CLN: Remove miscellaneous rarely used items from pandas.compat (#25873)

xref gh-25725

Author: jschendel

pandas/_libs/parsers.pyx

@@ -1,9 +1,13 @@
 # Copyright (c) 2012, Lambda Foundry, Inc.
 # See LICENSE for the license
+import bz2
+import gzip
+import lzma
 import os
 import sys
 import time
 import warnings
+import zipfile
 
 from csv import QUOTE_MINIMAL, QUOTE_NONNUMERIC, QUOTE_NONE
 from errno import ENOENT
@@ -624,16 +628,13 @@ cdef class TextReader:
 
         if self.compression:
             if self.compression == 'gzip':
-                import gzip
                 if isinstance(source, basestring):
                     source = gzip.GzipFile(source, 'rb')
                 else:
                     source = gzip.GzipFile(fileobj=source)
             elif self.compression == 'bz2':
-                import bz2
                 source = bz2.BZ2File(source, 'rb')
             elif self.compression == 'zip':
-                import zipfile
                 zip_file = zipfile.ZipFile(source)
                 zip_names = zip_file.namelist()
 
@@ -648,8 +649,6 @@ cdef class TextReader:
                     raise ValueError('Multiple files found in compressed '
                                      'zip file %s', str(zip_names))
             elif self.compression == 'xz':
-                lzma = compat.import_lzma()
-
                 if isinstance(source, basestring):
                     source = lzma.LZMAFile(source, 'rb')
                 else:

pandas/compat/__init__.py

@@ -5,7 +5,6 @@
 Cross-compatible functions for Python 2 and 3.
 
 Key items to import for 2/3 compatible code:
-* iterators: reduce()
 * lists: lrange(), lmap(), lzip(), lfilter()
 * iterable method compatibility: iteritems, iterkeys, itervalues
   * Uses the original method if available, otherwise uses items, keys, values.
@@ -100,15 +99,6 @@ def signature(f):
                                            'varargs', 'keywords'])
         return argspec(args, defaults, varargs, keywords)
 
-    def get_range_parameters(data):
-        """Gets the start, stop, and step parameters from a range object"""
-        return data.start, data.stop, data.step
-
-    # have to explicitly put builtins into the namespace
-    intern = sys.intern
-    reduce = functools.reduce
-    unichr = chr
-
     # list-producing versions of the major Python iterating functions
     def lrange(*args, **kwargs):
         return list(range(*args, **kwargs))
@@ -122,8 +112,6 @@ def lmap(*args, **kwargs):
     def lfilter(*args, **kwargs):
         return list(filter(*args, **kwargs))
 
-    from importlib import reload
-    reload = reload
     Hashable = collections.abc.Hashable
     Iterable = collections.abc.Iterable
     Iterator = collections.abc.Iterator
@@ -149,37 +137,12 @@ def bytes_to_str(b, encoding='ascii'):
     def signature(f):
         return inspect.getargspec(f)
 
-    def get_range_parameters(data):
-        """Gets the start, stop, and step parameters from a range object"""
-        # seems we only have indexing ops to infer
-        # rather than direct accessors
-        if len(data) > 1:
-            step = data[1] - data[0]
-            stop = data[-1] + step
-            start = data[0]
-        elif len(data):
-            start = data[0]
-            stop = data[0] + 1
-            step = 1
-        else:
-            start = stop = 0
-            step = 1
-
-        return start, stop, step
-
-    # import iterator versions of these functions
-    intern = intern
-    reduce = reduce
-    unichr = unichr
-
     # Python 2-builtin ranges produce lists
     lrange = builtins.range
     lzip = builtins.zip
     lmap = builtins.map
     lfilter = builtins.filter
 
-    reload = builtins.reload
-
     Hashable = collections.Hashable
     Iterable = collections.Iterable
     Iterator = collections.Iterator
@@ -247,7 +210,6 @@ class to receive bound method
 
 if PY3:
     string_types = str,
-    class_types = type,
     text_type = str
     binary_type = bytes
 
@@ -274,11 +236,6 @@ def east_asian_len(data, encoding=None, ambiguous_width=1):
         else:
             return len(data)
 
