BUG: align input on setting via ix #1630

Author: changhiskhan

RELEASE.rst

@@ -70,6 +70,8 @@ pandas 0.9.0
     a class of TypeErrors that was occurring in code where the dtype of a
     column would depend on the presence of data or not (e.g. a SQL query having
     results) (#1783)
+  - Setting parts of DataFrame/Panel using ix now aligns input Series/DataFrame
+    (#1630)
 
 **Bug fixes**
 

pandas/core/indexing.py

@@ -10,6 +10,13 @@
 # "null slice"
 _NS = slice(None, None)
 
+def _is_sequence(x):
+    try:
+        iter(x)
+        assert(not isinstance(x, basestring))
+        return True
+    except Exception:
+        return False
 
 class IndexingError(Exception):
     pass
@@ -82,7 +89,7 @@ def _convert_tuple(self, key):
         return tuple(keyidx)
 
     def _setitem_with_indexer(self, indexer, value):
-        from pandas.core.frame import DataFrame
+        from pandas.core.frame import DataFrame, Series
 
         # also has the side effect of consolidating in-place
 
@@ -92,6 +99,9 @@ def _setitem_with_indexer(self, indexer, value):
             if not isinstance(indexer, tuple):
                 indexer = self._tuplify(indexer)
 
+            if isinstance(value, Series):
+                value = self._align_series(indexer, value)
+
             het_axis = self.obj._het_axis
             het_idx = indexer[het_axis]
 
@@ -117,13 +127,66 @@ def _setitem_with_indexer(self, indexer, value):
             if isinstance(indexer, tuple):
                 indexer = _maybe_convert_ix(*indexer)
 
+            if isinstance(value, Series):
+                value = self._align_series(indexer, value)
+
             if isinstance(value, DataFrame):
-                value = value.values
-                if not isinstance(self.obj, DataFrame):
-                    value = value.T
+                value = self._align_frame(indexer, value)
 
             self.obj.values[indexer] = value
 
+    def _align_series(self, indexer, ser):
+        # indexer to assign Series can be tuple or scalar
+        if isinstance(indexer, tuple):
+            for i, idx in enumerate(indexer):
+                ax = self.obj.axes[i]
+                if _is_sequence(idx) or isinstance(idx, slice):
+                    new_ix = ax[idx]
+                    if ser.index.equals(new_ix):
+                        return ser.values.copy()
+                    return ser.reindex(new_ix).values
+
+        elif np.isscalar(indexer):
+            if ser.index.equals(self.obj.index):
+                return ser.values.copy()
+            return ser.reindex(self.obj.index).values
+
+        raise ValueError('Incompatible indexer with Series')
+
+    def _align_frame(self, indexer, df):
+        from pandas import DataFrame
+        is_frame = isinstance(self.obj, DataFrame)
+        if not is_frame:
+            df = df.T
+        if isinstance(indexer, tuple):
+            idx, cols = None, None
+            for i, ix in enumerate(indexer):
+                ax = self.obj.axes[i]
+                if _is_sequence(ix) or isinstance(ix, slice):
+                    if idx is None:
+                        idx = ax[ix]
+                    elif cols is None:
+                        cols = ax[ix]
+                    else:
+                        break
+
+            if idx is not None and cols is not None:
+                if df.index.equals(idx) and df.columns.equals(cols):
+                    val = df.copy().values
+                else:
+                    val = df.reindex(idx, columns=cols).values
+                return val
+
+        elif np.isscalar(indexer) and not is_frame:
+            idx = self.obj.axes[1]
+            cols = self.obj.axes[2]
+
+            if idx.equals(df.index) and cols.equals(df.columns):
+                return df.copy().values
+            return df.reindex(idx, columns=cols).values
+
+        raise ValueError('Incompatible indexer with DataFrame')
+
     def _getitem_tuple(self, tup):
         try:
             return self._getitem_lowerdim(tup)

pandas/tests/test_frame.py

@@ -686,6 +686,40 @@ def test_setitem_fancy_mixed_2d(self):
 
         assert_frame_equal(df, expected)
 
