CLN: Remove long and integer_types from pandas.compat

pandas/compat/__init__.py

@@ -7,7 +7,6 @@
 Key items to import for 2/3 compatible code:
 * iterators: reduce()
 * lists: lrange(), lmap(), lzip(), lfilter()
-* longs: long (int in Python 3)
 * iterable method compatibility: iteritems, iterkeys, itervalues
   * Uses the original method if available, otherwise uses items, keys, values.
 * types:
@@ -108,7 +107,6 @@ def get_range_parameters(data):
     # have to explicitly put builtins into the namespace
     intern = sys.intern
     reduce = functools.reduce
-    long = int
     unichr = chr
 
     # list-producing versions of the major Python iterating functions
@@ -172,7 +170,6 @@ def get_range_parameters(data):
     # import iterator versions of these functions
     intern = intern
     reduce = reduce
-    long = long
     unichr = unichr
 
     # Python 2-builtin ranges produce lists
@@ -250,7 +247,6 @@ class to receive bound method
 
 if PY3:
     string_types = str,
-    integer_types = int,
     class_types = type,
     text_type = str
     binary_type = bytes
@@ -293,7 +289,6 @@ def set_function_name(f, name, cls):
         return f
 else:
     string_types = basestring,
-    integer_types = (int, long)
     class_types = (type, types.ClassType)
     text_type = unicode
     binary_type = str

pandas/core/internals/blocks.py

@@ -1959,9 +1959,9 @@ def _can_hold_element(self, element):
                     not issubclass(tipo.type, (np.datetime64, np.timedelta64)))
         return (
             isinstance(
-                element, (float, int, np.floating, np.int_, compat.long))
-            and not isinstance(element, (bool, np.bool_, datetime, timedelta,
-                                         np.datetime64, np.timedelta64)))
+                element, (float, int, np.floating, np.int_)) and
+            not isinstance(element, (bool, np.bool_, datetime, timedelta,
+                                     np.datetime64, np.timedelta64)))
 
     def to_native_types(self, slicer=None, na_rep='', float_format=None,
                         decimal='.', quoting=None, **kwargs):
@@ -2011,8 +2011,8 @@ def _can_hold_element(self, element):
         return (
             isinstance(
                 element,
-                (float, int, complex, np.float_, np.int_, compat.long))
-            and not isinstance(element, (bool, np.bool_)))
+                (float, int, complex, np.float_, np.int_)) and
+            not isinstance(element, (bool, np.bool_)))
 
     def should_store(self, value):
         return issubclass(value.dtype.type, np.complexfloating)

pandas/core/sorting.py

@@ -5,7 +5,7 @@
 
 from pandas._libs import algos, hashtable, lib
 from pandas._libs.hashtable import unique_label_indices
-from pandas.compat import PY3, long, string_types
+from pandas.compat import PY3, string_types
 
 from pandas.core.dtypes.cast import infer_dtype_from_array
 from pandas.core.dtypes.common import (
@@ -45,9 +45,9 @@ def get_group_index(labels, shape, sort, xnull):
     labels are equal at all location.
     """
     def _int64_cut_off(shape):
-        acc = long(1)
+        acc = 1
         for i, mul in enumerate(shape):
-            acc *= long(mul)
+            acc *= int(mul)
             if not acc < _INT64_MAX:
                 return i
         return len(shape)
@@ -122,9 +122,9 @@ def get_compressed_ids(labels, sizes):
 
 
 def is_int64_overflow_possible(shape):
-    the_prod = long(1)
+    the_prod = 1
     for x in shape:
-        the_prod *= long(x)
+        the_prod *= int(x)
 
     return the_prod >= _INT64_MAX
 

pandas/io/json/json.py

@@ -6,7 +6,7 @@
 
 import pandas._libs.json as json
 from pandas._libs.tslibs import iNaT
-from pandas.compat import StringIO, long, to_str
+from pandas.compat import StringIO, to_str
 from pandas.errors import AbstractMethodError
 
 from pandas.core.dtypes.common import is_period_dtype
@@ -619,10 +619,10 @@ class Parser(object):
 
     _STAMP_UNITS = ('s', 'ms', 'us', 'ns')
     _MIN_STAMPS = {
-        's': long(31536000),
-        'ms': long(31536000000),
-        'us': long(31536000000000),
-        'ns': long(31536000000000000)}
+        's': 31536000,
+        'ms': 31536000000,
+        'us': 31536000000000,
+        'ns': 31536000000000000}
 
     def __init__(self, json, orient, dtype=None, convert_axes=True,
                  convert_dates=True, keep_default_dates=False, numpy=False,

pandas/io/stata.py

@@ -765,9 +765,9 @@ class StataMissingValue(StringMixin):
     bases = (101, 32741, 2147483621)
     for b in bases:
         # Conversion to long to avoid hash issues on 32 bit platforms #8968
-        MISSING_VALUES[compat.long(b)] = '.'
+        MISSING_VALUES[b] = '.'
         for i in range(1, 27):
-            MISSING_VALUES[compat.long(i + b)] = '.' + chr(96 + i)
+            MISSING_VALUES[i + b] = '.' + chr(96 + i)
 
     float32_base = b'\x00\x00\x00\x7f'
     increment = struct.unpack('<i', b'\x00\x08\x00\x00')[0]
@@ -798,8 +798,8 @@ class StataMissingValue(StringMixin):
 
     def __init__(self, value):
         self._value = value
-        # Conversion to long to avoid hash issues on 32 bit platforms #8968
-        value = compat.long(value) if value < 2147483648 else float(value)
+        # Conversion to int to avoid hash issues on 32 bit platforms #8968
+        value = int(value) if value < 2147483648 else float(value)
         self._str = self.MISSING_VALUES[value]
 
     string = property(lambda self: self._str,

pandas/tests/arithmetic/conftest.py

@@ -2,8 +2,6 @@
 import numpy as np
 import pytest
 
-from pandas.compat import long
-
 import pandas as pd
 import pandas.util.testing as tm
 
@@ -32,7 +30,7 @@ def one(request):
          for dtype in [np.int64, np.uint64, np.float64]]
 zeros.extend([np.array(0, dtype=dtype)
               for dtype in [np.int64, np.uint64, np.float64]])
-zeros.extend([0, 0.0, long(0)])
+zeros.extend([0, 0.0])
 
 
 @pytest.fixture(params=zeros)

pandas/tests/arithmetic/test_period.py

@@ -674,7 +674,7 @@ def test_pi_add_iadd_int(self, one):
     def test_pi_sub_isub_int(self, one):
         """
         PeriodIndex.__sub__ and __isub__ with several representations of
-        the integer 1, e.g. int, long, np.int64, np.uint8, ...
+        the integer 1, e.g. int, np.int64, np.uint8, ...
         """
         rng = pd.period_range('2000-01-01 09:00', freq='H', periods=10)
         result = rng - one

pandas/tests/arrays/categorical/test_dtypes.py

@@ -2,8 +2,6 @@
 import numpy as np
 import pytest
 
-from pandas.compat import long
-
 from pandas.core.dtypes.dtypes import CategoricalDtype
 
 from pandas import Categorical, CategoricalIndex, Index, Series, Timestamp
@@ -165,10 +163,9 @@ def test_astype_category(self, dtype_ordered, cat_ordered):
 
     def test_iter_python_types(self):
         # GH-19909
-        # TODO(Py2): Remove long
         cat = Categorical([1, 2])
-        assert isinstance(list(cat)[0], (int, long))
-        assert isinstance(cat.tolist()[0], (int, long))
+        assert isinstance(list(cat)[0], int)
+        assert isinstance(cat.tolist()[0], int)
 
     def test_iter_python_types_datetime(self):
         cat = Categorical([Timestamp('2017-01-01'),

pandas/tests/arrays/test_datetimelike.py

@@ -2,8 +2,6 @@
 import numpy as np
 import pytest
 
-import pandas.compat as compat
-
 import pandas as pd
 from pandas.core.arrays import DatetimeArray, PeriodArray, TimedeltaArray
 import pandas.util.testing as tm
@@ -133,10 +131,10 @@ def test_unbox_scalar(self):
         data = np.arange(10, dtype='i8') * 24 * 3600 * 10**9
         arr = self.array_cls(data, freq='D')
         result = arr._unbox_scalar(arr[0])
-        assert isinstance(result, (int, compat.long))
+        assert isinstance(result, int)
 
