Merge pull request pandas-dev#9498 from jreback/consist

Promote some code consistency in type testing methods

Author: jreback

pandas/core/categorical.py

@@ -10,15 +10,14 @@
 from pandas.core.algorithms import factorize
 from pandas.core.base import PandasObject, PandasDelegate
 from pandas.core.index import Index, _ensure_index
-from pandas.core.indexing import _is_null_slice
 from pandas.tseries.period import PeriodIndex
 import pandas.core.common as com
 from pandas.util.decorators import cache_readonly
 
 from pandas.core.common import (CategoricalDtype, ABCSeries, isnull, notnull,
                                 is_categorical_dtype, is_integer_dtype, is_object_dtype,
                                 _possibly_infer_to_datetimelike, get_dtype_kinds,
-                                is_list_like, is_sequence,
+                                is_list_like, is_sequence, is_null_slice,
                                 _ensure_platform_int, _ensure_object, _ensure_int64,
                                 _coerce_indexer_dtype, _values_from_object, take_1d)
 from pandas.util.terminal import get_terminal_size
@@ -78,11 +77,7 @@ def f(self, other):
 
     return f
 
-def _is_categorical(array):
-    """ return if we are a categorical possibility """
-    return isinstance(array, Categorical) or isinstance(array.dtype, CategoricalDtype)
-
-def _maybe_to_categorical(array):
+def maybe_to_categorical(array):
     """ coerce to a categorical if a series is given """
     if isinstance(array, ABCSeries):
         return array.values
@@ -1120,7 +1115,7 @@ def _slice(self, slicer):
         # only allow 1 dimensional slicing, but can
         # in a 2-d case be passd (slice(None),....)
         if isinstance(slicer, tuple) and len(slicer) == 2:
-            if not _is_null_slice(slicer[0]):
+            if not is_null_slice(slicer[0]):
                 raise AssertionError("invalid slicing for a 1-ndim categorical")
             slicer = slicer[1]
 
@@ -1267,7 +1262,7 @@ def __setitem__(self, key, value):
             # only allow 1 dimensional slicing, but can
             # in a 2-d case be passd (slice(None),....)
             if len(key) == 2:
-                if not _is_null_slice(key[0]):
+                if not is_null_slice(key[0]):
                     raise AssertionError("invalid slicing for a 1-ndim categorical")
                 key = key[1]
             elif len(key) == 1:

pandas/core/common.py

@@ -368,7 +368,7 @@ def notnull(obj):
         return not res
     return ~res
 
-def _is_null_datelike_scalar(other):
+def is_null_datelike_scalar(other):
     """ test whether the object is a null datelike, e.g. Nat
     but guard against passing a non-scalar """
     if other is pd.NaT or other is None:
@@ -2084,7 +2084,7 @@ def _try_timedelta(v):
     return value
 
 
-def _is_bool_indexer(key):
+def is_bool_indexer(key):
     if isinstance(key, (ABCSeries, np.ndarray)):
         if key.dtype == np.object_:
             key = np.asarray(_values_from_object(key))
@@ -2363,6 +2363,9 @@ def _maybe_make_list(obj):
         return [obj]
     return obj
 
+########################
+##### TYPE TESTING #####
+########################
 
 is_bool = lib.is_bool
 
@@ -2431,7 +2434,7 @@ def _get_dtype_type(arr_or_dtype):
     return arr_or_dtype.dtype.type
 
 
-def _is_any_int_dtype(arr_or_dtype):
+def is_any_int_dtype(arr_or_dtype):
     tipo = _get_dtype_type(arr_or_dtype)
     return issubclass(tipo, np.integer)
 
@@ -2442,7 +2445,7 @@ def is_integer_dtype(arr_or_dtype):
             not issubclass(tipo, (np.datetime64, np.timedelta64)))
 
 
-def _is_int_or_datetime_dtype(arr_or_dtype):
+def is_int_or_datetime_dtype(arr_or_dtype):
     tipo = _get_dtype_type(arr_or_dtype)
     return (issubclass(tipo, np.integer) or
             issubclass(tipo, (np.datetime64, np.timedelta64)))
@@ -2467,12 +2470,12 @@ def is_timedelta64_ns_dtype(arr_or_dtype):
     return tipo == _TD_DTYPE
 
 
-def _is_datetime_or_timedelta_dtype(arr_or_dtype):
+def is_datetime_or_timedelta_dtype(arr_or_dtype):
     tipo = _get_dtype_type(arr_or_dtype)
     return issubclass(tipo, (np.datetime64, np.timedelta64))
 
 
-needs_i8_conversion = _is_datetime_or_timedelta_dtype
+needs_i8_conversion = is_datetime_or_timedelta_dtype
 
 def i8_boxer(arr_or_dtype):
     """ return the scalar boxer for the dtype """
@@ -2493,7 +2496,7 @@ def is_float_dtype(arr_or_dtype):
     return issubclass(tipo, np.floating)
 
 
-def _is_floating_dtype(arr_or_dtype):
+def is_floating_dtype(arr_or_dtype):
     tipo = _get_dtype_type(arr_or_dtype)
     return isinstance(tipo, np.floating)
 
@@ -2502,6 +2505,10 @@ def is_bool_dtype(arr_or_dtype):
     tipo = _get_dtype_type(arr_or_dtype)
     return issubclass(tipo, np.bool_)
 
