block row 1, column 7 of the 32x32 bitmap (0-16); #f; ()
pixel-2-0	pixel_2_0	integer	Count of on pixels in 4x4 block row 2, column 0 of the 32x32 bitmap (0-16); #f; ()
pixel-2-1	pixel_2_1	integer	Count of on pixels in 4x4 block row 2, column 1 of the 32x32 bitmap (0-16); #f; ()
pixel-2-2	pixel_2_2	integer	Count of on pixels in 4x4 block row 2, column 2 of the 32x32 bitmap (0-16); #f; ()
pixel-2-3	pixel_2_3	integer	Count of on pixels in 4x4 block row 2, column 3 of the 32x32 bitmap (0-16); #f; ()
pixel-2-4	pixel_2_4	integer	Count of on pixels in 4x4 block row 2, column 4 of the 32x32 bitmap (0-16); #f; ()
pixel-2-5	pixel_2_5	integer	Count of on pixels in 4x4 block row 2, column 5 of the 32x32 bitmap (0-16); #f; ()
pixel-2-6	pixel_2_6	integer	Count of on pixels in 4x4 block row 2, column 6 of the 32x32 bitmap (0-16); #f; ()
pixel-2-7	pixel_2_7	integer	Count of on pixels in 4x4 block row 2, column 7 of the 32x32 bitmap (0-16); #f; ()
pixel-3-0	pixel_3_0	integer	Count of on pixels in 4x4 block row 3, column 0 of the 32x32 bitmap (0-16); #f; ()
pixel-3-1	pixel_3_1	integer	Count of on pixels in 4x4 block row 3, column 1 of the 32x32 bitmap (0-16); #f; ()
pixel-3-2	pixel_3_2	integer	Count of on pixels in 4x4 block row 3, column 2 of the 32x32 bitmap (0-16); #f; ()
pixel-3-3	pixel_3_3	integer	Count of on pixels in 4x4 block row 3, column 3 of the 32x32 bitmap (0-16); #f; ()
pixel-3-4	pixel_3_4	integer	Count of on pixels in 4x4 block row 3, column 4 of the 32x32 bitmap (0-16); #f; ()
pixel-3-5	pixel_3_5	integer	Count of on pixels in 4x4 block row 3, column 5 of the 32x32 bitmap (0-16); #f; ()
pixel-3-6	pixel_3_6	integer	Count of on pixels in 4x4 block row 3, column 6 of the 32x32 bitmap (0-16); #f; ()
pixel-3-7	pixel_3_7	integer	Count of on pixels in 4x4 block row 3, column 7 of the 32x32 bitmap (0-16); #f; ()
pixel-4-0	pixel_4_0	integer	Count of on pixels in 4x4 block row 4, column 0 of the 32x32 bitmap (0-16); #f; ()
pixel-4-1	pixel_4_1	integer	Count of on pixels in 4x4 block row 4, column 1 of the 32x32 bitmap (0-16); #f; ()
pixel-4-2	pixel_4_2	integer	Count of on pixels in 4x4 block row 4, column 2 of the 32x32 bitmap (0-16); #f; ()
pixel-4-3	pixel_4_3	integer	Count of on pixels in 4x4 block row 4, column 3 of the 32x32 bitmap (0-16); #f; ()
pixel-4-4	pixel_4_4	integer	Count of on pixels in 4x4 block row 4, column 4 of the 32x32 bitmap (0-16); #f; ()
pixel-4-5	pixel_4_5	integer	Count of on pixels in 4x4 block row 4, column 5 of the 32x32 bitmap (0-16); #f; ()
pixel-4-6	pixel_4_6	integer	Count of on pixels in 4x4 block row 4, column 6 of the 32x32 bitmap (0-16); #f; ()
pixel-4-7	pixel_4_7	integer	Count of on pixels in 4x4 block row 4, column 7 of the 32x32 bitmap (0-16); #f; ()
pixel-5-0	pixel_5_0	integer	Count of on pixels in 4x4 block row 5, column 0 of the 32x32 bitmap (0-16); #f; ()
