19524: Limit size of PCA input matrix.

Arvados-DCO-1.1-Signed-off-by: Tom Clegg <tom@curii.com>

diff --git a/slicenumpy.go b/slicenumpy.go
index 62982f5407519cf07c0528d778b2dc7730bf31fe..a9fee14c8d692430370b94f8ea0f3b35ca62fa43 100644 (file)
--- a/slicenumpy.go
+++ b/slicenumpy.go
@@ -80,7 +80,7 @@ func (cmd *sliceNumpy) run(prog string, args []string, stdin io.Reader, stdout,
        onehotChunked := flags.Bool("chunked-onehot", false, "generate one-hot tile-based matrix per input chunk")
        onlyPCA := flags.Bool("pca", false, "generate pca matrix")
        pcaComponents := flags.Int("pca-components", 4, "number of PCA components")
-       maxPCATiles := flags.Int("max-pca-tiles", 100000, "maximum tiles to use as PCA input (filter, then drop every 2nd colum pair until below max)")
+       maxPCATiles := flags.Int("max-pca-tiles", 0, "maximum tiles to use as PCA input (filter, then drop every 2nd colum pair until below max)")
        debugTag := flags.Int("debug-tag", -1, "log debugging details about specified tag")
        flags.IntVar(&cmd.threads, "threads", 16, "number of memory-hungry assembly threads, and number of VCPUs to request for arvados container")
        flags.StringVar(&cmd.chi2CaseControlFile, "chi2-case-control-file", "", "tsv file or directory indicating cases and controls for Χ² test (if directory, all .tsv files will be read)")
@@ -136,6 +136,7 @@ func (cmd *sliceNumpy) run(prog string, args []string, stdin io.Reader, stdout,
                        "-chunked-onehot=" + fmt.Sprintf("%v", *onehotChunked),
                        "-pca=" + fmt.Sprintf("%v", *onlyPCA),
                        "-pca-components=" + fmt.Sprintf("%d", *pcaComponents),
+                       "-max-pca-tiles=" + fmt.Sprintf("%d", *maxPCATiles),
                        "-chi2-case-control-file=" + cmd.chi2CaseControlFile,
                        "-chi2-case-control-column=" + cmd.chi2CaseControlColumn,
                        "-chi2-p-value=" + fmt.Sprintf("%f", cmd.chi2PValue),
@@ -1123,7 +1124,7 @@ func (cmd *sliceNumpy) run(prog string, args []string, stdin io.Reader, stdout,
                        }
                        log.Printf("have %d one-hot cols", cols)
                        stride := 1
-                       for cols > *maxPCATiles*2 {
+                       for *maxPCATiles > 0 && cols > *maxPCATiles*2 {
                                cols = cols / 2
                                stride = stride * 2
                        }