CLN: Make more core objects inherit PandasObject

CLN: Make Categorical inherit from PandasObject

CLN: Make GroupBy inherit from PandasObject

CLN/ENH: Make Sparse* into PandasObjects

Plus get all the string methods working...

CLN: Index now a PandasObject + str method cleanup

CLN: Make tseries/index fit with PandasObject.

CLN: Use PandasObject in internals + cleanup

CLN: Make Period into a PandasObject + cleanup

CLN: Remove extraneous __repr__ from io/excel

Author: jtratner

pandas/core/categorical.py

@@ -3,6 +3,7 @@
 import numpy as np
 
 from pandas.core.algorithms import factorize
+from pandas.core.base import PandasObject
 from pandas.core.index import Index
 import pandas.core.common as com
 from pandas.core.frame import DataFrame
@@ -25,8 +26,7 @@ def f(self, other):
 
     return f
 
-
-class Categorical(object):
+class Categorical(PandasObject):
     """
     Represents a categorical variable in classic R / S-plus fashion
 
@@ -134,9 +134,9 @@ def __array__(self, dtype=None):
     def __len__(self):
         return len(self.labels)
 
-    def __repr__(self):
+    def __unicode__(self):
         temp = 'Categorical: %s\n%s\n%s'
-        values = np.asarray(self)
+        values = com.pprint_thing(np.asarray(self))
         levheader = 'Levels (%d): ' % len(self.levels)
         levstring = np.array_repr(self.levels,
                                   max_line_width=60)
@@ -145,9 +145,9 @@ def __repr__(self):
         lines = levstring.split('\n')
         levstring = '\n'.join([lines[0]] +
                               [indent + x.lstrip() for x in lines[1:]])
+        name = '' if self.name is None else self.name
+        return temp % (name, values, levheader + levstring)
 
-        return temp % ('' if self.name is None else self.name,
-                       repr(values), levheader + levstring)
 
     def __getitem__(self, key):
         if isinstance(key, (int, np.integer)):

pandas/core/groupby.py

@@ -2,6 +2,7 @@
 import types
 import numpy as np
 
+from pandas.core.base import PandasObject
 from pandas.core.categorical import Categorical
 from pandas.core.frame import DataFrame
 from pandas.core.generic import NDFrame
@@ -100,7 +101,7 @@ def _last(x):
         return _last(x)
 
 
-class GroupBy(object):
+class GroupBy(PandasObject):
     """
     Class for grouping and aggregating relational data. See aggregate,
     transform, and apply functions on this object.
@@ -201,6 +202,10 @@ def __init__(self, obj, keys=None, axis=0, level=None,
     def __len__(self):
         return len(self.indices)
 
+    def __unicode__(self):
+        # TODO: Better unicode/repr for GroupBy object
+        return object.__repr__(self)
+
     @property
     def groups(self):
         return self.grouper.groups

pandas/core/index.py

@@ -9,6 +9,7 @@
 import pandas.algos as _algos
 import pandas.index as _index
 from pandas.lib import Timestamp
+from pandas.core.base import PandasObject
 
 from pandas.util.decorators import cache_readonly
 from pandas.core.common import isnull
@@ -47,7 +48,7 @@ def _shouldbe_timestamp(obj):
             or tslib.is_timestamp_array(obj))
 
 
-class Index(np.ndarray):
+class Index(PandasObject, np.ndarray):
     """
     Immutable ndarray implementing an ordered, sliceable set. The basic object
     storing axis labels for all pandas objects
@@ -142,28 +143,6 @@ def __array_finalize__(self, obj):
     def _shallow_copy(self):
         return self.view()
 
-    def __str__(self):
-        """
-        Return a string representation for a particular Index
-
-        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 Index
-
-        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 Index
@@ -173,14 +152,6 @@ def __unicode__(self):
         prepr = com.pprint_thing(self, escape_chars=('\t', '\r', '\n'),quote_strings=True)
         return '%s(%s, dtype=%s)' % (type(self).__name__, prepr, self.dtype)
 
-    def __repr__(self):
-        """
-        Return a string representation for a particular Index
-
-        Yields Bytestring in Py2, Unicode String in py3.
-        """
-        return str(self)
-
     def to_series(self):
         """
         return a series with both index and values equal to the index keys
@@ -1531,28 +1502,6 @@ def _array_values(self):
     def dtype(self):
         return np.dtype('O')
 
-    def __str__(self):
-        """
-        Return a string representation for a particular Index
-
-        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 Index
-
-        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 Index
@@ -1566,14 +1515,6 @@ def __unicode__(self):
 
         return output % summary
 
-    def __repr__(self):
-        """
-        Return a string representation for a particular Index
-
-        Yields Bytestring in Py2, Unicode String in py3.
-        """
-        return str(self)
-
     def __len__(self):
         return len(self.labels[0])
 

pandas/core/internals.py

@@ -4,6 +4,7 @@
 
 from numpy import nan
 import numpy as np
+from pandas.core.base import PandasObject
 
 from pandas.core.common import (_possibly_downcast_to_dtype, isnull, _NS_DTYPE,
                                 _TD_DTYPE)
@@ -19,7 +20,7 @@
 from pandas.util import py3compat
 
 
-class Block(object):
+class Block(PandasObject):
     """
     Canonical n-dimensional unit of homogeneous dtype contained in a pandas
     data structure
@@ -91,14 +92,12 @@ def set_ref_items(self, ref_items, maybe_rename=True):
             self.items = ref_items.take(self.ref_locs)
         self.ref_items = ref_items
 
