ENH: speed up in1d() in the case of ar1 >> ar2. Closes #1603.

A timing script justifying the switching criterion is attached to ticket 1603.

Thanks to Neil Crighton.

numpy/lib/arraysetops.py

@@ -277,7 +277,7 @@ def setxor1d(ar1, ar2, assume_unique=False):
 
 def in1d(ar1, ar2, assume_unique=False):
     """
-    Test whether each element of a 1D array is also present in a second array.
+    Test whether each element of a 1-D array is also present in a second array.
 
     Returns a boolean array the same length as `ar1` that is True
     where an element of `ar1` is in `ar2` and False otherwise.
@@ -305,7 +305,7 @@ def in1d(ar1, ar2, assume_unique=False):
     Notes
     -----
     `in1d` can be considered as an element-wise function version of the
-    python keyword `in`, for 1D sequences. ``in1d(a, b)`` is roughly
+    python keyword `in`, for 1-D sequences. ``in1d(a, b)`` is roughly
     equivalent to ``np.array([item in b for item in a])``.
 
     .. versionadded:: 1.4.0
@@ -321,6 +321,14 @@ def in1d(ar1, ar2, assume_unique=False):
     array([0, 2, 0])
 
     """
+    # This code is significantly faster when the condition is satisfied.
+    if len(ar2) < 10 * len(ar1) ** 0.145:
+        mask = np.zeros(len(ar1), dtype=np.bool)
+        for a in ar2:
+            mask |= (ar1 == a)
+        return mask
+
+    # Otherwise use sorting
     if not assume_unique:
         ar1, rev_idx = np.unique(ar1, return_inverse=True)
         ar2 = np.unique(ar2)

numpy/lib/tests/test_arraysetops.py

@@ -90,66 +90,62 @@ def test_ediff1d(self):
         assert_array_equal([1],ediff1d(two_elem))
 
     def test_in1d(self):
-        a = np.array( [5, 7, 1, 2] )
-        b = np.array( [2, 4, 3, 1, 5] )
-
-        ec = np.array( [True, False, True, True] )
-        c = in1d( a, b, assume_unique=True )
-        assert_array_equal( c, ec )
-
-        a[0] = 8
-        ec = np.array( [False, False, True, True] )
-        c = in1d( a, b, assume_unique=True )
-        assert_array_equal( c, ec )
-
-        a[0], a[3] = 4, 8
-        ec = np.array( [True, False, True, False] )
-        c = in1d( a, b, assume_unique=True )
-        assert_array_equal( c, ec )
-
-        a = np.array([5,4,5,3,4,4,3,4,3,5,2,1,5,5])
-        b = [2,3,4]
-
-        ec = [False, True, False, True, True, True, True, True, True, False,
-              True, False, False, False]
-        c = in1d(a, b)
-        assert_array_equal(c, ec)
-
-        b = b + [5, 5, 4]
-
-        ec = [True, True, True, True, True, True, True, True, True, True,
-              True, False, True, True]
-        c = in1d(a, b)
-        assert_array_equal(c, ec)
-
-        a = np.array([5, 7, 1, 2])
-        b = np.array([2, 4, 3, 1, 5])
-
-        ec = np.array([True, False, True, True])
-        c = in1d(a, b)
-        assert_array_equal(c, ec)
-
-        a = np.array([5, 7, 1, 1, 2])
-        b = np.array([2, 4, 3, 3, 1, 5])
-
-        ec = np.array([True, False, True, True, True])
-        c = in1d(a, b)
-        assert_array_equal(c, ec)
+        # we use two different sizes for the b array here to test the
+        # two different paths in in1d().
+        for mult in (1, 10):
+            a = np.array([5, 7, 1, 2])
+            b = np.array([2, 4, 3, 1, 5] * mult)
+            ec = np.array([True, False, True, True])
+            c = in1d(a, b, assume_unique=True)
+            assert_array_equal(c, ec)
+
+            a[0] = 8
+            ec = np.array([False, False, True, True])
+            c = in1d(a, b, assume_unique=True)
+            assert_array_equal(c, ec)
+
+            a[0], a[3] = 4, 8
+            ec = np.array([True, False, True, False])
+            c = in1d(a, b, assume_unique=True)
+            assert_array_equal(c, ec)
+
+            a = np.array([5, 4, 5, 3, 4, 4, 3, 4, 3, 5, 2, 1, 5, 5])
+            b = [2, 3, 4] * mult
+            ec = [False, True, False, True, True, True, True, True, True, False,
+                  True, False, False, False]
+            c = in1d(a, b)
+            assert_array_equal(c, ec)
+
+            b = b + [5, 5, 4] * mult
+            ec = [True, True, True, True, True, True, True, True, True, True,
+                  True, False, True, True]
+            c = in1d(a, b)
+            assert_array_equal(c, ec)
+
+            a = np.array([5, 7, 1, 2])
+            b = np.array([2, 4, 3, 1, 5] * mult)
+            ec = np.array([True, False, True, True])
+            c = in1d(a, b)
+            assert_array_equal(c, ec)
+
+            a = np.array([5, 7, 1, 1, 2])
+            b = np.array([2, 4, 3, 3, 1, 5] * mult)
+            ec = np.array([True, False, True, True, True])
+            c = in1d(a, b)
+            assert_array_equal(c, ec)
+
+            a = np.array([5, 5])
+            b = np.array([2, 2] * mult)
+            ec = np.array([False, False])
+            c = in1d(a, b)
+            assert_array_equal(c, ec)
 
         a = np.array([5])
         b = np.array([2])
-
         ec = np.array([False])
         c = in1d(a, b)
         assert_array_equal(c, ec)
 
-        a = np.array([5, 5])
-        b = np.array([2, 2])
-
-        ec = np.array([False, False])
-        c = in1d(a, b)
-        assert_array_equal(c, ec)
-
         assert_array_equal(in1d([], []), [])
 
     def test_in1d_char_array( self ):