pixel-5-1	pixel_5_1	integer	Count of on pixels in 4x4 block row 5, column 1 of the 32x32 bitmap (0-16); #f; ()
pixel-5-2	pixel_5_2	integer	Count of on pixels in 4x4 block row 5, column 2 of the 32x32 bitmap (0-16); #f; ()
pixel-5-3	pixel_5_3	integer	Count of on pixels in 4x4 block row 5, column 3 of the 32x32 bitmap (0-16); #f; ()
pixel-5-4	pixel_5_4	integer	Count of on pixels in 4x4 block row 5, column 4 of the 32x32 bitmap (0-16); #f; ()
pixel-5-5	pixel_5_5	integer	Count of on pixels in 4x4 block row 5, column 5 of the 32x32 bitmap (0-16); #f; ()
pixel-5-6	pixel_5_6	integer	Count of on pixels in 4x4 block row 5, column 6 of the 32x32 bitmap (0-16); #f; ()
pixel-5-7	pixel_5_7	integer	Count of on pixels in 4x4 block row 5, column 7 of the 32x32 bitmap (0-16); #f; ()
pixel-6-0	pixel_6_0	integer	Count of on pixels in 4x4 block row 6, column 0 of the 32x32 bitmap (0-16); #f; ()
pixel-6-1	pixel_6_1	integer	Count of on pixels in 4x4 block row 6, column 1 of the 32x32 bitmap (0-16); #f; ()
pixel-6-2	pixel_6_2	integer	Count of on pixels in 4x4 block row 6, column 2 of the 32x32 bitmap (0-16); #f; ()
pixel-6-3	pixel_6_3	integer	Count of on pixels in 4x4 block row 6, column 3 of the 32x32 bitmap (0-16); #f; ()
pixel-6-4	pixel_6_4	integer	Count of on pixels in 4x4 block row 6, column 4 of the 32x32 bitmap (0-16); #f; ()
pixel-6-5	pixel_6_5	integer	Count of on pixels in 4x4 block row 6, column 5 of the 32x32 bitmap (0-16); #f; ()
pixel-6-6	pixel_6_6	integer	Count of on pixels in 4x4 block row 6, column 6 of the 32x32 bitmap (0-16); #f; ()
pixel-6-7	pixel_6_7	integer	Count of on pixels in 4x4 block row 6, column 7 of the 32x32 bitmap (0-16); #f; ()
pixel-7-0	pixel_7_0	integer	Count of on pixels in 4x4 block row 7, column 0 of the 32x32 bitmap (0-16); #f; ()
pixel-7-1	pixel_7_1	integer	Count of on pixels in 4x4 block row 7, column 1 of the 32x32 bitmap (0-16); #f; ()
pixel-7-2	pixel_7_2	integer	Count of on pixels in 4x4 block row 7, column 2 of the 32x32 bitmap (0-16); #f; ()
pixel-7-3	pixel_7_3	integer	Count of on pixels in 4x4 block row 7, column 3 of the 32x32 bitmap (0-16); #f; ()
pixel-7-4	pixel_7_4	integer	Count of on pixels in 4x4 block row 7, column 4 of the 32x32 bitmap (0-16); #f; ()
pixel-7-5	pixel_7_5	integer	Count of on pixels in 4x4 block row 7, column 5 of the 32x32 bitmap (0-16); #f; ()
pixel-7-6	pixel_7_6	integer	Count of on pixels in 4x4 block row 7, column 6 of the 32x32 bitmap (0-16); #f; ()
pixel-7-7	pixel_7_7	integer	Count of on pixels in 4x4 block row 7, column 7 of the 32x32 bitmap (0-16); #f; ()
digit	class	integer	Digit class 0-9; #f; ()
split	split	categorical	Source file: train (optdigits.tra, 30 writers) or test (optdigits.tes, 13 other writers); #f; (train test)