-    def import_lzma():
-        """ import lzma from the std library """
-        import lzma
-        return lzma
-
     def set_function_name(f, name, cls):
         """ Bind the name/qualname attributes of the function """
         f.__name__ = name
@@ -289,7 +246,6 @@ def set_function_name(f, name, cls):
         return f
 else:
     string_types = basestring,
-    class_types = (type, types.ClassType)
     text_type = unicode
     binary_type = str
 
@@ -321,12 +277,6 @@ def east_asian_len(data, encoding=None, ambiguous_width=1):
         else:
             return len(data)
 
-    def import_lzma():
-        """ import the backported lzma library
-        or raise ImportError if not available """
-        from backports import lzma
-        return lzma
-
     def set_function_name(f, name, cls):
         """ Bind the name attributes of the function """
         f.__name__ = name
@@ -335,20 +285,6 @@ def set_function_name(f, name, cls):
 string_and_binary_types = string_types + (binary_type,)
 
 
-if PY2:
-    # In PY2 functools.wraps doesn't provide metadata pytest needs to generate
-    # decorated tests using parametrization. See pytest GH issue #2782
-    def wraps(wrapped, assigned=functools.WRAPPER_ASSIGNMENTS,
-              updated=functools.WRAPPER_UPDATES):
-        def wrapper(f):
-            f = functools.wraps(wrapped, assigned, updated)(f)
-            f.__wrapped__ = wrapped
-            return f
-        return wrapper
-else:
-    wraps = functools.wraps
-
-
 def add_metaclass(metaclass):
     """Class decorator for creating a class with a metaclass."""
     def wrapper(cls):

pandas/conftest.py

@@ -218,17 +218,15 @@ def all_compare_operators(request):
     return request.param
 
 
-@pytest.fixture(params=[None, 'gzip', 'bz2', 'zip',
-                        pytest.param('xz', marks=td.skip_if_no_lzma)])
+@pytest.fixture(params=[None, 'gzip', 'bz2', 'zip', 'xz'])
 def compression(request):
     """
     Fixture for trying common compression types in compression tests
     """
     return request.param
 
 
-@pytest.fixture(params=['gzip', 'bz2', 'zip',
-                        pytest.param('xz', marks=td.skip_if_no_lzma)])
+@pytest.fixture(params=['gzip', 'bz2', 'zip', 'xz'])
 def compression_only(request):
     """
     Fixture for trying common compression types in compression tests excluding

pandas/core/computation/common.py

@@ -1,6 +1,8 @@
+from functools import reduce
+
 import numpy as np
 
-from pandas.compat import reduce, string_types
+from pandas.compat import string_types
 
 import pandas as pd
 

pandas/core/computation/expr.py

@@ -2,14 +2,14 @@
 """
 
 import ast
-from functools import partial
+from functools import partial, reduce
 import itertools as it
 import operator
 import tokenize
 
 import numpy as np
 
-from pandas.compat import StringIO, lmap, reduce, string_types
+from pandas.compat import StringIO, lmap, string_types
 
 import pandas as pd
 from pandas import compat

pandas/core/indexes/range.py

@@ -7,7 +7,7 @@
 
 from pandas._libs import index as libindex, lib
 import pandas.compat as compat
-from pandas.compat import get_range_parameters, lrange
+from pandas.compat import lrange
 from pandas.compat.numpy import function as nv
 from pandas.util._decorators import Appender, cache_readonly
 
@@ -132,7 +132,7 @@ def from_range(cls, data, name=None, dtype=None, **kwargs):
                 '{0}(...) must be called with object coercible to a '
                 'range, {1} was passed'.format(cls.__name__, repr(data)))
 
-        start, stop, step = get_range_parameters(data)
+        start, stop, step = data.start, data.stop, data.step
         return RangeIndex(start, stop, step, dtype=dtype, name=name, **kwargs)
 
     @classmethod

pandas/core/internals/construction.py

@@ -10,8 +10,7 @@
 from pandas._libs import lib
 from pandas._libs.tslibs import IncompatibleFrequency
 import pandas.compat as compat
-from pandas.compat import (
-    get_range_parameters, lmap, lrange, raise_with_traceback)
+from pandas.compat import lmap, lrange, raise_with_traceback
 
 from pandas.core.dtypes.cast import (
     construct_1d_arraylike_from_scalar, construct_1d_ndarray_preserving_na,
@@ -612,8 +611,7 @@ def sanitize_array(data, index, dtype=None, copy=False,
 
     elif isinstance(data, range):
         # GH#16804
-        start, stop, step = get_range_parameters(data)
-        arr = np.arange(start, stop, step, dtype='int64')
+        arr = np.arange(data.start, data.stop, data.step, dtype='int64')
         subarr = _try_cast(arr, False, dtype, copy, raise_cast_failure)
     else:
         subarr = _try_cast(data, False, dtype, copy, raise_cast_failure)

pandas/io/common.py

@@ -1,8 +1,11 @@
 """Common IO api utilities"""
 
