CLN;: remove compat.lzip (#26311)

xref gh-25725

Author: topper-123

pandas/compat/__init__.py

@@ -5,7 +5,7 @@
 Cross-compatible functions for different versions of Python.
 
 Key items to import for compatible code:
-* lists: lrange(), lmap(), lzip()
+* lists: lrange(), lmap()
 
 Other items:
 * platform checker
@@ -24,10 +24,6 @@ def lrange(*args, **kwargs):
     return list(range(*args, **kwargs))
 
 
-def lzip(*args, **kwargs):
-    return list(zip(*args, **kwargs))
-
-
 def lmap(*args, **kwargs):
     return list(map(*args, **kwargs))
 

pandas/core/arrays/categorical.py

@@ -7,7 +7,6 @@
 from pandas._config import get_option
 
 from pandas._libs import algos as libalgos, lib
-from pandas.compat import lzip
 from pandas.compat.numpy import function as nv
 from pandas.util._decorators import (
     Appender, Substitution, cache_readonly, deprecate_kwarg)
@@ -2706,4 +2705,4 @@ def _factorize_from_iterables(iterables):
     if len(iterables) == 0:
         # For consistency, it should return a list of 2 lists.
         return [[], []]
-    return map(list, lzip(*[_factorize_from_iterable(it) for it in iterables]))
+    return map(list, zip(*(_factorize_from_iterable(it) for it in iterables)))

pandas/core/frame.py

@@ -31,7 +31,7 @@
 from pandas.util._validators import (validate_bool_kwarg,
                                      validate_axis_style_args)
 
-from pandas.compat import PY36, lmap, lzip, raise_with_traceback
+from pandas.compat import PY36, lmap, raise_with_traceback
 from pandas.compat.numpy import function as nv
 from pandas.core.dtypes.cast import (
     maybe_upcast,
@@ -1752,7 +1752,7 @@ def from_items(cls, items, columns=None, orient='columns'):
                       "preserve the key order.",
                       FutureWarning, stacklevel=2)
 
-        keys, values = lzip(*items)
+        keys, values = zip(*items)
 
         if orient == 'columns':
             if columns is not None:
@@ -4433,7 +4433,7 @@ def _maybe_casted_values(index, labels=None):
             if isinstance(self.index, MultiIndex):
                 names = [n if n is not None else ('level_%d' % i)
                          for (i, n) in enumerate(self.index.names)]
-                to_insert = lzip(self.index.levels, self.index.codes)
+                to_insert = zip(self.index.levels, self.index.codes)
             else:
                 default = 'index' if 'index' not in self else 'level_0'
                 names = ([default] if self.index.name is None

pandas/core/generic.py

@@ -15,7 +15,7 @@
 from pandas._config import config
 
 from pandas._libs import Timestamp, iNaT, properties
-from pandas.compat import lzip, set_function_name, to_str
+from pandas.compat import set_function_name, to_str
 from pandas.compat.numpy import function as nv
 from pandas.errors import AbstractMethodError
 from pandas.util._decorators import (
@@ -6546,7 +6546,7 @@ def replace(self, to_replace=None, value=None, inplace=False, limit=None,
                 regex = True
 
             items = list(to_replace.items())
-            keys, values = lzip(*items) or ([], [])
+            keys, values = zip(*items) if items else ([], [])
 
             are_mappings = [is_dict_like(v) for v in values]
 
@@ -6560,7 +6560,7 @@ def replace(self, to_replace=None, value=None, inplace=False, limit=None,
                 value_dict = {}
 
                 for k, v in items:
-                    keys, values = lzip(*v.items()) or ([], [])
+                    keys, values = list(zip(*v.items())) or ([], [])
                     if set(keys) & set(values):
                         raise ValueError("Replacement not allowed with "
                                          "overlapping keys and values")

pandas/core/groupby/generic.py

@@ -15,7 +15,6 @@
 import numpy as np
 
 from pandas._libs import Timestamp, lib
-from pandas.compat import lzip
 from pandas.errors import AbstractMethodError
 from pandas.util._decorators import Appender, Substitution
 
