From 4a911410399650f2bf9582cf457fa2760846d034 Mon Sep 17 00:00:00 2001
From: Tom Clegg <tom@curii.com>
Date: Fri, 29 Apr 2022 14:57:44 -0400
Subject: [PATCH] Add -log10(pvalue) row to onehot-columns.npy output from
 slicenumpy.

closes #19014

Arvados-DCO-1.1-Signed-off-by: Tom Clegg <tom@curii.com>
---
 slice_test.go | 20 ++++++++++++++++++++
 slicenumpy.go |  5 +++--
 2 files changed, 23 insertions(+), 2 deletions(-)

diff --git a/slice_test.go b/slice_test.go
index 74e0e34519..8af51614ae 100644
--- a/slice_test.go
+++ b/slice_test.go
@@ -352,6 +352,26 @@ pipeline1dup/input2	0
 				0, 0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6, 7, 7,
 			})
 		}
+
+		f, err = os.Open(npydir + "/onehot-columns.npy")
+		c.Assert(err, check.IsNil)
+		defer f.Close()
+		npy, err = gonpy.NewReader(f)
+		c.Assert(err, check.IsNil)
+		c.Check(npy.Shape, check.DeepEquals, []int{8, 5})
+		onehotcols, err := npy.GetInt32()
+		if c.Check(err, check.IsNil) {
+			for r := 0; r < npy.Shape[0]; r++ {
+				c.Logf("%v", onehotcols[r*npy.Shape[1]:(r+1)*npy.Shape[1]])
+			}
+			c.Check(onehotcols, check.DeepEquals, []int32{
+				0, 0, 1, 4, 4, 4, 6, 6,
+				2, 3, 2, 2, 3, 4, 2, 3,
+				0, 1, 0, 0, 0, 0, 0, 0,
+				157299, 157299, 157299, 157299, 157299, 157299, 157299, 157299,
+				803273, 803273, 803273, 803273, 803273, 803273, 803273, 803273,
+			})
+		}
 	}
 }
 
diff --git a/slicenumpy.go b/slicenumpy.go
index a2e03f4944..db4b0d367b 100644
--- a/slicenumpy.go
+++ b/slicenumpy.go
@@ -1001,7 +1001,7 @@ func (cmd *sliceNumpy) RunCommand(prog string, args []string, stdin io.Reader, s
 			return 1
 		}
 		fnm = fmt.Sprintf("%s/onehot-columns.npy", *outputDir)
-		err = writeNumpyInt32(fnm, onehotXref2int32(xrefs), 4, len(xrefs))
+		err = writeNumpyInt32(fnm, onehotXref2int32(xrefs), 5, len(xrefs))
 		if err != nil {
 			return 1
 		}
@@ -1355,7 +1355,7 @@ func bool2int8(in []bool) []int8 {
 // P-value row contains 1000000x actual p-value.
 func onehotXref2int32(xrefs []onehotXref) []int32 {
 	xcols := len(xrefs)
-	xdata := make([]int32, 4*xcols)
+	xdata := make([]int32, 5*xcols)
 	for i, xref := range xrefs {
 		xdata[i] = int32(xref.tag)
 		xdata[xcols+i] = int32(xref.variant)
@@ -1363,6 +1363,7 @@ func onehotXref2int32(xrefs []onehotXref) []int32 {
 			xdata[xcols*2+i] = 1
 		}
 		xdata[xcols*3+i] = int32(xref.pvalue * 1000000)
+		xdata[xcols*4+i] = int32(-math.Log10(xref.pvalue) * 1000000)
 	}
 	return xdata
 }
-- 
2.30.2