         result = arr._unbox_scalar(pd.NaT)
-        assert isinstance(result, (int, compat.long))
+        assert isinstance(result, int)
 
         with pytest.raises(ValueError):
             arr._unbox_scalar('foo')

pandas/tests/arrays/test_integer.py

@@ -509,7 +509,6 @@ def test_conversions(data_missing):
         if pd.isnull(r):
             assert pd.isnull(e)
         elif is_integer(r):
-            # PY2 can be int or long
             assert r == e
             assert is_integer(e)
         else:

pandas/tests/frame/test_api.py

@@ -9,7 +9,7 @@
 import numpy as np
 import pytest
 
-from pandas.compat import long, lrange
+from pandas.compat import lrange
 
 import pandas as pd
 from pandas import (
@@ -242,15 +242,15 @@ def test_itertuples(self, float_frame):
                          'ints': lrange(5)}, columns=['floats', 'ints'])
 
         for tup in df.itertuples(index=False):
-            assert isinstance(tup[1], (int, long))
+            assert isinstance(tup[1], int)
 
         df = self.klass(data={"a": [1, 2, 3], "b": [4, 5, 6]})
         dfaa = df[['a', 'a']]
 
         assert (list(dfaa.itertuples()) ==
                 [(0, 1, 1), (1, 2, 2), (2, 3, 3)])
 
-        # repr with be int/long on 32-bit/windows
+        # repr with int on 32-bit/windows
         if not (compat.is_platform_windows() or compat.is_platform_32bit()):
             assert (repr(list(df.itertuples(name=None))) ==
                     '[(0, 1, 4), (1, 2, 5), (2, 3, 6)]')

pandas/tests/frame/test_constructors.py

@@ -11,8 +11,7 @@
 import numpy.ma as ma
 import pytest
 
-from pandas.compat import (
-    PY36, is_platform_little_endian, lmap, long, lrange, lzip)
+from pandas.compat import PY36, is_platform_little_endian, lmap, lrange, lzip
 
 from pandas.core.dtypes.cast import construct_1d_object_array_from_listlike
 from pandas.core.dtypes.common import is_integer_dtype
@@ -193,9 +192,8 @@ def test_constructor_overflow_int64(self):
 
         # see gh-2355
         data_scores = [(6311132704823138710, 273), (2685045978526272070, 23),
-                       (8921811264899370420, 45),
-                       (long(17019687244989530680), 270),
-                       (long(9930107427299601010), 273)]
+                       (8921811264899370420, 45), (17019687244989530680, 270),
+                       (9930107427299601010, 273)]
         dtype = [('uid', 'u8'), ('score', 'u8')]
         data = np.zeros((len(data_scores),), dtype=dtype)
         data[:] = data_scores

pandas/tests/frame/test_convert_to.py

@@ -8,8 +8,6 @@
 import pytest
 import pytz
 
-from pandas.compat import long
-
 from pandas import (
     CategoricalDtype, DataFrame, MultiIndex, Series, Timestamp, compat,
     date_range)
@@ -472,7 +470,7 @@ def test_to_dict_box_scalars(self, orient, item_getter):
         # make sure that we are boxing properly
         df = DataFrame({'a': [1, 2], 'b': [.1, .2]})
         result = df.to_dict(orient=orient)
-        assert isinstance(item_getter(result, 'a', 0), (int, long))
+        assert isinstance(item_getter(result, 'a', 0), int)
         assert isinstance(item_getter(result, 'b', 0), float)
 
     def test_frame_to_dict_tz(self):

pandas/tests/frame/test_indexing.py

@@ -9,7 +9,7 @@
 import pytest
 
 from pandas._libs.tslib import iNaT
-from pandas.compat import long, lrange, lzip
+from pandas.compat import lrange, lzip
 
 from pandas.core.dtypes.common import is_float_dtype, is_integer, is_scalar
 from pandas.core.dtypes.dtypes import CategoricalDtype
@@ -2560,19 +2560,14 @@ def test_boolean_indexing(self):
 
