From c131bf09b60f395440afed4e1fdbaadedeb46726 Mon Sep 17 00:00:00 2001
From: Jayaram Kancherla <jayaram.kancherla@gmail.com>
Date: Wed, 27 Aug 2025 08:27:25 +0530
Subject: [PATCH 01/28] Use typed lists from biocutils for compressed lists

---
 src/compressed_lists/__init__.py              |  8 +-
 .../{CompressedList.py => base.py}            |  2 +-
 src/compressed_lists/bool_list.py             | 99 +++++++++++++++++++
 src/compressed_lists/float_list.py            | 99 +++++++++++++++++++
 ...mpressedIntegerList.py => integer_list.py} | 23 +++--
 ...CompressedStringList.py => string_list.py} | 20 +++-
 tests/test_comp_bool.py                       | 33 +++++++
 tests/test_comp_float.py                      | 33 +++++++
 tests/test_comp_int.py                        | 54 +++++-----
 tests/test_comp_str.py                        | 15 +--
 10 files changed, 336 insertions(+), 50 deletions(-)
 rename src/compressed_lists/{CompressedList.py => base.py} (99%)
 create mode 100644 src/compressed_lists/bool_list.py
 create mode 100644 src/compressed_lists/float_list.py
 rename src/compressed_lists/{CompressedIntegerList.py => integer_list.py} (75%)
 rename src/compressed_lists/{CompressedStringList.py => string_list.py} (77%)
 create mode 100644 tests/test_comp_bool.py
 create mode 100644 tests/test_comp_float.py

diff --git a/src/compressed_lists/__init__.py b/src/compressed_lists/__init__.py
index b320c98..5d615de 100644
--- a/src/compressed_lists/__init__.py
+++ b/src/compressed_lists/__init__.py
@@ -16,6 +16,8 @@
     del version, PackageNotFoundError
 
 from .partition import Partitioning
-from .CompressedList import CompressedList
-from .CompressedIntegerList import CompressedIntegerList
-from .CompressedStringList import CompressedStringList
+from .base import CompressedList
+from .integer_list import CompressedIntegerList
+from .string_list import CompressedStringList, CompressedCharacterList
+from .bool_list import CompressedBooleanList
+from .float_list import CompressedFloatList
\ No newline at end of file
diff --git a/src/compressed_lists/CompressedList.py b/src/compressed_lists/base.py
similarity index 99%
rename from src/compressed_lists/CompressedList.py
rename to src/compressed_lists/base.py
index 0f629bd..8422756 100644
--- a/src/compressed_lists/CompressedList.py
+++ b/src/compressed_lists/base.py
@@ -43,7 +43,7 @@ def __init__(
                 Vector-like object containing concatenated elements.
 
             partitioning:
-                Partitioning object defining element boundaries.
+                Partitioning object defining element boundaries (exclusive).
 
             element_type:
                 String identifier for the type of elements.
diff --git a/src/compressed_lists/bool_list.py b/src/compressed_lists/bool_list.py
new file mode 100644
index 0000000..4b1ac4f
--- /dev/null
+++ b/src/compressed_lists/bool_list.py
@@ -0,0 +1,99 @@
+from typing import List, Optional, Sequence
+
+from biocutils.BooleanList import BooleanList
+
+from .base import CompressedList
+from .partition import Partitioning
+
+__author__ = "Jayaram Kancherla"
+__copyright__ = "Jayaram Kancherla"
+__license__ = "MIT"
+
+
+class CompressedBooleanList(CompressedList):
+    """CompressedList implementation for lists of integers."""
+
+    def __init__(
+        self,
+        unlist_data: BooleanList,
+        partitioning: Partitioning,
+        element_metadata: dict = None,
+        metadata: dict = None,
+        **kwargs,
+    ):
+        """Initialize a CompressedIntegerList.
+
+        Args:
+            unlist_data:
+                List of booleans.
+
+            partitioning:
+                Partitioning object defining element boundaries.
+
+            element_metadata:
+                Optional metadata for elements.
+
+            metadata:
+                Optional general metadata.
+
+            kwargs:
+                Additional arguments.
+        """
+
+        if not isinstance(unlist_data, BooleanList):
+            try:
+                unlist_data = BooleanList(unlist_data)
+            except Exception as e:
+                raise TypeError("'unlist_data' must be an `BooleanList`, provided ", type(unlist_data)) from e
+
+        super().__init__(
+            unlist_data, partitioning, element_type="integer", element_metadata=element_metadata, metadata=metadata
+        )
+
+    def _extract_range(self, start: int, end: int) -> BooleanList:
+        """Extract a range from unlist_data.
+
+        Args:
+            start:
+                Start index (inclusive).
+
+            end:
+                End index (exclusive).
+
+        Returns:
+            Same type as unlist_data.
+        """
+        return self._unlist_data[start:end]
+
+    @classmethod
+    def from_list(
+        cls, lst: List[List[bool]], names: Optional[Sequence[str]] = None, metadata: dict = None
+    ) -> "CompressedBooleanList":
+        """
+        Create a `CompressedBooleanList` from a list of integer lists.
+
+        Args:
+            lst:
+                List of integer lists.
+
+            names:
+                Optional names for list elements.
+
+            metadata:
+                Optional metadata.
+
+        Returns:
+            A new `CompressedBooleanList`.
+        """
+        # Flatten the list
+        flat_data = []
+        for sublist in lst:
+            flat_data.extend(sublist)
+
+        # Create partitioning
+        partitioning = Partitioning.from_list(lst, names)
+
+        # Create unlist_data
+        unlist_data = BooleanList(data=flat_data)
+
+        return cls(unlist_data, partitioning, metadata=metadata)
diff --git a/src/compressed_lists/float_list.py b/src/compressed_lists/float_list.py
new file mode 100644
index 0000000..2a87d53
--- /dev/null
+++ b/src/compressed_lists/float_list.py
@@ -0,0 +1,99 @@
+from typing import List, Optional, Sequence
+
+from biocutils.FloatList import FloatList
+
+from .base import CompressedList
+from .partition import Partitioning
+
+__author__ = "Jayaram Kancherla"
+__copyright__ = "Jayaram Kancherla"
+__license__ = "MIT"
+
+
+class CompressedFloatList(CompressedList):
+    """CompressedList implementation for lists of integers."""
+
+    def __init__(
+        self,
+        unlist_data: FloatList,
+        partitioning: Partitioning,
+        element_metadata: dict = None,
+        metadata: dict = None,
+        **kwargs,
+    ):
+        """Initialize a CompressedIntegerList.
+
+        Args:
+            unlist_data:
+                List of floats.
+
+            partitioning:
+                Partitioning object defining element boundaries.
+
+            element_metadata:
+                Optional metadata for elements.
+
+            metadata:
+                Optional general metadata.
+
+            kwargs:
+                Additional arguments.
+        """
+
+        if not isinstance(unlist_data, FloatList):
+            try:
+                unlist_data = FloatList(unlist_data)
+            except Exception as e:
+                raise TypeError("'unlist_data' must be an `FloatList`, provided ", type(unlist_data)) from e
+
+        super().__init__(
+            unlist_data, partitioning, element_type="integer", element_metadata=element_metadata, metadata=metadata
+        )
+
+    def _extract_range(self, start: int, end: int) -> FloatList:
+        """Extract a range from unlist_data.
+
+        Args:
+            start:
+                Start index (inclusive).
+
+            end:
+                End index (exclusive).
+
+        Returns:
+            Same type as unlist_data.
+        """
+        return self._unlist_data[start:end]
+
+    @classmethod
+    def from_list(
+        cls, lst: List[List[bool]], names: Optional[Sequence[str]] = None, metadata: dict = None
+    ) -> "CompressedFloatList":
+        """
+        Create a `CompressedFloatList` from a list of integer lists.
+
+        Args:
+            lst:
+                List of integer lists.
+
+            names:
+                Optional names for list elements.
+
+            metadata:
+                Optional metadata.
+
+        Returns:
+            A new `CompressedFloatList`.
+        """
+        # Flatten the list
+        flat_data = []
+        for sublist in lst:
+            flat_data.extend(sublist)
+
+        # Create partitioning
+        partitioning = Partitioning.from_list(lst, names)
+
+        # Create unlist_data
+        unlist_data = FloatList(data=flat_data)
+
+        return cls(unlist_data, partitioning, metadata=metadata)
diff --git a/src/compressed_lists/CompressedIntegerList.py b/src/compressed_lists/integer_list.py
similarity index 75%
rename from src/compressed_lists/CompressedIntegerList.py
rename to src/compressed_lists/integer_list.py
index 5d3bae9..678b80b 100644
--- a/src/compressed_lists/CompressedIntegerList.py
+++ b/src/compressed_lists/integer_list.py
@@ -1,8 +1,8 @@
 from typing import List, Optional, Sequence
 
-import numpy as np
+from biocutils.IntegerList import IntegerList
 
-from .CompressedList import CompressedList
+from .base import CompressedList
 from .partition import Partitioning
 
 __author__ = "Jayaram Kancherla"
@@ -15,7 +15,7 @@ class CompressedIntegerList(CompressedList):
 
     def __init__(
         self,
-        unlist_data: np.ndarray,
+        unlist_data: IntegerList,
         partitioning: Partitioning,
         element_metadata: dict = None,
         metadata: dict = None,
@@ -25,7 +25,7 @@ def __init__(
 
         Args:
             unlist_data:
-                NumPy array of integers.
+                List of integers.
 
             partitioning:
                 Partitioning object defining element boundaries.
@@ -39,11 +39,18 @@ def __init__(
             kwargs:
                 Additional arguments.
         """
+
+        if not isinstance(unlist_data, IntegerList):
+            try:
+                unlist_data = IntegerList(unlist_data)
+            except Exception as e:
+                raise TypeError("'unlist_data' must be an `IntegerList`, provided ", type(unlist_data)) from e
+
         super().__init__(
             unlist_data, partitioning, element_type="integer", element_metadata=element_metadata, metadata=metadata
         )
 
-    def _extract_range(self, start: int, end: int) -> np.ndarray:
+    def _extract_range(self, start: int, end: int) -> IntegerList:
         """Extract a range from unlist_data.
 
         Args:
@@ -63,7 +70,7 @@ def from_list(
         cls, lst: List[List[int]], names: Optional[Sequence[str]] = None, metadata: dict = None
     ) -> "CompressedIntegerList":
         """
-        Create a CompressedIntegerList from a list of integer lists.
+        Create a `CompressedIntegerList` from a list of integer lists.
 
         Args:
             lst:
@@ -76,7 +83,7 @@ def from_list(
                 Optional metadata.
 
         Returns:
-            A new CompressedIntegerList.
+            A new `CompressedIntegerList`.
         """
         # Flatten the list
         flat_data = []
@@ -87,6 +94,6 @@ def from_list(
         partitioning = Partitioning.from_list(lst, names)
 
         # Create unlist_data
-        unlist_data = np.array(flat_data, dtype=np.int64)
+        unlist_data = IntegerList(data=flat_data)
 
         return cls(unlist_data, partitioning, metadata=metadata)
diff --git a/src/compressed_lists/CompressedStringList.py b/src/compressed_lists/string_list.py
similarity index 77%
rename from src/compressed_lists/CompressedStringList.py
rename to src/compressed_lists/string_list.py
index 88cce67..863229c 100644
--- a/src/compressed_lists/CompressedStringList.py
+++ b/src/compressed_lists/string_list.py
@@ -1,6 +1,8 @@
 from typing import List, Optional, Sequence
 
-from .CompressedList import CompressedList
+from biocutils.StringList import StringList
+
+from .base import CompressedList
 from .partition import Partitioning
 
 __author__ = "Jayaram Kancherla"
@@ -13,7 +15,7 @@ class CompressedStringList(CompressedList):
 
     def __init__(
         self,
-        unlist_data: List[str],
+        unlist_data: StringList,
         partitioning: Partitioning,
         element_metadata: dict = None,
         metadata: dict = None,
@@ -37,11 +39,17 @@ def __init__(
             kwargs:
                 Additional arguments.
         """
+        if not isinstance(unlist_data, StringList):
+            try:
+                unlist_data = StringList(unlist_data)
+            except Exception as e:
+                raise TypeError("'unlist_data' must be an `StringList`, provided ", type(unlist_data)) from e
+
         super().__init__(
             unlist_data, partitioning, element_type="string", element_metadata=element_metadata, metadata=metadata
         )
 
-    def _extract_range(self, start: int, end: int) -> List[str]:
+    def _extract_range(self, start: int, end: int) -> StringList:
         """Extract a range from unlist_data.
 
