matplotlib
diff --git a/‎examples/rec_groupby_demo.py
Copy file name to clipboardExpand all lines: examples/rec_groupby_demo.py
+12Lines changed: 12 additions & 0 deletions b/‎examples/rec_groupby_demo.py
Copy file name to clipboardExpand all lines: examples/rec_groupby_demo.py
+12Lines changed: 12 additions & 0 deletions
diff --git a/‎lib/matplotlib/mlab.py
Copy file name to clipboardExpand all lines: lib/matplotlib/mlab.py
+7Lines changed: 7 additions & 0 deletions b/‎lib/matplotlib/mlab.py
Copy file name to clipboardExpand all lines: lib/matplotlib/mlab.py
+7Lines changed: 7 additions & 0 deletions
diff --git a/‎lib/matplotlib/toolkits/exceltools.py
Copy file name to clipboardExpand all lines: lib/matplotlib/toolkits/exceltools.py
+5-1Lines changed: 5 additions & 1 deletion b/‎lib/matplotlib/toolkits/exceltools.py
Copy file name to clipboardExpand all lines: lib/matplotlib/toolkits/exceltools.py
+5-1Lines changed: 5 additions & 1 deletion
@@ -6,14 +6,20 @@
 r.sort()
 
 def daily_return(prices):
+    'an array of daily returns from price array'
     g = np.zeros_like(prices)
     g[1:] = (prices[1:]-prices[:-1])/prices[:-1]
     return g
 
 def volume_code(volume):
+    'code the continuous volume data categorically'
     ind = np.searchsorted([1e5,1e6, 5e6,10e6, 1e7], volume)
     return ind
 
+# a list of (dtype_name, summary_function, output_dtype_name).
+# rec_summarize will call on each function on the indicated recarray
+# attribute, and the result assigned to output name in the return
+# record array.
 summaryfuncs = (
     ('date', lambda x: [thisdate.year for thisdate in x], 'years'),
     ('date', lambda x: [thisdate.month for thisdate in x], 'months'),
@@ -24,13 +30,18 @@ def volume_code(volume):
 
 rsum = mlab.rec_summarize(r, summaryfuncs)
 
+# stats is a list of (dtype_name, function, output_dtype_name).
+# rec_groupby will summarize the attribute identified by the
+# dtype_name over the groups in the groupby list, and assign the
+# result to the output_dtype_name
 stats = (
     ('dreturn', len, 'rcnt'),
     ('dreturn', np.mean, 'rmean'),
     ('dreturn', np.median, 'rmedian'),
     ('dreturn', np.std, 'rsigma'),
     )
 
+# you can summarize over a single variable, like years or months
 print 'summary by years'
 ry = mlab.rec_groupby(rsum, ('years',), stats)
 print mlab. rec2txt(ry)
@@ -39,6 +50,7 @@ def volume_code(volume):
 rm = mlab.rec_groupby(rsum, ('months',), stats)
 print mlab.rec2txt(rm)
 
+# or over multiple variables like years and months
 print 'summary by year and month'
 rym = mlab.rec_groupby(rsum, ('years','months'), stats)
 print mlab.rec2txt(rym)
 
@@ -1944,6 +1944,13 @@ def safe_isnan(x):
     else: return b
 
 
+def safe_isinf(x):
+    'isnan for arbitrary types'
+    try: b = npy.isinf(x)
+    except NotImplementedError: return False
+    else: return b
+
+
 def rec_append_field(rec, name, arr, dtype=None):
     'return a new record array with field name populated with data from array arr'
     arr = npy.asarray(arr)
 
@@ -5,7 +5,7 @@
 
     import matplotlib.mlab as mlab
     import matplotlib.toolkits.exceltools as exceltools
-    
+
     r = mlab.csv2rec('somefile.csv', checkrows=0)
 
     formatd = dict(
@@ -107,6 +107,10 @@ def rec2excel(r, ws, formatd=None, rownum=0, colnum=0):
             else:
                 if mlab.safe_isnan(val):
                     ws.write(rownum, colnum+i, 'NaN')
+                elif mlab.safe_isinf(val):
+                    if val<0: sign='-'
+                    else: sign='+'
+                    ws.write(rownum, colnum+i, '%sInf'%sign)
                 else:
                     ws.write(rownum, colnum+i, val, format.xlstyle)
         rownum += 1