fri_c2_250_10 (Q6033392)

From MaRDI portal
OpenML dataset with id 657
Language Label Description Also known as
English
fri_c2_250_10
OpenML dataset with id 657

    Statements

    0 references
    0 references
    **Author**: \N**Source**: Unknown - Date unknown \N**Please cite**: \N\NThe Friedman datasets are 80 artificially generated datasets originating from: J.H. Friedman (1999). Stochastic Gradient Boosting\N\NThe dataset names are coded as "fri_colinearintydegree_samplenumber_featurenumber".\N\NFriedman is the one of the most used functions for data generation (Friedman, 1999). Friedman functions include both linear and non-linear relations between input and output, and a normalized noise (e) is added to the output. The Friedman function is as follows: \N\Ny=10*sin(pi*x1*x2)+20*(x3-0.5)^2=10*X4+5*X5+e\N\NIn the original Friedman function, there are 5 features for input. To measure the effects of non-related features, additional features are added to the datasets. These added features are independent from the output. However, to measure the algorithm's robustness to the colinearity, the datasets are generated with 5 different colinearity degrees. The colinearity degrees is the number of features depending on other features. \N\NThe generated Friedman dataset's parameters and values are given below: \NThe number of features: 5 10 25 50 100 (only the first 5 features are related to the output. The rest are completely random)\NThe number of samples: 100 250 500 1000\NColinearity degrees: 0 1 2 3 4\NFor the datasets with colinearity degree 4, the numbers of features are generated as 10, 25, 50 and 100.\NThe other datasets have 5, 10, 25 and 50 features.\N\NAs a result, 80 artificial datasets are generated by (4 different feature number * 4 different sample number * 5 different colinearity degree)\N\NThe last attribute in each file is the target.
    0 references
    4 October 2014
    0 references
    oz11
    0 references
    0 references
    0 references
    6f60924efa252d6dcbef47f7085b33dc
    0 references
    0
    0 references
    0
    0 references
    11
    0 references
    250
    0 references
    0
    0 references
    11
    0 references
    0 references