@@ -781,13 +780,13 @@ def _aggregate_multiple_funcs(self, arg, _level):
                     FutureWarning, stacklevel=3)
 
             columns = list(arg.keys())
-            arg = list(arg.items())
+            arg = arg.items()
         elif any(isinstance(x, (tuple, list)) for x in arg):
             arg = [(x, x) if not isinstance(x, (tuple, list)) else x
                    for x in arg]
 
             # indicated column order
-            columns = lzip(*arg)[0]
+            columns = next(zip(*arg))
         else:
             # list of functions / function names
             columns = []
@@ -797,7 +796,7 @@ def _aggregate_multiple_funcs(self, arg, _level):
                 else:
                     # protect against callables without names
                     columns.append(com.get_callable_name(f))
-            arg = lzip(columns, arg)
+            arg = zip(columns, arg)
 
         results = OrderedDict()
         for name, func in arg:

pandas/core/groupby/ops.py

@@ -13,7 +13,6 @@
 from pandas._libs import NaT, iNaT, lib
 import pandas._libs.groupby as libgroupby
 import pandas._libs.reduction as reduction
-from pandas.compat import lzip
 from pandas.errors import AbstractMethodError
 from pandas.util._decorators import cache_readonly
 
@@ -259,7 +258,7 @@ def groups(self):
         if len(self.groupings) == 1:
             return self.groupings[0].groups
         else:
-            to_groupby = lzip(*(ping.grouper for ping in self.groupings))
+            to_groupby = zip(*(ping.grouper for ping in self.groupings))
             to_groupby = Index(to_groupby)
             return self.axis.groupby(to_groupby)
 

pandas/core/indexes/multi.py

@@ -9,7 +9,6 @@
 
 from pandas._libs import (
     Timestamp, algos as libalgos, index as libindex, lib, tslibs)
-from pandas.compat import lzip
 from pandas.compat.numpy import function as nv
 from pandas.errors import PerformanceWarning, UnsortedIndexError
 from pandas.util._decorators import Appender, cache_readonly, deprecate_kwarg
@@ -402,7 +401,7 @@ def from_tuples(cls, tuples, sortorder=None, names=None):
         elif isinstance(tuples, list):
             arrays = list(lib.to_object_array_tuples(tuples).T)
         else:
-            arrays = lzip(*tuples)
+            arrays = zip(*tuples)
 
         return MultiIndex.from_arrays(arrays, sortorder=sortorder, names=names)
 
@@ -511,7 +510,7 @@ def from_frame(cls, df, sortorder=None, names=None):
         if not isinstance(df, ABCDataFrame):
             raise TypeError("Input must be a DataFrame")
 
-        column_names, columns = lzip(*df.iteritems())
+        column_names, columns = zip(*df.iteritems())
         names = column_names if names is None else names
         return cls.from_arrays(columns, sortorder=sortorder, names=names)
 
@@ -2941,7 +2940,7 @@ def union(self, other, sort=None):
                                                 other._ndarray_values],
                                                sort=sort)
 
-        return MultiIndex.from_arrays(lzip(*uniq_tuples), sortorder=0,
+        return MultiIndex.from_arrays(zip(*uniq_tuples), sortorder=0,
                                       names=result_names)
 
     def intersection(self, other, sort=False):
@@ -2984,7 +2983,7 @@ def intersection(self, other, sort=False):
                               codes=[[]] * self.nlevels,
                               names=result_names, verify_integrity=False)
         else:
-            return MultiIndex.from_arrays(lzip(*uniq_tuples), sortorder=0,
+            return MultiIndex.from_arrays(zip(*uniq_tuples), sortorder=0,
                                           names=result_names)
 
     def difference(self, other, sort=None):
@@ -3152,7 +3151,7 @@ def isin(self, values, level=None):
 
 
 def _sparsify(label_list, start=0, sentinel=''):
-    pivoted = lzip(*label_list)
+    pivoted = list(zip(*label_list))
     k = len(label_list)
 
     result = pivoted[:start + 1]
@@ -3176,7 +3175,7 @@ def _sparsify(label_list, start=0, sentinel=''):
 
         prev = cur
 
-    return lzip(*result)
+    return list(zip(*result))
 
 
 def _get_na_rep(dtype):

