This section describes main characteristics of the bands data set and its attributes:
General information
Cylinder Bands data set |
Type | Classification | Origin | Real world |
Features | 19 | (Real / Integer / Nominal) | (13 / 6 / 0) |
Classes | 2 |
Missing values? | Yes |
Total instances | 539 |
Instances without missing values | 365 |
Attribute description
Attribute | Domain | Attribute | Domain |
Proof_cut | [25.0,72.5] | Solvent_pct | [22.0,53.4] |
Viscosity | [35,72] | Esa_voltage | [0.0,16.0] |
Caliper | [0.133,0.533] | ESA_amperage | [0.0,6.0] |
Ink_temperature | [11.2,24.5] | Wax | [0.0,3.1] |
Humifity | [57,105] | Hardener | [0.0,3.0] |
Roughness | [0.056,1.25] | Roller_durometer | [28.0,60.0] |
Blade_pressure | [16,70] | Density | [30,45] |
Varnish_pct | [0.0,35.8] | Anode_ratio | [83.33,117.86] |
Press_speed | [0,2600] | Chrome_content | [90,100] |
Ink_pct | [41.0,76.9] | Band_type | {band,noband} |
Additional information
A classification problem from rotogravure printing, where the task is to determine a given piece is a cylinder band.
This data set is a modification of the original data set of the UCI repository. Nominal attributes has been removed, and also, 2 of the 541 instances of the originall data set were removed, as they become duplicated.
In this section you can download some files related to the bands data set:
- The complete data set already formatted in KEEL formatcan be downloaded from here.
- A copy of the data set already partitioned by means of a 10-folds cross validation procedure can be downloaded from here.
- A copy of the data set already partitioned by means of a 5-folds cross validation procedure can be downloaded from here.
- The header file associated to this data set can be downloaded from here.
- This is not a native data set from the KEEL project. It has been obtained from the UCI Machine Learning Repository. The original page where the data set can be found is: http://archive.ics.uci.edu/ml/datasets/Cylinder+Bands.
|