add ability to specify keywords to astype for creation defaults

Author: jreback

doc/source/whatsnew/v0.16.0.txt

@@ -355,6 +355,16 @@ New Behavior
    cat
    cat.ordered
 
+For ease of creation of series of ``Categoricals``, we have added the ability to pass keywords when calling ``.astype()``, these
+are passed directly to the constructor.
+
+.. ipython:: python
+
+   s = Series(["a","b","c","a"]).astype('category',ordered=True)
+   s
+   s = Series(["a","b","c","a"]).astype('category',categories=list('abcdef'),ordered=False)
+   s
+
 Indexing Changes
 ~~~~~~~~~~~~~~~~
 

pandas/core/generic.py

@@ -2207,7 +2207,7 @@ def blocks(self):
         "Internal property, property synonym for as_blocks()"
         return self.as_blocks()
 
-    def astype(self, dtype, copy=True, raise_on_error=True):
+    def astype(self, dtype, copy=True, raise_on_error=True, **kwargs):
         """
         Cast object to input numpy.dtype
         Return a copy when copy = True (be really careful with this!)
@@ -2216,14 +2216,15 @@ def astype(self, dtype, copy=True, raise_on_error=True):
         ----------
         dtype : numpy.dtype or Python type
         raise_on_error : raise on invalid input
+        kwargs : keyword arguments to pass on to the constructor
 
         Returns
         -------
         casted : type of caller
         """
 
         mgr = self._data.astype(
-            dtype=dtype, copy=copy, raise_on_error=raise_on_error)
+            dtype=dtype, copy=copy, raise_on_error=raise_on_error, **kwargs)
         return self._constructor(mgr).__finalize__(self)
 
     def copy(self, deep=True):

pandas/core/internals.py

@@ -367,12 +367,12 @@ def downcast(self, dtypes=None):
 
         return blocks
 
-    def astype(self, dtype, copy=False, raise_on_error=True, values=None):
+    def astype(self, dtype, copy=False, raise_on_error=True, values=None, **kwargs):
         return self._astype(dtype, copy=copy, raise_on_error=raise_on_error,
-                            values=values)
+                            values=values, **kwargs)
 
     def _astype(self, dtype, copy=False, raise_on_error=True, values=None,
-                klass=None):
+                klass=None, **kwargs):
         """
         Coerce to the new type (if copy=True, return a new copy)
         raise on an except if raise == True
@@ -381,7 +381,7 @@ def _astype(self, dtype, copy=False, raise_on_error=True, values=None,
         # may need to convert to categorical
         # this is only called for non-categoricals
         if self.is_categorical_astype(dtype):
-            return make_block(Categorical(self.values),
+            return make_block(Categorical(self.values, **kwargs),
                               ndim=self.ndim,
                               placement=self.mgr_locs)
 
@@ -1229,8 +1229,8 @@ def to_native_types(self, slicer=None, na_rep='', float_format=None, decimal='.'
         values = np.array(values, dtype=object)
         mask = isnull(values)
         values[mask] = na_rep
-        
-        
+
+
         if float_format and decimal != '.':
             formatter = lambda v : (float_format % v).replace('.',decimal,1)
         elif decimal != '.':
@@ -1239,12 +1239,12 @@ def to_native_types(self, slicer=None, na_rep='', float_format=None, decimal='.'
             formatter = lambda v : float_format % v
         else:
             formatter = None
-            
+
         if formatter:
             imask = (~mask).ravel()
             values.flat[imask] = np.array(
                 [formatter(val) for val in values.ravel()[imask]])
-        
+
         return values.tolist()
 
     def should_store(self, value):

pandas/tests/test_categorical.py

@@ -1195,6 +1195,17 @@ def test_creation_astype(self):
         df["cats"] =  df["cats"].astype("category")
         tm.assert_frame_equal(exp_df, df)
 
+        # with keywords
+        l = ["a","b","c","a"]
+        s = pd.Series(l)
+        exp = pd.Series(Categorical(l, ordered=True))
+        res = s.astype('category', ordered=True)
+        tm.assert_series_equal(res, exp)
+
+        exp = pd.Series(Categorical(l, categories=list('abcdef'), ordered=True))
+        res = s.astype('category', categories=list('abcdef'), ordered=True)
+        tm.assert_series_equal(res, exp)
+
     def test_construction_series(self):
 
         l = [1,2,3,1]