separate _libs/src/reduce.pyx to _libs.reduction (#19306)

Author: jbrockmendel

pandas/_libs/lib.pyx

@@ -6,7 +6,7 @@ from cython cimport Py_ssize_t
 
 import numpy as np
 cimport numpy as np
-from numpy cimport (ndarray, PyArray_NDIM, PyArray_GETITEM, PyArray_SETITEM,
+from numpy cimport (ndarray, PyArray_NDIM, PyArray_GETITEM,
                     PyArray_ITER_DATA, PyArray_ITER_NEXT, PyArray_IterNew,
                     flatiter, NPY_OBJECT,
                     int64_t,
@@ -57,8 +57,6 @@ cimport util
 cdef int64_t NPY_NAT = util.get_nat()
 from util cimport is_array, _checknull
 
-from libc.math cimport fabs, sqrt
-
 
 def values_from_object(object o):
     """ return my values or the object if we are say an ndarray """
@@ -1119,5 +1117,4 @@ def indices_fast(object index, ndarray[int64_t] labels, list keys,
     return result
 
 
-include "reduce.pyx"
 include "inference.pyx"

pandas/_libs/src/reduce.pyx pandas/_libs/reduction.pyxpandas/_libs/src/reduce.pyx renamed to pandas/_libs/reduction.pyx

@@ -1,9 +1,24 @@
 # -*- coding: utf-8 -*-
 # cython: profile=False
-import numpy as np
-
 from distutils.version import LooseVersion
 
+from cython cimport Py_ssize_t
+from cpython cimport Py_INCREF
+
+from libc.stdlib cimport malloc, free
+
+import numpy as np
+cimport numpy as np
+from numpy cimport (ndarray,
+                    int64_t,
+                    PyArray_SETITEM,
+                    PyArray_ITER_NEXT, PyArray_ITER_DATA, PyArray_IterNew,
+                    flatiter)
+np.import_array()
+
+cimport util
+from lib import maybe_convert_objects
+
 is_numpy_prior_1_6_2 = LooseVersion(np.__version__) < '1.6.2'
 
 

pandas/core/apply.py

@@ -1,6 +1,6 @@
 import numpy as np
 from pandas import compat
-from pandas._libs import lib
+from pandas._libs import reduction
 from pandas.core.dtypes.common import (
     is_extension_type,
     is_sequence)
@@ -114,7 +114,7 @@ def apply_empty_result(self):
 
     def apply_raw(self):
         try:
-            result = lib.reduce(self.values, self.f, axis=self.axis)
+            result = reduction.reduce(self.values, self.f, axis=self.axis)
         except Exception:
             result = np.apply_along_axis(self.f, self.axis, self.values)
 
@@ -150,10 +150,10 @@ def apply_standard(self):
 
                 try:
                     labels = self.agg_axis
-                    result = lib.reduce(values, self.f,
-                                        axis=self.axis,
-                                        dummy=dummy,
-                                        labels=labels)
+                    result = reduction.reduce(values, self.f,
+                                              axis=self.axis,
+                                              dummy=dummy,
+                                              labels=labels)
                     return Series(result, index=labels)
                 except Exception:
                     pass

pandas/core/groupby.py

@@ -63,7 +63,9 @@
 
 from pandas.plotting._core import boxplot_frame_groupby
 
-from pandas._libs import lib, groupby as libgroupby, Timestamp, NaT, iNaT
+from pandas._libs import (lib, reduction,
+                          groupby as libgroupby,
+                          Timestamp, NaT, iNaT)
 from pandas._libs.lib import count_level_2d
 
 _doc_template = """
@@ -1978,7 +1980,7 @@ def apply(self, f, data, axis=0):
             try:
                 values, mutated = splitter.fast_apply(f, group_keys)
                 return group_keys, values, mutated
-            except (lib.InvalidApply):
+            except reduction.InvalidApply:
                 # we detect a mutation of some kind
                 # so take slow path
                 pass
@@ -2401,8 +2403,8 @@ def _aggregate_series_fast(self, obj, func):
         obj = obj._take(indexer, convert=False).to_dense()
         group_index = algorithms.take_nd(
             group_index, indexer, allow_fill=False)
-        grouper = lib.SeriesGrouper(obj, func, group_index, ngroups,
-                                    dummy)
+        grouper = reduction.SeriesGrouper(obj, func, group_index, ngroups,
+                                          dummy)
         result, counts = grouper.get_result()
         return result, counts
 
