adding support for creating subset of a dataset.

3 files changed, 57 insertions, 0 deletions

diff --git a/AUTHORS b/AUTHORS
index bd0e0c4..309c1f5 100644
--- a/AUTHORS
+++ b/AUTHORS
@@ -28,3 +28,4 @@ Patches and Suggestions
 - Marc Abramowitz
 - Alex Gaynor
 - James Douglass
+- Rabin Nankhwa
\ No newline at end of file
diff --git a/tablib/core.py b/tablib/core.py
index 76f4569..3fc55cb 100644
--- a/tablib/core.py
+++ b/tablib/core.py
@@ -933,6 +933,42 @@ class Dataset(object):
         self.__headers = None
 
 
+    def subset(self, rows=None, cols=None):
+        """Returns a new instance of the :class:`Dataset`,
+        including only specified rows and columns.
+        """
+
+        # Don't return if no data
+        if not self:
+            return
+        
+        if rows is None:
+            rows = list(range(self.height))
+        
+        if cols is None:
+            cols = list(self.headers)
+            
+        _dset = Dataset()
+        
+        #filtering rows and columns
+        _dset.headers = list(cols)
+
+        _dset._data = []
+        for row_no, row in enumerate(self._data):
+            data_row = []
+            for key in _dset.headers:
+                if key in self.headers:
+                    pos = self.headers.index(key)
+                    data_row.append(row[pos])
+                else:
+                    raise KeyError
+
+            if row_no in rows:
+                _dset.append(row=Row(data_row))
+        
+        return _dset
+
+
 
 class Databook(object):
     """A book of :class:`Dataset` objects.
diff --git a/test_tablib.py b/test_tablib.py
index ba57170..54049b1 100755
--- a/test_tablib.py
+++ b/test_tablib.py
@@ -713,6 +713,26 @@ class TablibTestCase(unittest.TestCase):
         self.assertTrue(data[0] == new_row)
 
 
+    def test_subset(self):
+        """Create a subset of a dataset"""
+        
+        rows = (0, 2)
+        columns = ('first_name','gpa')
+        
+        data.headers = self.headers
+
+        data.append(self.john)
+        data.append(self.george)
+        data.append(self.tom)
+        
+        #Verify data is truncated
+        subset = data.subset(rows=rows, cols=columns)
+        self.assertEqual(type(subset), tablib.Dataset)
+        self.assertEqual(subset.headers, list(columns))
+        self.assertEqual(subset._data[0].list, ['John', 90])
+        self.assertEqual(subset._data[1].list, ['Thomas', 50])
+
+
     def test_formatters(self):
         """Confirm formatters are being triggered."""