BUG: Fix wrong SparseBlock initialization in where method

Author: Licht-T

pandas/core/internals.py

@@ -46,6 +46,7 @@
     find_common_type)
 from pandas.core.dtypes.missing import (
     isna, notna, array_equivalent,
+    na_value_for_dtype,
     _isna_compat,
     is_null_datelike_scalar)
 import pandas.core.dtypes.concat as _concat
@@ -442,12 +443,19 @@ def make_a_block(nv, ref_loc):
                     nv = _block_shape(nv, ndim=self.ndim)
                 except (AttributeError, NotImplementedError):
                     pass
-                block = self.make_block(values=nv,
-                                        placement=ref_loc, fastpath=True)
+
+                if isinstance(self, SparseBlock):
+                    block = self.make_block_same_class(values=nv,
+                                                       placement=ref_loc,
+                                                       fastpath=True)
+                else:
+                    block = self.make_block(values=nv,
+                                            placement=ref_loc,
+                                            fastpath=True)
             return block
 
         # ndim == 1
-        if self.ndim == 1:
+        if self.ndim == 1 or isinstance(self, SparseBlock):
             if mask.any():
                 nv = f(mask, new_values, None)
             else:
@@ -527,7 +535,7 @@ def f(m, v, i):
 
         return self.split_and_operate(None, f, False)
 
-    def astype(self, dtype, copy=False, errors='raise', values=None, **kwargs):
+    def astype(self, dtype, copy=True, errors='raise', values=None, **kwargs):
         return self._astype(dtype, copy=copy, errors=errors, values=values,
                             **kwargs)
 
@@ -613,7 +621,9 @@ def _can_hold_element(self, element):
             element = np.asarray(element)
             tipo = element.dtype.type
             return issubclass(tipo, dtype)
-        return isinstance(element, dtype)
+        else:
+            element_dtype = infer_dtype_from(element, pandas_dtype=True)[0]
+            return isinstance(element, dtype) or dtype == element_dtype
 
     def _try_cast_result(self, result, dtype=None):
         """ try to cast the result to our original type, we may have
@@ -1394,6 +1404,8 @@ def where(self, other, cond, align=True, raise_on_error=True,
         if not hasattr(cond, 'shape'):
             raise ValueError("where must have a condition that is ndarray "
                              "like")
+        else:
+            cond = cond.reshape(values.shape)
 
         # our where function
         def func(cond, values, other):
@@ -1440,7 +1452,13 @@ def func(cond, values, other):
             if try_cast:
                 result = self._try_cast_result(result)
 
-            return self.make_block(result)
+            if isinstance(self, SparseBlock):
+                fill_value = na_value_for_dtype(result.dtype)
+                return self.make_block_same_class(result,
+                                                  self.mgr_locs,
+                                                  fill_value=fill_value)
+            else:
+                return self.make_block(result)
 
         # might need to separate out blocks
         axis = cond.ndim - 1
@@ -1454,7 +1472,8 @@ def func(cond, values, other):
                 r = self._try_cast_result(result.take(m.nonzero()[0],
                                                       axis=axis))
                 result_blocks.append(
-                    self.make_block(r.T, placement=self.mgr_locs[m]))
+                    self.make_block_same_class(r.T,
+                                               placement=self.mgr_locs[m]))
 
         return result_blocks
 
@@ -2653,7 +2672,7 @@ def sp_index(self):
     def kind(self):
         return self.values.kind
 
-    def _astype(self, dtype, copy=False, raise_on_error=True, values=None,
+    def _astype(self, dtype, copy=True, raise_on_error=True, values=None,
                 klass=None, mgr=None, **kwargs):
         if values is None:
             values = self.values

pandas/core/sparse/frame.py

@@ -321,8 +321,8 @@ def _apply_columns(self, func):
             data=new_data, index=self.index, columns=self.columns,
             default_fill_value=self.default_fill_value).__finalize__(self)
 
-    def astype(self, dtype):
-        return self._apply_columns(lambda x: x.astype(dtype))
+    def astype(self, dtype, copy=True, errors='raise'):
+        return self._apply_columns(lambda x: x.astype(dtype, copy, errors))
 
     def copy(self, deep=True):
         """