         Args:
@@ -83,4 +91,8 @@ def from_list(
         # Create partitioning
         partitioning = Partitioning.from_list(lst, names)
 
-        return cls(flat_data, partitioning, metadata=metadata)
+        return cls(StringList(flat_data), partitioning, metadata=metadata)
+
+
+class CompressedCharacterList(CompressedStringList):
+    pass
diff --git a/tests/test_comp_bool.py b/tests/test_comp_bool.py
new file mode 100644
index 0000000..077ae35
--- /dev/null
+++ b/tests/test_comp_bool.py
@@ -0,0 +1,33 @@
+import pytest
+from biocutils.BooleanList import BooleanList
+
+from compressed_lists import CompressedBooleanList
+
+__author__ = "Jayaram Kancherla"
+__copyright__ = "Jayaram Kancherla"
+__license__ = "MIT"
+
+
+@pytest.fixture
+def bool_data():
+    return [[True, False], [False, True, False], [False]]
+
+
+@pytest.fixture
+def bool_list(bool_data):
+    names = ["fruits1", "fruits2", "fruits3"]
+    return CompressedBooleanList.from_list(bool_data, names)
+
+
+def test_creation(bool_data):
+    bool_list = CompressedBooleanList.from_list(bool_data)
+
+    assert len(bool_list) == 3
+    assert isinstance(bool_list.unlist_data, BooleanList)
+    assert list(bool_list.get_unlist_data()) == [True, False, False, True, False, False]
+    assert list(bool_list.get_element_lengths()) == [2, 3, 1]
+
+
+def test_getitem(bool_list):
+    assert list(bool_list[0]) == [True, False]
+    assert list(bool_list["fruits2"]) == [False, True, False]
diff --git a/tests/test_comp_float.py b/tests/test_comp_float.py
new file mode 100644
index 0000000..1913508
--- /dev/null
+++ b/tests/test_comp_float.py
@@ -0,0 +1,33 @@
+import pytest
+from biocutils.FloatList import FloatList
+
+from compressed_lists import CompressedFloatList
+
+__author__ = "Jayaram Kancherla"
+__copyright__ = "Jayaram Kancherla"
+__license__ = "MIT"
+
+
+@pytest.fixture
+def float_data():
+    return [[1.1, 1.2], [2.1, 2.2, 2.3], [3]]
+
+
+@pytest.fixture
+def float_list(float_data):
+    names = ["fruits1", "fruits2", "fruits3"]
+    return CompressedFloatList.from_list(float_data, names)
+
+
+def test_creation(float_data):
+    float_list = CompressedFloatList.from_list(float_data)
+
+    assert len(float_list) == 3
+    assert isinstance(float_list.unlist_data, FloatList)
+    assert list(float_list.get_unlist_data()) == [1.1, 1.2, 2.1, 2.2, 2.3, 3.0]
+    assert list(float_list.get_element_lengths()) == [2, 3, 1]
+
+
+def test_getitem(float_list):
+    assert list(float_list[0]) == [1.1, 1.2]
+    assert list(float_list["fruits2"]) == [2.1, 2.2, 2.3]
diff --git a/tests/test_comp_int.py b/tests/test_comp_int.py
index 5771031..daac5d5 100644
--- a/tests/test_comp_int.py
+++ b/tests/test_comp_int.py
@@ -1,5 +1,6 @@
 import numpy as np
 import pytest
+from biocutils.IntegerList import IntegerList
 
 from compressed_lists import CompressedIntegerList, Partitioning
 
@@ -23,16 +24,16 @@ def test_creation(int_data):
     int_list = CompressedIntegerList.from_list(int_data)
 
     assert len(int_list) == 3
-    assert isinstance(int_list.unlist_data, np.ndarray)
+    assert isinstance(int_list.unlist_data, IntegerList)
     assert list(int_list.get_unlist_data()) == [1, 2, 3, 4, 5, 6, 7, 8, 9]
     assert list(int_list.get_element_lengths()) == [3, 2, 4]
 
 
 def test_creation_from_parts():
-    int_list = CompressedIntegerList(np.array([1, 2, 3, 4, 5, 6, 7, 8, 9]), Partitioning(ends=[3, 5, 9]))
+    int_list = CompressedIntegerList([1, 2, 3, 4, 5, 6, 7, 8, 9], Partitioning(ends=[3, 5, 9]))
 
     assert len(int_list) == 3
-    assert isinstance(int_list.unlist_data, np.ndarray)
+    assert isinstance(int_list.unlist_data, IntegerList)
     assert list(int_list.get_unlist_data()) == [1, 2, 3, 4, 5, 6, 7, 8, 9]
     assert list(int_list.get_element_lengths()) == [3, 2, 4]
 
@@ -45,7 +46,7 @@ def test_creation_with_names(int_data):
 
 
 def test_validation():
-    data = np.array([1, 2, 3, 4, 5])
+    data = IntegerList([1, 2, 3, 4, 5])
     partitioning = Partitioning([2, 4, 7])
 
     with pytest.raises(ValueError):
@@ -53,20 +54,19 @@ def test_validation():
 
 
 def test_getitem_by_index(int_list):
-    assert np.allclose(int_list[0], [1, 2, 3])
-    assert np.allclose(int_list[1], [4, 5])
-    assert np.allclose(int_list[2], [6, 7, 8, 9])
-
-    assert np.allclose(int_list[-1], [6, 7, 8, 9])
+    assert np.allclose(list(int_list[0]), [1, 2, 3])
+    assert np.allclose(list(int_list[1]), [4, 5])
+    assert np.allclose(list(int_list[2]), [6, 7, 8, 9])
+    assert np.allclose(list(int_list[-1]), [6, 7, 8, 9])
 
     with pytest.raises(IndexError):
         int_list[3]
 
 
 def test_getitem_by_name(int_list):
-    assert np.allclose(int_list["A"], [1, 2, 3])
-    assert np.allclose(int_list["B"], [4, 5])
-    assert np.allclose(int_list["C"], [6, 7, 8, 9])
+    assert np.allclose(list(int_list["A"]), [1, 2, 3])
+    assert np.allclose(list(int_list["B"]), [4, 5])
+    assert np.allclose(list(int_list["C"]), [6, 7, 8, 9])
 
     with pytest.raises(KeyError):
         int_list["D"]
@@ -76,8 +76,8 @@ def test_getitem_by_slice(int_list):
     sliced = int_list[1:3]
 
     assert len(sliced) == 2
-    assert np.allclose(sliced[0], [4, 5])
-    assert np.allclose(sliced[1], [6, 7, 8, 9])
+    assert np.allclose(list(sliced[0]), [4, 5])
+    assert np.allclose(list(sliced[1]), [6, 7, 8, 9])
     assert list(sliced.names) == ["B", "C"]
 
     # Empty slice
@@ -89,41 +89,41 @@ def test_iteration(int_list, int_data):
     items = list(int_list)
     print(items, int_data)
     for i, lst in enumerate(items):
-        assert np.allclose(lst, int_data[i])
+        assert np.allclose(list(lst), int_data[i])
 
 
 def test_to_list(int_list, int_data):
     regular_list = int_list.to_list()
     for i, lst in enumerate(regular_list):
-        assert np.allclose(lst, int_data[i])
+        assert np.allclose(list(lst), int_data[i])
 
 
 def test_unlist(int_list):
     unlisted = int_list.unlist()
-    assert isinstance(unlisted, np.ndarray)
+    assert isinstance(unlisted, IntegerList)
     assert np.allclose(list(unlisted), [1, 2, 3, 4, 5, 6, 7, 8, 9])
 
 
 def test_relist(int_list):
-    new_data = np.array([10, 20, 30, 40, 50, 60, 70, 80, 90], dtype=np.int64)
+    new_data = IntegerList([10, 20, 30, 40, 50, 60, 70, 80, 90])
     relisted = int_list.relist(new_data)
 
     assert len(relisted) == len(int_list)
     assert list(relisted.get_names()) == list(int_list.names)
-    assert np.allclose(relisted[0], [10, 20, 30])
-    assert np.allclose(relisted[1], [40, 50])
-    assert np.allclose(relisted[2], [60, 70, 80, 90])
+    assert np.allclose(list(relisted[0]), [10, 20, 30])
+    assert np.allclose(list(relisted[1]), [40, 50])
+    assert np.allclose(list(relisted[2]), [60, 70, 80, 90])
 
     with pytest.raises(ValueError):
-        int_list.relist(np.array([1, 2, 3]))
+        int_list.relist(IntegerList([1, 2, 3]))
 
 
 def test_extract_subset(int_list):
     subset = int_list.extract_subset([0, 2])
 
     assert len(subset) == 2
-    assert np.allclose(subset[0], [1, 2, 3])
-    assert np.allclose(subset[1], [6, 7, 8, 9])
+    assert np.allclose(list(subset[0]), [1, 2, 3])
+    assert np.allclose(list(subset[1]), [6, 7, 8, 9])
     assert list(subset.names) == ["A", "C"]
 
     with pytest.raises(IndexError):
@@ -134,6 +134,6 @@ def test_lapply(int_list):
     squared = int_list.lapply(lambda x: [i**2 for i in x])
 
     assert len(squared) == len(int_list)
-    assert np.allclose(squared[0], [1, 4, 9])
-    assert np.allclose(squared[1], [16, 25])
-    assert np.allclose(squared[2], [36, 49, 64, 81])
+    assert np.allclose(list(squared[0]), [1, 4, 9])
+    assert np.allclose(list(squared[1]), [16, 25])
+    assert np.allclose(list(squared[2]), [36, 49, 64, 81])
diff --git a/tests/test_comp_str.py b/tests/test_comp_str.py
index ef54f8c..d65adbd 100644
--- a/tests/test_comp_str.py
+++ b/tests/test_comp_str.py
@@ -1,4 +1,5 @@
 import pytest
+from biocutils.StringList import StringList
 
 from compressed_lists import CompressedStringList
 
@@ -22,20 +23,20 @@ def test_creation(char_data):
     char_list = CompressedStringList.from_list(char_data)
 
     assert len(char_list) == 3
-    assert isinstance(char_list.unlist_data, list)
-    assert char_list.get_unlist_data() == ["apple", "banana", "cherry", "date", "elderberry", "fig"]
+    assert isinstance(char_list.unlist_data, StringList)
+    assert list(char_list.get_unlist_data()) == ["apple", "banana", "cherry", "date", "elderberry", "fig"]
     assert list(char_list.get_element_lengths()) == [2, 3, 1]
 
 
 def test_getitem(char_list):
-    assert char_list[0] == ["apple", "banana"]
-    assert char_list["fruits2"] == ["cherry", "date", "elderberry"]
+    assert list(char_list[0]) == ["apple", "banana"]
+    assert list(char_list["fruits2"]) == ["cherry", "date", "elderberry"]
 
 
 def test_lapply(char_list):
     uppercased = char_list.lapply(lambda x: [s.upper() for s in x])
 
     assert len(uppercased) == len(char_list)
-    assert uppercased[0] == ["APPLE", "BANANA"]
-    assert uppercased[1] == ["CHERRY", "DATE", "ELDERBERRY"]
-    assert uppercased[2] == ["FIG"]
+    assert list(uppercased[0]) == ["APPLE", "BANANA"]
+    assert list(uppercased[1]) == ["CHERRY", "DATE", "ELDERBERRY"]
+    assert list(uppercased[2]) == ["FIG"]

From 1d01f858431e4b5c28954850d04191e791350b33 Mon Sep 17 00:00:00 2001
From: Jayaram Kancherla <jayaram.kancherla@gmail.com>
Date: Wed, 27 Aug 2025 08:28:17 +0530
Subject: [PATCH 02/28] Update changelog

---
 CHANGELOG.md | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 792a416..fb081ab 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -1,5 +1,9 @@
 # Changelog
 
+## Version 0.2.0
+
+- Switch to typed lists from the biocutils package.
+
 ## Version 0.1.0 - 0.1.1
 
 - Initial implementation of various classes - Partitioning and CompressedLists.

From c475591c7e644ffa32cb158badfa6c612f31763d Mon Sep 17 00:00:00 2001
From: "pre-commit-ci[bot]"
 <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Date: Wed, 27 Aug 2025 02:58:59 +0000
Subject: [PATCH 03/28] [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci
---
 src/compressed_lists/__init__.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/compressed_lists/__init__.py b/src/compressed_lists/__init__.py
index 5d615de..baa8bb1 100644
--- a/src/compressed_lists/__init__.py
+++ b/src/compressed_lists/__init__.py
@@ -20,4 +20,4 @@
 from .integer_list import CompressedIntegerList
 from .string_list import CompressedStringList, CompressedCharacterList
 from .bool_list import CompressedBooleanList
-from .float_list import CompressedFloatList
\ No newline at end of file
+from .float_list import CompressedFloatList

From 4b9ca3d625d743c83dbac79631b98e2fa5b9b1d1 Mon Sep 17 00:00:00 2001
From: Jayaram Kancherla <jayaram.kancherla@gmail.com>
Date: Wed, 27 Aug 2025 08:30:37 +0530
Subject: [PATCH 04/28] fix element type

---
 src/compressed_lists/bool_list.py  | 2 +-
 src/compressed_lists/float_list.py | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/src/compressed_lists/bool_list.py b/src/compressed_lists/bool_list.py
index 4b1ac4f..deb16ca 100644
--- a/src/compressed_lists/bool_list.py
+++ b/src/compressed_lists/bool_list.py
@@ -47,7 +47,7 @@ def __init__(
                 raise TypeError("'unlist_data' must be an `BooleanList`, provided ", type(unlist_data)) from e
 
         super().__init__(
-            unlist_data, partitioning, element_type="integer", element_metadata=element_metadata, metadata=metadata
+            unlist_data, partitioning, element_type="boolean", element_metadata=element_metadata, metadata=metadata
         )
 
     def _extract_range(self, start: int, end: int) -> BooleanList:
diff --git a/src/compressed_lists/float_list.py b/src/compressed_lists/float_list.py
index 2a87d53..4ca3c60 100644
--- a/src/compressed_lists/float_list.py
+++ b/src/compressed_lists/float_list.py
@@ -47,7 +47,7 @@ def __init__(
                 raise TypeError("'unlist_data' must be an `FloatList`, provided ", type(unlist_data)) from e
 
         super().__init__(
-            unlist_data, partitioning, element_type="integer", element_metadata=element_metadata, metadata=metadata
+            unlist_data, partitioning, element_type="float", element_metadata=element_metadata, metadata=metadata
         )
 
     def _extract_range(self, start: int, end: int) -> FloatList:

From 220aad0e840ad1ac71c89fba626b01d8c4fcd93b Mon Sep 17 00:00:00 2001
From: Jayaram Kancherla <jayaram.kancherla@gmail.com>
Date: Wed, 27 Aug 2025 08:54:53 +0530
Subject: [PATCH 05/28] Compressed NumPy lis

---
 setup.cfg                          |   1 +
 src/compressed_lists/__init__.py   |   1 +
 src/compressed_lists/bool_list.py  |   8 +--
 src/compressed_lists/float_list.py |  10 +--
 src/compressed_lists/numpy_list.py | 100 ++++++++++++++++++++++++++++
 tests/test_comp_numpy.py           | 103 +++++++++++++++++++++++++++++
 6 files changed, 214 insertions(+), 9 deletions(-)
 create mode 100644 src/compressed_lists/numpy_list.py
 create mode 100644 tests/test_comp_numpy.py

diff --git a/setup.cfg b/setup.cfg
index 01e5b74..72798f5 100644
--- a/setup.cfg
+++ b/setup.cfg
@@ -50,6 +50,7 @@ python_requires = >=3.9
 install_requires =
     importlib-metadata; python_version<"3.8"
     biocutils
+    numpy
 
 
 [options.packages.find]
diff --git a/src/compressed_lists/__init__.py b/src/compressed_lists/__init__.py
index baa8bb1..7471663 100644
--- a/src/compressed_lists/__init__.py
+++ b/src/compressed_lists/__init__.py
@@ -21,3 +21,4 @@
 from .string_list import CompressedStringList, CompressedCharacterList
 from .bool_list import CompressedBooleanList
 from .float_list import CompressedFloatList
+from .numpy_list import CompressedNumpyList
\ No newline at end of file
diff --git a/src/compressed_lists/bool_list.py b/src/compressed_lists/bool_list.py
index deb16ca..2d1e429 100644
--- a/src/compressed_lists/bool_list.py
+++ b/src/compressed_lists/bool_list.py
@@ -11,7 +11,7 @@
 
 
 class CompressedBooleanList(CompressedList):
-    """CompressedList implementation for lists of integers."""
+    """CompressedList implementation for lists of booleans."""
 
     def __init__(
         self,
@@ -21,7 +21,7 @@ def __init__(
         metadata: dict = None,
         **kwargs,
     ):
-        """Initialize a CompressedIntegerList.
+        """Initialize a CompressedBooleanList.
 
         Args:
             unlist_data:
@@ -70,11 +70,11 @@ def from_list(
         cls, lst: List[List[bool]], names: Optional[Sequence[str]] = None, metadata: dict = None
     ) -> "CompressedBooleanList":
         """
-        Create a `CompressedBooleanList` from a list of integer lists.
+        Create a `CompressedBooleanList` from a list of boolean lists.
 
         Args:
             lst:
-                List of integer lists.
+                List of boolean lists.
 
             names:
                 Optional names for list elements.
diff --git a/src/compressed_lists/float_list.py b/src/compressed_lists/float_list.py
index 4ca3c60..a694a8a 100644
--- a/src/compressed_lists/float_list.py
+++ b/src/compressed_lists/float_list.py
@@ -11,7 +11,7 @@
 
 
 class CompressedFloatList(CompressedList):
-    """CompressedList implementation for lists of integers."""
+    """CompressedList implementation for lists of floats."""
 
     def __init__(
         self,
@@ -21,7 +21,7 @@ def __init__(
         metadata: dict = None,
         **kwargs,
     ):
-        """Initialize a CompressedIntegerList.
+        """Initialize a CompressedFloatList.
 
         Args:
             unlist_data:
@@ -67,14 +67,14 @@ def _extract_range(self, start: int, end: int) -> FloatList:
 
     @classmethod
     def from_list(
-        cls, lst: List[List[bool]], names: Optional[Sequence[str]] = None, metadata: dict = None
+        cls, lst: List[List[float]], names: Optional[Sequence[str]] = None, metadata: dict = None
     ) -> "CompressedFloatList":
         """
-        Create a `CompressedFloatList` from a list of integer lists.
+        Create a `CompressedFloatList` from a list of float lists.
 
         Args:
             lst:
-                List of integer lists.
+                List of float lists.
 
             names:
                 Optional names for list elements.
diff --git a/src/compressed_lists/numpy_list.py b/src/compressed_lists/numpy_list.py
new file mode 100644
index 0000000..018fd7a
--- /dev/null
+++ b/src/compressed_lists/numpy_list.py
@@ -0,0 +1,100 @@
+from typing import List, Optional, Sequence
+
+import numpy as np
+from biocutils.IntegerList import IntegerList
+
+from .base import CompressedList
+from .partition import Partitioning
+
+__author__ = "Jayaram Kancherla"
+__copyright__ = "Jayaram Kancherla"
+__license__ = "MIT"
+
+
+class CompressedNumpyList(CompressedList):
+    """CompressedList implementation for lists of NumPy vectors."""
+
+    def __init__(
+        self,
+        unlist_data: np.ndarray,
+        partitioning: Partitioning,
+        element_metadata: dict = None,
+        metadata: dict = None,
+        **kwargs,
+    ):
+        """Initialize a CompressedNumpyList.
+
+        Args:
+            unlist_data:
+                NumPy vector.
+
+            partitioning:
+                Partitioning object defining element boundaries.
+
+            element_metadata:
+                Optional metadata for elements.
+
+            metadata:
+                Optional general metadata.
+
+            kwargs:
+                Additional arguments.
+        """
+
+        if not isinstance(unlist_data, np.ndarray):
+            try:
+                unlist_data = np.array(unlist_data)
+            except Exception as e:
+                raise TypeError("'unlist_data' must be an `np.ndarray`, provided ", type(unlist_data)) from e
+
+        print(unlist_data)
+        super().__init__(
+            unlist_data, partitioning, element_type="ndarray", element_metadata=element_metadata, metadata=metadata
+        )
+
+    def _extract_range(self, start: int, end: int) -> np.ndarray:
+        """Extract a range from unlist_data.
+
+        Args:
+            start:
+                Start index (inclusive).
+
+            end:
+                End index (exclusive).
+
+        Returns:
+            Same type as unlist_data.
+        """
+        return self._unlist_data[start:end]
+
+    @classmethod
+    def from_list(
+        cls, lst: List[List[np.ndarray]], names: Optional[Sequence[str]] = None, metadata: dict = None
+    ) -> "CompressedNumpyList":
+        """
+        Create a `CompressedNumpyList` from a list of NumPy vectors.
+
+        Args:
+            lst:
+                List of NumPy vectors.
+
+            names:
+                Optional names for list elements.
+
+            metadata:
+                Optional metadata.
+
+        Returns:
+            A new `CompressedNumpyList`.
+        """
+
+        # Create partitioning
+        partitioning = Partitioning.from_list(lst, names)
+
+        # Create unlist_data
+        if len(lst) == 0:
+            unlist_data = np.array([])
+        else:
+            unlist_data = np.hstack(lst)
+
+        return cls(unlist_data, partitioning, metadata=metadata)
diff --git a/tests/test_comp_numpy.py b/tests/test_comp_numpy.py
new file mode 100644
index 0000000..aebffb0
--- /dev/null
+++ b/tests/test_comp_numpy.py
@@ -0,0 +1,103 @@
+import numpy as np
+import pytest
+
+from compressed_lists import CompressedNumpyList, Partitioning
+
+__author__ = "Jayaram Kancherla"
+__copyright__ = "Jayaram Kancherla"
+__license__ = "MIT"
+
+
+@pytest.fixture
+def numpy_data():
+    return [np.array([1, 2, 3]), np.array([4, 5]), np.array([6, 7, 8, 9])]
+
+
+@pytest.fixture
+def numpy_list(numpy_data):
+    names = ["A", "B", "C"]
+    return CompressedNumpyList.from_list(numpy_data, names)
+
+
+def test_creation(numpy_data):
+    numpy_list = CompressedNumpyList.from_list(numpy_data)
+
+    assert len(numpy_list) == 3
+    assert isinstance(numpy_list.unlist_data, np.ndarray)
+    assert list(numpy_list.get_unlist_data()) == [1, 2, 3, 4, 5, 6, 7, 8, 9]
+    assert list(numpy_list.get_element_lengths()) == [3, 2, 4]
+
+
+def test_creation_from_parts():
+    numpy_list = CompressedNumpyList([1, 2, 3, 4, 5, 6, 7, 8, 9], Partitioning(ends=[3, 5, 9]))
+
+    assert len(numpy_list) == 3
+    assert isinstance(numpy_list.unlist_data, np.ndarray)
+    assert list(numpy_list.get_unlist_data()) == [1, 2, 3, 4, 5, 6, 7, 8, 9]
+    assert list(numpy_list.get_element_lengths()) == [3, 2, 4]
+
+
+def test_creation_with_names(numpy_data):
+    names = ["A", "B", "C"]
+    numpy_list = CompressedNumpyList.from_list(numpy_data, names)
+
+    assert list(numpy_list.names) == names
+
+
+def test_validation():
+    data = np.array([1, 2, 3, 4, 5])
+    partitioning = Partitioning([2, 4, 7])
+
+    with pytest.raises(ValueError):
+        CompressedNumpyList(data, partitioning)
+
+
+def test_getitem_by_index(numpy_list):
+    assert np.allclose(numpy_list[0], [1, 2, 3])
+    assert np.allclose(numpy_list[1], [4, 5])
+    assert np.allclose(numpy_list[2], [6, 7, 8, 9])
+    assert np.allclose(numpy_list[-1], [6, 7, 8, 9])
+
+    with pytest.raises(IndexError):
+        numpy_list[3]
+
+
+def test_getitem_by_name(numpy_list):
+    assert np.allclose(numpy_list["A"], [1, 2, 3])
+    assert np.allclose(numpy_list["B"], [4, 5])
+    assert np.allclose(numpy_list["C"], [6, 7, 8, 9])
+
+    with pytest.raises(KeyError):
+        numpy_list["D"]
+
+
+def test_getitem_by_slice(numpy_list):
+    sliced = numpy_list[1:3]
+
+    assert len(sliced) == 2
+    assert np.allclose(sliced[0], [4, 5])
+    assert np.allclose(sliced[1], [6, 7, 8, 9])
+    assert list(sliced.names) == ["B", "C"]
+
+    # Empty slice
+    empty = numpy_list[3:4]
+    assert len(empty) == 0
+
+
+def test_iteration(numpy_list, numpy_data):
+    items = list(numpy_list)
+    print(items, numpy_data)
+    for i, lst in enumerate(items):
+        assert np.allclose(lst, numpy_data[i])
+
+
+def test_to_list(numpy_list, numpy_data):
+    regular_list = numpy_list.to_list()
+    for i, lst in enumerate(regular_list):
+        assert np.allclose(list(lst), numpy_data[i])
+
+
+def test_unlist(numpy_list):
+    unlisted = numpy_list.unlist()
+    assert isinstance(unlisted, np.ndarray)
+    assert np.allclose(unlisted, [1, 2, 3, 4, 5, 6, 7, 8, 9])

From e9f5fc4861ea2b38e97128a6105be28eec849439 Mon Sep 17 00:00:00 2001
From: "pre-commit-ci[bot]"
 <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Date: Wed, 27 Aug 2025 03:25:19 +0000
Subject: [PATCH 06/28] [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci
---
 src/compressed_lists/__init__.py   | 2 +-
 src/compressed_lists/numpy_list.py | 1 -
 2 files changed, 1 insertion(+), 2 deletions(-)

diff --git a/src/compressed_lists/__init__.py b/src/compressed_lists/__init__.py
index 7471663..3715ce0 100644
--- a/src/compressed_lists/__init__.py
+++ b/src/compressed_lists/__init__.py
@@ -21,4 +21,4 @@
 from .string_list import CompressedStringList, CompressedCharacterList
 from .bool_list import CompressedBooleanList
 from .float_list import CompressedFloatList
-from .numpy_list import CompressedNumpyList
\ No newline at end of file
+from .numpy_list import CompressedNumpyList
diff --git a/src/compressed_lists/numpy_list.py b/src/compressed_lists/numpy_list.py
index 018fd7a..b8e165b 100644
--- a/src/compressed_lists/numpy_list.py
+++ b/src/compressed_lists/numpy_list.py
@@ -1,7 +1,6 @@
 from typing import List, Optional, Sequence
 
 import numpy as np
-from biocutils.IntegerList import IntegerList
 
 from .base import CompressedList
 from .partition import Partitioning

From 16d899d6b744866123cd3f329acfb777f2cfc6de Mon Sep 17 00:00:00 2001
From: Jayaram Kancherla <jayaram.kancherla@gmail.com>
Date: Thu, 28 Aug 2025 07:47:35 +0530
Subject: [PATCH 07/28] Base is not an abstract class anymore

---
 src/compressed_lists/base.py         | 35 +++++++++++++------
 src/compressed_lists/bool_list.py    | 52 +---------------------------
 src/compressed_lists/float_list.py   | 52 +---------------------------
 src/compressed_lists/integer_list.py | 52 +---------------------------
 src/compressed_lists/numpy_list.py   | 18 +---------
 src/compressed_lists/string_list.py  | 48 +------------------------
 tests/test_comp_custom.py            | 23 ++++++------
 7 files changed, 41 insertions(+), 239 deletions(-)

diff --git a/src/compressed_lists/base.py b/src/compressed_lists/base.py
index 8422756..e3c770f 100644
--- a/src/compressed_lists/base.py
+++ b/src/compressed_lists/base.py
@@ -1,4 +1,3 @@
-from abc import ABC, abstractmethod
 from typing import Any, Callable, Iterator, List, Optional, Sequence, Union
 from warnings import warn
 
@@ -20,7 +19,7 @@ def _validate_data_and_partitions(unlist_data, partition):
         )
 
 
-class CompressedList(ABC):
+class CompressedList:
     """Base class for compressed list objects.
 
