CLN: Remove PY2/PY3 flags from pandas.compat (#26047)

* CLN: Remove PY2/PY3 flags from pandas.compat

* lint

* no longer mention py2

Author: jschendel

pandas/_libs/tslibs/parsing.pyx

@@ -11,8 +11,6 @@ from cpython.datetime cimport datetime
 
 import numpy as np
 
-import six
-
 # dateutil compat
 from dateutil.tz import (tzoffset,
                          tzlocal as _dateutil_tzlocal,
@@ -526,14 +524,8 @@ def try_parse_datetime_components(object[:] years,
 # Copyright (c) 2017 - dateutil contributors
 class _timelex(object):
     def __init__(self, instream):
-        if six.PY2:
-            # In Python 2, we can't duck type properly because unicode has
-            # a 'decode' function, and we'd be double-decoding
-            if isinstance(instream, (bytes, bytearray)):
-                instream = instream.decode()
-        else:
-            if getattr(instream, 'decode', None) is not None:
-                instream = instream.decode()
+        if getattr(instream, 'decode', None) is not None:
+            instream = instream.decode()
 
         if isinstance(instream, str):
             self.stream = instream

pandas/_version.py

@@ -14,8 +14,6 @@
 import sys
 from typing import Callable, Dict
 
-from pandas.compat import PY3
-
 
 def get_keywords():
     # these strings will be replaced by git during git-archive.
@@ -84,9 +82,7 @@ def run_command(commands, args, cwd=None, verbose=False, hide_stderr=False):
         if verbose:
             print("unable to find command, tried %s" % (commands,))
         return None
-    stdout = p.communicate()[0].strip()
-    if PY3:
-        stdout = stdout.decode()
+    stdout = p.communicate()[0].strip().decode()
     if p.returncode != 0:
         if verbose:
             print("unable to run {dispcmd} (error)".format(dispcmd=dispcmd))

pandas/compat/__init__.py

@@ -2,9 +2,9 @@
 compat
 ======
 
-Cross-compatible functions for Python 2 and 3.
+Cross-compatible functions for different versions of Python.
 
-Key items to import for 2/3 compatible code:
+Key items to import for compatible code:
 * lists: lrange(), lmap(), lzip(), lfilter()
 * iterable method compatibility: iteritems, iterkeys, itervalues
   * Uses the original method if available, otherwise uses items, keys, values.
@@ -23,8 +23,6 @@
 import platform
 import struct
 
-PY2 = sys.version_info[0] == 2
-PY3 = sys.version_info[0] >= 3
 PY36 = sys.version_info >= (3, 6)
 PY37 = sys.version_info >= (3, 7)
 PYPY = platform.python_implementation() == 'PyPy'
@@ -47,25 +45,16 @@ def lfilter(*args, **kwargs):
     return list(filter(*args, **kwargs))
 
 
-if PY2:
-    def iteritems(obj, **kw):
-        return obj.iteritems(**kw)
+def iteritems(obj, **kw):
+    return iter(obj.items(**kw))
 
-    def iterkeys(obj, **kw):
-        return obj.iterkeys(**kw)
 
-    def itervalues(obj, **kw):
-        return obj.itervalues(**kw)
+def iterkeys(obj, **kw):
+    return iter(obj.keys(**kw))
 
-else:
-    def iteritems(obj, **kw):
-        return iter(obj.items(**kw))
-
-    def iterkeys(obj, **kw):
-        return iter(obj.keys(**kw))
 
-    def itervalues(obj, **kw):
-        return iter(obj.values(**kw))
+def itervalues(obj, **kw):
+    return iter(obj.values(**kw))
 
 # ----------------------------------------------------------------------------
 # functions largely based / taken from the six module
@@ -75,42 +64,33 @@ def itervalues(obj, **kw):
 # found at https://bitbucket.org/gutworth/six
 
 
-if PY3:
-    def to_str(s):
-        """
-        Convert bytes and non-string into Python 3 str
-        """
-        if isinstance(s, bytes):
-            s = s.decode('utf-8')
-        elif not isinstance(s, str):
-            s = str(s)
-        return s
-
-    def set_function_name(f, name, cls):
-        """ Bind the name/qualname attributes of the function """
-        f.__name__ = name
-        f.__qualname__ = '{klass}.{name}'.format(
-            klass=cls.__name__,
-            name=name)
-        f.__module__ = cls.__module__
-        return f
-else:
-    def to_str(s):
-        """
-        Convert unicode and non-string into Python 2 str
-        """
-        if not isinstance(s, basestring):
-            s = str(s)
-        return s
+def to_str(s):
+    """
+    Convert bytes and non-string into Python 3 str
+    """
+    if isinstance(s, bytes):
+        s = s.decode('utf-8')
+    elif not isinstance(s, str):
+        s = str(s)
+    return s
 
