CLN: Refactor string methods and add PandasObject

Previous PandasObject becomes PandasContainer. New PandasObject becomes
baseclass for more elements (like Index, Categorical, etc.), moves
string methods to baseclass and subclassing objects need only define
`__unicode__` methods to get all string methods for free (and Py2/3
compatible).

CLN: Cleanup extraneous str methods from Panel

CLN: Remove unnecessary string methods from frame

CLN: Change name of TestPandasObjects --> TestPandasContainer

Author: jtratner

pandas/core/base.py

@@ -0,0 +1,53 @@
+"""
+Base class(es) for all pandas objects.
+"""
+from pandas.util import py3compat
+
+class StringMixin(object):
+    """implements string methods so long as object defines a `__unicode__` method.
+    Handles Python2/3 compatibility transparently."""
+    # side note - this could be made into a metaclass if more than one object nees
+    def __str__(self):
+        """
+        Return a string representation for a particular object.
+
+        Invoked by str(obj) in both py2/py3.
+        Yields Bytestring in Py2, Unicode String in py3.
+        """
+
+        if py3compat.PY3:
+            return self.__unicode__()
+        return self.__bytes__()
+
+    def __bytes__(self):
+        """
+        Return a string representation for a particular object.
+
+        Invoked by bytes(obj) in py3 only.
+        Yields a bytestring in both py2/py3.
+        """
+        from pandas.core.config import get_option
+
+        encoding = get_option("display.encoding")
+        return self.__unicode__().encode(encoding, 'replace')
+
+    def __repr__(self):
+        """
+        Return a string representation for a particular object.
+
+        Yields Bytestring in Py2, Unicode String in py3.
+        """
+        return str(self)
+
+class PandasObject(StringMixin):
+    """baseclass for various pandas objects"""
+
+    def __unicode__(self):
+        """
+        Return a string representation for a particular object.
+
+        Invoked by unicode(obj) in py2 only. Yields a Unicode String in both
+        py2/py3.
+        """
+        # Should be overwritten by base classes
+        return object.__repr__(self)

pandas/core/common.py

@@ -64,10 +64,10 @@ def _isnull_new(obj):
     if lib.isscalar(obj):
         return lib.checknull(obj)
 
-    from pandas.core.generic import PandasObject
+    from pandas.core.generic import PandasContainer
     if isinstance(obj, np.ndarray):
         return _isnull_ndarraylike(obj)
-    elif isinstance(obj, PandasObject):
+    elif isinstance(obj, PandasContainer):
         # TODO: optimize for DataFrame, etc.
         return obj.apply(isnull)
     elif isinstance(obj, list) or hasattr(obj, '__array__'):
@@ -91,10 +91,10 @@ def _isnull_old(obj):
     if lib.isscalar(obj):
         return lib.checknull_old(obj)
 
-    from pandas.core.generic import PandasObject
+    from pandas.core.generic import PandasContainer
     if isinstance(obj, np.ndarray):
         return _isnull_ndarraylike_old(obj)
-    elif isinstance(obj, PandasObject):
+    elif isinstance(obj, PandasContainer):
         # TODO: optimize for DataFrame, etc.
         return obj.apply(_isnull_old)
     elif isinstance(obj, list) or hasattr(obj, '__array__'):

pandas/core/frame.py

@@ -653,28 +653,6 @@ def _repr_fits_horizontal_(self,ignore_width=False):
 
         return repr_width < width
 
-    def __str__(self):
-        """
-        Return a string representation for a particular DataFrame
-
-        Invoked by str(df) in both py2/py3.
-        Yields Bytestring in Py2, Unicode String in py3.
-        """
-
-        if py3compat.PY3:
-            return self.__unicode__()
-        return self.__bytes__()
-
-    def __bytes__(self):
-        """
-        Return a string representation for a particular DataFrame
-
-        Invoked by bytes(df) in py3 only.
-        Yields a bytestring in both py2/py3.
-        """
-        encoding = com.get_option("display.encoding")
-        return self.__unicode__().encode(encoding, 'replace')
-
     def __unicode__(self):
         """
         Return a string representation for a particular DataFrame
@@ -714,14 +692,6 @@ def __unicode__(self):
 
         return value
 
-    def __repr__(self):
-        """
-        Return a string representation for a particular DataFrame
-
-        Yields Bytestring in Py2, Unicode String in py3.
-        """
-        return str(self)
-
     def _repr_html_(self):
         """
         Return a html representation for a particular DataFrame.

pandas/core/generic.py

@@ -1,20 +1,21 @@
 # pylint: disable=W0231,E1101
 
 import numpy as np
+import pandas.lib as lib
+from pandas.core.base import PandasObject
 
 from pandas.core.index import MultiIndex
 import pandas.core.indexing as indexing
 from pandas.core.indexing import _maybe_convert_indices
 from pandas.tseries.index import DatetimeIndex
 import pandas.core.common as com
-import pandas.lib as lib
 
 
 class PandasError(Exception):
     pass
 
 
-class PandasObject(object):
+class PandasContainer(PandasObject):
 
     _AXIS_NUMBERS = {
         'index': 0,
@@ -52,6 +53,12 @@ def __hash__(self):
         raise TypeError('{0!r} objects are mutable, thus they cannot be'
                               ' hashed'.format(self.__class__.__name__))
 
+    def __unicode__(self):
+        # unicode representation based upon iterating over self
+        # (since, by definition, `PandasContainers` are iterable)
+        prepr = '[%s]' % ','.join(map(com.pprint_thing, self))
+        return '%s(%s)' % (self.__class__.__name__, prepr)
+
 
     #----------------------------------------------------------------------
     # Axis name business
@@ -578,9 +585,10 @@ def to_json(self, path_or_buf=None, orient=None, date_format='epoch',
 