     `CompressedList` stores list elements concatenated in a single vector-like object
@@ -31,7 +30,7 @@ def __init__(
         self,
         unlist_data: Any,
         partitioning: Partitioning,
-        element_type: str = None,
+        element_type: Any = None,
         element_metadata: dict = None,
         metadata: Optional[dict] = None,
         validate: bool = True,
@@ -46,7 +45,7 @@ def __init__(
                 Partitioning object defining element boundaries (exclusive).
 
             element_type:
-                String identifier for the type of elements.
+                class for the type of elements.
 
             element_metadata:
                 Optional metadata for elements.
@@ -414,7 +413,7 @@ def __getitem__(self, key: Union[int, str, slice]) -> Any:
                 raise IndexError(f"List index '{key}' out of range.")
 
             start, end = self._partitioning.get_partition_range(key)
-            return self._extract_range(start, end)
+            return self.extract_range(start, end)
 
         # slices
         elif isinstance(key, slice):
@@ -422,7 +421,7 @@ def __getitem__(self, key: Union[int, str, slice]) -> Any:
             result = []
             for i in indices:
                 start, end = self._partitioning.get_partition_range(i)
-                result.append(self._extract_range(start, end))
+                result.append(self.extract_range(start, end))
 
             # Create a new CompressedList from the result
             return self.__class__.from_list(
@@ -436,8 +435,7 @@ def __getitem__(self, key: Union[int, str, slice]) -> Any:
     ######>> abstract methods <<######
     ##################################
 
-    @abstractmethod
-    def _extract_range(self, start: int, end: int) -> Any:
+    def extract_range(self, start: int, end: int) -> Any:
         """Extract a range from `unlist_data`.
 
         This method must be implemented by subclasses to handle
@@ -453,10 +451,14 @@ def _extract_range(self, start: int, end: int) -> Any:
         Returns:
             Extracted element.
         """
-        pass
+        try:
+            return self._unlist_data[start:end]
+        except Exception as e:
+            raise NotImplementedError(
+                "Custom classes should implement their own `extract_range` method for slice operations"
+            ) from e
 
     @classmethod
-    @abstractmethod
     def from_list(
         cls, lst: List[Any], names: Optional[Sequence[str]] = None, metadata: dict = None
     ) -> "CompressedList[Any]":
@@ -478,7 +480,18 @@ def from_list(
         Returns:
             A new `CompressedList`.
         """
-        pass
+        # Flatten the list
+        flat_data = []
+        for sublist in lst:
+            flat_data.extend(sublist)
+
+        # Create partitioning
+        partitioning = Partitioning.from_list(lst, names)
+
+        # Create unlist_data
+        # unlist_data = cls._element_type(data=flat_data)
+
+        return cls(flat_data, partitioning, metadata=metadata)
 
     ###########################
     ######>> coercions <<######
diff --git a/src/compressed_lists/bool_list.py b/src/compressed_lists/bool_list.py
index 2d1e429..c948665 100644
--- a/src/compressed_lists/bool_list.py
+++ b/src/compressed_lists/bool_list.py
@@ -1,5 +1,3 @@
-from typing import List, Optional, Sequence
-
 from biocutils.BooleanList import BooleanList
 
 from .base import CompressedList
@@ -47,53 +45,5 @@ def __init__(
                 raise TypeError("'unlist_data' must be an `BooleanList`, provided ", type(unlist_data)) from e
 
         super().__init__(
-            unlist_data, partitioning, element_type="boolean", element_metadata=element_metadata, metadata=metadata
+            unlist_data, partitioning, element_type=BooleanList, element_metadata=element_metadata, metadata=metadata
         )
-
-    def _extract_range(self, start: int, end: int) -> BooleanList:
-        """Extract a range from unlist_data.
-
-        Args:
-            start:
-                Start index (inclusive).
-
-            end:
-                End index (exclusive).
-
-        Returns:
-            Same type as unlist_data.
-        """
-        return self._unlist_data[start:end]
-
-    @classmethod
-    def from_list(
-        cls, lst: List[List[bool]], names: Optional[Sequence[str]] = None, metadata: dict = None
-    ) -> "CompressedBooleanList":
-        """
-        Create a `CompressedBooleanList` from a list of boolean lists.
-
-        Args:
-            lst:
-                List of boolean lists.
-
-            names:
-                Optional names for list elements.
-
-            metadata:
-                Optional metadata.
-
-        Returns:
-            A new `CompressedBooleanList`.
-        """
-        # Flatten the list
-        flat_data = []
-        for sublist in lst:
-            flat_data.extend(sublist)
-
-        # Create partitioning
-        partitioning = Partitioning.from_list(lst, names)
-
-        # Create unlist_data
-        unlist_data = BooleanList(data=flat_data)
-
-        return cls(unlist_data, partitioning, metadata=metadata)
diff --git a/src/compressed_lists/float_list.py b/src/compressed_lists/float_list.py
index a694a8a..908fc56 100644
--- a/src/compressed_lists/float_list.py
+++ b/src/compressed_lists/float_list.py
@@ -1,5 +1,3 @@
-from typing import List, Optional, Sequence
-
 from biocutils.FloatList import FloatList
 
 from .base import CompressedList
@@ -47,53 +45,5 @@ def __init__(
                 raise TypeError("'unlist_data' must be an `FloatList`, provided ", type(unlist_data)) from e
 
         super().__init__(
-            unlist_data, partitioning, element_type="float", element_metadata=element_metadata, metadata=metadata
+            unlist_data, partitioning, element_type=FloatList, element_metadata=element_metadata, metadata=metadata
         )
-
-    def _extract_range(self, start: int, end: int) -> FloatList:
-        """Extract a range from unlist_data.
-
-        Args:
-            start:
-                Start index (inclusive).
-
-            end:
-                End index (exclusive).
-
-        Returns:
-            Same type as unlist_data.
-        """
-        return self._unlist_data[start:end]
-
-    @classmethod
-    def from_list(
-        cls, lst: List[List[float]], names: Optional[Sequence[str]] = None, metadata: dict = None
-    ) -> "CompressedFloatList":
-        """
-        Create a `CompressedFloatList` from a list of float lists.
-
-        Args:
-            lst:
-                List of float lists.
-
-            names:
-                Optional names for list elements.
-
-            metadata:
-                Optional metadata.
-
-        Returns:
-            A new `CompressedFloatList`.
-        """
-        # Flatten the list
-        flat_data = []
-        for sublist in lst:
-            flat_data.extend(sublist)
-
-        # Create partitioning
-        partitioning = Partitioning.from_list(lst, names)
-
-        # Create unlist_data
-        unlist_data = FloatList(data=flat_data)
-
-        return cls(unlist_data, partitioning, metadata=metadata)
diff --git a/src/compressed_lists/integer_list.py b/src/compressed_lists/integer_list.py
index 678b80b..d4f58d1 100644
--- a/src/compressed_lists/integer_list.py
+++ b/src/compressed_lists/integer_list.py
@@ -1,5 +1,3 @@
-from typing import List, Optional, Sequence
-
 from biocutils.IntegerList import IntegerList
 
 from .base import CompressedList
@@ -47,53 +45,5 @@ def __init__(
                 raise TypeError("'unlist_data' must be an `IntegerList`, provided ", type(unlist_data)) from e
 
         super().__init__(
-            unlist_data, partitioning, element_type="integer", element_metadata=element_metadata, metadata=metadata
+            unlist_data, partitioning, element_type=IntegerList, element_metadata=element_metadata, metadata=metadata
         )
-
-    def _extract_range(self, start: int, end: int) -> IntegerList:
-        """Extract a range from unlist_data.
-
-        Args:
-            start:
-                Start index (inclusive).
-
-            end:
-                End index (exclusive).
-
-        Returns:
-            Same type as unlist_data.
-        """
-        return self._unlist_data[start:end]
-
-    @classmethod
-    def from_list(
-        cls, lst: List[List[int]], names: Optional[Sequence[str]] = None, metadata: dict = None
-    ) -> "CompressedIntegerList":
-        """
-        Create a `CompressedIntegerList` from a list of integer lists.
-
-        Args:
-            lst:
-                List of integer lists.
-
-            names:
-                Optional names for list elements.
-
-            metadata:
-                Optional metadata.
-
-        Returns:
-            A new `CompressedIntegerList`.
-        """
-        # Flatten the list
-        flat_data = []
-        for sublist in lst:
-            flat_data.extend(sublist)
-
-        # Create partitioning
-        partitioning = Partitioning.from_list(lst, names)
-
-        # Create unlist_data
-        unlist_data = IntegerList(data=flat_data)
-
-        return cls(unlist_data, partitioning, metadata=metadata)
diff --git a/src/compressed_lists/numpy_list.py b/src/compressed_lists/numpy_list.py
index 018fd7a..a283a4f 100644
--- a/src/compressed_lists/numpy_list.py
+++ b/src/compressed_lists/numpy_list.py
@@ -1,7 +1,6 @@
 from typing import List, Optional, Sequence
 
 import numpy as np
-from biocutils.IntegerList import IntegerList
 
 from .base import CompressedList
 from .partition import Partitioning
@@ -49,24 +48,9 @@ def __init__(
 
         print(unlist_data)
         super().__init__(
-            unlist_data, partitioning, element_type="ndarray", element_metadata=element_metadata, metadata=metadata
+            unlist_data, partitioning, element_type=np.array, element_metadata=element_metadata, metadata=metadata
         )
 
-    def _extract_range(self, start: int, end: int) -> np.ndarray:
-        """Extract a range from unlist_data.
-
-        Args:
-            start:
-                Start index (inclusive).
-
-            end:
-                End index (exclusive).
-
-        Returns:
-            Same type as unlist_data.
-        """
-        return self._unlist_data[start:end]
-
     @classmethod
     def from_list(
         cls, lst: List[List[np.ndarray]], names: Optional[Sequence[str]] = None, metadata: dict = None
diff --git a/src/compressed_lists/string_list.py b/src/compressed_lists/string_list.py
index 863229c..c1ab643 100644
--- a/src/compressed_lists/string_list.py
+++ b/src/compressed_lists/string_list.py
@@ -1,5 +1,3 @@
-from typing import List, Optional, Sequence
-
 from biocutils.StringList import StringList
 
 from .base import CompressedList
@@ -46,53 +44,9 @@ def __init__(
                 raise TypeError("'unlist_data' must be an `StringList`, provided ", type(unlist_data)) from e
 
         super().__init__(
-            unlist_data, partitioning, element_type="string", element_metadata=element_metadata, metadata=metadata
+            unlist_data, partitioning, element_type=StringList, element_metadata=element_metadata, metadata=metadata
         )
 
-    def _extract_range(self, start: int, end: int) -> StringList:
-        """Extract a range from unlist_data.
-
-        Args:
-            start:
-                Start index (inclusive).
-
-            end:
-                End index (exclusive).
-
-        Returns:
-            List of strings.
-        """
-        return self._unlist_data[start:end]
-
-    @classmethod
-    def from_list(
-        cls, lst: List[List[str]], names: Optional[Sequence[str]] = None, metadata: dict = None
-    ) -> "CompressedStringList":
-        """Create a `CompressedStringList` from a list of string lists.
-
-        Args:
-            lst:
-                List of string lists.
-
-            names:
-                Optional names for list elements.
-
-            metadata:
-                Optional metadata.
-
-        Returns:
-            A new `CompressedStringList`.
-        """
-        # Flatten the list
-        flat_data = []
-        for sublist in lst:
-            flat_data.extend(sublist)
-
-        # Create partitioning
-        partitioning = Partitioning.from_list(lst, names)
-
-        return cls(StringList(flat_data), partitioning, metadata=metadata)
-
 
 class CompressedCharacterList(CompressedStringList):
     pass
diff --git a/tests/test_comp_custom.py b/tests/test_comp_custom.py
index 1476109..276df4f 100644
--- a/tests/test_comp_custom.py
+++ b/tests/test_comp_custom.py
@@ -11,11 +11,11 @@
 
 
 @pytest.fixture
-def CompressedFloatList():
-    class CompressedFloatList(CompressedList):
+def CompressedCustomFloatList():
+    class CompressedCustomFloatList(CompressedList):
         def __init__(
             self,
-            unlist_data: np.ndarray,
+            unlist_data: List[float],
             partitioning: Partitioning,
             element_metadata: dict = None,
             metadata: dict = None,
@@ -24,26 +24,27 @@ def __init__(
                 unlist_data, partitioning, element_type="float", element_metadata=element_metadata, metadata=metadata
             )
 
-        def _extract_range(self, start: int, end: int) -> List[float]:
-            return self._unlist_data[start:end].tolist()
+        def extract_range(self, start: int, end: int) -> List[float]:
+            return self._unlist_data[start:end]
 
