Merge https://github.com/JohnLangford/vowpal_wabbit into cbify

Conflicts: vowpalwabbit/vw_dynamic.vcxproj
manofdale · Mar 16, 2016 · 2193af9 · 2193af9
2 parents 808f88c + 4faae05
commit 2193af9
Show file tree

Hide file tree

Showing 18 changed files with 3,225 additions and 570 deletions.
diff --git a/Makefile b/Makefile
@@ -131,6 +131,9 @@ test_gcov: .FORCE vw_gcov library_example_gcov
 install: $(BINARIES)
 	cd vowpalwabbit; cp $(BINARIES) /usr/local/bin; cd ../cluster; $(MAKE) install
 
+doc:
+	(cd doc && doxygen Doxyfile)
+
 clean:
 	cd vowpalwabbit && $(MAKE) clean
 	cd cluster && $(MAKE) clean
@@ -140,4 +143,4 @@ ifneq ($(JAVA_HOME),)
 	cd java    && $(MAKE) clean
 endif
 
-.PHONY: all clean install
+.PHONY: all clean install doc
diff --git a/README.md b/README.md
@@ -168,3 +168,11 @@ $ sh autogen.sh --enable-libc++
 $ make
 $ make test    # (optional)
 ```
+
+## Code Documentation
+
+To browse the code more easily, do
+
+make doc
+
+and then point your browser to doc/html/index.html .
diff --git a/doc/Doxyfile b/doc/Doxyfile
diff --git a/doc/DoxygenLayout.xml b/doc/DoxygenLayout.xml
@@ -0,0 +1,195 @@
+<doxygenlayout version="1.0">
+  <!-- Generated by doxygen 1.8.11 -->
+  <!-- Navigation index tabs for HTML output -->
+  <navindex>
+    <tab type="mainpage" visible="yes" title=""/>
+    <tab type="pages" visible="yes" title="" intro=""/>
+    <tab type="modules" visible="yes" title="" intro=""/>
+    <tab type="namespaces" visible="yes" title="">
+      <tab type="namespacelist" visible="yes" title="" intro=""/>
+      <tab type="namespacemembers" visible="yes" title="" intro=""/>
+    </tab>
+    <tab type="classes" visible="yes" title="">
+      <tab type="classlist" visible="yes" title="" intro=""/>
+      <tab type="classindex" visible="$ALPHABETICAL_INDEX" title=""/> 
+      <tab type="hierarchy" visible="yes" title="" intro=""/>
+      <tab type="classmembers" visible="yes" title="" intro=""/>
+    </tab>
+    <tab type="files" visible="yes" title="">
+      <tab type="filelist" visible="yes" title="" intro=""/>
+      <tab type="globals" visible="yes" title="" intro=""/>
+    </tab>
+    <tab type="examples" visible="yes" title="" intro=""/>  
+    <tab type="user" url="https://github.com/JohnLangford/vowpal_wabbit/wiki" title="Wiki"/>
+  </navindex>
+
+  <!-- Layout definition for a class page -->
+  <class>
+    <briefdescription visible="yes"/>
+    <includes visible="$SHOW_INCLUDE_FILES"/>
+    <inheritancegraph visible="$CLASS_GRAPH"/>
+    <collaborationgraph visible="$COLLABORATION_GRAPH"/>
+    <memberdecl>
+      <nestedclasses visible="yes" title=""/>
+      <publictypes title=""/>
+      <services title=""/>
+      <interfaces title=""/>
+      <publicslots title=""/>
+      <signals title=""/>
+      <publicmethods title=""/>
+      <publicstaticmethods title=""/>
+      <publicattributes title=""/>
+      <publicstaticattributes title=""/>
+      <protectedtypes title=""/>
+      <protectedslots title=""/>
+      <protectedmethods title=""/>
+      <protectedstaticmethods title=""/>
+      <protectedattributes title=""/>
+      <protectedstaticattributes title=""/>
+      <packagetypes title=""/>
+      <packagemethods title=""/>
+      <packagestaticmethods title=""/>
+      <packageattributes title=""/>
+      <packagestaticattributes title=""/>
+      <properties title=""/>
+      <events title=""/>
+      <privatetypes title=""/>
+      <privateslots title=""/>
+      <privatemethods title=""/>
+      <privatestaticmethods title=""/>
+      <privateattributes title=""/>
+      <privatestaticattributes title=""/>
+      <friends title=""/>
+      <related title="" subtitle=""/>
+      <membergroups visible="yes"/>
+    </memberdecl>
+    <detaileddescription title=""/>
+    <memberdef>
+      <inlineclasses title=""/>
+      <typedefs title=""/>
+      <enums title=""/>
+      <services title=""/>
+      <interfaces title=""/>
