CLN: Remove special handling of nans in the float64-case of isin

It is no longer needed because the hash-table handles the nans correctly out of the box (see GH21866)

Not having to scan the values via isna(...).any()  will improve the perfomance.

Author: realead

pandas/_libs/hashtable_func_helper.pxi.in

@@ -210,10 +210,10 @@ def duplicated_{{dtype}}({{scalar}}[:] values, object keep='first'):
 @cython.boundscheck(False)
 {{if dtype == 'object'}}
 
-def ismember_{{dtype}}(ndarray[{{scalar}}] arr, ndarray[{{scalar}}] values, bint hasnans=0):
+def ismember_{{dtype}}(ndarray[{{scalar}}] arr, ndarray[{{scalar}}] values):
 {{else}}
 
-def ismember_{{dtype}}({{scalar}}[:] arr, {{scalar}}[:] values, bint hasnans=0):
+def ismember_{{dtype}}({{scalar}}[:] arr, {{scalar}}[:] values):
 {{endif}}
 
     """
@@ -224,7 +224,6 @@ def ismember_{{dtype}}({{scalar}}[:] arr, {{scalar}}[:] values, bint hasnans=0):
     ----------
     arr : {{dtype}} ndarray
     values : {{dtype}} ndarray
-    hasnans : bint, optional
 
     Returns
     -------
@@ -259,19 +258,13 @@ def ismember_{{dtype}}({{scalar}}[:] arr, {{scalar}}[:] values, bint hasnans=0):
     for i in range(n):
         val = arr[i]
         k = kh_get_{{ttype}}(table, <PyObject*> val)
-        if k != table.n_buckets:
-            result[i] = 1
-        else:
-            result[i] = hasnans and val != val
+        result[i] = (k != table.n_buckets)
     {{else}}
     with nogil:
         for i in range(n):
             val = arr[i]
             k = kh_get_{{ttype}}(table, val)
-            if k != table.n_buckets:
-                result[i] = 1
-            else:
-                result[i] = hasnans and val != val
+            result[i] = (k != table.n_buckets)
     {{endif}}
 
     kh_destroy_{{ttype}}(table)

pandas/core/algorithms.py

@@ -437,8 +437,7 @@ def isin(comps, values):
         try:
             values = values.astype('float64', copy=False)
             comps = comps.astype('float64', copy=False)
-            checknull = isna(values).any()
-            f = lambda x, y: htable.ismember_float64(x, y, checknull)
+            f = lambda x, y: htable.ismember_float64(x, y)
         except (TypeError, ValueError):
             values = values.astype(object)
             comps = comps.astype(object)

pandas/tests/test_algos.py

@@ -623,6 +623,27 @@ def test_empty(self, empty):
         result = algos.isin(vals, empty)
         tm.assert_numpy_array_equal(expected, result)
 
+    def test_different_nans_as_float64(self):
+        # create different nans from bit-patterns,
+        # these nans will land in different buckets in the hash-table
+        # if no special care is taken
+        NAN1 = struct.unpack("d", struct.pack("=Q", 0x7ff8000000000000))[0]
+        NAN2 = struct.unpack("d", struct.pack("=Q", 0x7ff8000000000001))[0]
+        assert NAN1 != NAN1
+        assert NAN2 != NAN2
+
+        # check that NAN1 and NAN2 are equivalent:
+        arr = np.array([NAN1, NAN2], dtype=np.float64)
+        lookup1 = np.array([NAN1], dtype=np.float64)
+        result = algos.isin(arr, lookup1)
+        expected = np.array([True, True])
+        tm.assert_numpy_array_equal(result, expected)
+
+        lookup2 = np.array([NAN2], dtype=np.float64)
+        result = algos.isin(arr, lookup2)
+        expected = np.array([True, True])
+        tm.assert_numpy_array_equal(result, expected)
+
 
 class TestValueCounts(object):