Data
UNIX_user_data

UNIX_user_data

active ARFF Publicly available Visibility: public Uploaded 27-09-2014 by Joaquin Vanschoren
0 likes downloaded by 8 people , 11 total downloads 0 issues 0 downvotes
Issue #Downvotes for this reason By


Loading wiki
Help us complete this description Edit
Author: Terran Lane (terran@ecn.purdue.edu) Source: [UCI](https://archive.ics.uci.edu/ml/datasets/UNIX+User+Data) - Date unknown Please cite: This file contains 9 sets of sanitized user data drawn from the command histories of 8 UNIX computer users at Purdue over the course of up to 2 years (USER0 and USER1 were generated by the same person, working on different platforms and different projects). The data is drawn from tcsh(1) history files and has been parsed and sanitized to remove filenames, user names, directory structures, web addresses, host names, and other possibly identifying items. Command names, flags, and shell metacharacters have been preserved. Additionally, SOF and EOF tokens have been inserted at the start and end of shell sessions, respectively. Sessions are concatenated by date order and tokens appear in the order issued within the shell session, but no timestamps are included in this data. For example, the two sessions: cd ~/private/docs ls -laF | more cat foo.txt bar.txt zorch.txt > somewhere exit cd ~/games/ xquake & fg vi scores.txt mailx john_doe@somewhere.com exit would be represented by the token stream SOF cd \<1\> (one "file name" argument) ls -laF | more cat \<3\> (three "file" arguments) \> \<1\> exit EOF SOF cd \<1\> xquake & fg vi \<1\> mailx \<1\> exit EOF This data is made available under conditions of anonymity for the contributing users and may be used for research purposes only. Summaries and research results employing this data may be published, but literal tokens or token sequences from the data may not be published except with express consent of the originators of the data. No portion of this data may be released with or included in a commercial product, nor may any portion of this data be sold or redistributed for profit or as part of of a profit-making endeavor.

3 features

user (target)nominal9 unique values
0 missing
historynumeric2961 unique values
0 missing
sessionstring5964 unique values
0 missing

19 properties

9100
Number of instances (rows) of the dataset.
3
Number of attributes (columns) of the dataset.
9
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.
1
Number of numeric attributes.
1
Number of nominal attributes.
0
Percentage of binary attributes.
0
Percentage of instances having missing values.
0
Percentage of missing values.
1
Average class difference between consecutive instances.
33.33
Percentage of numeric attributes.
0
Number of attributes divided by the number of instances.
33.33
Percentage of nominal attributes.
26.65
Percentage of instances belonging to the most frequent class.
2425
Number of instances belonging to the most frequent class.
5.32
Percentage of instances belonging to the least frequent class.
484
Number of instances belonging to the least frequent class.
0
Number of binary attributes.

14 tasks

7 runs - estimation_procedure: 10-fold Crossvalidation - evaluation_measure: predictive_accuracy - target_feature: user
4 runs - estimation_procedure: 10 times 10-fold Crossvalidation - evaluation_measure: predictive_accuracy - target_feature: user
0 runs - estimation_procedure: Interleaved Test then Train - target_feature: user
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