1.15 seeds🔗ℹ

210 rows × 8 columns. X-ray measurements of 210 wheat kernels. The source file separates some fields with two tabs; fields are split on whitespace. The archive carries no documentation file; names follow the UCI dataset page.

Charytanowicz, M., Niewczas, J., Kulczycki, P., Kowalski, P. and Lukasik, S. (2010). Seeds. UCI Machine Learning Repository. doi:10.24432/C5H30K. https://archive.ics.uci.edu/dataset/236/seeds Described in: Charytanowicz, M., Niewczas, J., Kulczycki, P., Kowalski, P. A., Lukasik, S. and Zak, S. (2010). Complete Gradient Clustering Algorithm for Features Analysis of X-Ray Images. Information Technologies in Biomedicine. doi:10.1007/978-3-642-13105-9_2

UCI snapshot 2026-10-23 (hash pinned); CC-BY-4.0

Column	Original	Type	Description / unit / levels
area	area	real	Area A; #f; ()
perimeter	perimeter	real	Perimeter P; #f; ()
compactness	compactness	real	Compactness C = 4piA/P^2; #f; ()
length-of-kernel	length of kernel	real	length of kernel; #f; ()
width-of-kernel	width of kernel	real	width of kernel; #f; ()
asymmetry-coefficient	asymmetry coefficient	real	asymmetry coefficient; #f; ()
length-of-kernel-groove	length of kernel groove	real	length of kernel groove; #f; ()
class	class	integer	Wheat variety (1, 2 or 3): Kama, Rosa and Canadian, 70 kernels each; #f; ()

1.16 spambase🔗ℹ

4601 rows × 58 columns. 4,601 e-mails: 48 word and 6 character frequencies (percent), three capital-run-length statistics and the spam class. Character columns are named after the character (char_freq_; is char-freq-semicolon, and so on).

Hopkins, M., Reeber, E., Forman, G. and Suermondt, J. (1999). Spambase. UCI Machine Learning Repository. doi:10.24432/C53G6X. https://archive.ics.uci.edu/dataset/94/spambase

