update

Eventual-Inc · Oct 25, 2024 · d5769f7 · d5769f7
1 parent b2a6bc1
commit d5769f7
Show file tree

Hide file tree

Showing 3 changed files with 3 additions and 3 deletions.
diff --git a/daft/expressions/expressions.py b/daft/expressions/expressions.py
@@ -1202,7 +1202,7 @@ def minhash(
             num_hashes: The number of hash permutations to compute.
             ngram_size: The number of tokens in each shingle/ngram.
             seed (optional): Seed used for generating permutations and the initial string hashes. Defaults to 1.
-            hash_function (optional): Hash function to use for initial string hashing. One of "murmur3", "xxhash", or "sha1". Defaults to "murmur3".
+            hash_function (optional): Hash function to use for initial string hashing. One of "murmurhash3", "xxhash", or "sha1". Defaults to "murmurhash3".
 
         """
         assert isinstance(num_hashes, int)

diff --git a/src/daft-sql/src/modules/hashing.rs b/src/daft-sql/src/modules/hashing.rs
@@ -95,7 +95,7 @@ impl TryFrom<SQLFunctionArguments> for MinHashFunction {
                     })
             })
             .transpose()?
-            .unwrap_or("murmur3");
+            .unwrap_or("murmur3hash3");
 
         Ok(Self {
             num_hashes,

diff --git a/tests/series/test_minhash.py b/tests/series/test_minhash.py
@@ -41,7 +41,7 @@ def minhash_none(
 @pytest.mark.parametrize("num_hashes", [1, 2, 16, 128])
 @pytest.mark.parametrize("ngram_size", [1, 2, 4, 5, 100])
 @pytest.mark.parametrize("seed", [1, -1, 123, None])
-@pytest.mark.parametrize("hash_function", ["murmur3", "xxhash", "sha1"])
+@pytest.mark.parametrize("hash_function", ["murmurhash3", "xxhash", "sha1"])
 def test_minhash(num_hashes, ngram_size, seed, hash_function):
     minhash = minhash_none(test_series, num_hashes, ngram_size, seed, hash_function)
     assert minhash[4] is None and minhash[-1] is None