Repository: systemml Updated Branches: refs/heads/master 1db240767 -> 627a6c40d
[MINOR] l2-svm.dml and l2-svm-predict.dml doc improvements Add input parameter descriptions to l2-svm.dml and l2-svm-predict.dml scripts. Fix CsplineCG.dml input parameter description spacing issue. Closes #560. Project: http://git-wip-us.apache.org/repos/asf/systemml/repo Commit: http://git-wip-us.apache.org/repos/asf/systemml/commit/627a6c40 Tree: http://git-wip-us.apache.org/repos/asf/systemml/tree/627a6c40 Diff: http://git-wip-us.apache.org/repos/asf/systemml/diff/627a6c40 Branch: refs/heads/master Commit: 627a6c40d6db9c19e06cf0bc4a0e43089e5e4c5f Parents: 1db2407 Author: krishnakalyan3 <krishnakaly...@gmail.com> Authored: Fri Jul 7 12:42:48 2017 -0700 Committer: Deron Eriksson <de...@us.ibm.com> Committed: Fri Jul 7 12:42:48 2017 -0700 ---------------------------------------------------------------------- scripts/algorithms/CsplineCG.dml | 4 ++-- scripts/algorithms/l2-svm-predict.dml | 14 ++++++++++++++ scripts/algorithms/l2-svm.dml | 17 +++++++++++++++++ 3 files changed, 33 insertions(+), 2 deletions(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/systemml/blob/627a6c40/scripts/algorithms/CsplineCG.dml ---------------------------------------------------------------------- diff --git a/scripts/algorithms/CsplineCG.dml b/scripts/algorithms/CsplineCG.dml index 8193561..e3b4ac3 100644 --- a/scripts/algorithms/CsplineCG.dml +++ b/scripts/algorithms/CsplineCG.dml @@ -27,8 +27,8 @@ # -------------------------------------------------------------------------------------------- # X String --- Location (on HDFS) to read the 1-column matrix of x values knots # Y String --- Location (on HDFS) to read the 1-column matrix of corresponding y values knots -# K String --- Location to store the $k_{i}$ -file for the calculated k vectors. the default is to print it to the standard output -# O String --- Location to store the output predicted y the default is to print it to the standard output +# K String --- Location to store the $k_{i}$ -file for the calculated k vectors. the default is to print it to the standard output +# O String --- Location to store the output predicted y the default is to print it to the standard output # inp_x Double --- the given input x, for which the cspline will find predicted y. # Log String " " Location to store iteration-specific variables for monitoring and debugging purposes # http://git-wip-us.apache.org/repos/asf/systemml/blob/627a6c40/scripts/algorithms/l2-svm-predict.dml ---------------------------------------------------------------------- diff --git a/scripts/algorithms/l2-svm-predict.dml b/scripts/algorithms/l2-svm-predict.dml index 604ef64..9052265 100644 --- a/scripts/algorithms/l2-svm-predict.dml +++ b/scripts/algorithms/l2-svm-predict.dml @@ -25,6 +25,20 @@ # Given ground truth labels, the script will compute an # accuracy (%) for the predictions # +# INPUT PARAMETERS: +# --------------------------------------------------------------------------------------------- +# NAME TYPE DEFAULT MEANING +# --------------------------------------------------------------------------------------------- +# X String --- Location to read the matrix X of feature vectors +# model String --- Location of the existing model generated by l2-svm +# fmt String "text" The output format of the output, such as "text" or "csv" +# Y String --- [OPTIONAL] Location to read the true label matrix Y. Only needed +# for evaluating performance (accuracy, confusion) of the model. +# confusion String --- [OPTIONAL] Location to write confusion matrix, valid if Y supplied +# accuracy String --- [OPTIONAL] Location to write accuracy matrix, valid if Y supplied +# scores String --- [OPTIONAL] Location to write model predictions +# --------------------------------------------------------------------------------------------- +# # Example Usage: # hadoop jar SystemML.jar -f l2-svm-predict.dml -nvargs X=data Y=labels model=model scores=scores accuracy=accuracy confusion=confusion fmt="text" # http://git-wip-us.apache.org/repos/asf/systemml/blob/627a6c40/scripts/algorithms/l2-svm.dml ---------------------------------------------------------------------- diff --git a/scripts/algorithms/l2-svm.dml b/scripts/algorithms/l2-svm.dml index a33d199..d5c7e02 100644 --- a/scripts/algorithms/l2-svm.dml +++ b/scripts/algorithms/l2-svm.dml @@ -26,6 +26,23 @@ # Assume input and output directories are on hdfs as INPUT_DIR and OUTPUT_DIR # Assume epsilon = 0.001, lambda = 1, maxiterations = 100 # +# INPUT PARAMETERS: +# --------------------------------------------------------------------------------------------- +# NAME TYPE DEFAULT MEANING +# --------------------------------------------------------------------------------------------- +# X String --- Location to read the matrix X of feature vectors +# Y String --- Location to read response matrix Y +# icpt Int 0 Intercept presence +# 0 = no intercept +# 1 = add intercept; +# tol Double 0.001 Tolerance (epsilon); +# reg Double 1.0 Regularization parameter (lambda) for L2 regularization +# maxiter Int 100 Maximum number of conjugate gradient iterations +# model String --- Location to write model +# fmt String "text" The output format of the output, such as "text" or "csv" +# Log String --- [OPTIONAL] Location to write the log file +# --------------------------------------------------------------------------------------------- + # hadoop jar SystemML.jar -f $L2SVM_HOME/l2-svm.dml -nvargs X=$INPUT_DIR/X Y=$INPUT_DIR/Y icpt=0 tol=0.001 reg=1 maxiter=100 model=$OUPUT_DIR/w Log=$OUTPUT_DIR/Log fmt="text" # # Note about inputs:
