From 76ae48f526cfad971ef921601a50460bbf1553a5 Mon Sep 17 00:00:00 2001
From: Bjoern Brandenburg <bbb@bbb1-cs.cs.unc.edu>
Date: Thu, 4 Sep 2008 22:12:54 -0400
Subject: add transposing of matrices(= csv files)

---
 csv_tool | 47 +++++++++++++++++++++++++++++++++++------------
 1 file changed, 35 insertions(+), 12 deletions(-)

(limited to 'csv_tool')

diff --git a/csv_tool b/csv_tool
index 455037c..10f5ee0 100755
--- a/csv_tool
+++ b/csv_tool
@@ -71,6 +71,19 @@ def row_reduce(row_op, fixup=lambda key, rows, res: res):
 row_mul = make_scalar_op(operator.mul)
 row_div = make_scalar_op(operator.div)
 
+def transpose(rows):
+    rows = list(rows)
+    if rows:
+        r = len(rows)
+        c = max([len(x) for x in rows]) 
+        def at(x, y):
+            try:
+                return rows[x][y]
+            except IndexError:
+                return 0
+        for i in xrange(c):
+            yield [at(j, i) for j in xrange(r) ]
+
 def select_by_key(rows, col, cast=None):
     by_key = defdict(list)
     order  = []
@@ -87,32 +100,42 @@ class CsvApp(defapp.App):
     def __init__(self):
         defapp.App.__init__(self, opts, defaults)
 
-    def ordered_transform(self, make_iterator):
+    def transform(self, make_iterator, ordered=True):
         """Average all rows with the same key in a given column."""
         files = list(self.args)
         del files[0]
-        try:
-            for fn in files:
+        for fn in files:
+            try:
                 # read in content
-                (order, by_key) = select_by_key(csv.reader(open(fn, 'r')),
-                                                self.options.col, float)
+                rows = csv.reader(open(fn, 'r'))
+                # set up transformation
+                if ordered:
+                    (order, by_key) = select_by_key(rows, self.options.col, float)
+                    rows = make_iterator(order, by_key)
+                else:
+                    rows = make_iterator(rows)
                 # write out
-                csv.writer(self.outfile()).writerows(make_iterator(order, by_key))
-        except IOError, ex:
-            print "Error:", ex
-        
+                csv.writer(self.outfile()).writerows(rows)
+            except IOError, ex:
+                self.err("%s:%s"  % (fn, str(ex)))
+            except IndexError, ex:
+                self.err("%s: Sorry, index out of range." % fn)
+
     def do_avg(self, _):
         def fixup_avg(key, rows, res):
             res = row_div(len(rows), res)
             res[self.options.col] = key
             return res
-        self.ordered_transform(row_reduce(row_add, fixup_avg))
+        self.transform(row_reduce(row_add, fixup_avg))
                 
     def do_max(self, _):
-        self.ordered_transform(row_reduce(row_max))
+        self.transform(row_reduce(row_max))
 
     def do_min(self, _):
-        self.ordered_transform(row_reduce(row_min))
+        self.transform(row_reduce(row_min))
+
+    def do_transpose(self, _):
+        self.transform(transpose, ordered=False)
 
 if __name__ == '__main__':
     CsvApp().launch()
-- 
cgit v1.2.2