infer types

Author: jreback

pandas/core/arrays/sparse.py

@@ -1907,18 +1907,17 @@ def make_sparse(arr, kind='block', fill_value=None, dtype=None, copy=False):
     index = _make_index(length, indices, kind)
     sparsified_values = arr[mask]
 
-    # careful about casting here
-    # as we could easily specify a type that cannot hold the resulting values
-    # e.g. integer when we have floats
+    # careful about casting here as we could easily specify a type that
+    # cannot hold the resulting values, e.g. integer when we have floats
+    # if we don't have an object specified then use this as the cast
     if dtype is not None:
-        try:
-            sparsified_values = astype_nansafe(
-                sparsified_values, dtype=dtype, casting='same_kind')
-        except TypeError:
-            dtype = 'float64'
-            sparsified_values = astype_nansafe(
-                sparsified_values, dtype=dtype, casting='unsafe')
 
+        ok_to_cast = all(not (is_object_dtype(t) or is_bool_dtype(t))
+                         for t in (dtype, sparsified_values.dtype))
+        if ok_to_cast:
+            dtype = find_common_type([dtype, sparsified_values.dtype])
+        sparsified_values = astype_nansafe(
+            sparsified_values, dtype=dtype)
 
     # TODO: copy
     return sparsified_values, index, fill_value

pandas/core/internals/construction.py

@@ -667,7 +667,10 @@ def sanitize_array(data, index, dtype=None, copy=False,
                 data = np.array(data, dtype=dtype, copy=False)
             subarr = np.array(data, dtype=object, copy=copy)
 
-    if is_object_dtype(subarr.dtype) and dtype != 'object':
+    if (not (is_extension_array_dtype(subarr.dtype) or
+             is_extension_array_dtype(dtype)) and
+            is_object_dtype(subarr.dtype) and
+            not is_object_dtype(dtype)):
         inferred = lib.infer_dtype(subarr, skipna=False)
         if inferred == 'period':
             try:

pandas/core/sparse/frame.py

@@ -284,20 +284,26 @@ def _unpickle_sparse_frame_compat(self, state):
     def to_dense(self):
         return SparseFrameAccessor(self).to_dense()
 
-    def _apply_columns(self, func):
+    def _apply_columns(self, func, *args, **kwargs):
         """
         Get new SparseDataFrame applying func to each columns
         """
 
-        new_data = {col: func(series)
+        new_data = {col: func(series, *args, **kwargs)
                     for col, series in self.items()}
 
         return self._constructor(
             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, **kwargs):
+
+        def f(x, dtype, **kwargs):
+            if isinstance(dtype, (dict, Series)):
+                dtype = dtype[x.name]
+            return x.astype(dtype, **kwargs)
+
+        return self._apply_columns(f, dtype=dtype, **kwargs)
 
     def copy(self, deep=True):
         """

pandas/tests/sparse/frame/test_analytics.py

@@ -55,5 +55,5 @@ def test_ufunc(data, dtype, func):
     result = func(df)
     expected = DataFrame(
         {'A': Series(func(data),
-                     dtype=dtype)})
+                     dtype=SparseDtype('float64', dtype.fill_value))})
     tm.assert_frame_equal(result, expected)

pandas/tests/sparse/series/test_analytics.py

@@ -16,5 +16,5 @@ def test_ufunc(data, dtype, func):
     s = Series(data, dtype=dtype)
     result = func(s)
     expected = Series(func(data),
-                      dtype=dtype)
+                      dtype=SparseDtype('float64', dtype.fill_value))
     tm.assert_series_equal(result, expected)