pandas.hashtable -> pandas.libs.hashtable

Author: jreback

Makefile

@@ -1,4 +1,4 @@
-tseries: pandas/libs/lib.pyx pandas/libs/tslib.pyx pandas/hashtable.pyx
+tseries: pandas/libs/lib.pyx pandas/libs/tslib.pyx pandas/libs/hashtable.pyx
 	python setup.py build_ext --inplace
 
 .PHONY : develop build clean clean_pyc tseries doc

doc/source/whatsnew/v0.20.0.txt

@@ -469,6 +469,7 @@ If indicated, a deprecation warning will be issued if you reference that module.
     "pandas.index", "pandas.libs.index", ""
     "pandas.algos", "pandas.libs.algos", ""
     "pandas.lib", "pandas.libs.lib", "X"
+    "pandas.hastable", "pandas.libs.hashtable", ""
 
 
 .. _whatsnew_0200.api_breaking.groupby_describe:

pandas/__init__.py

@@ -23,8 +23,9 @@
 from pandas.compat.numpy import *
 
 try:
-    from pandas import hashtable
-    from pandas.libs import lib as _lib, tslib as _tslib
+    from pandas.libs import (hashtable as _hashtable,
+                             lib as _lib,
+                             tslib as _tslib)
 except ImportError as e:  # pragma: no cover
     # hack but overkill to use re
     module = str(e).lstrip('cannot import name ')

pandas/core/algorithms.py

@@ -34,9 +34,8 @@
 from pandas.types.missing import isnull
 
 import pandas.core.common as com
-import pandas.hashtable as htable
 from pandas.compat import string_types
-from pandas.libs import algos, lib
+from pandas.libs import algos, lib, hashtable as htable
 from pandas.libs.tslib import iNaT
 
 

pandas/core/categorical.py

@@ -1890,7 +1890,7 @@ def mode(self):
         modes : `Categorical` (sorted)
         """
 
-        import pandas.hashtable as htable
+        import pandas.libs.hashtable as htable
         good = self._codes != -1
         values = sorted(htable.mode_int64(_ensure_int64(self._codes[good])))
         result = self._constructor(values=values, categories=self.categories,

pandas/core/frame.py

@@ -3170,7 +3170,7 @@ def duplicated(self, subset=None, keep='first'):
         duplicated : Series
         """
         from pandas.core.sorting import get_group_index
-        from pandas.hashtable import duplicated_int64, _SIZE_HINT_LIMIT
+        from pandas.libs.hashtable import duplicated_int64, _SIZE_HINT_LIMIT
 
         def f(vals):
             labels, shape = algos.factorize(vals,

pandas/core/sorting.py

@@ -8,8 +8,8 @@
                                  is_categorical_dtype)
 from pandas.types.missing import isnull
 import pandas.core.algorithms as algos
-from pandas.libs import lib, algos as _algos
-import pandas.hashtable as _hash
+from pandas.libs import lib, algos as _algos, hashtable as _hash
+from pandas.libs.hashtable import unique_label_indices
 
 
 _INT64_MAX = np.iinfo(np.int64).max
@@ -130,7 +130,6 @@ def decons_obs_group_ids(comp_ids, obs_ids, shape, labels, xnull):
     xnull: boolean,
         if nulls are excluded; i.e. -1 labels are passed through
     """
-    from pandas.hashtable import unique_label_indices
 
     if not xnull:
         lift = np.fromiter(((a == -1).any() for a in labels), dtype='i8')

pandas/indexes/category.py

@@ -303,7 +303,7 @@ def unique(self):
                                                    False: 'first'})
     @Appender(base._shared_docs['duplicated'] % _index_doc_kwargs)
     def duplicated(self, keep='first'):
-        from pandas.hashtable import duplicated_int64
+        from pandas.libs.hashtable import duplicated_int64
         codes = self.codes.astype('i8')
         return duplicated_int64(codes, keep)
 

pandas/indexes/multi.py

@@ -6,8 +6,7 @@
 from sys import getsizeof
 
 import numpy as np
-import pandas.libs.lib as lib
-import pandas.libs.index as _index
+from pandas.libs import index as _index, lib
 from pandas.libs.lib import Timestamp
 
 from pandas.compat import range, zip, lrange, lzip, map
@@ -762,7 +761,7 @@ def f(k, stringify):
     @Appender(base._shared_docs['duplicated'] % _index_doc_kwargs)
     def duplicated(self, keep='first'):
         from pandas.core.sorting import get_group_index
-        from pandas.hashtable import duplicated_int64
+        from pandas.libs.hashtable import duplicated_int64
 
         shape = map(len, self.levels)
         ids = get_group_index(self.labels, shape, sort=False, xnull=False)

pandas/hashtable.pxd renamed to pandas/libs/hashtable.pxd

@@ -16,9 +16,8 @@ cimport util
 import numpy as np
 
 cimport tslib
-from ..hashtable cimport *
-from pandas import hashtable as _hash
-from pandas.libs import tslib, algos
+from hashtable cimport *
+from pandas.libs import tslib, algos, hashtable as _hash
 from pandas.libs.tslib import Timestamp, Timedelta
 
 from datetime cimport (get_datetime64_value, _pydatetime_to_dts,

pandas/hashtable.pyx renamed to pandas/libs/hashtable.pyx

@@ -23,7 +23,7 @@ on_dtypes = ['uint8_t', 'uint16_t', 'uint32_t', 'uint64_t',
 }}
 