UCI snapshot 2026-10-23 (hash pinned); CC-BY-4.0

Column	Original	Type	Description / unit / levels
word-freq-make	word_freq_make	real	word_freq_make; #f; ()
word-freq-address	word_freq_address	real	word_freq_address; #f; ()
word-freq-all	word_freq_all	real	word_freq_all; #f; ()
word-freq-3d	word_freq_3d	real	word_freq_3d; #f; ()
word-freq-our	word_freq_our	real	word_freq_our; #f; ()
word-freq-over	word_freq_over	real	word_freq_over; #f; ()
word-freq-remove	word_freq_remove	real	word_freq_remove; #f; ()
word-freq-internet	word_freq_internet	real	word_freq_internet; #f; ()
word-freq-order	word_freq_order	real	word_freq_order; #f; ()
word-freq-mail	word_freq_mail	real	word_freq_mail; #f; ()
word-freq-receive	word_freq_receive	real	word_freq_receive; #f; ()
word-freq-will	word_freq_will	real	word_freq_will; #f; ()
word-freq-people	word_freq_people	real	word_freq_people; #f; ()
word-freq-report	word_freq_report	real	word_freq_report; #f; ()
word-freq-addresses	word_freq_addresses	real	word_freq_addresses; #f; ()
word-freq-free	word_freq_free	real	word_freq_free; #f; ()
word-freq-business	word_freq_business	real	word_freq_business; #f; ()
word-freq-email	word_freq_email	real	word_freq_email; #f; ()
word-freq-you	word_freq_you	real	word_freq_you; #f; ()
word-freq-credit	word_freq_credit	real	word_freq_credit; #f; ()
word-freq-your	word_freq_your	real	word_freq_your; #f; ()
word-freq-font	word_freq_font	real	word_freq_font; #f; ()
word-freq-000	word_freq_000	real	word_freq_000; #f; ()
word-freq-money	word_freq_money	real	word_freq_money; #f; ()
word-freq-hp	word_freq_hp	real	word_freq_hp; #f; ()
word-freq-hpl	word_freq_hpl	real	word_freq_hpl; #f; ()
word-freq-george	word_freq_george	real	word_freq_george; #f; ()
word-freq-650	word_freq_650	real	word_freq_650; #f; ()
word-freq-lab	word_freq_lab	real	word_freq_lab; #f; ()
word-freq-labs	word_freq_labs	real	word_freq_labs; #f; ()
word-freq-telnet	word_freq_telnet	real	word_freq_telnet; #f; ()
word-freq-857	word_freq_857	real	word_freq_857; #f; ()
word-freq-data	word_freq_data	real	word_freq_data; #f; ()
word-freq-415	word_freq_415	real	word_freq_415; #f; ()
word-freq-85	word_freq_85	real	word_freq_85; #f; ()
word-freq-technology	word_freq_technology	real	word_freq_technology; #f; ()
word-freq-1999	word_freq_1999	real	word_freq_1999; #f; ()
word-freq-parts	word_freq_parts	real	word_freq_parts; #f; ()
word-freq-pm	word_freq_pm	real	word_freq_pm; #f; ()
word-freq-direct	word_freq_direct	real	word_freq_direct; #f; ()
word-freq-cs	word_freq_cs	real	word_freq_cs; #f; ()
word-freq-meeting	word_freq_meeting	real	word_freq_meeting; #f; ()
word-freq-original	word_freq_original	real	word_freq_original; #f; ()
word-freq-project	word_freq_project	real	word_freq_project; #f; ()
word-freq-re	word_freq_re	real	word_freq_re; #f; ()
word-freq-edu	word_freq_edu	real	word_freq_edu; #f; ()
word-freq-table	word_freq_table	real	word_freq_table; #f; ()
word-freq-conference	word_freq_conference	real	word_freq_conference; #f; ()
char-freq-semicolon	char_freq_;	real	char_freq_;; #f; ()
char-freq-paren	char_freq_(	real	char_freq_(; #f; ()
char-freq-bracket	char_freq_[	real	char_freq_[; #f; ()
char-freq-exclamation	char_freq_!	real	char_freq_!; #f; ()
char-freq-dollar	char_freq_$	real	char_freq_$; #f; ()
char-freq-hash	char_freq_#	real	char_freq_#; #f; ()
capital-run-length-average	capital_run_length_average	real	capital_run_length_average; #f; ()
capital-run-length-longest	capital_run_length_longest	integer	capital_run_length_longest; #f; ()
capital-run-length-total	capital_run_length_total	integer	capital_run_length_total; #f; ()
spam	spam	integer	1 = spam, 0 = not spam; #f; ()

1.17 student-performance🔗ℹ

1044 rows × 34 columns. Two Portuguese secondary schools in one table: the 395 mathematics rows, then the 649 Portuguese-language rows, told apart by subject. Some students appear in both courses; the source has no student identifier.

Cortez, P. (2008). Student Performance. UCI Machine Learning Repository. doi:10.24432/C5TG7T. https://archive.ics.uci.edu/dataset/320/student+performance Described in: Cortez, P. and Silva, A. (2008). Using data mining to predict secondary school student performance. Proceedings of the 5th Annual Future Business Technology Conference.

