CLN: remove compat.lmap (#26322)

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()
+* lists: lrange()
 
 Other items:
 * platform checker
@@ -24,10 +24,6 @@ def lrange(*args, **kwargs):
     return list(range(*args, **kwargs))
 
 
-def lmap(*args, **kwargs):
-    return list(map(*args, **kwargs))
-
-
 # ----------------------------------------------------------------------------
 # functions largely based / taken from the six module
 

pandas/core/computation/expr.py

@@ -11,8 +11,6 @@
 
 import numpy as np
 
-from pandas.compat import lmap
-
 import pandas as pd
 from pandas.core import common as com
 from pandas.core.base import StringMixin
@@ -180,7 +178,7 @@ def _preparse(source, f=_compose(_replace_locals, _replace_booleans,
     the ``tokenize`` module and ``tokval`` is a string.
     """
     assert callable(f), 'f must be callable'
-    return tokenize.untokenize(lmap(f, tokenize_string(source)))
+    return tokenize.untokenize((f(x) for x in tokenize_string(source)))
 
 
 def _is_type(t):

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, raise_with_traceback
+from pandas.compat import PY36, raise_with_traceback
 from pandas.compat.numpy import function as nv
 from pandas.core.dtypes.cast import (
     maybe_upcast,
@@ -1633,7 +1633,7 @@ def to_records(self, index=True, convert_datetime64=None,
             else:
                 if isinstance(self.index, MultiIndex):
                     # array of tuples to numpy cols. copy copy copy
-                    ix_vals = lmap(np.array, zip(*self.index.values))
+                    ix_vals = list(map(np.array, zip(*self.index.values)))
                 else:
                     ix_vals = [self.index.values]
 
@@ -1650,10 +1650,11 @@ def to_records(self, index=True, convert_datetime64=None,
             elif index_names[0] is None:
                 index_names = ['index']
 
-            names = lmap(str, index_names) + lmap(str, self.columns)
+            names = [str(name) for name in itertools.chain(index_names,
+                                                           self.columns)]
         else:
             arrays = [self[c].get_values() for c in self.columns]
-            names = lmap(str, self.columns)
+            names = [str(c) for c in self.columns]
             index_names = []
 
         index_len = len(index_names)

pandas/core/internals/construction.py

@@ -9,7 +9,7 @@
 
 from pandas._libs import lib
 from pandas._libs.tslibs import IncompatibleFrequency
-from pandas.compat import lmap, raise_with_traceback
+from pandas.compat import raise_with_traceback
 
 from pandas.core.dtypes.cast import (
     construct_1d_arraylike_from_scalar, construct_1d_ndarray_preserving_na,
@@ -413,7 +413,7 @@ def to_arrays(data, columns, coerce_float=False, dtype=None):
         return arrays, columns
     else:
         # last ditch effort
-        data = lmap(tuple, data)
+        data = [tuple(x) for x in data]
         return _list_to_arrays(data, columns, coerce_float=coerce_float,
                                dtype=dtype)
 

pandas/core/sparse/frame.py

@@ -7,7 +7,6 @@
 import numpy as np
 
 from pandas._libs.sparse import BlockIndex, get_blocks
-from pandas.compat import lmap
 from pandas.compat.numpy import function as nv
 from pandas.util._decorators import Appender
 
@@ -945,7 +944,7 @@ def applymap(self, func):
         -------
         applied : DataFrame
         """
-        return self.apply(lambda x: lmap(func, x))
+        return self.apply(lambda x: [func(y) for y in x])
 
 
 def to_manager(sdf, columns, index):

pandas/core/sparse/scipy_sparse.py

@@ -5,8 +5,6 @@
 """
 from collections import OrderedDict
 
-from pandas.compat import lmap
-
 from pandas.core.index import Index, MultiIndex
 from pandas.core.series import Series
 