         @classmethod
-        def from_list(cls, lst: List[List[float]], names: list = None, metadata: dict = None) -> "CompressedFloatList":
+        def from_list(
+            cls, lst: List[List[float]], names: list = None, metadata: dict = None
+        ) -> "CompressedCustomFloatList":
             flat_data = []
             for sublist in lst:
                 flat_data.extend(sublist)
 
             partitioning = Partitioning.from_list(lst, names)
-            unlist_data = np.array(flat_data, dtype=np.float64)
-            return cls(unlist_data, partitioning, metadata=metadata)
+            return cls(flat_data, partitioning, metadata=metadata)
 
-    return CompressedFloatList
+    return CompressedCustomFloatList
 
 
-def test_custom_class(CompressedFloatList):
+def test_custom_class(CompressedCustomFloatList):
     float_data = [[1.1, 2.2, 3.3], [4.4, 5.5], [6.6, 7.7, 8.8, 9.9]]
     names = ["X", "Y", "Z"]
-    float_list = CompressedFloatList.from_list(float_data, names)
+    float_list = CompressedCustomFloatList.from_list(float_data, names)
 
     assert len(float_list) == 3
     assert float_list._element_type == "float"

From be24a2f5808b821f893f750da0d8075456cce439 Mon Sep 17 00:00:00 2001
From: "pre-commit-ci[bot]"
 <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Date: Thu, 28 Aug 2025 02:17:55 +0000
Subject: [PATCH 08/28] [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci
---
 tests/test_comp_custom.py | 1 -
 1 file changed, 1 deletion(-)

diff --git a/tests/test_comp_custom.py b/tests/test_comp_custom.py
index 276df4f..8284b22 100644
--- a/tests/test_comp_custom.py
+++ b/tests/test_comp_custom.py
@@ -1,6 +1,5 @@
 from typing import List
 
-import numpy as np
 import pytest
 
 from compressed_lists import CompressedList, Partitioning

From b0c56acab01d1515ebb05fd78560e5c6b8d36e6e Mon Sep 17 00:00:00 2001
From: Jayaram Kancherla <jayaram.kancherla@gmail.com>
Date: Tue, 16 Sep 2025 23:41:15 -0700
Subject: [PATCH 09/28] update test

---
 tests/test_comp_custom.py | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/tests/test_comp_custom.py b/tests/test_comp_custom.py
index 8284b22..d6cb817 100644
--- a/tests/test_comp_custom.py
+++ b/tests/test_comp_custom.py
@@ -55,3 +55,13 @@ def test_custom_class(CompressedCustomFloatList):
     assert rounded[0] == [1.0, 2.0, 3.0]
     assert rounded[1] == [4.0, 6.0]
     assert rounded[2] == [7.0, 8.0, 9.0, 10.0]
+
+
+def test_custom_plain_list():
+    list_of_bools = [[True, False], [False, True, False], [False]]
+    unclassed = CompressedList.from_list(list_of_bools)
+
+    assert unclassed is not None
+    assert isinstance(unclassed, CompressedList)
+    assert len(unclassed) == 3
+    assert list(unclassed.get_element_lengths()) == [2, 3, 1]
\ No newline at end of file

From 4c496b93de7c786b78a851f6d8c9e0155e731bc7 Mon Sep 17 00:00:00 2001
From: "pre-commit-ci[bot]"
 <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Date: Wed, 17 Sep 2025 06:41:56 +0000
Subject: [PATCH 10/28] [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci
---
 tests/test_comp_custom.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tests/test_comp_custom.py b/tests/test_comp_custom.py
index d6cb817..aa4f582 100644
--- a/tests/test_comp_custom.py
+++ b/tests/test_comp_custom.py
@@ -64,4 +64,4 @@ def test_custom_plain_list():
     assert unclassed is not None
     assert isinstance(unclassed, CompressedList)
     assert len(unclassed) == 3
-    assert list(unclassed.get_element_lengths()) == [2, 3, 1]
\ No newline at end of file
+    assert list(unclassed.get_element_lengths()) == [2, 3, 1]

From 7c7f2be205ef68369b48f6805f2c1d4a5f9cc333 Mon Sep 17 00:00:00 2001
From: Jayaram Kancherla <jayaram.kancherla@gmail.com>
Date: Wed, 17 Sep 2025 01:22:09 -0700
Subject: [PATCH 11/28] thinking of split generic

---
 src/compressed_lists/split_generic.py | 76 +++++++++++++++++++++++++++
 1 file changed, 76 insertions(+)
 create mode 100644 src/compressed_lists/split_generic.py

diff --git a/src/compressed_lists/split_generic.py b/src/compressed_lists/split_generic.py
new file mode 100644
index 0000000..4488faf
--- /dev/null
+++ b/src/compressed_lists/split_generic.py
@@ -0,0 +1,76 @@
+from functools import singledispatch
+from typing import Any, List, Optional, Sequence, Type, Union
+
+import numpy as np
+import pandas as pd
+from base import CompressedList
+
+__author__ = "Jayaram Kancherla"
+__copyright__ = "Jayaram Kancherla"
+__license__ = "MIT"
+
+
+@singledispatch
+def splitAsCompressedList(
+    data: Any, names: Optional[List[str]] = None, metadata: Optional[dict] = None
+) -> CompressedList:
+    """Generic function to split data into an appropriate `CompressedList` subclass.
+
+    This function uses single dispatch to automatically choose the right
+    `CompressedList` subclass based on the data type. Third parties can
+    register their own types by using the @splitAsCompressedList.register
+    decorator.
+
+    Args:
+        data:
+            The data to split into a `CompressedList`.
+
+        names:
+            Optional names for the list elements.
+
+        metadata:
+            Optional metadata for the `CompressedList`.
+
+    Returns:
+        An appropriate `CompressedList` subclass instance.
+    """
+    raise NotImplementedError(f"No `splitAsCompressedList` implementation for type {type(data)}.")
+
+
+@splitAsCompressedList.register
+def _(data: list, names: Optional[Sequence[str]] = None, metadata: Optional[dict] = None) -> CompressedList:
+    """Handle regular Python lists by inspecting element types."""
+    if not data:
+        raise ValueError("Cannot create `CompressedList` from empty list.")
+
+    first_element = None
+    for item in data:
+        if item and len(item) > 0:
+            first_element = item[0]
+            break
+
+    if first_element is None:
+        raise ValueError("All elements are empty, cannot determine type")
+
+    if isinstance(first_element, int):
+        from integer_list import CompressedIntegerList
+
+        return CompressedIntegerList.from_list(data, names, metadata)
+    elif isinstance(first_element, str):
+        from string_list import CompressedCharacterList
+
+        return CompressedCharacterList.from_list(data, names, metadata)
+    elif isinstance(first_element, float):
+        from float_list import CompressedFloatList
+
+        return CompressedFloatList.from_list(data, names, metadata)
+    elif isinstance(first_element, float):
+        from bool_list import CompressedBooleanList
+
+        return CompressedBooleanList.from_list(data, names, metadata)
+    elif isinstance(first_element, np.ndarray):
+        from numpy_list import CompressedNumpyList
+
+        return CompressedNumpyList.from_list(data, names, metadata)
+    else:
+        raise NotImplementedError(f"No `CompressedList` implementation for element type {type(first_element)}.")

From 8d32fee48debecb3567b405633a7985b693e7e88 Mon Sep 17 00:00:00 2001
From: "pre-commit-ci[bot]"
 <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Date: Wed, 17 Sep 2025 08:24:04 +0000
Subject: [PATCH 12/28] [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci
---
 src/compressed_lists/split_generic.py | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/src/compressed_lists/split_generic.py b/src/compressed_lists/split_generic.py
index 4488faf..388d155 100644
--- a/src/compressed_lists/split_generic.py
+++ b/src/compressed_lists/split_generic.py
@@ -1,8 +1,7 @@
 from functools import singledispatch
-from typing import Any, List, Optional, Sequence, Type, Union
+from typing import Any, List, Optional, Sequence
 
 import numpy as np
-import pandas as pd
 from base import CompressedList
 
 __author__ = "Jayaram Kancherla"

From b5424d47bbad814e644d43705bf353c9d43b07de Mon Sep 17 00:00:00 2001
From: Jayaram Kancherla <jayaram.kancherla@gmail.com>
Date: Wed, 17 Sep 2025 22:48:36 -0700
Subject: [PATCH 13/28] implement generic

---
 src/compressed_lists/bool_list.py     | 11 +++++++++++
 src/compressed_lists/float_list.py    | 11 +++++++++++
 src/compressed_lists/integer_list.py  | 11 +++++++++++
 src/compressed_lists/numpy_list.py    | 11 ++++++++---
 src/compressed_lists/split_generic.py |  9 +++------
 src/compressed_lists/string_list.py   | 11 +++++++++++
 6 files changed, 55 insertions(+), 9 deletions(-)

diff --git a/src/compressed_lists/bool_list.py b/src/compressed_lists/bool_list.py
index c948665..2341cd6 100644
--- a/src/compressed_lists/bool_list.py
+++ b/src/compressed_lists/bool_list.py
@@ -1,7 +1,10 @@
+from typing import List, Union
+
 from biocutils.BooleanList import BooleanList
 
 from .base import CompressedList
 from .partition import Partitioning
+from .split_generic import splitAsCompressedList
 
 __author__ = "Jayaram Kancherla"
 __copyright__ = "Jayaram Kancherla"
@@ -47,3 +50,11 @@ def __init__(
         super().__init__(
             unlist_data, partitioning, element_type=BooleanList, element_metadata=element_metadata, metadata=metadata
         )
+
+
+@splitAsCompressedList.register
+def _(
+    data: Union[List[List[bool]], List[BooleanList]], names: List[str] = None, metadata: dict = None
+) -> CompressedBooleanList:
+    """Handle lists of boolean."""
+    return CompressedBooleanList.from_list(data, names, metadata)
diff --git a/src/compressed_lists/float_list.py b/src/compressed_lists/float_list.py
index 908fc56..60ca68d 100644
--- a/src/compressed_lists/float_list.py
+++ b/src/compressed_lists/float_list.py
@@ -1,7 +1,10 @@
+from typing import List, Union
+
 from biocutils.FloatList import FloatList
 
 from .base import CompressedList
 from .partition import Partitioning
+from .split_generic import splitAsCompressedList
 
 __author__ = "Jayaram Kancherla"
 __copyright__ = "Jayaram Kancherla"
@@ -47,3 +50,11 @@ def __init__(
         super().__init__(
             unlist_data, partitioning, element_type=FloatList, element_metadata=element_metadata, metadata=metadata
         )
+
+
+@splitAsCompressedList.register
+def _(
+    data: Union[List[List[float]], List[FloatList]], names: List[str] = None, metadata: dict = None
+) -> CompressedFloatList:
+    """Handle lists of floats."""
+    return CompressedFloatList.from_list(data, names, metadata)
diff --git a/src/compressed_lists/integer_list.py b/src/compressed_lists/integer_list.py
index d4f58d1..750e007 100644
--- a/src/compressed_lists/integer_list.py
+++ b/src/compressed_lists/integer_list.py
@@ -1,7 +1,10 @@
+from typing import List, Union
+
 from biocutils.IntegerList import IntegerList
 
 from .base import CompressedList
 from .partition import Partitioning
+from .split_generic import splitAsCompressedList
 
 __author__ = "Jayaram Kancherla"
 __copyright__ = "Jayaram Kancherla"
@@ -47,3 +50,11 @@ def __init__(
         super().__init__(
             unlist_data, partitioning, element_type=IntegerList, element_metadata=element_metadata, metadata=metadata
         )
+
+
+@splitAsCompressedList.register
+def _(
+    data: Union[List[List[int]], List[IntegerList]], names: List[str] = None, metadata: dict = None
+) -> CompressedIntegerList:
+    """Handle lists of integers."""
+    return CompressedIntegerList.from_list(data, names, metadata)
diff --git a/src/compressed_lists/numpy_list.py b/src/compressed_lists/numpy_list.py
index a283a4f..92fd087 100644
--- a/src/compressed_lists/numpy_list.py
+++ b/src/compressed_lists/numpy_list.py
@@ -1,4 +1,4 @@
-from typing import List, Optional, Sequence
+from typing import List, Optional, Sequence, Union
 
 import numpy as np
 
@@ -46,14 +46,13 @@ def __init__(
             except Exception as e:
                 raise TypeError("'unlist_data' must be an `np.ndarray`, provided ", type(unlist_data)) from e
 
-        print(unlist_data)
         super().__init__(
             unlist_data, partitioning, element_type=np.array, element_metadata=element_metadata, metadata=metadata
         )
 
     @classmethod
     def from_list(
-        cls, lst: List[List[np.ndarray]], names: Optional[Sequence[str]] = None, metadata: dict = None
+        cls, lst: List[List[np.ndarray]], names: List[str] = None, metadata: dict = None
     ) -> "CompressedNumpyList":
         """
         Create a `CompressedNumpyList` from a list of NumPy vectors.
@@ -82,3 +81,9 @@ def from_list(
             unlist_data = np.hstack(lst)
 
         return cls(unlist_data, partitioning, metadata=metadata)
+
+
+@splitAsCompressedList.register
+def _(data: List[np.ndarray], names: List[str] = None, metadata: dict = None) -> CompressedNumpyList:
+    """Handle lists of numpy vectors."""
+    return CompressedNumpyList.from_list(data, names, metadata)
diff --git a/src/compressed_lists/split_generic.py b/src/compressed_lists/split_generic.py
index 4488faf..af08848 100644
--- a/src/compressed_lists/split_generic.py
+++ b/src/compressed_lists/split_generic.py
@@ -1,8 +1,7 @@
 from functools import singledispatch
-from typing import Any, List, Optional, Sequence, Type, Union
+from typing import Any, List, Optional, Sequence
 
 import numpy as np
-import pandas as pd
 from base import CompressedList
 
 __author__ = "Jayaram Kancherla"
@@ -11,9 +10,7 @@
 
 
 @singledispatch
-def splitAsCompressedList(
-    data: Any, names: Optional[List[str]] = None, metadata: Optional[dict] = None
-) -> CompressedList:
+def splitAsCompressedList(data: Any, names: List[str] = None, metadata: dict = None) -> CompressedList:
     """Generic function to split data into an appropriate `CompressedList` subclass.
 
