Merge pull request #2875 from jreback/sparse

BUG: issue in get_dtype_counts for SparseDataFrame (introduced by dtypes)

Author: jreback

pandas/sparse/frame.py

@@ -42,6 +42,11 @@ def shape(self):
     def axes(self):
         return [self.sp_frame.columns, self.sp_frame.index]
 
+    @property
+    def blocks(self):
+        """ return our series in the column order """
+        s = self.sp_frame._series
+        return [ self.iget(i) for i in self.sp_frame.columns ]
 
 class SparseDataFrame(DataFrame):
     """
@@ -235,6 +240,13 @@ def to_dense(self):
         data = dict((k, v.to_dense()) for k, v in self.iteritems())
         return DataFrame(data, index=self.index)
 
+    def get_dtype_counts(self):
+        from collections import defaultdict
+        d = defaultdict(int)
+        for k, v in self.iteritems():
+            d[v.dtype.name] += 1
+        return Series(d)
+     
     def astype(self, dtype):
         raise NotImplementedError
 

pandas/sparse/tests/test_sparse.py

@@ -821,6 +821,39 @@ def test_constructor_convert_index_once(self):
         sdf = SparseDataFrame(columns=range(4), index=arr)
         self.assertTrue(sdf[0].index is sdf[1].index)
 
+    def test_constructor_from_series(self):
+
+        # GH 2873
+        x = Series(np.random.randn(10000), name='a')
+        x = x.to_sparse(fill_value=0)
+        self.assert_(isinstance(x,SparseSeries))
+        df = SparseDataFrame(x)
+        self.assert_(isinstance(df,SparseDataFrame))
+
+        x = Series(np.random.randn(10000), name ='a')
+        y = Series(np.random.randn(10000), name ='b')
+        x.ix[:9998] = 0
+        x = x.to_sparse(fill_value=0)
+        
+        # currently fails
+        #df1 = SparseDataFrame([x, y])
+
+    def test_dtypes(self):
+        df = DataFrame(np.random.randn(10000, 4))
+        df.ix[:9998] = np.nan
+        sdf = df.to_sparse()
+
+        result = sdf.get_dtype_counts()
+        expected = Series({ 'float64' : 4 })
+        assert_series_equal(result, expected)
+
+    def test_str(self):
+        df = DataFrame(np.random.randn(10000, 4))
+        df.ix[:9998] = np.nan
+        sdf = df.to_sparse()
+
+        str(sdf)
+        
     def test_array_interface(self):
         res = np.sqrt(self.frame)
         dres = np.sqrt(self.frame.to_dense())