+def is_categorical(array):
+    """ return if we are a categorical possibility """
+    return isinstance(array, ABCCategorical) or isinstance(array.dtype, CategoricalDtype)
+
 def is_categorical_dtype(arr_or_dtype):
     if hasattr(arr_or_dtype,'dtype'):
         arr_or_dtype = arr_or_dtype.dtype
@@ -2537,9 +2544,13 @@ def is_re_compilable(obj):
 
 
 def is_list_like(arg):
-    return (hasattr(arg, '__iter__') and
+     return (hasattr(arg, '__iter__') and
             not isinstance(arg, compat.string_and_binary_types))
 
+def is_null_slice(obj):
+    return (isinstance(obj, slice) and obj.start is None and
+            obj.stop is None and obj.step is None)
+
 
 def is_hashable(arg):
     """Return True if hash(arg) will succeed, False otherwise.

pandas/core/frame.py

@@ -30,9 +30,9 @@
                                 is_categorical_dtype)
 from pandas.core.generic import NDFrame, _shared_docs
 from pandas.core.index import Index, MultiIndex, _ensure_index
-from pandas.core.indexing import (_maybe_droplevels,
-                                  _convert_to_index_sliceable,
-                                  _check_bool_indexer)
+from pandas.core.indexing import (maybe_droplevels,
+                                  convert_to_index_sliceable,
+                                  check_bool_indexer)
 from pandas.core.internals import (BlockManager,
                                    create_block_manager_from_arrays,
                                    create_block_manager_from_blocks)
@@ -1765,7 +1765,7 @@ def __getitem__(self, key):
             pass
 
         # see if we can slice the rows
-        indexer = _convert_to_index_sliceable(self, key)
+        indexer = convert_to_index_sliceable(self, key)
         if indexer is not None:
             return self._getitem_slice(indexer)
 
@@ -1798,7 +1798,7 @@ def _getitem_slice(self, key):
 
     def _getitem_array(self, key):
         # also raises Exception if object array with NA values
-        if com._is_bool_indexer(key):
+        if com.is_bool_indexer(key):
             # warning here just in case -- previously __setitem__ was
             # reindexing but __getitem__ was not; it seems more reasonable to
             # go with the __setitem__ behavior since that is more consistent
@@ -1809,9 +1809,9 @@ def _getitem_array(self, key):
             elif len(key) != len(self.index):
                 raise ValueError('Item wrong length %d instead of %d.' %
                                  (len(key), len(self.index)))
-            # _check_bool_indexer will throw exception if Series key cannot
+            # check_bool_indexer will throw exception if Series key cannot
             # be reindexed to match DataFrame rows
-            key = _check_bool_indexer(self.index, key)
+            key = check_bool_indexer(self.index, key)
             indexer = key.nonzero()[0]
             return self.take(indexer, axis=0, convert=False)
         else:
@@ -1822,7 +1822,7 @@ def _getitem_multilevel(self, key):
         loc = self.columns.get_loc(key)
         if isinstance(loc, (slice, Series, np.ndarray, Index)):
             new_columns = self.columns[loc]
-            result_columns = _maybe_droplevels(new_columns, key)
+            result_columns = maybe_droplevels(new_columns, key)
             if self._is_mixed_type:
                 result = self.reindex(columns=new_columns)
                 result.columns = result_columns
@@ -2097,7 +2097,7 @@ def _box_col_values(self, values, items):
     def __setitem__(self, key, value):
 
         # see if we can slice the rows
-        indexer = _convert_to_index_sliceable(self, key)
+        indexer = convert_to_index_sliceable(self, key)
         if indexer is not None:
             return self._setitem_slice(indexer, value)
 
@@ -2115,11 +2115,11 @@ def _setitem_slice(self, key, value):
 
     def _setitem_array(self, key, value):
         # also raises Exception if object array with NA values
-        if com._is_bool_indexer(key):
+        if com.is_bool_indexer(key):
             if len(key) != len(self.index):
                 raise ValueError('Item wrong length %d instead of %d!' %
                                  (len(key), len(self.index)))
-            key = _check_bool_indexer(self.index, key)
+            key = check_bool_indexer(self.index, key)
             indexer = key.nonzero()[0]
             self._check_setitem_copy()
             self.ix._setitem_with_indexer(indexer, value)
@@ -2246,7 +2246,7 @@ def reindexer(value):
             if isinstance(self.columns, MultiIndex) and key in self.columns:
                 loc = self.columns.get_loc(key)
                 if isinstance(loc, (slice, Series, np.ndarray, Index)):
-                    cols = _maybe_droplevels(self.columns[loc], key)
+                    cols = maybe_droplevels(self.columns[loc], key)
                     if len(cols) and not cols.equals(value.columns):
                         value = value.reindex_axis(cols, axis=1)
             # now align rows

pandas/core/groupby.py

@@ -25,7 +25,7 @@
                                notnull, _DATELIKE_DTYPES, is_numeric_dtype,
                                is_timedelta64_dtype, is_datetime64_dtype,
                                is_categorical_dtype, _values_from_object,
-                               _is_datetime_or_timedelta_dtype, is_bool_dtype)
+                               is_datetime_or_timedelta_dtype, is_bool_dtype)
 from pandas.core.config import option_context
 import pandas.lib as lib
 from pandas.lib import Timestamp
@@ -1491,7 +1491,7 @@ def aggregate(self, values, how, axis=0):
 
         is_numeric = is_numeric_dtype(values.dtype)
 
-        if _is_datetime_or_timedelta_dtype(values.dtype):
+        if is_datetime_or_timedelta_dtype(values.dtype):
             values = values.view('int64')
         elif is_bool_dtype(values.dtype):
             values = _algos.ensure_float64(values)