@@ -53,7 +51,7 @@ def _get_label_to_i_dict(labels, sort_labels=False):
             """ Return OrderedDict of unique labels to number.
             Optionally sort by label.
             """
-            labels = Index(lmap(tuple, labels)).unique().tolist()  # squish
+            labels = Index(map(tuple, labels)).unique().tolist()  # squish
             if sort_labels:
                 labels = sorted(list(labels))
             d = OrderedDict((k, i) for i, k in enumerate(labels))

pandas/io/html.py

@@ -9,7 +9,7 @@
 import os
 import re
 
-from pandas.compat import lmap, raise_with_traceback
+from pandas.compat import raise_with_traceback
 from pandas.errors import AbstractMethodError, EmptyDataError
 
 from pandas.core.dtypes.common import is_list_like
@@ -764,7 +764,7 @@ def _parse_tfoot_tr(self, table):
 
 
 def _expand_elements(body):
-    lens = Series(lmap(len, body))
+    lens = Series([len(elem) for elem in body])
     lens_max = lens.max()
     not_max = lens[lens != lens_max]
 

pandas/io/stata.py

@@ -23,7 +23,6 @@
 
 from pandas._libs.lib import infer_dtype
 from pandas._libs.writers import max_len_string_array
-from pandas.compat import lmap
 from pandas.util._decorators import Appender, deprecate_kwarg
 
 from pandas.core.dtypes.common import (
@@ -1030,7 +1029,7 @@ def _read_header(self):
                                     if type(x) is int]) > 0
 
         # calculate size of a data record
-        self.col_sizes = lmap(lambda x: self._calcsize(x), self.typlist)
+        self.col_sizes = [self._calcsize(typ) for typ in self.typlist]
 
     def _read_new_header(self, first_char):
         # The first part of the header is common to 117 and 118.
@@ -1573,9 +1572,9 @@ def read(self, nrows=None, convert_dates=None,
         data = self._do_convert_missing(data, convert_missing)
 
         if convert_dates:
-            cols = np.where(lmap(lambda x: any(x.startswith(fmt)
-                                               for fmt in _date_formats),
-                                 self.fmtlist))[0]
+            def any_startswith(x: str) -> bool:
+                return any(x.startswith(fmt) for fmt in _date_formats)
+            cols = np.where([any_startswith(x) for x in self.fmtlist])[0]
             for i in cols:
                 col = data.columns[i]
                 try:

pandas/plotting/_misc.py

@@ -1,7 +1,7 @@
 # being a bit too dynamic
 import numpy as np
 
-from pandas.compat import lmap, lrange
+from pandas.compat import lrange
 from pandas.util._decorators import deprecate_kwarg
 
 from pandas.core.dtypes.missing import notna
@@ -625,7 +625,7 @@ def r(h):
         return ((data[:n - h] - mean) *
                 (data[h:] - mean)).sum() / float(n) / c0
     x = np.arange(n) + 1
-    y = lmap(r, x)
+    y = [r(loc) for loc in x]
     z95 = 1.959963984540054
     z99 = 2.5758293035489004
     ax.axhline(y=z99 / np.sqrt(n), linestyle='--', color='grey')

pandas/plotting/_style.py

@@ -4,7 +4,7 @@
 
 import numpy as np
 
-from pandas.compat import lmap, lrange
+from pandas.compat import lrange
 
 from pandas.core.dtypes.common import is_list_like
 
@@ -20,7 +20,7 @@ def _get_standard_colors(num_colors=None, colormap=None, color_type='default',
             colormap = cm.get_cmap(colormap)
             if colormap is None:
                 raise ValueError("Colormap {0} is not recognized".format(cmap))
-        colors = lmap(colormap, np.linspace(0, 1, num=num_colors))
+        colors = [colormap(num) for num in np.linspace(0, 1, num=num_colors)]
     elif color is not None:
         if colormap is not None:
             warnings.warn("'color' and 'colormap' cannot be used "
@@ -49,7 +49,7 @@ def random_color(column):
                 rs = com.random_state(column)
                 return rs.rand(3).tolist()
 