@@ -2615,7 +2617,7 @@ def groupings(self):
 
     def agg_series(self, obj, func):
         dummy = obj[:0]
-        grouper = lib.SeriesBinGrouper(obj, func, self.bins, dummy)
+        grouper = reduction.SeriesBinGrouper(obj, func, self.bins, dummy)
         return grouper.get_result()
 
     # ----------------------------------------------------------------------
@@ -4755,7 +4757,8 @@ def fast_apply(self, f, names):
             return [], True
 
         sdata = self._get_sorted_data()
-        results, mutated = lib.apply_frame_axis0(sdata, f, names, starts, ends)
+        results, mutated = reduction.apply_frame_axis0(sdata, f, names,
+                                                       starts, ends)
 
         return results, mutated
 

pandas/tests/groupby/test_bin_groupby.py

@@ -9,7 +9,7 @@
 from pandas import Index, isna
 from pandas.util.testing import assert_almost_equal
 import pandas.util.testing as tm
-from pandas._libs import lib, groupby
+from pandas._libs import lib, groupby, reduction
 
 
 def test_series_grouper():
@@ -19,7 +19,7 @@ def test_series_grouper():
 
     labels = np.array([-1, -1, -1, 0, 0, 0, 1, 1, 1, 1], dtype=np.int64)
 
-    grouper = lib.SeriesGrouper(obj, np.mean, labels, 2, dummy)
+    grouper = reduction.SeriesGrouper(obj, np.mean, labels, 2, dummy)
     result, counts = grouper.get_result()
 
     expected = np.array([obj[3:6].mean(), obj[6:].mean()])
@@ -36,7 +36,7 @@ def test_series_bin_grouper():
 
     bins = np.array([3, 6])
 
-    grouper = lib.SeriesBinGrouper(obj, np.mean, bins, dummy)
+    grouper = reduction.SeriesBinGrouper(obj, np.mean, bins, dummy)
     result, counts = grouper.get_result()
 
     expected = np.array([obj[:3].mean(), obj[3:6].mean(), obj[6:].mean()])
@@ -127,26 +127,27 @@ def test_int_index(self):
         from pandas.core.series import Series
 
         arr = np.random.randn(100, 4)
-        result = lib.reduce(arr, np.sum, labels=Index(np.arange(4)))
+        result = reduction.reduce(arr, np.sum, labels=Index(np.arange(4)))
         expected = arr.sum(0)
         assert_almost_equal(result, expected)
 
-        result = lib.reduce(arr, np.sum, axis=1, labels=Index(np.arange(100)))
+        result = reduction.reduce(arr, np.sum, axis=1,
+                                  labels=Index(np.arange(100)))
         expected = arr.sum(1)
         assert_almost_equal(result, expected)
 
         dummy = Series(0., index=np.arange(100))
-        result = lib.reduce(arr, np.sum, dummy=dummy,
-                            labels=Index(np.arange(4)))
+        result = reduction.reduce(arr, np.sum, dummy=dummy,
+                                  labels=Index(np.arange(4)))
         expected = arr.sum(0)
         assert_almost_equal(result, expected)
 
         dummy = Series(0., index=np.arange(4))
-        result = lib.reduce(arr, np.sum, axis=1, dummy=dummy,
-                            labels=Index(np.arange(100)))
+        result = reduction.reduce(arr, np.sum, axis=1, dummy=dummy,
+                                  labels=Index(np.arange(100)))
         expected = arr.sum(1)
         assert_almost_equal(result, expected)
 
-        result = lib.reduce(arr, np.sum, axis=1, dummy=dummy,
-                            labels=Index(np.arange(100)))
+        result = reduction.reduce(arr, np.sum, axis=1, dummy=dummy,
+                                  labels=Index(np.arange(100)))
         assert_almost_equal(result, expected)

setup.py

@@ -309,6 +309,7 @@ class CheckSDist(sdist_class):
                  'pandas/_libs/interval.pyx',
                  'pandas/_libs/hashing.pyx',
                  'pandas/_libs/missing.pyx',
+                 'pandas/_libs/reduction.pyx',
                  'pandas/_libs/testing.pyx',
                  'pandas/_libs/window.pyx',
                  'pandas/_libs/skiplist.pyx',
@@ -506,6 +507,8 @@ def pxd(name):
                     'pandas/_libs/src/numpy_helper.h'],
         'sources': ['pandas/_libs/src/parser/tokenizer.c',
                     'pandas/_libs/src/parser/io.c']},
+    '_libs.reduction': {
+        'pyxfile': '_libs/reduction'},
     '_libs.tslibs.period': {
         'pyxfile': '_libs/tslibs/period',
         'pxdfiles': ['_libs/src/util',