membership operator for lsh

README.md

@@ -172,9 +172,16 @@ lsh = MinHashLSH(threshold=0.5, num_perm=128)
 lsh.insert("m2", m2)
 lsh.insert("m3", m3)
 
+# Check for membership using the key
+print("m2" in lsh)
+print("m3" in lsh)
+
 # Using m1 as the query, retrieve the keys of the qualifying datasets
 result = lsh.query(m1)
 print("Candidates with Jaccard similarity > 0.5", result)
+
+# Remove key from lsh
+lsh.remove("m2")
 ```
 
 The Jaccard similarity threshold must be set at initialization, and cannot

datasketch/lsh.py

@@ -99,6 +99,12 @@ def is_empty(self):
     def _H(self, hs):
         return "".join("%.8x" % h for h in hs)
 
+    def __contains__(self, key):
+        '''
+        Return True only if the key exists in the index.
+        '''
+        return key in self.keys
+
     def insert(self, key, minhash):
         '''
         Insert a unique `key` to the index, together
@@ -133,9 +139,9 @@ def query(self, minhash):
                     candidates.add(key)
         return list(candidates)
 
-    def delete(self, key):
+    def remove(self, key):
         '''
-        Delete the key from the index.
+        Remove the key from the index.
         '''
         if key not in self.keys:
             raise ValueError("The given key does not exist")

setup.py

@@ -20,7 +20,7 @@
     # Versions should comply with PEP440.  For a discussion on single-sourcing
     # the version across setup.py and the project code, see
     # https://packaging.python.org/en/latest/single_source_version.html
-    version='0.2.2',
+    version='0.2.3',
 
     description='Probabilistic data structures for processing very large datasets',
     long_description=long_description,

test/lsh_test.py

@@ -33,8 +33,8 @@ def test_insert(self):
                 items.extend(t[H])
             self.assertTrue("a" in items)
             self.assertTrue("b" in items)
-        self.assertTrue("a" in lsh.keys)
-        self.assertTrue("b" in lsh.keys)
+        self.assertTrue("a" in lsh)
+        self.assertTrue("b" in lsh)
         for i, H in enumerate(lsh.keys["a"]):
             self.assertTrue("a" in lsh.hashtables[i][H])
 
@@ -57,7 +57,7 @@ def test_query(self):
         m3 = MinHash(18)
         self.assertRaises(ValueError, lsh.query, m3)
 
-    def test_delete(self):
+    def test_remove(self):
         lsh = MinHashLSH(threshold=0.5, num_perm=16)
         m1 = MinHash(16)
         m1.update("a".encode("utf8"))
@@ -66,14 +66,14 @@ def test_delete(self):
         lsh.insert("a", m1)
         lsh.insert("b", m2)
 
-        lsh.delete("a")
+        lsh.remove("a")
         self.assertTrue("a" not in lsh.keys)
         for table in lsh.hashtables:
             for H in table:
                 self.assertGreater(len(table[H]), 0)
                 self.assertTrue("a" not in table[H])
 
-        self.assertRaises(ValueError, lsh.delete, "c")
+        self.assertRaises(ValueError, lsh.remove, "c")
 
     def test_pickle(self):
         lsh = MinHashLSH(threshold=0.5, num_perm=16)
@@ -115,8 +115,8 @@ def test_insert(self):
                 items.extend(t[H])
             self.assertTrue("a" in items)
             self.assertTrue("b" in items)
-        self.assertTrue("a" in lsh.keys)
-        self.assertTrue("b" in lsh.keys)
+        self.assertTrue("a" in lsh)
+        self.assertTrue("b" in lsh)
         for i, H in enumerate(lsh.keys["a"]):
             self.assertTrue("a" in lsh.hashtables[i][H])
 
@@ -140,22 +140,22 @@ def test_query(self):
         m3 = mg.minhash(np.random.uniform(1, 10, 10))
         self.assertRaises(ValueError, lsh.query, m3)
 
-    def test_delete(self):
+    def test_remove(self):
         lsh = WeightedMinHashLSH(threshold=0.5, sample_size=4)
         mg = WeightedMinHashGenerator(10, 4)
         m1 = mg.minhash(np.random.uniform(1, 10, 10))
         m2 = mg.minhash(np.random.uniform(1, 10, 10))
         lsh.insert("a", m1)
         lsh.insert("b", m2)
 
-        lsh.delete("a")
+        lsh.remove("a")
         self.assertTrue("a" not in lsh.keys)
         for table in lsh.hashtables:
             for H in table:
                 self.assertGreater(len(table[H]), 0)
                 self.assertTrue("a" not in table[H])
 
-        self.assertRaises(ValueError, lsh.delete, "c")
+        self.assertRaises(ValueError, lsh.remove, "c")
 
     def test_pickle(self):
         lsh = WeightedMinHashLSH(threshold=0.5, sample_size=4)