change the regression demo data set

demo/regression/mapfeat.py

@@ -1,48 +1,21 @@
 #!/usr/bin/python
 import sys
 
-def loadfmap( fname ):
-    fmap = {}
-    nmap = {}
-    
-    for l in open( fname ):
-        arr = l.split()
-        if arr[0].find('.') != -1:            
-            idx = int( arr[0].strip('.') )
-            assert idx not in fmap        
-            fmap[ idx ] = {}
-            ftype = arr[1].strip(':')        
-            content = arr[2]
-        else:
-            content = arr[0]
-        for it in content.split(','):
-            if it.strip() == '':
-                continue
-            k , v = it.split('=')
-            fmap[ idx ][ v ] = len(nmap)
-            nmap[ len(nmap) ] = ftype+'='+k
-    return fmap, nmap
-
-def write_nmap( fo, nmap ):    
-    for i in xrange( len(nmap) ):
-        fo.write('%d\t%s\ti\n' % (i, nmap[i]) )
-
-# start here
-fmap, nmap = loadfmap( 'agaricus-lepiota.fmap' )
-fo = open( 'featmap.txt', 'w' )
-write_nmap( fo, nmap )
-fo.close()
-
-fo = open( 'agaricus.txt', 'w' ) 
-for l in open( 'agaricus-lepiota.data' ):
+fo = open( 'machine.txt', 'w' ) 
+cnt = 6
+fmap = {}
+for l in open( 'machine.data' ):
     arr = l.split(',')
-    if arr[0] == 'p':
-        fo.write('1')
-    else:
-        assert arr[0] == 'e'
-        fo.write('0')
-    for i in xrange( 1,len(arr) ):
-        fo.write( ' %d:1' % fmap[i][arr[i].strip()] )
+    fo.write(arr[8])
+    for i in xrange( 0,6 ):
+        fo.write( ' %d:%s' %(i,arr[i+2]) )
+    
+    if arr[0] not in fmap.keys():
+        fmap[arr[0]] = cnt
+        cnt += 1
+    
+    fo.write( ' %d:1' % fmap[arr[0]] )
+	
     fo.write('\n')
 
 fo.close()