Classes:
| Name | Description |
|---|---|
ConcreteCompressiveStrength |
Concrete compressive strength (1,030 × 8). |
ParkinsonsTelemonitoring |
Parkinsons telemonitoring (5,875 × 21). |
ProteinStructure |
Physicochemical properties of protein tertiary structure (45,730 × 9). |
RoadNetwork |
3D Road Network (434,874 × 2). |
WineQuality |
Wine quality prediction from physicochemical properties (4,898 × 11). |
ConcreteCompressiveStrength(
root: str | Path = None,
transform: Callable | None = Lambda(
lambda x: (
x
- as_tensor(
[
281.1656,
73.8955,
54.1871,
181.5664,
6.2031,
972.9186,
773.5789,
45.6621,
]
)
)
/ as_tensor(
[
104.5071,
86.2791,
63.9965,
21.3556,
5.9735,
77.7538,
80.1754,
63.1699,
]
)
),
target_transform: Callable | None = Lambda(
lambda y: (y - 35.8178) / 16.7057
),
download: bool = False,
)
Bases: RegressionDataset
Concrete compressive strength (1,030 × 8).
This UCI dataset contains the ingredients of concrete mixtures and their age. The regression task is to predict the concrete's compressive strength.
Source: https://archive.ics.uci.edu/dataset/165/concrete+compressive+strength
Methods:
| Name | Description |
|---|---|
download |
|
Attributes:
| Name | Type | Description |
|---|---|---|
URL |
|
|
filepath |
str
|
|
md5 |
|
|
root |
|
|
target_transform |
|
|
transform |
|
ParkinsonsTelemonitoring(
root: str | Path = None,
transform: Callable | None = Lambda(
lambda x: (
x
- as_tensor(
[
21.494,
64.805,
0.31779,
92.864,
21.296,
0.0061538,
4.4027e-05,
0.0029872,
0.0032769,
0.0089617,
0.034035,
0.31096,
0.017156,
0.020144,
0.027481,
0.051467,
0.03212,
21.679,
0.54147,
0.65324,
0.21959,
]
)
)
/ as_tensor(
[
12.372,
8.8215,
0.46566,
53.446,
8.1293,
0.0056242,
3.5983e-05,
0.0031238,
0.0037315,
0.0093715,
0.025835,
0.23025,
0.013237,
0.016664,
0.019986,
0.039711,
0.059692,
4.2911,
0.10099,
0.070902,
0.091498,
]
)
),
target_transform: Callable | None = Lambda(
lambda y: (y - 29.0189) / 10.7003
),
download: bool = False,
)
Bases: RegressionDataset
Parkinsons telemonitoring (5,875 × 21).
This UCI dataset is composed of a range of biomedical voice measurements from 42 people with early-stage Parkinson's disease recruited to a six-month trial of a telemonitoring device for remote symptom progression monitoring. The recordings were automatically captured in the patient's homes. The original study used a range of linear and nonlinear regression methods to predict the clinician's Parkinson's disease symptom score on the UPDRS scale.
Source: https://archive.ics.uci.edu/ml/datasets/parkinsons+telemonitoring
Methods:
| Name | Description |
|---|---|
download |
|
Attributes:
| Name | Type | Description |
|---|---|---|
URL |
|
|
filepath |
str
|
|
md5 |
|
|
root |
|
|
target_transform |
|
|
transform |
|
ProteinStructure(
root: str | Path = None,
transform: Callable | None = Lambda(
lambda x: (
x
- as_tensor(
[
9871.6,
3017.4,
0.30239,
103.49,
1368300.0,
145.64,
3989.8,
69.975,
34.524,
]
)
)
/ as_tensor(
[
4058.1,
1464.3,
0.062886,
55.425,
564040.0,
69.999,
1993.6,
56.493,
5.9798,
]
)
),
target_transform: Callable | None = Lambda(
lambda y: (y - 7.7485) / 6.1183
),
download: bool = False,
)
Bases: RegressionDataset
Physicochemical properties of protein tertiary structure (45,730 × 9).
This UCI dataset encompasses the physicochemical properties of protein tertiary structure, sourced from CASP 5-9. There are 45,730 decoys with 9 attributes and sizes varying from 0 to 21 angstroms.
Source: https://archive.ics.uci.edu/ml/datasets/Physicochemical+Properties+of+Protein+Tertiary+Structure
Methods:
| Name | Description |
|---|---|
download |
|
Attributes:
| Name | Type | Description |
|---|---|---|
URL |
|
|
filepath |
str
|
|
md5 |
|
|
root |
|
|
target_transform |
|
|
transform |
|
RoadNetwork(
root: str | Path = None,
transform: Callable | None = Lambda(
lambda x: (x - as_tensor([9.7318, 57.0838]))
/ as_tensor([0.6273, 0.2895])
),
target_transform: Callable | None = Lambda(
lambda y: (y - 22.1854) / 18.618
),
download: bool = False,
)
Bases: RegressionDataset
3D Road Network (434,874 × 2).
This UCI Dataset contains longitude, latitude and altitude values of a road network in North Jutland, Denmark (covering a region of 185x135 km2). Elevation values where extracted from a publicly available massive Laser Scan Point Cloud for Denmark. The regression task is to predict the altitude from longitude and latitude measurements.
Source: https://archive.ics.uci.edu/ml/datasets/3D+Road+Network+(North+Jutland,+Denmark)
Methods:
| Name | Description |
|---|---|
download |
|
Attributes:
| Name | Type | Description |
|---|---|---|
URL |
|
|
filepath |
str
|
|
md5 |
|
|
root |
|
|
target_transform |
|
|
transform |
|
WineQuality(
root: str | Path = None,
transform: Callable | None = Lambda(
lambda x: (
x
- as_tensor(
[
8.3196,
0.5278,
0.271,
2.5388,
0.0875,
15.8749,
46.4678,
0.9967,
3.3111,
0.6581,
10.423,
]
)
)
/ as_tensor(
[
1.7411,
0.17906,
0.1948,
1.4099,
0.047065,
10.46,
32.895,
0.0018873,
0.15439,
0.16951,
1.0657,
]
)
),
target_transform: Callable | None = Lambda(
lambda y: (y - 5.636) / 0.8076
),
download: bool = False,
wine_type: Literal["red", "white"] = "red",
)
Bases: RegressionDataset
Wine quality prediction from physicochemical properties (4,898 × 11).
This UCI dataset contains red and white vinho verde wine samples, from the north of Portugal. The goal is to model wine quality based on physicochemical tests.
Source: https://archive.ics.uci.edu/dataset/186/wine+quality
Methods:
| Name | Description |
|---|---|
download |
|
Attributes:
| Name | Type | Description |
|---|---|---|
URL |
|
|
filepath |
str
|
|
md5 |
|
|
root |
|
|
target_transform |
|
|
transform |
|
|
wine_type |
|