 
-from hashtable cimport *
+from libs.hashtable cimport *
 
 {{for table_type, by_dtype in by_dtypes}}
 {{for on_dtype in on_dtypes}}

pandas/libs/index.pyx

@@ -36,10 +36,6 @@ class TestPDApi(Base, tm.TestCase):
            'test', 'tools', 'tseries', 'sparse',
            'types', 'util', 'options', 'io', 'libs']
 
-    # top-level packages that are c-imports, should rename to _*
-    # to avoid naming conflicts
-    lib_to_rename = ['hashtable']
-
     # these are already deprecated; awaiting removal
     deprecated_modules = ['stats', 'datetools', 'parser', 'json', 'lib']
 
@@ -118,7 +114,7 @@ class TestPDApi(Base, tm.TestCase):
     def test_api(self):
 
         self.check(pd,
-                   self.lib + self.lib_to_rename + self.misc +
+                   self.lib + self.misc +
                    self.modules + self.deprecated_modules +
                    self.classes + self.deprecated_classes +
                    self.deprecated_classes_in_future +

pandas/src/joins_func_helper.pxi.in

@@ -2182,7 +2182,7 @@ def check(nlevels, with_nulls):
 
         for keep in ['first', 'last', False]:
             left = mi.duplicated(keep=keep)
-            right = pd.hashtable.duplicated_object(mi.values, keep=keep)
+            right = pd.libs.hashtable.duplicated_object(mi.values, keep=keep)
             tm.assert_numpy_array_equal(left, right)
 
         # GH5873

pandas/tests/api/test_api.py

@@ -10,11 +10,11 @@
 import pandas as pd
 
 from pandas import compat
-import pandas.libs.algos as _algos
+from pandas.libs import algos as _algos, hashtable
+from pandas.libs.hashtable import unique_label_indices
 from pandas.compat import lrange
 import pandas.core.algorithms as algos
 import pandas.util.testing as tm
-import pandas.hashtable as hashtable
 from pandas.compat.numpy import np_array_datetime64_compat
 from pandas.util.testing import assert_almost_equal
 
@@ -972,7 +972,6 @@ def test_quantile():
 
 
 def test_unique_label_indices():
-    from pandas.hashtable import unique_label_indices
 
     a = np.random.randint(1, 1 << 10, 1 << 15).astype('i8')
 

pandas/tests/indexes/test_multi.py

@@ -39,7 +39,7 @@
 import pandas.core.common as com
 
 import pandas._join as _join
-import pandas.hashtable as _hash
+from pandas.libs import hashtable as _hash
 
 
 # back-compat of pseudo-public API

pandas/tests/test_algos.py

@@ -327,7 +327,7 @@ class CheckSDist(sdist_class):
     """Custom sdist that ensures Cython has compiled all pyx files to c."""
 
     _pyxfiles = ['pandas/lib.pyx',
-                 'pandas/hashtable.pyx',
+                 'pandas/libs/hashtable.pyx',
                  'pandas/libs/tslib.pyx',
                  'pandas/libs/index.pyx',
                  'pandas/libs/algos.pyx',
@@ -474,10 +474,10 @@ def pxd(name):
     'libs.lib': {'pyxfile': 'libs/lib',
                  'pxdfiles': [],
                  'depends': lib_depends},
-    'hashtable': {'pyxfile': 'hashtable',
-                  'pxdfiles': ['hashtable'],
-                  'depends': (['pandas/src/klib/khash_python.h']
-                              + _pxi_dep['hashtable'])},
+    'libs.hashtable': {'pyxfile': 'libs/hashtable',
+                       'pxdfiles': ['libs/hashtable'],
+                       'depends': (['pandas/src/klib/khash_python.h']
+                                   + _pxi_dep['hashtable'])},
     'libs.tslib': {'pyxfile': 'libs/tslib',
                    'depends': tseries_depends,
                    'sources': ['pandas/src/datetime/np_datetime.c',
@@ -491,13 +491,13 @@ def pxd(name):
     'libs.index': {'pyxfile': 'libs/index',
                    'sources': ['pandas/src/datetime/np_datetime.c',
                                'pandas/src/datetime/np_datetime_strings.c'],
-              'pxdfiles': ['src/util', 'hashtable'],
+              'pxdfiles': ['src/util', 'libs/hashtable'],
               'depends': _pxi_dep['index']},
     'libs.algos': {'pyxfile': 'libs/algos',
-                   'pxdfiles': ['src/util', 'hashtable'],
+                   'pxdfiles': ['src/util', 'libs/hashtable'],
               'depends': _pxi_dep['algos']},
     '_join': {'pyxfile': 'src/join',
-              'pxdfiles': ['src/util', 'hashtable'],
+              'pxdfiles': ['src/util', 'libs/hashtable'],
               'depends': _pxi_dep['join']},
     '_window': {'pyxfile': 'window',
                 'pxdfiles': ['src/skiplist', 'src/util'],