-    def set_function_name(f, name, cls):
-        """ Bind the name attributes of the function """
-        f.__name__ = name
-        return f
+
+def set_function_name(f, name, cls):
+    """
+    Bind the name/qualname attributes of the function
+    """
+    f.__name__ = name
+    f.__qualname__ = '{klass}.{name}'.format(
+        klass=cls.__name__,
+        name=name)
+    f.__module__ = cls.__module__
+    return f
 
 
 def add_metaclass(metaclass):
-    """Class decorator for creating a class with a metaclass."""
+    """
+    Class decorator for creating a class with a metaclass.
+    """
     def wrapper(cls):
         orig_vars = cls.__dict__.copy()
         orig_vars.pop('__dict__', None)
@@ -121,22 +101,14 @@ def wrapper(cls):
     return wrapper
 
 
-if PY3:
-    def raise_with_traceback(exc, traceback=Ellipsis):
-        if traceback == Ellipsis:
-            _, _, traceback = sys.exc_info()
-        raise exc.with_traceback(traceback)
-else:
-    # this version of raise is a syntax error in Python 3
-    exec("""
 def raise_with_traceback(exc, traceback=Ellipsis):
+    """
+    Raise exception with existing traceback.
+    If traceback is not passed, uses sys.exc_info() to get traceback.
+    """
     if traceback == Ellipsis:
         _, _, traceback = sys.exc_info()
-    raise exc, None, traceback
-""")
-
-raise_with_traceback.__doc__ = """Raise exception with existing traceback.
-If traceback is not passed, uses sys.exc_info() to get traceback."""
+    raise exc.with_traceback(traceback)
 
 # In Python 3.7, the private re._pattern_type is removed.
 # Python 3.5+ have typing.re.Pattern

pandas/conftest.py

@@ -9,7 +9,6 @@
 import pytest
 from pytz import FixedOffset, utc
 
-from pandas.compat import PY3
 import pandas.util._test_decorators as td
 
 import pandas as pd
@@ -134,8 +133,6 @@ def observed(request):
                              '__truediv__', '__rtruediv__',
                              '__pow__', '__rpow__',
                              '__mod__', '__rmod__']
-if not PY3:
-    _all_arithmetic_operators.extend(['__div__', '__rdiv__'])
 
 
 @pytest.fixture(params=_all_arithmetic_operators)
@@ -248,12 +245,7 @@ def datetime_tz_utc():
     return timezone.utc
 
 
-utc_objs = ['utc', 'dateutil/UTC', utc, tzutc()]
-if PY3:
-    utc_objs.append(timezone.utc)
-
-
-@pytest.fixture(params=utc_objs)
+@pytest.fixture(params=['utc', 'dateutil/UTC', utc, tzutc(), timezone.utc])
 def utc_fixture(request):
     """
     Fixture to provide variants of UTC timezone strings and tzinfo objects
@@ -406,9 +398,9 @@ def tz_aware_fixture(request):
 OBJECT_DTYPES = [object, 'object']
 
 ALL_REAL_DTYPES = FLOAT_DTYPES + ALL_INT_DTYPES
-ALL_NUMPY_DTYPES = (ALL_REAL_DTYPES + COMPLEX_DTYPES + STRING_DTYPES
-                    + DATETIME_DTYPES + TIMEDELTA_DTYPES + BOOL_DTYPES
-                    + OBJECT_DTYPES + BYTES_DTYPES * PY3)  # bytes only for PY3
+ALL_NUMPY_DTYPES = (ALL_REAL_DTYPES + COMPLEX_DTYPES + STRING_DTYPES +
+                    DATETIME_DTYPES + TIMEDELTA_DTYPES + BOOL_DTYPES +
+                    OBJECT_DTYPES + BYTES_DTYPES)
 
 
 @pytest.fixture(params=STRING_DTYPES)
@@ -559,8 +551,7 @@ def any_numpy_dtype(request):
 # categoricals are handled separately
 _any_skipna_inferred_dtype = [
     ('string', ['a', np.nan, 'c']),
-    ('unicode' if not PY3 else 'string', ['a', np.nan, 'c']),
-    ('bytes' if PY3 else 'string', [b'a', np.nan, b'c']),
+    ('bytes', [b'a', np.nan, b'c']),
     ('empty', [np.nan, np.nan, np.nan]),
     ('empty', []),
     ('mixed-integer', ['a', np.nan, 2]),
@@ -592,9 +583,8 @@ def any_skipna_inferred_dtype(request):
 