     This function uses single dispatch to automatically choose the right
@@ -38,7 +35,7 @@ def splitAsCompressedList(
 
 
 @splitAsCompressedList.register
-def _(data: list, names: Optional[Sequence[str]] = None, metadata: Optional[dict] = None) -> CompressedList:
+def _(data: list, names: List[str] = None, metadata: dict = None) -> CompressedList:
     """Handle regular Python lists by inspecting element types."""
     if not data:
         raise ValueError("Cannot create `CompressedList` from empty list.")
diff --git a/src/compressed_lists/string_list.py b/src/compressed_lists/string_list.py
index c1ab643..1607b83 100644
--- a/src/compressed_lists/string_list.py
+++ b/src/compressed_lists/string_list.py
@@ -1,7 +1,10 @@
+from typing import List, Union
+
 from biocutils.StringList import StringList
 
 from .base import CompressedList
 from .partition import Partitioning
+from .split_generic import splitAsCompressedList
 
 __author__ = "Jayaram Kancherla"
 __copyright__ = "Jayaram Kancherla"
@@ -50,3 +53,11 @@ def __init__(
 
 class CompressedCharacterList(CompressedStringList):
     pass
+
+
+@splitAsCompressedList.register
+def _(
+    data: Union[List[List[str]], List[StringList]], names: List[str] = None, metadata: dict = None
+) -> CompressedStringList:
+    """Handle lists of strings."""
+    return CompressedStringList.from_list(data, names, metadata)

From f59bdfebfaefd07eb15c37df2501d5a99d650abb Mon Sep 17 00:00:00 2001
From: "pre-commit-ci[bot]"
 <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Date: Thu, 18 Sep 2025 05:48:59 +0000
Subject: [PATCH 14/28] [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci
---
 src/compressed_lists/numpy_list.py    | 2 +-
 src/compressed_lists/split_generic.py | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/src/compressed_lists/numpy_list.py b/src/compressed_lists/numpy_list.py
index 92fd087..6b30336 100644
--- a/src/compressed_lists/numpy_list.py
+++ b/src/compressed_lists/numpy_list.py
@@ -1,4 +1,4 @@
-from typing import List, Optional, Sequence, Union
+from typing import List
 
 import numpy as np
 
diff --git a/src/compressed_lists/split_generic.py b/src/compressed_lists/split_generic.py
index af08848..7b6503d 100644
--- a/src/compressed_lists/split_generic.py
+++ b/src/compressed_lists/split_generic.py
@@ -1,5 +1,5 @@
 from functools import singledispatch
-from typing import Any, List, Optional, Sequence
+from typing import Any, List
 
 import numpy as np
 from base import CompressedList

From 1265d6c40375d31bf8ac4a6bae45842501c7e9d7 Mon Sep 17 00:00:00 2001
From: Jayaram Kancherla <jayaram.kancherla@gmail.com>
Date: Wed, 17 Sep 2025 23:05:31 -0700
Subject: [PATCH 15/28] fix import

---
 src/compressed_lists/split_generic.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/compressed_lists/split_generic.py b/src/compressed_lists/split_generic.py
index 7b6503d..27a4a0c 100644
--- a/src/compressed_lists/split_generic.py
+++ b/src/compressed_lists/split_generic.py
@@ -2,7 +2,7 @@
 from typing import Any, List
 
 import numpy as np
-from base import CompressedList
+from .base import CompressedList
 
 __author__ = "Jayaram Kancherla"
 __copyright__ = "Jayaram Kancherla"

From 7cb79715cd83f33edbac0a6d259137f946ab31f2 Mon Sep 17 00:00:00 2001
From: Jayaram Kancherla <jayaram.kancherla@gmail.com>
Date: Tue, 7 Oct 2025 11:55:33 -0700
Subject: [PATCH 16/28] adding the generic and other changes to support
 initialization

---
 src/compressed_lists/base.py          |  41 +++++----
 src/compressed_lists/bool_list.py     |  52 +++++++++--
 src/compressed_lists/float_list.py    |  50 +++++++++--
 src/compressed_lists/integer_list.py  |  51 +++++++++--
 src/compressed_lists/numpy_list.py    |  59 +++++++++++--
 src/compressed_lists/partition.py     |  16 ++--
 src/compressed_lists/split_generic.py | 120 +++++++++++++++++---------
 src/compressed_lists/string_list.py   |  52 +++++++++--
 8 files changed, 342 insertions(+), 99 deletions(-)

diff --git a/src/compressed_lists/base.py b/src/compressed_lists/base.py
index e3c770f..f4253ec 100644
--- a/src/compressed_lists/base.py
+++ b/src/compressed_lists/base.py
@@ -31,7 +31,7 @@ def __init__(
         unlist_data: Any,
         partitioning: Partitioning,
         element_type: Any = None,
-        element_metadata: dict = None,
+        element_metadata: Optional[dict] = None,
         metadata: Optional[dict] = None,
         validate: bool = True,
     ):
@@ -65,7 +65,7 @@ class for the type of elements.
         if validate:
             _validate_data_and_partitions(self._unlist_data, self._partitioning)
 
-    def _define_output(self, in_place: bool = False) -> "Partitioning":
+    def _define_output(self, in_place: bool = False) -> "CompressedList":
         if in_place is True:
             return self
         else:
@@ -207,7 +207,7 @@ def get_names(self) -> Optional[ut.NamedList]:
         """Get the names of list elements."""
         return self._partitioning.get_names()
 
-    def set_names(self, names: Sequence[str], in_place: bool = False) -> "CompressedList":
+    def set_names(self, names: List[str], in_place: bool = False) -> "CompressedList":
         """Set the names of list elements.
 
         names:
@@ -401,7 +401,7 @@ def __getitem__(self, key: Union[int, str, slice]) -> Any:
         """
         # string keys (names)
         if isinstance(key, str):
-            if key not in self.names:
+            if key not in list(self.get_names()):
                 raise KeyError(f"No element named '{key}'.")
             key = list(self.names).index(key)
 
@@ -422,14 +422,14 @@ def __getitem__(self, key: Union[int, str, slice]) -> Any:
             for i in indices:
                 start, end = self._partitioning.get_partition_range(i)
                 result.append(self.extract_range(start, end))
-
-            # Create a new CompressedList from the result
-            return self.__class__.from_list(
+            
+            current_class_const = type(self)
+            return current_class_const.from_list(
                 result, names=[self.names[i] for i in indices] if self.names[0] is not None else None
             )
 
         else:
-            raise TypeError("Index must be int, str, or slice.")
+            raise TypeError("'key' must be int, str, or slice.")
 
     ##################################
     ######>> abstract methods <<######
@@ -460,8 +460,8 @@ def extract_range(self, start: int, end: int) -> Any:
 
     @classmethod
     def from_list(
-        cls, lst: List[Any], names: Optional[Sequence[str]] = None, metadata: dict = None
-    ) -> "CompressedList[Any]":
+        cls, lst: List[Any], names: Optional[Sequence[str]] = None, metadata: Optional[dict] = None
+    ) -> "CompressedList":
         """Create a CompressedList from a regular list.
 
         This method must be implemented by subclasses to handle
@@ -519,7 +519,7 @@ def unlist(self, use_names: bool = True) -> Any:
         """
         return self._unlist_data
 
-    def relist(self, unlist_data: Any) -> "CompressedList[Any]":
+    def relist(self, unlist_data: Any) -> "CompressedList":
         """Create a new `CompressedList` with the same partitioning but different data.
 
         Args:
@@ -531,7 +531,8 @@ def relist(self, unlist_data: Any) -> "CompressedList[Any]":
         """
         _validate_data_and_partitions(unlist_data, self._partitioning)
 
-        return self.__class__(
+        current_class_const = type(self)
+        return current_class_const(
             unlist_data,
             self._partitioning.copy(),
             element_type=self._element_type,
@@ -539,7 +540,7 @@ def relist(self, unlist_data: Any) -> "CompressedList[Any]":
             metadata=self._metadata.copy(),
         )
 
-    def extract_subset(self, indices: Sequence[int]) -> "CompressedList[Any]":
+    def extract_subset(self, indices: Sequence[int]) -> "CompressedList":
         """Extract a subset of elements by indices.
 
         Args:
@@ -555,8 +556,8 @@ def extract_subset(self, indices: Sequence[int]) -> "CompressedList[Any]":
                 raise IndexError(f"Index {i} out of range")
 
         # Extract element lengths and names
-        new_lengths = [self.get_element_lengths()[i] for i in indices]
-        new_names = [self.names[i] for i in indices] if self.names[0] is not None else None
+        new_lengths = ut.subset_sequence(self.get_element_lengths(), indices)
+        new_names = ut.subset_sequence(self.names, indices) if self.names is not None else None
 
         # Create new partitioning
         new_partitioning = Partitioning.from_lengths(new_lengths, new_names)
@@ -573,8 +574,8 @@ def extract_subset(self, indices: Sequence[int]) -> "CompressedList[Any]":
         if isinstance(self._unlist_data, np.ndarray):
             new_data = np.concatenate(new_data)
 
-        # Create new compressed list
-        return self.__class__(
+        current_class_const = type(self)
+        return current_class_const(
             new_data,
             new_partitioning,
             element_type=self._element_type,
@@ -582,7 +583,7 @@ def extract_subset(self, indices: Sequence[int]) -> "CompressedList[Any]":
             metadata=self._metadata.copy(),
         )
 
-    def lapply(self, func: Callable) -> "CompressedList[Any]":
+    def lapply(self, func: Callable) -> "CompressedList":
         """Apply a function to each element.
 
         Args:
@@ -593,4 +594,6 @@ def lapply(self, func: Callable) -> "CompressedList[Any]":
             A new CompressedList with the results.
         """
         result = [func(elem) for elem in self]
-        return self.__class__.from_list(result, self.names, self._metadata)
+        
+        current_class_const = type(self)
+        return current_class_const.from_list(result, self.names, self._metadata)
diff --git a/src/compressed_lists/bool_list.py b/src/compressed_lists/bool_list.py
index 2341cd6..980b866 100644
--- a/src/compressed_lists/bool_list.py
+++ b/src/compressed_lists/bool_list.py
@@ -1,10 +1,11 @@
-from typing import List, Union
+from typing import List, Optional, Sequence, Union
 
+import numpy as np
 from biocutils.BooleanList import BooleanList
 
 from .base import CompressedList
 from .partition import Partitioning
-from .split_generic import splitAsCompressedList
+from .split_generic import _generic_register_helper, splitAsCompressedList
 
 __author__ = "Jayaram Kancherla"
 __copyright__ = "Jayaram Kancherla"
@@ -18,8 +19,8 @@ def __init__(
         self,
         unlist_data: BooleanList,
         partitioning: Partitioning,
-        element_metadata: dict = None,
-        metadata: dict = None,
+        element_metadata: Optional[dict] = None,
+        metadata: Optional[dict] = None,
         **kwargs,
     ):
         """Initialize a CompressedBooleanList.
@@ -51,10 +52,47 @@ def __init__(
             unlist_data, partitioning, element_type=BooleanList, element_metadata=element_metadata, metadata=metadata
         )
 
+    @classmethod
+    def from_partitioned_data(
+        cls, partitioned_data: List[List], partitioning: Partitioning, metadata: Optional[dict] = None
+    ) -> "CompressedBooleanList":
+        """Create `CompressedBooleanList` from already-partitioned data.
+
+        Args:
+            partitioned_data:
+                List of `BooleanList`'s, each containing booleans for one partition.
+
+            partitioning:
+                Partitioning object defining the boundaries.
+
+            metadata:
+                Optional metadata.
+
+        Returns:
+            A new `CompressedBooleanList`.
+        """
+        flat_data = []
+        for partition in partitioned_data:
+            flat_data.extend(partition)
+
+        unlist_data = BooleanList(flat_data)
+
+        return cls(unlist_data, partitioning, metadata=metadata)
+
 
 @splitAsCompressedList.register
 def _(
-    data: Union[List[List[bool]], List[BooleanList]], names: List[str] = None, metadata: dict = None
+    data: BooleanList,
+    groups_or_partitions: Union[list, Partitioning],
+    names: Optional[Sequence[str]] = None,
+    metadata: Optional[dict] = None,
 ) -> CompressedBooleanList:
-    """Handle lists of boolean."""
-    return CompressedBooleanList.from_list(data, names, metadata)
+    """Handle lists of booleans."""
+
+    partitioned_data, groups_or_partitions = _generic_register_helper(
+        data=data, groups_or_partitions=groups_or_partitions, names=names
+    )
+
+    return CompressedBooleanList.from_partitioned_data(
+        partitioned_data=partitioned_data, partitioning=groups_or_partitions, metadata=metadata
+    )
diff --git a/src/compressed_lists/float_list.py b/src/compressed_lists/float_list.py
index 60ca68d..59efcff 100644
--- a/src/compressed_lists/float_list.py
+++ b/src/compressed_lists/float_list.py
@@ -1,10 +1,11 @@
-from typing import List, Union
+from typing import List, Optional, Sequence, Union
 