+    def test_ix_align(self):
+        b = Series(randn(10))
+        b.sort()
+        df_orig = DataFrame(randn(10, 4))
+        df = df_orig.copy()
+
+        df.ix[:, 0] = b
+        assert_series_equal(df.ix[:, 0].reindex(b.index), b)
+
+        dft = df_orig.T
+        dft.ix[0, :] = b
+        assert_series_equal(dft.ix[0, :].reindex(b.index), b)
+
+        df = df_orig.copy()
+        df.ix[:5, 0] = b
+        s = df.ix[:5, 0]
+        assert_series_equal(s, b.reindex(s.index))
+
+        dft = df_orig.T
+        dft.ix[0, :5] = b
+        s = dft.ix[0, :5]
+        assert_series_equal(s, b.reindex(s.index))
+
+        df = df_orig.copy()
+        idx = [0, 1, 3, 5]
+        df.ix[idx, 0] = b
+        s = df.ix[idx, 0]
+        assert_series_equal(s, b.reindex(s.index))
+
+        dft = df_orig.T
+        dft.ix[0, idx] = b
+        s = dft.ix[0, idx]
+        assert_series_equal(s, b.reindex(s.index))
+
     def test_getitem_setitem_non_ix_labels(self):
         df = tm.makeTimeDataFrame()
 
@@ -976,7 +1010,7 @@ def test_setitem_single_column_mixed(self):
 
     def test_setitem_frame(self):
         piece = self.frame.ix[:2, ['A', 'B']]
-        self.frame.ix[-2:, ['A', 'B']] = piece
+        self.frame.ix[-2:, ['A', 'B']] = piece.values
         assert_almost_equal(self.frame.ix[-2:, ['A', 'B']].values,
                            piece.values)
 
@@ -985,6 +1019,14 @@ def test_setitem_frame(self):
         key = (slice(-2, None), ['A', 'B'])
         self.assertRaises(ValueError, f, key, piece)
 
+    def test_setitem_frame_align(self):
+        piece = self.frame.ix[:2, ['A', 'B']]
+        piece.index = self.frame.index[-2:]
+        piece.columns = ['A', 'B']
+        self.frame.ix[-2:, ['A', 'B']] = piece
+        assert_almost_equal(self.frame.ix[-2:, ['A', 'B']].values,
+                           piece.values)
+
     def test_setitem_fancy_exceptions(self):
         pass
 

pandas/tests/test_panel.py

@@ -583,6 +583,44 @@ def test_ix_setitem_slice_dataframe(self):
 
         assert_frame_equal(a.ix[:, 22, [111, 333]], b)
 
+    def test_ix_align(self):
+        from pandas import Series
+        b = Series(np.random.randn(10))
+        b.sort()
+        df_orig = Panel(np.random.randn(3, 10, 2))
+        df = df_orig.copy()
+
+        df.ix[0, :, 0] = b
+        assert_series_equal(df.ix[0, :, 0].reindex(b.index), b)
+
+        df = df_orig.swapaxes(0, 1)
+        df.ix[:, 0, 0] = b
+        assert_series_equal(df.ix[:, 0, 0].reindex(b.index), b)
+
+        df = df_orig.swapaxes(1, 2)
+        df.ix[0, 0, :] = b
+        assert_series_equal(df.ix[0, 0, :].reindex(b.index), b)
+
+    def test_ix_frame_align(self):
+        from pandas import DataFrame
+        df = DataFrame(np.random.randn(2, 10))
+        df.sort_index(inplace=True)
+        p_orig = Panel(np.random.randn(3, 10, 2))
+
+        p = p_orig.copy()
+        p.ix[0, :, :] = df
+        out = p.ix[0, :, :].T.reindex(df.index, columns=df.columns)
+        assert_frame_equal(out, df)
+
+        p = p_orig.copy()
+        p.ix[0] = df
+        out = p.ix[0].T.reindex(df.index, columns=df.columns)
+        assert_frame_equal(out, df)
+
+        p = p_orig.copy()
+        p.ix[0, [0, 1, 3, 5], -2:] = df
+        out = p.ix[0, [0, 1, 3, 5], -2:]
+        assert_frame_equal(out, df.T.reindex([0, 1, 3, 5], p.minor_axis[-2:]))
 
     def _check_view(self, indexer, comp):
         cp = self.panel.copy()