     The covered (inferred) types are:
     * 'string'
-    * 'unicode' (if PY2)
     * 'empty'
-    * 'bytes' (if PY3)
+    * 'bytes'
     * 'mixed'
     * 'mixed-integer'
     * 'mixed-integer-float'

pandas/core/arrays/base.py

@@ -10,7 +10,7 @@
 
 import numpy as np
 
-from pandas.compat import PY3, set_function_name
+from pandas.compat import set_function_name
 from pandas.compat.numpy import function as nv
 from pandas.errors import AbstractMethodError
 from pandas.util._decorators import Appender, Substitution
@@ -991,10 +991,6 @@ def _add_arithmetic_ops(cls):
         cls.__rfloordiv__ = cls._create_arithmetic_method(ops.rfloordiv)
         cls.__truediv__ = cls._create_arithmetic_method(operator.truediv)
         cls.__rtruediv__ = cls._create_arithmetic_method(ops.rtruediv)
-        if not PY3:
-            cls.__div__ = cls._create_arithmetic_method(operator.div)
-            cls.__rdiv__ = cls._create_arithmetic_method(ops.rdiv)
-
         cls.__divmod__ = cls._create_arithmetic_method(divmod)
         cls.__rdivmod__ = cls._create_arithmetic_method(ops.rdivmod)
 

pandas/core/arrays/sparse.py

@@ -1593,8 +1593,6 @@ def __array_ufunc__(self, ufunc, method, *inputs, **kwargs):
 
         special = {'add', 'sub', 'mul', 'pow', 'mod', 'floordiv', 'truediv',
                    'divmod', 'eq', 'ne', 'lt', 'gt', 'le', 'ge', 'remainder'}
-        if compat.PY2:
-            special.add('div')
         aliases = {
             'subtract': 'sub',
             'multiply': 'mul',

pandas/core/arrays/timedeltas.py

@@ -566,10 +566,6 @@ def __rtruediv__(self, other):
                             .format(dtype=other.dtype,
                                     cls=type(self).__name__))
 
-    if compat.PY2:
-        __div__ = __truediv__
-        __rdiv__ = __rtruediv__
-
     def __floordiv__(self, other):
         if isinstance(other, (ABCSeries, ABCDataFrame, ABCIndexClass)):
             return NotImplemented

pandas/core/base.py

@@ -34,10 +34,8 @@
 
 
 class StringMixin(object):
-    """implements string methods so long as object defines a `__unicode__`
-    method.
-
-    Handles Python2/3 compatibility transparently.
+    """
+    Implements string methods so long as object defines a `__unicode__` method.
     """
     # side note - this could be made into a metaclass if more than one
     #             object needs
@@ -51,21 +49,12 @@ def __unicode__(self):
     def __str__(self):
         """
         Return a string representation for a particular Object
-
-        Invoked by str(df) in both py2/py3.
-        Yields Bytestring in Py2, Unicode String in py3.
         """
-
-        if compat.PY3:
-            return self.__unicode__()
-        return self.__bytes__()
+        return self.__unicode__()
 
     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._config import get_option
 
@@ -75,8 +64,6 @@ def __bytes__(self):
     def __repr__(self):
         """
         Return a string representation for a particular object.
-
-        Yields Bytestring in Py2, Unicode String in py3.
         """
         return str(self)
 
@@ -93,9 +80,6 @@ def _constructor(self):
     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/computation/ops.py

@@ -9,7 +9,6 @@
 import numpy as np
 
 from pandas._libs.tslibs import Timestamp
-from pandas.compat import PY3
 
 from pandas.core.dtypes.common import is_list_like, is_scalar
 
@@ -272,8 +271,8 @@ def _not_in(x, y):
 _bool_ops_dict = dict(zip(_bool_ops_syms, _bool_ops_funcs))
 
 _arith_ops_syms = '+', '-', '*', '/', '**', '//', '%'
-_arith_ops_funcs = (op.add, op.sub, op.mul, op.truediv if PY3 else op.div,
-                    op.pow, op.floordiv, op.mod)
+_arith_ops_funcs = (op.add, op.sub, op.mul, op.truediv, op.pow, op.floordiv,
+                    op.mod)
 _arith_ops_dict = dict(zip(_arith_ops_syms, _arith_ops_funcs))
 
 _special_case_arith_ops_syms = '**', '//', '%'
@@ -471,10 +470,9 @@ def __init__(self, lhs, rhs, truediv, *args, **kwargs):
                                                       lhs.return_type,
                                                       rhs.return_type))
 
-        if truediv or PY3:
-            # do not upcast float32s to float64 un-necessarily
-            acceptable_dtypes = [np.float32, np.float_]
-            _cast_inplace(com.flatten(self), acceptable_dtypes, np.float_)
+        # do not upcast float32s to float64 un-necessarily
+        acceptable_dtypes = [np.float32, np.float_]
+        _cast_inplace(com.flatten(self), acceptable_dtypes, np.float_)
 
 
 _unary_ops_syms = '+', '-', '~', 'not'