+      <constructors title=""/>
+      <functions title=""/>
+      <related title=""/>
+      <variables title=""/>
+      <properties title=""/>
+      <events title=""/>
+    </memberdef>
+    <allmemberslink visible="yes"/>
+    <usedfiles visible="$SHOW_USED_FILES"/>
+    <authorsection visible="yes"/>
+  </class>
+
+  <!-- Layout definition for a namespace page -->
+  <namespace>
+    <briefdescription visible="yes"/>
+    <memberdecl>
+      <nestednamespaces visible="yes" title=""/>
+      <constantgroups visible="yes" title=""/>
+      <classes visible="yes" title=""/>
+      <typedefs title=""/>
+      <enums title=""/>
+      <functions title=""/>
+      <variables title=""/>
+      <membergroups visible="yes"/>
+    </memberdecl>
+    <detaileddescription title=""/>
+    <memberdef>
+      <inlineclasses title=""/>
+      <typedefs title=""/>
+      <enums title=""/>
+      <functions title=""/>
+      <variables title=""/>
+    </memberdef>
+    <authorsection visible="yes"/>
+  </namespace>
+
+  <!-- Layout definition for a file page -->
+  <file>
+    <briefdescription visible="yes"/>
+    <includes visible="$SHOW_INCLUDE_FILES"/>
+    <includegraph visible="$INCLUDE_GRAPH"/>
+    <includedbygraph visible="$INCLUDED_BY_GRAPH"/>
+    <sourcelink visible="yes"/>
+    <memberdecl>
+      <classes visible="yes" title=""/>
+      <namespaces visible="yes" title=""/>
+      <constantgroups visible="yes" title=""/>
+      <defines title=""/>
+      <typedefs title=""/>
+      <enums title=""/>
+      <functions title=""/>
+      <variables title=""/>
+      <membergroups visible="yes"/>
+    </memberdecl>
+    <detaileddescription title=""/>
+    <memberdef>
+      <inlineclasses title=""/>
+      <defines title=""/>
+      <typedefs title=""/>
+      <enums title=""/>
+      <functions title=""/>
+      <variables title=""/>
+    </memberdef>
+    <authorsection/>
+  </file>
+
+  <!-- Layout definition for a group page -->
+  <group>
+    <briefdescription visible="yes"/>
+    <groupgraph visible="$GROUP_GRAPHS"/>
+    <memberdecl>
+      <nestedgroups visible="yes" title=""/>
+      <dirs visible="yes" title=""/>
+      <files visible="yes" title=""/>
+      <namespaces visible="yes" title=""/>
+      <classes visible="yes" title=""/>
+      <defines title=""/>
+      <typedefs title=""/>
+      <enums title=""/>
+      <enumvalues title=""/>
+      <functions title=""/>
+      <variables title=""/>
+      <signals title=""/>
+      <publicslots title=""/>
+      <protectedslots title=""/>
+      <privateslots title=""/>
+      <events title=""/>
+      <properties title=""/>
+      <friends title=""/>
+      <membergroups visible="yes"/>
+    </memberdecl>
+    <detaileddescription title=""/>
+    <memberdef>
+      <pagedocs/>
+      <inlineclasses title=""/>
+      <defines title=""/>
+      <typedefs title=""/>
+      <enums title=""/>
+      <enumvalues title=""/>
+      <functions title=""/>
+      <variables title=""/>
+      <signals title=""/>
+      <publicslots title=""/>
+      <protectedslots title=""/>
+      <privateslots title=""/>
+      <events title=""/>
+      <properties title=""/>
+      <friends title=""/>
+    </memberdef>
+    <authorsection visible="yes"/>
+  </group>
+
+  <!-- Layout definition for a directory page -->
+  <directory>
+    <briefdescription visible="yes"/>
+    <directorygraph visible="yes"/>
+    <memberdecl>
+      <dirs visible="yes"/>
+      <files visible="yes"/>
+    </memberdecl>
+    <detaileddescription title=""/>
+  </directory>
+</doxygenlayout>
diff --git a/doc/Makefile b/doc/Makefile
@@ -0,0 +1,3 @@
+doc:
+	cd ..; make doc ; cd doc
+
diff --git a/test/RunTests b/test/RunTests
@@ -1399,3 +1399,13 @@ printf '3 |f a b c |e x y z\n2 |f a y c |e x\n' | \
 {VW} -d train-sets/test_named_csoaa -i models/test_named_csoaa.model --audit_regressor csoaa.audit_regr
     train-sets/ref/csoaa_audit_regr.stderr