+import numpy as np
 from biocutils.FloatList import FloatList
 
 from .base import CompressedList
 from .partition import Partitioning
-from .split_generic import splitAsCompressedList
+from .split_generic import _generic_register_helper, splitAsCompressedList
 
 __author__ = "Jayaram Kancherla"
 __copyright__ = "Jayaram Kancherla"
@@ -18,8 +19,8 @@ def __init__(
         self,
         unlist_data: FloatList,
         partitioning: Partitioning,
-        element_metadata: dict = None,
-        metadata: dict = None,
+        element_metadata: Optional[dict] = None,
+        metadata: Optional[dict] = None,
         **kwargs,
     ):
         """Initialize a CompressedFloatList.
@@ -51,10 +52,47 @@ def __init__(
             unlist_data, partitioning, element_type=FloatList, element_metadata=element_metadata, metadata=metadata
         )
 
+    @classmethod
+    def from_partitioned_data(
+        cls, partitioned_data: List[List], partitioning: Partitioning, metadata: Optional[dict] = None
+    ) -> "CompressedFloatList":
+        """Create `CompressedFloatList` from already-partitioned data.
+
+        Args:
+            partitioned_data:
+                List of lists, each containing floats for one partition.
+
+            partitioning:
+                Partitioning object defining the boundaries.
+
+            metadata:
+                Optional metadata.
+
+        Returns:
+            A new `CompressedFloatList`.
+        """
+        flat_data = []
+        for partition in partitioned_data:
+            flat_data.extend(partition)
+
+        unlist_data = FloatList(flat_data)
+
+        return cls(unlist_data, partitioning, metadata=metadata)
+
 
 @splitAsCompressedList.register
 def _(
-    data: Union[List[List[float]], List[FloatList]], names: List[str] = None, metadata: dict = None
+    data: FloatList,
+    groups_or_partitions: Union[list, Partitioning],
+    names: Optional[Sequence[str]] = None,
+    metadata: Optional[dict] = None,
 ) -> CompressedFloatList:
     """Handle lists of floats."""
-    return CompressedFloatList.from_list(data, names, metadata)
+
+    partitioned_data, groups_or_partitions = _generic_register_helper(
+        data=data, groups_or_partitions=groups_or_partitions, names=names
+    )
+
+    return CompressedFloatList.from_partitioned_data(
+        partitioned_data=partitioned_data, partitioning=groups_or_partitions, metadata=metadata
+    )
diff --git a/src/compressed_lists/integer_list.py b/src/compressed_lists/integer_list.py
index 750e007..adc601d 100644
--- a/src/compressed_lists/integer_list.py
+++ b/src/compressed_lists/integer_list.py
@@ -1,10 +1,11 @@
-from typing import List, Union
+from typing import Optional, Sequence, Union
 
+import numpy as np
 from biocutils.IntegerList import IntegerList
 
 from .base import CompressedList
 from .partition import Partitioning
-from .split_generic import splitAsCompressedList
+from .split_generic import splitAsCompressedList, _generic_register_helper
 
 __author__ = "Jayaram Kancherla"
 __copyright__ = "Jayaram Kancherla"
@@ -18,8 +19,8 @@ def __init__(
         self,
         unlist_data: IntegerList,
         partitioning: Partitioning,
-        element_metadata: dict = None,
-        metadata: dict = None,
+        element_metadata: Optional[dict] = None,
+        metadata: Optional[dict] = None,
         **kwargs,
     ):
         """Initialize a CompressedIntegerList.
@@ -51,10 +52,48 @@ def __init__(
             unlist_data, partitioning, element_type=IntegerList, element_metadata=element_metadata, metadata=metadata
         )
 
+    @classmethod
+    def from_partitioned_data(
+        cls, partitioned_data: Sequence[IntegerList], partitioning: Partitioning, metadata: Optional[dict] = None
+    ) -> "CompressedIntegerList":
+        """Create `CompressedIntegerList` from already-partitioned data.
+
+        Args:
+            partitioned_data:
+                List of `IntegerList`'s, each containing integers for one partition.
+
+            partitioning:
+                Partitioning object defining the boundaries.
+
+            metadata:
+                Optional metadata.
+
+        Returns:
+            A new `CompressedIntegerList`.
+        """
+
+        flat_data = []
+        for partition in partitioned_data:
+            flat_data.extend(partition)
+
+        unlist_data = IntegerList(flat_data)
+
+        return cls(unlist_data, partitioning, metadata=metadata)
+
 
 @splitAsCompressedList.register
 def _(
-    data: Union[List[List[int]], List[IntegerList]], names: List[str] = None, metadata: dict = None
+    data: IntegerList,
+    groups_or_partitions: Union[list, Partitioning],
+    names: Optional[Sequence[str]] = None,
+    metadata: Optional[dict] = None,
 ) -> CompressedIntegerList:
     """Handle lists of integers."""
-    return CompressedIntegerList.from_list(data, names, metadata)
+    
+    partitioned_data, groups_or_partitions = _generic_register_helper(
+        data=data, groups_or_partitions=groups_or_partitions, names=names
+    )
+    
+    return CompressedIntegerList.from_partitioned_data(
+        partitioned_data=partitioned_data, partitioning=groups_or_partitions, metadata=metadata
+    )
diff --git a/src/compressed_lists/numpy_list.py b/src/compressed_lists/numpy_list.py
index 6b30336..deb52a5 100644
--- a/src/compressed_lists/numpy_list.py
+++ b/src/compressed_lists/numpy_list.py
@@ -1,9 +1,10 @@
-from typing import List
+from typing import List, Optional
 
 import numpy as np
 
 from .base import CompressedList
 from .partition import Partitioning
+from .split_generic import splitAsCompressedList
 
 __author__ = "Jayaram Kancherla"
 __copyright__ = "Jayaram Kancherla"
@@ -17,8 +18,8 @@ def __init__(
         self,
         unlist_data: np.ndarray,
         partitioning: Partitioning,
-        element_metadata: dict = None,
-        metadata: dict = None,
+        element_metadata: Optional[dict] = None,
+        metadata: Optional[dict] = None,
         **kwargs,
     ):
         """Initialize a CompressedNumpyList.
@@ -52,7 +53,7 @@ def __init__(
 
     @classmethod
     def from_list(
-        cls, lst: List[List[np.ndarray]], names: List[str] = None, metadata: dict = None
+        cls, lst: List[List[np.ndarray]], names: Optional[List[str]] = None, metadata: Optional[dict] = None
     ) -> "CompressedNumpyList":
         """
         Create a `CompressedNumpyList` from a list of NumPy vectors.
@@ -82,8 +83,52 @@ def from_list(
 
         return cls(unlist_data, partitioning, metadata=metadata)
 
+    @classmethod
+    def _from_partitioned_data(
+        cls, partitioned_data: List[List], partitioning: Partitioning, metadata: Optional[dict] = None
+    ) -> "CompressedNumpyList":
+        """Create CompressedNumpyList from already-partitioned data.
+
+        Args:
+            partitioned_data: List of arrays, each containing numpy data for one partition
+            partitioning: Partitioning object defining the boundaries
+            metadata: Optional metadata
+
+        Returns:
+            A new CompressedNumpyList
+        """
+        import numpy as np
+
+        # Concatenate the numpy arrays
+        if not partitioned_data or not partitioned_data[0]:
+            unlist_data = np.array([])
+        else:
+            unlist_data = np.concatenate(partitioned_data)
+
+        return cls(unlist_data, partitioning, metadata=metadata)
+
 
 @splitAsCompressedList.register
-def _(data: List[np.ndarray], names: List[str] = None, metadata: dict = None) -> CompressedNumpyList:
-    """Handle lists of numpy vectors."""
-    return CompressedNumpyList.from_list(data, names, metadata)
+def _(
+    data: np.ndarray,
+    names: Optional[List[str]] = None,
+    metadata: Optional[dict] = None,
+    groups: Optional[list] = None,
+    partitions: Optional[Partitioning] = None,
+):
+    """Handle NumPy arrays."""
+
+    if groups is not None:
+        return _splitAsCompressedList_by_groups(data, groups, names, metadata)
+    elif partitions is not None:
+        return _splitAsCompressedList_by_partitions(data, partitions, names, metadata)
+    else:
+        # Original behavior: convert single array to list of arrays
+        if data.ndim == 1:
+            list_data = [data]
+        else:
+            list_data = [row for row in data]
+
+        from .numpy_list import CompressedNumpyList
+
+        return CompressedNumpyList.from_list(list_data, names, metadata)
diff --git a/src/compressed_lists/partition.py b/src/compressed_lists/partition.py
index 154ad5e..6782c65 100644
--- a/src/compressed_lists/partition.py
+++ b/src/compressed_lists/partition.py
@@ -46,7 +46,7 @@ def __init__(self, ends: Sequence[int], names: Optional[Sequence[str]] = None, v
 
         self._names = None
         if names is not None:
-            self._names = ut.NamedList(names)
+            self._names = ut.Names(names)
 
         if validate:
             _validate_names(names, len(ends))
@@ -212,11 +212,11 @@ def __getitem__(self, key: Union[int, slice]) -> Union[tuple, List[tuple]]:
     ######>> names <<#####
     ######################
 
-    def get_names(self) -> Optional[ut.NamedList]:
+    def get_names(self) -> Optional[ut.Names]:
         """Return the names of each partition."""
         return self._names
 
-    def set_names(self, names: Optional[List[str]], in_place: bool = False) -> "Partitioning":
+    def set_names(self, names: Optional[Sequence[str]], in_place: bool = False) -> "Partitioning":
         """Set the names of list elements.
 
         Args:
@@ -247,7 +247,7 @@ def names(self) -> Optional[ut.Names]:
         return self.get_names()
 
     @names.setter
-    def names(self, names: Optional[List[str]]):
+    def names(self, names: Optional[Sequence[str]]):
         """Alias for :py:meth:`~set_names` with ``in_place = True``.
 
         As this mutates the original object, a warning is raised.
@@ -262,12 +262,12 @@ def names(self, names: Optional[List[str]]):
     ######>> ends <<#####
     #####################
 
-    def get_ends(self) -> Optional[ut.NamedList]:
+    def get_ends(self) -> np.ndarray:
         """Return the names of each partition."""
         return self._ends
 
     @property
-    def ends(self) -> Optional[ut.Names]:
+    def ends(self) -> np.ndarray:
         """Alias for :py:attr:`~get_ends`, provided for back-compatibility."""
         return self.get_ends()
 
@@ -275,11 +275,11 @@ def ends(self) -> Optional[ut.Names]:
     ######>> starts <<#####
     #######################
 
-    def get_starts(self) -> Optional[ut.NamedList]:
+    def get_starts(self) -> np.ndarray:
         """Return the starts of each partition."""
         return self._starts
 
     @property
-    def starts(self) -> Optional[ut.Names]:
+    def starts(self) -> np.ndarray:
         """Alias for :py:attr:`~get_starts`, provided for back-compatibility."""
         return self.get_starts()
diff --git a/src/compressed_lists/split_generic.py b/src/compressed_lists/split_generic.py
index 27a4a0c..97321d6 100644
--- a/src/compressed_lists/split_generic.py
+++ b/src/compressed_lists/split_generic.py
@@ -1,27 +1,81 @@
+from collections import defaultdict
 from functools import singledispatch
-from typing import Any, List
+from typing import Any, List, Optional, Sequence, Tuple, Union
 
 import numpy as np
+
 from .base import CompressedList
+from .partition import Partitioning
 
 __author__ = "Jayaram Kancherla"
 __copyright__ = "Jayaram Kancherla"
 __license__ = "MIT"
 
 
+def groups_to_partition(
+    data: Any, groups: list, names: Optional[Sequence[str]] = None
+) -> Tuple[List[Any], Partitioning]:
+    """Convert group membership vector to partitioned data and Partitioning object.
+
+    Args:
+        data:
+            The data to be split (flat vector-like object).
+
+        groups:
+            Group membership vector, same length as data.
+
+        names:
+            Optional names for groups.
+
+    Returns:
+        Tuple of (partitioned_data_list, partitioning_object)
+    """
+
+    if len(data) != len(groups):
+        raise ValueError(f"Length of data ({len(data)}) must match length of groups ({len(groups)})")
+
+    group_dict = defaultdict(list)
+    for item, group in zip(data, groups):
+        group_dict[group].append(item)
+
+    sorted_groups = sorted(group_dict.keys())
+    partitioned_data = [group_dict[group] for group in sorted_groups]
+
+    if names is None:
+        group_names = [str(group) for group in sorted_groups]
+    else:
+        if len(names) != len(sorted_groups):
+            raise ValueError(
+                f"Length of names ({len(names)}) must match number of unique groups ({len(sorted_groups)})"
+            )
+        group_names = names
+
+    partitioning = Partitioning.from_list(partitioned_data, group_names)
+
+    return partitioned_data, partitioning
+
+
 @singledispatch
-def splitAsCompressedList(data: Any, names: List[str] = None, metadata: dict = None) -> CompressedList:
+def splitAsCompressedList(
+    data: Any,
+    groups_or_partitions: Union[list, Partitioning],
+    names: Optional[Sequence[str]] = None,
+    metadata: Optional[dict] = None,
+) -> CompressedList:
     """Generic function to split data into an appropriate `CompressedList` subclass.
 
