Data
fri_c2_100_5

fri_c2_100_5

active ARFF Publicly available Visibility: public Uploaded 04-10-2014 by Joaquin Vanschoren
0 likes downloaded by 0 people , 0 total downloads 0 issues 0 downvotes
Issue #Downvotes for this reason By


Loading wiki
Help us complete this description Edit
Author: Source: Unknown - Date unknown Please cite: The Friedman datasets are 80 artificially generated datasets originating from: J.H. Friedman (1999). Stochastic Gradient Boosting The dataset names are coded as "fri_colinearintydegree_samplenumber_featurenumber". Friedman 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: y=10*sin(pi*x1*x2)+20*(x3-0.5)^2=10*X4+5*X5+e In 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. The generated Friedman dataset's parameters and values are given below: The number of features: 5 10 25 50 100 (only the first 5 features are related to the output. The rest are completely random) The number of samples: 100 250 500 1000 Colinearity degrees: 0 1 2 3 4 For the datasets with colinearity degree 4, the numbers of features are generated as 10, 25, 50 and 100. The other datasets have 5, 10, 25 and 50 features. As a result, 80 artificial datasets are generated by (4 different feature number * 4 different sample number * 5 different colinearity degree) The last attribute in each file is the target.

6 features

oz6 (target)numeric100 unique values
0 missing
oz1numeric100 unique values
0 missing
oz2numeric100 unique values
0 missing
oz3numeric100 unique values
0 missing
oz4numeric100 unique values
0 missing
oz5numeric100 unique values
0 missing

19 properties

100
Number of instances (rows) of the dataset.
6
Number of attributes (columns) of the dataset.
0
Number of distinct values of the target attribute (if it is nominal).
0
Number of missing values in the dataset.
0
Number of instances with at least one value missing.
6
Number of numeric attributes.
0
Number of nominal attributes.
0
Percentage of binary attributes.
0
Percentage of instances having missing values.
-0.02
Average class difference between consecutive instances.
0
Percentage of missing values.
0.06
Number of attributes divided by the number of instances.
100
Percentage of numeric attributes.
Percentage of instances belonging to the most frequent class.
0
Percentage of nominal attributes.
Number of instances belonging to the most frequent class.
Percentage of instances belonging to the least frequent class.
Number of instances belonging to the least frequent class.
0
Number of binary attributes.

13 tasks

0 runs - estimation_procedure: 10 times 10-fold Crossvalidation - evaluation_measure: mean_absolute_error - target_feature: oz6
0 runs - estimation_procedure: 10-fold Crossvalidation - evaluation_measure: mean_absolute_error - target_feature: oz6
0 runs - estimation_procedure: 50 times Clustering
0 runs - estimation_procedure: 50 times Clustering
0 runs - estimation_procedure: 50 times Clustering
0 runs - estimation_procedure: 50 times Clustering
0 runs - estimation_procedure: 50 times Clustering
0 runs - estimation_procedure: 50 times Clustering
0 runs - estimation_procedure: 50 times Clustering
0 runs - estimation_procedure: 50 times Clustering
0 runs - estimation_procedure: 50 times Clustering
0 runs - estimation_procedure: 50 times Clustering
Define a new task