pandas/core/reshape/concat.py

@@ -6,7 +6,7 @@
 
 import pandas.core.dtypes.concat as _concat
 
-from pandas import DataFrame, Index, MultiIndex, Series, compat
+from pandas import DataFrame, Index, MultiIndex, Series
 from pandas.core import common as com
 from pandas.core.arrays.categorical import (
     _factorize_from_iterable, _factorize_from_iterables)
@@ -536,7 +536,7 @@ def _make_concat_multiindex(indexes, keys, levels=None, names=None):
 
     if ((levels is None and isinstance(keys[0], tuple)) or
             (levels is not None and len(levels) > 1)):
-        zipped = compat.lzip(*keys)
+        zipped = list(zip(*keys))
         if names is None:
             names = [None] * len(zipped)
 

pandas/core/reshape/merge.py

@@ -9,7 +9,6 @@
 import numpy as np
 
 from pandas._libs import hashtable as libhashtable, join as libjoin, lib
-from pandas.compat import lzip
 from pandas.errors import MergeError
 from pandas.util._decorators import Appender, Substitution
 
@@ -1512,7 +1511,7 @@ def flip(xs):
             labels = list(string.ascii_lowercase[:len(xs)])
             dtypes = [x.dtype for x in xs]
             labeled_dtypes = list(zip(labels, dtypes))
-            return np.array(lzip(*xs), labeled_dtypes)
+            return np.array(list(zip(*xs)), labeled_dtypes)
 
         # values to compare
         left_values = (self.left.index.values if self.left_index else

pandas/io/formats/format.py

@@ -15,7 +15,6 @@
 from pandas._libs import lib
 from pandas._libs.tslib import format_array_from_datetime
 from pandas._libs.tslibs import NaT, Timedelta, Timestamp, iNaT
-from pandas.compat import lzip
 
 from pandas.core.dtypes.common import (
     is_categorical_dtype, is_complex_dtype, is_datetime64_dtype,
@@ -753,7 +752,7 @@ def _get_formatted_column_labels(self, frame):
 
         if isinstance(columns, ABCMultiIndex):
             fmt_columns = columns.format(sparsify=False, adjoin=False)
-            fmt_columns = lzip(*fmt_columns)
+            fmt_columns = list(zip(*fmt_columns))
             dtypes = self.frame.dtypes._values
 
             # if we have a Float level, they don't use leading space at all

pandas/io/formats/html.py

@@ -7,8 +7,6 @@
 
 from pandas._config import get_option
 
-from pandas.compat import lzip
-
 from pandas.core.dtypes.generic import ABCMultiIndex
 
 from pandas import option_context
@@ -414,7 +412,7 @@ def _write_hierarchical_rows(self, fmt_values, indent):
 
         idx_values = frame.index.format(sparsify=False, adjoin=False,
                                         names=False)
-        idx_values = lzip(*idx_values)
+        idx_values = list(zip(*idx_values))
 
         if self.fmt.sparsify:
             # GH3547

pandas/io/parsers.py

@@ -18,7 +18,6 @@
 import pandas._libs.parsers as parsers
 from pandas._libs.tslibs import parsing
 import pandas.compat as compat
-from pandas.compat import lzip
 from pandas.errors import (
     AbstractMethodError, EmptyDataError, ParserError, ParserWarning)
 from pandas.util._decorators import Appender
@@ -1489,7 +1488,7 @@ def _extract_multi_indexer_columns(self, header, index_names, col_names,
         def extract(r):
             return tuple(r[i] for i in range(field_count) if i not in sic)
 
-        columns = lzip(*[extract(r) for r in header])
+        columns = list(zip(*(extract(r) for r in header)))
         names = ic + columns
 