     train-sets/ref/csoaa.audit_regr
+
+# Test 119: MWT learn test
+{VW} train-sets/cb_eval --multiworld_test f --learn 2 -p mwt_learn.preds
+    train-sets/ref/mwt_learn.stderr
+    pred-sets/ref/mwt_learn.preds
+
+# Test 120: MWT learn exclude test
+{VW} train-sets/cb_eval --multiworld_test f --learn 2 --exclude_eval -p mwt_learn_exclude.preds
+    train-sets/ref/mwt_learn_exclude.stderr
+    pred-sets/ref/mwt_learn_exclude.preds
diff --git a/test/pred-sets/ref/mwt_learn.preds b/test/pred-sets/ref/mwt_learn.preds
@@ -0,0 +1,8 @@
+1 0 0
+1 0 1
+1 0 0.666667
+1 0 1
+1 0 0.8
+1 0 1
+1 0 0.857143
+1 0 1
diff --git a/test/pred-sets/ref/mwt_learn_exclude.preds b/test/pred-sets/ref/mwt_learn_exclude.preds
@@ -0,0 +1,8 @@
+1 0 0
+1 0 1
+1 0 0.666667
+1 0 1
+1 0 0.8
+1 0 1
+1 0 0.857143
+1 0 1
diff --git a/test/train-sets/ref/cb_adf_dr.stderr b/test/train-sets/ref/cb_adf_dr.stderr
@@ -9,12 +9,12 @@ num sources = 1
 average  since         example        example  current  current  current
 loss     last          counter         weight    label  predict features
 2.000000 2.000000            1            1.0    known        0...       19
-0.920996 -0.158008            2            2.0    known        1...        9
+0.905402 -0.189197            2            2.0    known        1...        9
 
 finished run
 number of examples per pass = 3
 passes used = 1
 weighted example sum = 3.000000
 weighted label sum = 0.000000
-average loss = 0.613997
+average loss = 0.603601
 total feature number = 37
diff --git a/test/train-sets/ref/mwt_learn.stderr b/test/train-sets/ref/mwt_learn.stderr
@@ -0,0 +1,22 @@
+predictions = mwt_learn.preds
+Num weight bits = 18
+learning rate = 0.5
+initial_t = 0
+power_t = 0.5
+using no cache
+Reading datafile = train-sets/cb_eval
+num sources = 1
+average  since         example        example  current  current  current
+loss     last          counter         weight    label  predict features
+0.000000 0.000000            1            1.0  unknown        1        3
+0.000000 0.000000            2            2.0  unknown        1        3
+0.000000 0.000000            4            4.0  unknown        1        3
+0.000000 0.000000            8            8.0  unknown        1        3
+
+finished run
+number of examples per pass = 8
+passes used = 1
+weighted example sum = 8.000000
+weighted label sum = 0.000000
+average loss = 0.000000
+total feature number = 24
diff --git a/test/train-sets/ref/mwt_learn_exclude.stderr b/test/train-sets/ref/mwt_learn_exclude.stderr
@@ -0,0 +1,22 @@
+predictions = mwt_learn_exclude.preds
+Num weight bits = 18
+learning rate = 0.5
+initial_t = 0
+power_t = 0.5
+using no cache
+Reading datafile = train-sets/cb_eval
+num sources = 1
+average  since         example        example  current  current  current
+loss     last          counter         weight    label  predict features
+0.000000 0.000000            1            1.0  unknown        1        3
+0.000000 0.000000            2            2.0  unknown        1        3
+0.000000 0.000000            4            4.0  unknown        1        3
+0.000000 0.000000            8            8.0  unknown        1        3
+
+finished run
+number of examples per pass = 8
+passes used = 1
+weighted example sum = 8.000000
+weighted label sum = 0.000000
+average loss = 0.000000
+total feature number = 24
diff --git a/test/train-sets/ref/rcv1_cb_eval.stderr b/test/train-sets/ref/rcv1_cb_eval.stderr
@@ -11,17 +11,17 @@ loss     last          counter         weight    label  predict features
 0.000000 0.000000            2            2.0    known        2      103
 0.000000 0.000000            4            4.0    known        2      134
 0.000000 0.000000            8            8.0    known        2      145
-0.476507 0.953014           16           16.0    known        2       23
-0.500997 0.525487           32           32.0    known        2       31
-0.581606 0.662214           64           64.0    known        2       60