+import bz2
 import codecs
 from contextlib import closing, contextmanager
 import csv
+import gzip
+import lzma
 import mmap
 import os
 import zipfile
@@ -364,15 +367,13 @@ def _get_handle(path_or_buf, mode, encoding=None, compression=None,
 
         # GZ Compression
         if compression == 'gzip':
-            import gzip
             if is_path:
                 f = gzip.open(path_or_buf, mode)
             else:
                 f = gzip.GzipFile(fileobj=path_or_buf)
 
         # BZ Compression
         elif compression == 'bz2':
-            import bz2
             if is_path:
                 f = bz2.BZ2File(path_or_buf, mode)
             elif compat.PY2:
@@ -404,7 +405,6 @@ def _get_handle(path_or_buf, mode, encoding=None, compression=None,
 
         # XZ Compression
         elif compression == 'xz':
-            lzma = compat.import_lzma()
             f = lzma.LZMAFile(path_or_buf, mode)
 
         # Unrecognized Compression

pandas/io/formats/excel.py

@@ -1,14 +1,13 @@
 """Utilities for conversion to writer-agnostic Excel representation
 """
 
+from functools import reduce
 import itertools
 import re
 import warnings
 
 import numpy as np
 
-from pandas.compat import reduce
-
 from pandas.core.dtypes import missing
 from pandas.core.dtypes.common import is_float, is_scalar
 from pandas.core.dtypes.generic import ABCMultiIndex, ABCPeriodIndex

pandas/io/formats/html.py

@@ -8,11 +8,11 @@
 
 from pandas._config import get_option
 
-from pandas.compat import lzip, unichr
+from pandas.compat import lzip
 
 from pandas.core.dtypes.generic import ABCMultiIndex
 
-from pandas import compat, option_context
+from pandas import option_context
 
 from pandas.io.common import _is_url
 from pandas.io.formats.format import TableFormatter, get_level_lengths
@@ -145,7 +145,7 @@ def render(self):
         self._write_table()
 
         if self.should_show_dimensions:
-            by = chr(215) if compat.PY3 else unichr(215)  # ×
+            by = chr(215)
             self.write('<p>{rows} rows {by} {cols} columns</p>'
                        .format(rows=len(self.frame),
                                by=by,

pandas/tests/computation/test_eval.py

@@ -1,4 +1,5 @@
 from distutils.version import LooseVersion
+from functools import reduce
 from itertools import product
 import operator
 import warnings
@@ -7,7 +8,6 @@
 from numpy.random import rand, randint, randn
 import pytest
 
-from pandas.compat import reduce
 from pandas.errors import PerformanceWarning
 import pandas.util._test_decorators as td
 

pandas/tests/io/parser/test_network.py

@@ -19,12 +19,8 @@
 
 
 @pytest.mark.network
-@pytest.mark.parametrize(
-    "compress_type, extension", [
-        ('gzip', '.gz'), ('bz2', '.bz2'), ('zip', '.zip'),
-        pytest.param('xz', '.xz', marks=td.skip_if_no_lzma)
-    ]
-)
+@pytest.mark.parametrize("compress_type, extension", [
+    ('gzip', '.gz'), ('bz2', '.bz2'), ('zip', '.zip'), ('xz', '.xz')])
 @pytest.mark.parametrize('mode', ['explicit', 'infer'])
 @pytest.mark.parametrize('engine', ['python', 'c'])
 def test_compressed_urls(salaries_table, compress_type, extension, mode,

pandas/tests/io/test_html.py

@@ -1,4 +1,5 @@
 from functools import partial
+from importlib import reload
 import os
 import re
 import threading
@@ -7,7 +8,7 @@
 from numpy.random import rand
 import pytest
 
-from pandas.compat import BytesIO, StringIO, is_platform_windows, reload
+from pandas.compat import BytesIO, StringIO, is_platform_windows
 from pandas.errors import ParserError
 import pandas.util._test_decorators as td