-            colors = lmap(random_color, lrange(num_colors))
+            colors = [random_color(num) for num in lrange(num_colors)]
         else:
             raise ValueError("color_type must be either 'default' or 'random'")
 

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
+from pandas.compat import PY36, is_platform_little_endian
 
 from pandas.core.dtypes.cast import construct_1d_object_array_from_listlike
 from pandas.core.dtypes.common import is_integer_dtype
@@ -2224,7 +2224,7 @@ def __iter__(self):
                 return iter(self.args)
 
         recs = [Record(1, 2, 3), Record(4, 5, 6), Record(7, 8, 9)]
-        tups = lmap(tuple, recs)
+        tups = [tuple(rec) for rec in recs]
 
         result = DataFrame.from_records(recs)
         expected = DataFrame.from_records(tups)

pandas/tests/frame/test_to_csv.py

@@ -5,7 +5,6 @@
 import numpy as np
 import pytest
 
-from pandas.compat import lmap
 from pandas.errors import ParserError
 
 import pandas as pd
@@ -120,8 +119,8 @@ def test_to_csv_from_csv3(self):
             df2.to_csv(path, mode='a', header=False)
             xp = pd.concat([df1, df2])
             rs = pd.read_csv(path, index_col=0)
-            rs.columns = lmap(int, rs.columns)
-            xp.columns = lmap(int, xp.columns)
+            rs.columns = [int(label) for label in rs.columns]
+            xp.columns = [int(label) for label in xp.columns]
             assert_frame_equal(xp, rs)
 
     def test_to_csv_from_csv4(self):
@@ -292,19 +291,24 @@ def _to_uni(x):
             if r_dtype:
                 if r_dtype == 'u':  # unicode
                     r_dtype = 'O'
-                    recons.index = np.array(lmap(_to_uni, recons.index),
-                                            dtype=r_dtype)
-                    df.index = np.array(lmap(_to_uni, df.index), dtype=r_dtype)
+                    recons.index = np.array(
+                        [_to_uni(label) for label in recons.index],
+                        dtype=r_dtype)
+                    df.index = np.array(
+                        [_to_uni(label) for label in df.index], dtype=r_dtype)
                 elif r_dtype == 'dt':  # unicode
                     r_dtype = 'O'
-                    recons.index = np.array(lmap(Timestamp, recons.index),
-                                            dtype=r_dtype)
+                    recons.index = np.array(
+                        [Timestamp(label) for label in recons.index],
+                        dtype=r_dtype)
                     df.index = np.array(
-                        lmap(Timestamp, df.index), dtype=r_dtype)
+                        [Timestamp(label) for label in df.index],
+                        dtype=r_dtype)
                 elif r_dtype == 'p':
                     r_dtype = 'O'
+                    idx_list = to_datetime(recons.index)
                     recons.index = np.array(
-                        list(map(Timestamp, to_datetime(recons.index))),
+                        [Timestamp(label) for label in idx_list],
                         dtype=r_dtype)
                     df.index = np.array(
                         list(map(Timestamp, df.index.to_timestamp())),
@@ -316,23 +320,29 @@ def _to_uni(x):
             if c_dtype:
                 if c_dtype == 'u':
                     c_dtype = 'O'
-                    recons.columns = np.array(lmap(_to_uni, recons.columns),
-                                              dtype=c_dtype)
+                    recons.columns = np.array(
+                        [_to_uni(label) for label in recons.columns],
+                        dtype=c_dtype)
                     df.columns = np.array(
-                        lmap(_to_uni, df.columns), dtype=c_dtype)
+                        [_to_uni(label) for label in df.columns],
+                        dtype=c_dtype)
                 elif c_dtype == 'dt':
                     c_dtype = 'O'
-                    recons.columns = np.array(lmap(Timestamp, recons.columns),
-                                              dtype=c_dtype)
+                    recons.columns = np.array(
+                        [Timestamp(label) for label in recons.columns],
+                        dtype=c_dtype)
                     df.columns = np.array(
-                        lmap(Timestamp, df.columns), dtype=c_dtype)
+                        [Timestamp(label) for label in df.columns],
+                        dtype=c_dtype)
                 elif c_dtype == 'p':
                     c_dtype = 'O'
+                    col_list = to_datetime(recons.columns)
                     recons.columns = np.array(
-                        lmap(Timestamp, to_datetime(recons.columns)),
+                        [Timestamp(label) for label in col_list],
                         dtype=c_dtype)
+                    col_list = df.columns.to_timestamp()
                     df.columns = np.array(
-                        lmap(Timestamp, df.columns.to_timestamp()),
+                        [Timestamp(label) for label in col_list],
                         dtype=c_dtype)
                 else:
                     c_dtype = type_map.get(c_dtype)