         # If we find unnamed columns all in a single

pandas/io/stata.py

@@ -23,7 +23,7 @@
 
 from pandas._libs.lib import infer_dtype
 from pandas._libs.writers import max_len_string_array
-from pandas.compat import lmap, lzip
+from pandas.compat import lmap
 from pandas.util._decorators import Appender, deprecate_kwarg
 
 from pandas.core.dtypes.common import (
@@ -852,17 +852,16 @@ def __init__(self):
         # NOTE: the byte type seems to be reserved for categorical variables
         # with a label, but the underlying variable is -127 to 100
         # we're going to drop the label and cast to int
-        self.DTYPE_MAP = \
-            dict(
-                lzip(range(1, 245), ['a' + str(i) for i in range(1, 245)]) +
-                [
-                    (251, np.int8),
-                    (252, np.int16),
-                    (253, np.int32),
-                    (254, np.float32),
-                    (255, np.float64)
-                ]
-            )
+        self.DTYPE_MAP = dict(
+            list(zip(range(1, 245), ['a' + str(i) for i in range(1, 245)])) +
+            [
+                (251, np.int8),
+                (252, np.int16),
+                (253, np.int32),
+                (254, np.float32),
+                (255, np.float64)
+            ]
+        )
         self.DTYPE_MAP_XML = \
             dict(
                 [

pandas/tests/frame/test_axis_select_reindex.py

@@ -3,7 +3,7 @@
 import numpy as np
 import pytest
 
-from pandas.compat import lrange, lzip
+from pandas.compat import lrange
 from pandas.errors import PerformanceWarning
 
 import pandas as pd
@@ -100,7 +100,7 @@ def test_drop(self):
                            simple[['B']])
 
         # non-unique - wheee!
-        nu_df = DataFrame(lzip(range(3), range(-3, 1), list('abc')),
+        nu_df = DataFrame(list(zip(range(3), range(-3, 1), list('abc'))),
                           columns=['a', 'a', 'b'])
         assert_frame_equal(nu_df.drop('a', axis=1), nu_df[['b']])
         assert_frame_equal(nu_df.drop('b', axis='columns'), nu_df['a'])

pandas/tests/frame/test_constructors.py

@@ -7,7 +7,7 @@
 import numpy.ma as ma
 import pytest
 
-from pandas.compat import PY36, is_platform_little_endian, lmap, lrange, lzip
+from pandas.compat import PY36, is_platform_little_endian, lmap, lrange
 
 from pandas.core.dtypes.cast import construct_1d_object_array_from_listlike
 from pandas.core.dtypes.common import is_integer_dtype
@@ -132,12 +132,11 @@ def _make_mixed_dtypes_df(typ, ad=None):
                 arrays = [np.array(np.random.randint(
                     10, size=10), dtype=d) for d in dtypes]
 
-            zipper = lzip(dtypes, arrays)
-            for d, a in zipper:
+            for d, a in zip(dtypes, arrays):
                 assert(a.dtype == d)
             if ad is None:
                 ad = dict()
-            ad.update({d: a for d, a in zipper})
+            ad.update({d: a for d, a in zip(dtypes, arrays)})
             return DataFrame(ad)
 
         def _check_mixed_dtypes(df, dtypes=None):

pandas/tests/frame/test_indexing.py

@@ -5,7 +5,7 @@
 import pytest
 
 from pandas._libs.tslib import iNaT
-from pandas.compat import lrange, lzip
+from pandas.compat import lrange
 
 from pandas.core.dtypes.common import is_float_dtype, is_integer, is_scalar
 from pandas.core.dtypes.dtypes import CategoricalDtype
@@ -178,7 +178,7 @@ def test_setitem_list_not_dataframe(self):
         assert_almost_equal(self.frame[['A', 'B']].values, data)
 
     def test_setitem_list_of_tuples(self):
-        tuples = lzip(self.frame['A'], self.frame['B'])
+        tuples = list(zip(self.frame['A'], self.frame['B']))
         self.frame['tuples'] = tuples
 
         result = self.frame['tuples']
@@ -998,11 +998,11 @@ def test_setitem_fancy_2d(self):
             assert_frame_equal(frame, expected)
 
         # new corner case of boolean slicing / setting
-        frame = DataFrame(lzip([2, 3, 9, 6, 7], [np.nan] * 5),
+        frame = DataFrame(zip([2, 3, 9, 6, 7], [np.nan] * 5),
                           columns=['a', 'b'])
         lst = [100]
         lst.extend([np.nan] * 4)
-        expected = DataFrame(lzip([100, 3, 9, 6, 7], lst),
+        expected = DataFrame(zip([100, 3, 9, 6, 7], lst),
                              columns=['a', 'b'])
         frame[frame['a'] == 2] = 100
         assert_frame_equal(frame, expected)