Merge branch 'master' of https://github.com/ncbi/tree-tool

dm/conversion/Makefile

@@ -17,6 +17,7 @@ all:	\
   attr2_2phylip \
 	obj_attr2dm \
 	pairs2dm \
+	tsv2dm
 
 
 attr2_2pairs.o:  $(DM_HPP) 
@@ -49,4 +50,9 @@ pairs2dm:	$(pairs2dmOBJS)
 	$(CXX) -o $@ $(pairs2dmOBJS) $(LIBS)
 	$(ECHO)
 
+tsv2dm.o:  $(DM_HPP) 
+tsv2dmOBJS=tsv2dm.o $(DM_OBJ) $(TSV_DIR)/tsv.o
+tsv2dm:	$(tsv2dmOBJS)
+	$(CXX) -o $@ $(tsv2dmOBJS) $(LIBS)
+	$(ECHO)
 

dm/conversion/tsv2dm.cpp

@@ -0,0 +1,136 @@
+// tsv2dm.cpp
+
+/*===========================================================================
+*
+*                            PUBLIC DOMAIN NOTICE                          
+*               National Center for Biotechnology Information
+*                                                                          
+*  This software/database is a "United States Government Work" under the   
+*  terms of the United States Copyright Act.  It was written as part of    
+*  the author's official duties as a United States Government employee and 
+*  thus cannot be copyrighted.  This software/database is freely available 
+*  to the public for use. The National Library of Medicine and the U.S.    
+*  Government have not placed any restriction on its use or reproduction.  
+*                                                                          
+*  Although all reasonable efforts have been taken to ensure the accuracy  
+*  and reliability of the software and data, the NLM and the U.S.          
+*  Government do not and cannot warrant the performance or results that    
+*  may be obtained by using this software or data. The NLM and the U.S.    
+*  Government disclaim all warranties, express or implied, including       
+*  warranties of performance, merchantability or fitness for any particular
+*  purpose.                                                                
+*                                                                          
+*  Please cite the author in any work or product based on this material.   
+*
+* ===========================================================================
+*
+* Author: Vyacheslav Brover
+*
+* File Description:
+*   Convert a .tsv-table into .dm-format
+*
+*/
+
+#undef NDEBUG
+
+#include "../../common.hpp"
+#include "../../tsv/tsv.hpp"
+using namespace Common_sp;
+#include "../dataset.hpp"
+using namespace DM_sp;
+#include "../../version.inc"
+
+#include "../../common.inc"
+
+
+
+namespace
+{
+
+
+
+struct ThisApplication : Application
+{
+  ThisApplication ()
+    : Application ("Print a .tsv-table in .dm-format")
+  	{
+      version = VERSION;
+  	  addPositional ("in", "tsv-table");
+  	  addPositional ("col", "Object name column");
+  	}
+
+
+
+	void body () const final
+	{
+		const string inFName    = getArg ("in");
+		const string objColName = getArg ("col");
+
+
+    const TextTable tt (inFName);
+    tt. qc ();
+
+    const TextTable::ColNum objCol = tt. col2num (objColName);
+
+    Dataset ds;
+    FFOR (TextTable::RowNum, i, tt. rows. size ())
+    {
+      string name (tt. rows [i] [objCol]);
+      replace (name, ' ', '_');
+      ds. appendObj (name);
+    }
+    ds. setName2objNum ();
+
+    VectorPtr<Attr1> attrs;  attrs. reserve (tt. header. size ());
+    FFOR (TextTable::ColNum, col, tt. header. size ())
+    {
+      Attr1* attr = nullptr;
+      if (col != objCol)
+      {
+        const TextTable::Header& h = tt. header [col];
+        string name (h. name);
+        replace (name, ' ', '_');
+        if (h. numeric)
+          if (h. scientific || h. decimals)
+            attr = new RealAttr1 (name, ds, h. decimals);
+          else
+            attr = new IntAttr1 (name, ds);
+        else
+          if (h. choices. size () <= TextTable::Header::choices_max)
+            attr = new NominAttr1 (name, ds);
+      }
+      attrs << attr;
+    }
+    ASSERT (attrs. size () == tt. header. size ());
+    ds. qc ();
+
+    FFOR (TextTable::RowNum, i, tt. rows. size ())
+    {
+      const StringVector& row = tt. rows [i];
+    //ASSERT (ds. getName2objNum (row [objCol]) == i);  // ' ' -> '_'
+      FFOR (TextTable::ColNum, col, tt. header. size ())
+        if (const Attr1* attr = attrs [col])
+          if (! row [col]. empty ())
+            var_cast (attr) -> str2value (i, row [col]);
+    }
+
+    ds. qc ();
+    ds. saveText (cout);    
+	}
+};
+
+
+
+}  // namespace
+
+
+
+int main (int argc, 
+          const char* argv[])
+{
+  ThisApplication app;
+  return app. run (argc, argv);
+}
+
+
+