pandas/tests/groupby/test_groupby.py

@@ -6,7 +6,6 @@
 import numpy as np
 import pytest
 
-from pandas.compat import lmap
 from pandas.errors import PerformanceWarning
 
 import pandas as pd
@@ -874,7 +873,7 @@ def test_mutate_groups():
         'cat1': ['a'] * 8 + ['b'] * 6,
         'cat2': ['c'] * 2 + ['d'] * 2 + ['e'] * 2 + ['f'] * 2 + ['c'] * 2 +
         ['d'] * 2 + ['e'] * 2,
-        'cat3': lmap(lambda x: 'g%s' % x, range(1, 15)),
+        'cat3': ['g{}'.format(x) for x in range(1, 15)],
         'val': np.random.randint(100, size=14),
     })
 
@@ -1248,17 +1247,17 @@ def test_groupby_sort_multi():
                     'c': [0, 1, 2],
                     'd': np.random.randn(3)})
 
-    tups = lmap(tuple, df[['a', 'b', 'c']].values)
+    tups = [tuple(row) for row in df[['a', 'b', 'c']].values]
     tups = com.asarray_tuplesafe(tups)
     result = df.groupby(['a', 'b', 'c'], sort=True).sum()
     tm.assert_numpy_array_equal(result.index.values, tups[[1, 2, 0]])
 
-    tups = lmap(tuple, df[['c', 'a', 'b']].values)
+    tups = [tuple(row) for row in df[['c', 'a', 'b']].values]
     tups = com.asarray_tuplesafe(tups)
     result = df.groupby(['c', 'a', 'b'], sort=True).sum()
     tm.assert_numpy_array_equal(result.index.values, tups)
 
-    tups = lmap(tuple, df[['b', 'c', 'a']].values)
+    tups = [tuple(x) for x in df[['b', 'c', 'a']].values]
     tups = com.asarray_tuplesafe(tups)
     result = df.groupby(['b', 'c', 'a'], sort=True).sum()
     tm.assert_numpy_array_equal(result.index.values, tups[[2, 1, 0]])
@@ -1270,7 +1269,7 @@ def test_groupby_sort_multi():
     result = grouped.sum()
 
     def _check_groupby(df, result, keys, field, f=lambda x: x.sum()):
-        tups = lmap(tuple, df[keys].values)
+        tups = [tuple(row) for row in df[keys].values]
         tups = com.asarray_tuplesafe(tups)
         expected = f(df.groupby(tups)[field])
         for k, v in expected.items():

pandas/tests/indexes/datetimes/test_tools.py

@@ -14,7 +14,6 @@
 
 from pandas._libs import tslib
 from pandas._libs.tslibs import iNaT, parsing
-from pandas.compat import lmap
 from pandas.errors import OutOfBoundsDatetime
 import pandas.util._test_decorators as td
 
@@ -1264,7 +1263,7 @@ def test_to_datetime_types(self, cache):
         # array = ['2012','20120101','20120101 12:01:01']
         array = ['20120101', '20120101 12:01:01']
         expected = list(to_datetime(array, cache=cache))
-        result = lmap(Timestamp, array)
+        result = [Timestamp(date_str) for date_str in array]
         tm.assert_almost_equal(result, expected)
 
         # currently fails ###