UCI snapshot 2026-10-23 (hash pinned); CC-BY-4.0

Column	Original	Type	Description / unit / levels
school	school	categorical	school; #f; (GP MS)
sex	sex	categorical	sex; #f; (F M)
age	age	integer	age; #f; ()
address	address	categorical	address; #f; (U R)
famsize	famsize	categorical	famsize; #f; (LE3 GT3)
pstatus	Pstatus	categorical	Pstatus; #f; (T A)
medu	Medu	integer	Medu; #f; ()
fedu	Fedu	integer	Fedu; #f; ()
mjob	Mjob	categorical	Mjob; #f; (teacher health services at_home other)
fjob	Fjob	categorical	Fjob; #f; (teacher health services at_home other)
reason	reason	categorical	reason; #f; (home reputation course other)
guardian	guardian	categorical	guardian; #f; (mother father other)
traveltime	traveltime	integer	traveltime; #f; ()
studytime	studytime	integer	studytime; #f; ()
failures	failures	integer	failures; #f; ()
schoolsup	schoolsup	categorical	schoolsup; #f; (no yes)
famsup	famsup	categorical	famsup; #f; (no yes)
paid	paid	categorical	paid; #f; (no yes)
activities	activities	categorical	activities; #f; (no yes)
nursery	nursery	categorical	nursery; #f; (no yes)
higher	higher	categorical	higher; #f; (no yes)
internet	internet	categorical	internet; #f; (no yes)
romantic	romantic	categorical	romantic; #f; (no yes)
famrel	famrel	integer	famrel; #f; ()
freetime	freetime	integer	freetime; #f; ()
goout	goout	integer	goout; #f; ()
dalc	Dalc	integer	Dalc; #f; ()
walc	Walc	integer	Walc; #f; ()
health	health	integer	health; #f; ()
absences	absences	integer	absences; #f; ()
g1	G1	integer	First period grade (0-20); #f; ()
g2	G2	integer	Second period grade (0-20); #f; ()
g3	G3	integer	Final grade (0-20); #f; ()
subject	subject	categorical	Course: math (student-mat.csv) or portuguese (student-por.csv); #f; (math portuguese)

1.18 wine-quality🔗ℹ

6497 rows × 13 columns. Red and white vinho verde in one table: the 1,599 red rows, then the 4,898 white rows, told apart by colour.

Cortez, P., Cerdeira, A., Almeida, F., Matos, T. and Reis, J. (2009). Wine Quality. UCI Machine Learning Repository. doi:10.24432/C56S3T. https://archive.ics.uci.edu/dataset/186/wine+quality Described in: Cortez, P., Cerdeira, A., Almeida, F., Matos, T. and Reis, J. (2009). Modeling wine preferences by data mining from physicochemical properties. Decision Support Systems 47(4), 547-553. doi:10.1016/j.dss.2009.05.016

UCI snapshot 2026-10-23 (hash pinned); CC-BY-4.0

Column	Original	Type	Description / unit / levels
fixed-acidity	fixed acidity	real	fixed acidity; #f; ()
volatile-acidity	volatile acidity	real	volatile acidity; #f; ()
citric-acid	citric acid	real	citric acid; #f; ()
residual-sugar	residual sugar	real	residual sugar; #f; ()
chlorides	chlorides	real	chlorides; #f; ()
free-sulfur-dioxide	free sulfur dioxide	real	free sulfur dioxide; #f; ()
total-sulfur-dioxide	total sulfur dioxide	real	total sulfur dioxide; #f; ()
density	density	real	density; #f; ()
ph	pH	real	pH; #f; ()
sulphates	sulphates	real	sulphates; #f; ()
alcohol	alcohol	real	alcohol; #f; ()
quality	quality	integer	Sensory quality score between 0 and 10; #f; ()
colour	colour	categorical	Red or white vinho verde; #f; (red white)

1.1	abalone
1.2	adult
1.3	auto-mpg
1.4	bank-marketing
1.5	banknote-authentication
1.6	bike-sharing-daily
1.7	bike-sharing-hourly
1.8	car-evaluation
1.9	concrete-strength
1.10	digits
1.11	energy-efficiency
1.12	heart-disease
1.13	mushroom
1.14	optdigits
1.15	seeds
1.16	spambase
1.17	student-performance
1.18	wine-quality

1 datasets-uci🔗ℹ

1.1 abalone🔗ℹ

1.2 adult🔗ℹ

1.3 auto-mpg🔗ℹ

1.4 bank-marketing🔗ℹ

1.5 banknote-authentication🔗ℹ

1.6 bike-sharing-daily🔗ℹ

1.7 bike-sharing-hourly🔗ℹ

1.8 car-evaluation🔗ℹ

1.9 concrete-strength🔗ℹ

1.10 digits🔗ℹ

1.11 energy-efficiency🔗ℹ

1.12 heart-disease🔗ℹ

1.13 mushroom🔗ℹ

1.14 optdigits🔗ℹ

1.15 seeds🔗ℹ

1.16 spambase🔗ℹ

1.17 student-performance🔗ℹ

1.18 wine-quality🔗ℹ