 # install the indexerse
 for _name, _indexer in indexing.get_indexers_list():
-    PandasObject._create_indexer(_name,_indexer)
+    PandasContainer._create_indexer(_name,_indexer)
 
-class NDFrame(PandasObject):
+
+class NDFrame(PandasContainer):
     """
     N-dimensional analogue of DataFrame. Store multi-dimensional in a
     size-mutable, labeled data structure
@@ -633,9 +641,6 @@ def _constructor(self):
     def axes(self):
         return self._data.axes
 
-    def __repr__(self):
-        return 'NDFrame'
-
     @property
     def values(self):
         return self._data.as_matrix()

pandas/core/panel.py

@@ -466,28 +466,6 @@ def __invert__(self):
     #----------------------------------------------------------------------
     # Magic methods
 
-    def __str__(self):
-        """
-        Return a string representation for a particular Panel
-
-        Invoked by str(df) in both py2/py3.
-        Yields Bytestring in Py2, Unicode String in py3.
-        """
-
-        if py3compat.PY3:
-            return self.__unicode__()
-        return self.__bytes__()
-
-    def __bytes__(self):
-        """
-        Return a string representation for a particular Panel
-
-        Invoked by bytes(df) in py3 only.
-        Yields a bytestring in both py2/py3.
-        """
-        encoding = com.get_option("display.encoding")
-        return self.__unicode__().encode(encoding, 'replace')
-
     def __unicode__(self):
         """
         Return a string representation for a particular Panel
@@ -515,14 +493,6 @@ def axis_pretty(a):
             [class_name, dims] + [axis_pretty(a) for a in self._AXIS_ORDERS])
         return output
 
-    def __repr__(self):
-        """
-        Return a string representation for a particular Panel
-
-        Yields Bytestring in Py2, Unicode String in py3.
-        """
-        return str(self)
-
     def __iter__(self):
         return iter(getattr(self, self._info_axis))
 

pandas/core/series.py

@@ -394,8 +394,7 @@ def f(self, axis=0, dtype=None, out=None, skipna=True, level=None):
 #----------------------------------------------------------------------
 # Series class
 
-
-class Series(pa.Array, generic.PandasObject):
+class Series(generic.PandasContainer, pa.Array):
     """
     One-dimensional ndarray with axis labels (including time series).
     Labels need not be unique but must be any hashable type. The object
@@ -1096,28 +1095,6 @@ def reset_index(self, level=None, drop=False, name=None, inplace=False):
 
             return df.reset_index(level=level, drop=drop)
 
-    def __str__(self):
-        """
-        Return a string representation for a particular DataFrame
-
-        Invoked by str(df) in both py2/py3.
-        Yields Bytestring in Py2, Unicode String in py3.
-        """
-
-        if py3compat.PY3:
-            return self.__unicode__()
-        return self.__bytes__()
-
-    def __bytes__(self):
-        """
-        Return a string representation for a particular DataFrame
-
-        Invoked by bytes(df) in py3 only.
-        Yields a bytestring in both py2/py3.
-        """
-        encoding = com.get_option("display.encoding")
-        return self.__unicode__().encode(encoding, 'replace')
-
     def __unicode__(self):
         """
         Return a string representation for a particular DataFrame
@@ -1142,14 +1119,6 @@ def __unicode__(self):
             raise AssertionError()
         return result
 
-    def __repr__(self):
-        """
-        Return a string representation for a particular Series
-
-        Yields Bytestring in Py2, Unicode String in py3.
-        """
-        return str(self)
-
     def _tidy_repr(self, max_vals=20):
         """
 

pandas/io/tests/test_json/test_pandas.py

@@ -33,7 +33,7 @@
 
 _mixed_frame = _frame.copy()
 
-class TestPandasObjects(unittest.TestCase):
+class TestPandasContainer(unittest.TestCase):
 
     def setUp(self):
         self.ts = tm.makeTimeSeries()
@@ -68,7 +68,7 @@ def _check_orient(df, orient, dtype=None, numpy=False, convert_axes=True, check_
                     if type(detail) == raise_ok:
                         return
                     raise
-                    
+
             unser = unser.sort()
 
             if dtype is False:
@@ -104,7 +104,7 @@ def _check_all_orients(df, dtype=None, convert_axes=True, raise_ok=None):
                 _check_orient(df, "split", dtype=dtype)
                 _check_orient(df, "index", dtype=dtype)
                 _check_orient(df, "values", dtype=dtype)
-            
+
             _check_orient(df, "columns", dtype=dtype, convert_axes=False)
             _check_orient(df, "records", dtype=dtype, convert_axes=False)
             _check_orient(df, "split", dtype=dtype, convert_axes=False)
@@ -347,7 +347,7 @@ def test_convert_dates(self):
         assert_series_equal(result,ts)
 
     def test_date_format(self):
-        
+
         df = self.tsframe.copy()
         df['date'] = Timestamp('20130101')
         df_orig = df.copy()
@@ -412,7 +412,7 @@ def test_misc_example(self):
     @network
     @slow
     def test_round_trip_exception_(self):
-		# GH 3867
+        # GH 3867
 
         df = pd.read_csv('https://raw.github.com/hayd/lahman2012/master/csvs/Teams.csv')
         s = df.to_json()
@@ -429,9 +429,9 @@ def test_url(self):
             result = read_json(url,convert_dates=True)
             for c in ['created_at','closed_at','updated_at']:
                 self.assert_(result[c].dtype == 'datetime64[ns]')
-            
+
             url = 'http://search.twitter.com/search.json?q=pandas%20python'
             result = read_json(url)
-            
+
         except urllib2.URLError:
             raise nose.SkipTest