-    def __repr__(self):
+    def __unicode__(self):
         shape = ' x '.join([com.pprint_thing(s) for s in self.shape])
         name = type(self).__name__
         result = '%s: %s, %s, dtype %s' % (
             name, com.pprint_thing(self.items), shape, self.dtype)
-        if py3compat.PY3:
-            return unicode(result)
-        return com.console_encode(result)
+        return result
 
     def __contains__(self, item):
         return item in self.items
@@ -969,7 +968,7 @@ def make_block(values, items, ref_items, klass=None, fastpath=False, placement=N
 # TODO: flexible with index=None and/or items=None
 
 
-class BlockManager(object):
+class BlockManager(PandasObject):
     """
     Core internal data structure to implement DataFrame
 
@@ -1213,7 +1212,7 @@ def __setstate__(self, state):
     def __len__(self):
         return len(self.items)
 
-    def __repr__(self):
+    def __unicode__(self):
         output = 'BlockManager'
         for i, ax in enumerate(self.axes):
             if i == 0:
@@ -1222,7 +1221,7 @@ def __repr__(self):
                 output += '\nAxis %d: %s' % (i, ax)
 
         for block in self.blocks:
-            output += '\n%s' % repr(block)
+            output += '\n%s' % com.pprint_thing(block)
         return output
 
     @property

pandas/io/excel.py

@@ -73,9 +73,6 @@ def __init__(self, path_or_buf, kind=None, **kwds):
             data = path_or_buf.read()
             self.book = xlrd.open_workbook(file_contents=data)
 
-    def __repr__(self):
-        return object.__repr__(self)
-
     def parse(self, sheetname, header=0, skiprows=None, skip_footer=0,
               index_col=None, parse_cols=None, parse_dates=False,
               date_parser=None, na_values=None, thousands=None, chunksize=None,

pandas/sparse/array.py

@@ -8,6 +8,7 @@
 import numpy as np
 
 import operator
+from pandas.core.base import PandasObject
 import pandas.core.common as com
 
 from pandas.util import py3compat
@@ -86,8 +87,7 @@ def _sparse_fillop(this, other, name):
 
     return result, result_index
 
-
-class SparseArray(np.ndarray):
+class SparseArray(PandasObject, np.ndarray):
     """Data structure for labeled, sparse floating point data
 
 Parameters
@@ -184,9 +184,9 @@ def __setstate__(self, state):
     def __len__(self):
         return self.sp_index.length
 
-    def __repr__(self):
-        return '%s\n%s' % (np.ndarray.__repr__(self),
-                           repr(self.sp_index))
+    def __unicode__(self):
+        return '%s\n%s' % (com.pprint_thing(self),
+                           com.pprint_thing(self.sp_index))
 
     # Arithmetic operators
 

pandas/sparse/list.py

@@ -1,10 +1,12 @@
 import numpy as np
+from pandas.core.base import PandasObject
+from pandas.core.common import pprint_thing
 
 from pandas.sparse.array import SparseArray
 import pandas._sparse as splib
 
 
-class SparseList(object):
+class SparseList(PandasObject):
     """
     Data structure for accumulating data to be converted into a
     SparseArray. Has similar API to the standard Python list
@@ -21,9 +23,9 @@ def __init__(self, data=None, fill_value=np.nan):
         if data is not None:
             self.append(data)
 
-    def __repr__(self):
+    def __unicode__(self):
         contents = '\n'.join(repr(c) for c in self._chunks)
-        return '%s\n%s' % (object.__repr__(self), contents)
+        return '%s\n%s' % (object.__repr__(self), pprint_thing(contents))
 
     def __len__(self):
         return sum(len(c) for c in self._chunks)

pandas/sparse/series.py

@@ -241,8 +241,9 @@ def __setstate__(self, state):
     def __len__(self):
         return self.sp_index.length
 
-    def __repr__(self):
-        series_rep = Series.__repr__(self)
+    def __unicode__(self):
+        # currently, unicode is same as repr...fixes infinite loop
+        series_rep = Series.__unicode__(self)
         rep = '%s\n%s' % (series_rep, repr(self.sp_index))
         return rep
 

pandas/tseries/index.py

@@ -488,7 +488,7 @@ def _mpl_repr(self):
         # how to represent ourselves to matplotlib
         return tslib.ints_to_pydatetime(self.asi8, self.tz)
 
-    def __repr__(self):
+    def __unicode__(self):
         from pandas.core.format import _format_datetime64
         values = self.values
 
@@ -514,8 +514,6 @@ def __repr__(self):
 
         return summary
 
-    __str__ = __repr__
-
     def __reduce__(self):
         """Necessary for making this object picklable"""
         object_state = list(np.ndarray.__reduce__(self))

pandas/tseries/period.py

@@ -3,6 +3,7 @@
 
 from datetime import datetime, date
 import numpy as np
+from pandas.core.base import PandasObject
 
 import pandas.tseries.offsets as offsets
 from pandas.tseries.frequencies import (get_freq_code as _gfc,
@@ -40,7 +41,7 @@ def f(self):
     return property(f)
 
 
-class Period(object):
+class Period(PandasObject):
     """
     Represents an period of time
 
@@ -272,28 +273,6 @@ def __repr__(self):
 
         return "Period('%s', '%s')" % (formatted, freqstr)
 
-    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
@@ -303,9 +282,7 @@ def __unicode__(self):
         """
         base, mult = _gfc(self.freq)
         formatted = tslib.period_format(self.ordinal, base)
-        value = (u"%s" % formatted)
-        assert type(value) == unicode
-
+        value = ("%s" % formatted)
         return value