     def test_boolean_indexing_mixed(self):
         df = DataFrame({
-            long(0): {35: np.nan, 40: np.nan, 43: np.nan,
-                      49: np.nan, 50: np.nan},
-            long(1): {35: np.nan,
-                      40: 0.32632316859446198,
-                      43: np.nan,
-                      49: 0.32632316859446198,
-                      50: 0.39114724480578139},
-            long(2): {35: np.nan, 40: np.nan, 43: 0.29012581014105987,
-                      49: np.nan, 50: np.nan},
-            long(3): {35: np.nan, 40: np.nan, 43: np.nan, 49: np.nan,
-                      50: np.nan},
-            long(4): {35: 0.34215328467153283, 40: np.nan, 43: np.nan,
-                      49: np.nan, 50: np.nan},
+            0: {35: np.nan, 40: np.nan, 43: np.nan, 49: np.nan, 50: np.nan},
+            1: {35: np.nan, 40: 0.32632316859446198, 43: np.nan,
+                49: 0.32632316859446198, 50: 0.39114724480578139},
+            2: {35: np.nan, 40: np.nan, 43: 0.29012581014105987, 49: np.nan,
+                50: np.nan},
+            3: {35: np.nan, 40: np.nan, 43: np.nan, 49: np.nan, 50: np.nan},
+            4: {35: 0.34215328467153283, 40: np.nan, 43: np.nan, 49: np.nan,
+                50: np.nan},
             'y': {35: 0, 40: 0, 43: 0, 49: 0, 50: 1}})
 
         # mixed int/float ok

pandas/tests/groupby/test_groupby.py

@@ -770,7 +770,7 @@ def test_empty_groups_corner(mframe):
 
 def test_nonsense_func():
     df = DataFrame([0])
-    msg = r"unsupported operand type\(s\) for \+: '(int|long)' and 'str'"
+    msg = r"unsupported operand type\(s\) for \+: 'int' and 'str'"
     with pytest.raises(TypeError, match=msg):
         df.groupby(lambda x: x + 'foo')
 

pandas/tests/groupby/test_grouping.py

@@ -5,7 +5,7 @@
 import numpy as np
 import pytest
 
-from pandas.compat import long, lrange
+from pandas.compat import lrange
 
 import pandas as pd
 from pandas import (
@@ -396,21 +396,21 @@ def test_multiindex_columns_empty_level(self):
         lst = [['count', 'values'], ['to filter', '']]
         midx = MultiIndex.from_tuples(lst)
 
-        df = DataFrame([[long(1), 'A']], columns=midx)
+        df = DataFrame([[1, 'A']], columns=midx)
 
         grouped = df.groupby('to filter').groups
         assert grouped['A'] == [0]
 
         grouped = df.groupby([('to filter', '')]).groups
         assert grouped['A'] == [0]
 
-        df = DataFrame([[long(1), 'A'], [long(2), 'B']], columns=midx)
+        df = DataFrame([[1, 'A'], [2, 'B']], columns=midx)
 
         expected = df.groupby('to filter').groups
         result = df.groupby([('to filter', '')]).groups
         assert result == expected
 
-        df = DataFrame([[long(1), 'A'], [long(2), 'A']], columns=midx)
+        df = DataFrame([[1, 'A'], [2, 'A']], columns=midx)
 
         expected = df.groupby('to filter').groups
         result = df.groupby([('to filter', '')]).groups

pandas/tests/indexes/conftest.py

@@ -1,7 +1,7 @@
 import numpy as np
 import pytest
 
-from pandas.compat import long, lzip
+from pandas.compat import lzip
 
 import pandas as pd
 from pandas.core.indexes.api import Index, MultiIndex
@@ -39,7 +39,7 @@ def one(request):
          for dtype in [np.int64, np.uint64, np.float64]]
 zeros.extend([np.array(0, dtype=dtype)
               for dtype in [np.int64, np.uint64, np.float64]])
-zeros.extend([0, 0.0, long(0)])
+zeros.extend([0, 0.0])
 
 
 @pytest.fixture(params=zeros)