1mlpack_linear_regression(1) General Commands Manualmlpack_linear_regression(1)
2
3
4
6 mlpack_linear_regression - simple linear regression and prediction
7
9 mlpack_linear_regression [-h] [-v]
10
12 An implementation of simple linear regression and simple ridge regres‐
13 sion using ordinary least squares. This solves the problem
14
15 y = X * b + e
16
17 where X (--input_file) and y (the last column of --input_file, or
18 --input_responses) are known and b is the desired variable. If the
19 covariance matrix (X'X) is not invertible, or if the solution is
20 overdetermined, then specify a Tikhonov regularization constant
21 (--lambda) greater than 0, which will regularize the covariance matrix
22 to make it invertible. The calculated b is saved to disk (--out‐
23 put_file).
24
25 Optionally, the calculated value of b is used to predict the responses
26 for another matrix X' (--test_file):
27
28 y' = X' * b
29
30 and these predicted responses, y', are saved to a file (--output_pre‐
31 dictions). This type of regression is related to least-angle regres‐
32 sion, which mlpack implements with the 'lars' executable.
33
35 --help (-h)
36 Default help info.
37
38 --info [string]
39 Get help on a specific module or option. Default value ''.
40 --input_model_file (-m) [string] File containing existing model
41 (parameters). Default value ''.
42
43 --lambda (-l) [double]
44 Tikhonov regularization for ridge regression. If 0, the method
45 reduces to linear regression. Default value 0.
46
47 --test_file (-T) [string]
48 File containing X' (test regressors). Default value ''.
49 --training_file (-t) [string] File containing training set X
50 (regressors). Default value ''. --training_responses (-r)
51 [string] Optional file containing y (responses). If not given,
52 the responses are assumed to be the last row of the input file.
53 Default value ''.
54
55 --verbose (-v)
56 Display informational messages and the full list of parameters
57 and timers at the end of execution.
58
59 --version (-V)
60 Display the version of mlpack.
61
63 --output_model_file (-M) [string] File to save trained model to.
64 Default value ’'. --output_predictions_file (-o) [string] If
65 --test_file is specified, this file is where the predicted responses
66 will be saved. Default value ''.
67
70 For further information, including relevant papers, citations, and the‐
71 ory, For further information, including relevant papers, citations, and
72 theory, consult the documentation found at http://www.mlpack.org or
73 included with your consult the documentation found at
74 http://www.mlpack.org or included with your DISTRIBUTION OF MLPACK.
75 DISTRIBUTION OF MLPACK.
76
77
78
79 mlpack_linear_regression(1)