From 9060c5f302e245f8bf1fc940440a2982b04c05da Mon Sep 17 00:00:00 2001
From: Tomas Nykodym <tomas.nykodym@gmail.com>
Date: Mon, 13 Apr 2015 15:46:25 -0700
Subject: [PATCH] Fixed ignored_columns handling in glm.

---
 smalldata/glm_test/abcd.csv     | 10 +++++-----
 src/main/java/hex/glm/GLM2.java | 28 ++++++++--------------------
 2 files changed, 13 insertions(+), 25 deletions(-)

diff --git a/smalldata/glm_test/abcd.csv b/smalldata/glm_test/abcd.csv
index 0fe0917f23..0d9038448a 100644
--- a/smalldata/glm_test/abcd.csv
+++ b/smalldata/glm_test/abcd.csv
@@ -1,5 +1,5 @@
-A B C D E
-1 0 0 0 1
-0 1 0 0 1
-0 0 1 0 1
-1 1 0 1 1
\ No newline at end of file
+A B C D E F
+1 0 0 0 1 5
+0 1 0 0 1 5
+0 0 1 0 1 5
+1 1 0 1 1 5
\ No newline at end of file
diff --git a/src/main/java/hex/glm/GLM2.java b/src/main/java/hex/glm/GLM2.java
index 0432208c9f..7cf5130809 100644
--- a/src/main/java/hex/glm/GLM2.java
+++ b/src/main/java/hex/glm/GLM2.java
@@ -434,17 +434,9 @@ private double computeIntercept(DataInfo dinfo, double ymu, Vec offset, Vec resp
       _glm = new GLMParams(family, tweedie_variance_power, link, tweedie_link_power);
       source2 = new Frame(source);
       assert sorted(ignored_cols);
-      if (offset != null) {
-        if (offset.isEnum())
-          throw new IllegalArgumentException("Categorical offsets are not supported. Can not use column '" + source2.names()[source2.find(offset)] + "' as offset");
-        int id = source.find(offset);
-        int idx = Arrays.binarySearch(ignored_cols, id);
-        if (idx >= 0) Utils.remove(ignored_cols, idx);
-        source2.remove(ignored_cols);
-        String name = source2.names()[id];
-//        source2.add(name, source2.remove(id));
-        _noffsets = 1;
-      }
+      source2.remove(ignored_cols);
+      if(offset != null)
+        source2.remove(source2.find(offset)); // remove offset and add it later explicitly (so that it does not interfere with DataInfo.prepareFrame)
       if (nlambdas == -1)
         nlambdas = 100;
       if (lambda_search && lambda.length > 1)
@@ -470,20 +462,16 @@ private double computeIntercept(DataInfo dinfo, double ymu, Vec offset, Vec resp
           //pass
       }
       toEnum = family == Family.binomial && (!response.isEnum() && (response.min() < 0 || response.max() > 1));
-      String offsetName = "";
-      int offsetId = -1;
-      if(offset != null) {
-        offsetId = source2.find(offset);
-        offsetName = source2.names()[offsetId];
-        source2.remove(offsetId);
-      }
 
       Frame fr = DataInfo.prepareFrame(source2, response, new int[0], toEnum, true, true);
-      if(offset != null){ // now put the offset just before response
+      if(offset != null){ // now put the offset just in front of response
+        int id = source.find(offset);
+        String name = source.names()[id];
         String responseName = fr.names()[fr.numCols()-1];
         Vec responseVec = fr.remove(fr.numCols()-1);
-        fr.add(offsetName, offset);
+        fr.add(name, offset);
         fr.add(responseName,responseVec);
+        _noffsets = 1;
       }
       TransformType dt = TransformType.NONE;
       if (standardize)