-0.484693 0.387780          128          128.0    known        2      105
-0.481404 0.478114          256          256.0    known        2      122
-0.520069 0.558734          512          512.0    known        2       74
+0.476387 0.952774           16           16.0    known        2       23
+0.500349 0.524312           32           32.0    known        2       31
+0.579655 0.658960           64           64.0    known        2       60
+0.483685 0.387716          128          128.0    known        2      105
+0.480882 0.478079          256          256.0    known        2      122
+0.520439 0.559997          512          512.0    known        2       74
 
 finished run
 number of examples per pass = 1000
 passes used = 1
 weighted example sum = 1000.000000
 weighted label sum = 0.000000
-average loss = 0.507619
+average loss = 0.508724
 total feature number = 76670
diff --git a/test/train-sets/ref/rcv1_raw_cb_dm.stderr b/test/train-sets/ref/rcv1_raw_cb_dm.stderr
@@ -13,17 +13,17 @@ loss     last          counter         weight    label  predict features
 1.000000 0.000000            2            2.0    known        2      598
 0.500000 0.000000            4            4.0    known        2      784
 0.250000 0.000000            8            8.0    known        2      850
-0.620405 0.990810           16           16.0    known        2      118
-0.320962 0.021519           32           32.0    known        1      166
-0.334178 0.347393           64           64.0    known        1      340
-0.288107 0.242037          128          128.0    known        1      610
-0.234279 0.180451          256          256.0    known        2      712
-0.204043 0.173807          512          512.0    known        1      424
+0.620300 0.990600           16           16.0    known        2      118
+0.367739 0.115178           32           32.0    known        1      166
+0.355549 0.343359           64           64.0    known        1      340
+0.270033 0.184517          128          128.0    known        2      610
+0.214834 0.159635          256          256.0    known        2      712
+0.193233 0.171632          512          512.0    known        1      424
 
 finished run
 number of examples per pass = 1000
 passes used = 1
 weighted example sum = 1000.000000
 weighted label sum = 0.000000
-average loss = 0.147070
+average loss = 0.140738
 total feature number = 440020
diff --git a/test/train-sets/ref/rcv1_raw_cb_dr.stderr b/test/train-sets/ref/rcv1_raw_cb_dr.stderr
@@ -13,17 +13,17 @@ loss     last          counter         weight    label  predict features
 1.000000 0.000000            2            2.0    known        2      598
 0.500000 0.000000            4            4.0    known        2      784
 0.250000 0.000000            8            8.0    known        2      850
-0.620259 0.990518           16           16.0    known        2      118
-0.324506 0.028753           32           32.0    known        1      166
-0.334902 0.345299           64           64.0    known        1      340
-0.258627 0.182351          128          128.0    known        2      610
-0.214591 0.170556          256          256.0    known        2      712
-0.186576 0.158562          512          512.0    known        1      424
+0.620249 0.990498           16           16.0    known        2      118
+0.325918 0.031587           32           32.0    known        1      166
+0.336368 0.346819           64           64.0    known        1      340
+0.259987 0.183606          128          128.0    known        2      610
+0.215063 0.170140          256          256.0    known        2      712
+0.186591 0.158118          512          512.0    known        1      424
 
 finished run
 number of examples per pass = 1000
 passes used = 1
 weighted example sum = 1000.000000
 weighted label sum = 0.000000
-average loss = 0.129796
+average loss = 0.130576
 total feature number = 440020