feature: Add LibSVM serializer

Author: edwardjkim

src/sagemaker/serializers.py

@@ -241,3 +241,27 @@ def serialize(self, data):
         buffer = io.BytesIO()
         scipy.sparse.save_npz(buffer, data)
         return buffer.getvalue()
+
+
+class LibSVMSerializer(BaseSerializer):
+    """Searilize data of various formats to a LibSVM-formatted string."""
+
+    CONTENT_TYPE = "text/libsvm"
+
+    def serialize(self, data):
+        """Serialize data of various formats to a LibSVM-formatted string.
+
+        Args:
+            data (object): Data to be serialized. Can be a string or a
+                file-like object.
+
+        Returns:
+            str: The data serialized as a LibSVM-formatted string.
+        """
+        if isinstance(data, str):
+            return data
+
+        if hasattr(data, "read"):
+            return data.read()
+
+        raise ValueError("Unable to handle input format: ", type(data))

src/sagemaker/xgboost/model.py

@@ -21,7 +21,7 @@
 from sagemaker.fw_utils import model_code_key_prefix
 from sagemaker.model import FrameworkModel, MODEL_SERVER_WORKERS_PARAM_NAME
 from sagemaker.predictor import Predictor
-from sagemaker.serializers import NumpySerializer
+from sagemaker.serializers import LibSVMSerializer
 from sagemaker.xgboost.defaults import XGBOOST_NAME
 
 logger = logging.getLogger("sagemaker")
@@ -44,7 +44,7 @@ def __init__(self, endpoint_name, sagemaker_session=None):
                 chain.
         """
         super(XGBoostPredictor, self).__init__(
-            endpoint_name, sagemaker_session, NumpySerializer(), CSVDeserializer()
+            endpoint_name, sagemaker_session, LibSVMSerializer(), CSVDeserializer()
         )
 
 

tests/data/xgboost_abalone/abalone

@@ -0,0 +1,5 @@
+15 1:1 2:0.455 3:0.365 4:0.095 5:0.514 6:0.2245 7:0.101 8:0.15
+7 1:1 2:0.35 3:0.265 4:0.09 5:0.2255 6:0.0995 7:0.0485 8:0.07
+9 1:2 2:0.53 3:0.42 4:0.135 5:0.677 6:0.2565 7:0.1415 8:0.21
+10 1:1 2:0.44 3:0.365 4:0.125 5:0.516 6:0.2155 7:0.114 8:0.155
+7 1:3 2:0.33 3:0.255 4:0.08 5:0.205 6:0.0895 7:0.0395 8:0.055

tests/unit/sagemaker/test_serializers.py

@@ -26,6 +26,7 @@
     JSONSerializer,
     SparseMatrixSerializer,
     JSONLinesSerializer,
+    LibSVMSerializer,
 )
 from tests.unit import DATA_DIR
 
@@ -298,3 +299,23 @@ def test_sparse_matrix_serializer(sparse_matrix_serializer):
     result = scipy.sparse.load_npz(stream).toarray()
     expected = data.toarray()
     assert np.array_equal(result, expected)
+
+
+@pytest.fixture
+def libsvm_serializer():
+    return LibSVMSerializer()
+
+
+def test_libsvm_serializer_str(libsvm_serializer):
+    original = "0 0:1 5:1"
+    result = libsvm_serializer.serialize("0 0:1 5:1")
+    assert result == original
+
+
+def test_libsvm_serializer_file_like(libsvm_serializer):
+    libsvm_file_path = os.path.join(DATA_DIR, "xgboost_abalone", "abalone")
+    with open(libsvm_file_path) as libsvm_file:
+        validation_data = libsvm_file.read()
+        libsvm_file.seek(0)
+        result = libsvm_serializer.serialize(libsvm_file)
+        assert result == validation_data