dm/dataset.cpp

@@ -62,6 +62,8 @@ void Obj::qc () const
   Root::qc ();
 
   QC_IMPLY (! name. empty (), goodName (name));
+  QC_ASSERT (! contains (name, ' '));
+
   QC_ASSERT (mult >= 0.0); 
   QC_ASSERT (mult < inf);
 }
@@ -132,6 +134,8 @@ void Attr::qc () const
   Root::qc ();
 
   QC_ASSERT (*dsIt == this);
+  QC_ASSERT (! contains (name, ' '));
+  QC_IMPLY (! name. empty (), goodName (name));
 }
 
 
@@ -1241,7 +1245,7 @@ void CompactBoolAttr1::setAll (bool value)
 
 
 
-// NominAttr1::Dependene
+// NominAttr1::Dependence
 
 void NominAttr1::Dependence::qc () const
 {
@@ -1340,6 +1344,7 @@ void NominAttr1::summary (ostream & /*f*/) const
 void NominAttr1::str2value (size_t objNum,
                             const string &s)
 {
+#if 0
 	size_t index = missing;
   FFOR (size_t, i, categories. size ())
     if (categories [i] == s)
@@ -1356,6 +1361,9 @@ void NominAttr1::str2value (size_t objNum,
   }
 
 	values [objNum] = index;
+#else
+	values [objNum] = category2index (s);
+#endif
 }
 
 

dm/dataset.hpp

@@ -62,7 +62,8 @@ struct Obj : Root, DisjointCluster
 // Object
 {
   string name;
-    // Me be empty()
+    // May be empty()
+    // No space
   Real mult {1.0};
     // >= 0.0
     // Multiplicity (absolute frequency)
@@ -151,6 +152,7 @@ struct Attr : Root, Nocopy
 public:
   string name;
     // May be empty()
+    // No space
   bool rightAlign {false};
     // true iff the value strings are to be right-aligned 
 /*
@@ -585,6 +587,7 @@ struct BoolAttr1 : NumAttr1
 {
   typedef ebool Value;
   static const Value missing;  
+//array<bool,string> names;  ??
 
 
 protected:

dm/linreg.cpp

@@ -70,7 +70,7 @@ struct ThisApplication : Application
 
     Dataset ds (inFName);
     if (intercept)
-      ds. addRealAttr1Unit ();
+      ds. addRealAttr1Unit ("intercept");
     ds. qc ();    
 
     const auto targetAttr = checkPtr (ds. name2attr (target)) -> asRealAttr1 ();

phylogeny/data/featureTree/obj.featureTree

@@ -2,16 +2,16 @@
 
 
 # Objects:              297
-# Interior nodes:       235
+# Interior nodes:       241
 # Common core features: 0
 # Singleton features:   0
 # Other features:       907
 Genome size ave.:       487.404
 Time: Used
-Lambda_0          = 4.486e-01
-Initial time      = 7.420e-02
+Lambda_0          = 4.567e-01
+Initial time      = 7.409e-02
 timeOptimFrac     = 1.000e+00
 # Root core features = 90
 Tree length min.  = 0
-Tree length       = 73368
+Tree length       = 73180