-    This function uses single dispatch to automatically choose the right
-    `CompressedList` subclass based on the data type. Third parties can
-    register their own types by using the @splitAsCompressedList.register
-    decorator.
+    This function can work in two modes:
+    1. Group-based splitting where a flat vector is split according to group membership.
+    2. Partition-based splitting where a flat vector is split according to explicit partitions.
 
     Args:
         data:
             The data to split into a `CompressedList`.
 
+        groups_or_partitions:
+            Optional group membership vector (same length as data) or
+            explicit partitioning object.
+
         names:
             Optional names for the list elements.
 
@@ -31,43 +85,31 @@ def splitAsCompressedList(data: Any, names: List[str] = None, metadata: dict = N
     Returns:
         An appropriate `CompressedList` subclass instance.
     """
-    raise NotImplementedError(f"No `splitAsCompressedList` implementation for type {type(data)}.")
+    element_type = type(data)
+    raise NotImplementedError(f"No `splitAsCompressedList` dispatcher found for element type {element_type}")
 
 
-@splitAsCompressedList.register
-def _(data: list, names: List[str] = None, metadata: dict = None) -> CompressedList:
-    """Handle regular Python lists by inspecting element types."""
-    if not data:
-        raise ValueError("Cannot create `CompressedList` from empty list.")
+def _generic_register_helper(data, groups_or_partitions, names=None):
+    if groups_or_partitions is None:
+        raise ValueError("'groups_or_paritions' cannot be 'None'.")
 
-    first_element = None
-    for item in data:
-        if item and len(item) > 0:
-            first_element = item[0]
-            break
-
-    if first_element is None:
-        raise ValueError("All elements are empty, cannot determine type")
-
-    if isinstance(first_element, int):
-        from integer_list import CompressedIntegerList
-
-        return CompressedIntegerList.from_list(data, names, metadata)
-    elif isinstance(first_element, str):
-        from string_list import CompressedCharacterList
-
-        return CompressedCharacterList.from_list(data, names, metadata)
-    elif isinstance(first_element, float):
-        from float_list import CompressedFloatList
+    if not data:
+        raise ValueError("'data' cannot be empty.")
 
-        return CompressedFloatList.from_list(data, names, metadata)
-    elif isinstance(first_element, float):
-        from bool_list import CompressedBooleanList
+    if isinstance(groups_or_partitions, (list, np.ndarray)):
+        partitioned_data, groups_or_partitions = groups_to_partition(data, groups=groups_or_partitions, names=names)
 
-        return CompressedBooleanList.from_list(data, names, metadata)
-    elif isinstance(first_element, np.ndarray):
-        from numpy_list import CompressedNumpyList
+        if len(partitioned_data) == 0:
+            raise ValueError("No data after grouping")
+    elif isinstance(groups_or_partitions, Partitioning):
+        if names is not None:
+            groups_or_partitions = groups_or_partitions.set_names(names, in_place=False)
 
-        return CompressedNumpyList.from_list(data, names, metadata)
+        partitioned_data = []
+        for i in range(len(groups_or_partitions)):
+            start, end = groups_or_partitions.get_partition_range(i)
+            partitioned_data.append(data[start:end])
     else:
-        raise NotImplementedError(f"No `CompressedList` implementation for element type {type(first_element)}.")
+        raise ValueError("'groups_or_paritions' must be a group vector or a Partition object.")
+
+    return partitioned_data, groups_or_partitions
\ No newline at end of file
diff --git a/src/compressed_lists/string_list.py b/src/compressed_lists/string_list.py
index 1607b83..20f85ce 100644
--- a/src/compressed_lists/string_list.py
+++ b/src/compressed_lists/string_list.py
@@ -1,10 +1,11 @@
-from typing import List, Union
+from typing import List, Optional, Sequence, Union
 
+import numpy as np
 from biocutils.StringList import StringList
 
 from .base import CompressedList
 from .partition import Partitioning
-from .split_generic import splitAsCompressedList
+from .split_generic import _generic_register_helper, splitAsCompressedList
 
 __author__ = "Jayaram Kancherla"
 __copyright__ = "Jayaram Kancherla"
@@ -18,8 +19,8 @@ def __init__(
         self,
         unlist_data: StringList,
         partitioning: Partitioning,
-        element_metadata: dict = None,
-        metadata: dict = None,
+        element_metadata: Optional[dict] = None,
+        metadata: Optional[dict] = None,
         **kwargs,
     ):
         """Initialize a CompressedStringList.
@@ -50,6 +51,33 @@ def __init__(
             unlist_data, partitioning, element_type=StringList, element_metadata=element_metadata, metadata=metadata
         )
 
+    @classmethod
+    def from_partitioned_data(
+        cls, partitioned_data: List[List], partitioning: Partitioning, metadata: Optional[dict] = None
+    ) -> "CompressedStringList":
+        """Create `CompressedStringList` from already-partitioned data.
+
+        Args:
+            partitioned_data:
+                List of lists, each containing strings for one partition.
+
+            partitioning:
+                Partitioning object defining the boundaries.
+
+            metadata:
+                Optional metadata.
+
+        Returns:
+            A new `CompressedStringList`.
+        """
+        flat_data = []
+        for partition in partitioned_data:
+            flat_data.extend(partition)
+
+        unlist_data = StringList(flat_data)
+
+        return cls(unlist_data, partitioning, metadata=metadata)
+
 
 class CompressedCharacterList(CompressedStringList):
     pass
@@ -57,7 +85,17 @@ class CompressedCharacterList(CompressedStringList):
 
 @splitAsCompressedList.register
 def _(
-    data: Union[List[List[str]], List[StringList]], names: List[str] = None, metadata: dict = None
+    data: StringList,
+    groups_or_partitions: Union[list, Partitioning],
+    names: Optional[Sequence[str]] = None,
+    metadata: Optional[dict] = None,
 ) -> CompressedStringList:
-    """Handle lists of strings."""
-    return CompressedStringList.from_list(data, names, metadata)
+    """Handle lists of floats."""
+
+    partitioned_data, groups_or_partitions = _generic_register_helper(
+        data=data, groups_or_partitions=groups_or_partitions, names=names
+    )
+
+    return CompressedStringList.from_partitioned_data(
+        partitioned_data=partitioned_data, partitioning=groups_or_partitions, metadata=metadata
+    )

From e58ff7bf2bde383358c8afd676a7af61148dd0e2 Mon Sep 17 00:00:00 2001
From: "pre-commit-ci[bot]"
 <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Date: Tue, 7 Oct 2025 18:55:44 +0000
Subject: [PATCH 17/28] [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci
---
 src/compressed_lists/base.py          | 4 ++--
 src/compressed_lists/bool_list.py     | 1 -
 src/compressed_lists/float_list.py    | 1 -
 src/compressed_lists/integer_list.py  | 5 ++---
 src/compressed_lists/split_generic.py | 2 +-
 src/compressed_lists/string_list.py   | 1 -
 6 files changed, 5 insertions(+), 9 deletions(-)

diff --git a/src/compressed_lists/base.py b/src/compressed_lists/base.py
index f4253ec..f450059 100644
--- a/src/compressed_lists/base.py
+++ b/src/compressed_lists/base.py
@@ -422,7 +422,7 @@ def __getitem__(self, key: Union[int, str, slice]) -> Any:
             for i in indices:
                 start, end = self._partitioning.get_partition_range(i)
                 result.append(self.extract_range(start, end))
-            
+
             current_class_const = type(self)
             return current_class_const.from_list(
                 result, names=[self.names[i] for i in indices] if self.names[0] is not None else None
@@ -594,6 +594,6 @@ def lapply(self, func: Callable) -> "CompressedList":
             A new CompressedList with the results.
         """
         result = [func(elem) for elem in self]
-        
+
         current_class_const = type(self)
         return current_class_const.from_list(result, self.names, self._metadata)
diff --git a/src/compressed_lists/bool_list.py b/src/compressed_lists/bool_list.py
index 980b866..19a0903 100644
--- a/src/compressed_lists/bool_list.py
+++ b/src/compressed_lists/bool_list.py
@@ -1,6 +1,5 @@
 from typing import List, Optional, Sequence, Union
 
-import numpy as np
 from biocutils.BooleanList import BooleanList
 
 from .base import CompressedList
diff --git a/src/compressed_lists/float_list.py b/src/compressed_lists/float_list.py
index 59efcff..2b56884 100644
--- a/src/compressed_lists/float_list.py
+++ b/src/compressed_lists/float_list.py
@@ -1,6 +1,5 @@
 from typing import List, Optional, Sequence, Union
 
-import numpy as np
 from biocutils.FloatList import FloatList
 
 from .base import CompressedList
diff --git a/src/compressed_lists/integer_list.py b/src/compressed_lists/integer_list.py
index adc601d..10410a1 100644
--- a/src/compressed_lists/integer_list.py
+++ b/src/compressed_lists/integer_list.py
@@ -1,6 +1,5 @@
 from typing import Optional, Sequence, Union
 
-import numpy as np
 from biocutils.IntegerList import IntegerList
 
 from .base import CompressedList
@@ -89,11 +88,11 @@ def _(
     metadata: Optional[dict] = None,
 ) -> CompressedIntegerList:
     """Handle lists of integers."""
-    
+
     partitioned_data, groups_or_partitions = _generic_register_helper(
         data=data, groups_or_partitions=groups_or_partitions, names=names
     )
-    
+
     return CompressedIntegerList.from_partitioned_data(
         partitioned_data=partitioned_data, partitioning=groups_or_partitions, metadata=metadata
     )
diff --git a/src/compressed_lists/split_generic.py b/src/compressed_lists/split_generic.py
index 97321d6..bfe9cae 100644
--- a/src/compressed_lists/split_generic.py
+++ b/src/compressed_lists/split_generic.py
@@ -112,4 +112,4 @@ def _generic_register_helper(data, groups_or_partitions, names=None):
     else:
         raise ValueError("'groups_or_paritions' must be a group vector or a Partition object.")
 
-    return partitioned_data, groups_or_partitions
\ No newline at end of file
+    return partitioned_data, groups_or_partitions
diff --git a/src/compressed_lists/string_list.py b/src/compressed_lists/string_list.py
index 20f85ce..b7cbd4d 100644
--- a/src/compressed_lists/string_list.py
+++ b/src/compressed_lists/string_list.py
@@ -1,6 +1,5 @@
 from typing import List, Optional, Sequence, Union
 
-import numpy as np
 from biocutils.StringList import StringList
 
 from .base import CompressedList

From 056f32a59693f689082f10d38d1a82943202b72e Mon Sep 17 00:00:00 2001
From: Jayaram Kancherla <jayaram.kancherla@gmail.com>
Date: Tue, 7 Oct 2025 22:53:12 -0700
Subject: [PATCH 18/28] cleaning up numpylists

---
 src/compressed_lists/numpy_list.py | 57 ++++++++++++++----------------
 tests/test_comp_numpy.py           |  2 +-
 2 files changed, 28 insertions(+), 31 deletions(-)

diff --git a/src/compressed_lists/numpy_list.py b/src/compressed_lists/numpy_list.py
index deb52a5..74becd0 100644
--- a/src/compressed_lists/numpy_list.py
+++ b/src/compressed_lists/numpy_list.py
@@ -1,10 +1,10 @@
-from typing import List, Optional
+from typing import List, Optional, Sequence, Union
 
 import numpy as np
 
 from .base import CompressedList
 from .partition import Partitioning
-from .split_generic import splitAsCompressedList
+from .split_generic import _generic_register_helper, splitAsCompressedList
 
 __author__ = "Jayaram Kancherla"
 __copyright__ = "Jayaram Kancherla"
@@ -26,7 +26,7 @@ def __init__(
 
         Args:
             unlist_data:
-                NumPy vector.
+                List of NumPy vectors.
 
             partitioning:
                 Partitioning object defining element boundaries.
@@ -43,17 +43,17 @@ def __init__(
 
         if not isinstance(unlist_data, np.ndarray):
             try:
-                unlist_data = np.array(unlist_data)
+                unlist_data = np.concatenate(unlist_data)
             except Exception as e:
                 raise TypeError("'unlist_data' must be an `np.ndarray`, provided ", type(unlist_data)) from e
 
         super().__init__(
-            unlist_data, partitioning, element_type=np.array, element_metadata=element_metadata, metadata=metadata
+            unlist_data, partitioning, element_type=np.ndarray, element_metadata=element_metadata, metadata=metadata
         )
 
     @classmethod
     def from_list(
-        cls, lst: List[List[np.ndarray]], names: Optional[List[str]] = None, metadata: Optional[dict] = None
+        cls, lst: List[np.ndarray], names: Optional[Sequence[str]] = None, metadata: Optional[dict] = None
     ) -> "CompressedNumpyList":
         """
         Create a `CompressedNumpyList` from a list of NumPy vectors.
@@ -79,23 +79,28 @@ def from_list(
         if len(lst) == 0:
             unlist_data = np.array([])
         else:
-            unlist_data = np.hstack(lst)
+            unlist_data = np.concatenate(lst)
 
         return cls(unlist_data, partitioning, metadata=metadata)
 
     @classmethod
-    def _from_partitioned_data(
+    def from_partitioned_data(
         cls, partitioned_data: List[List], partitioning: Partitioning, metadata: Optional[dict] = None
     ) -> "CompressedNumpyList":
-        """Create CompressedNumpyList from already-partitioned data.
+        """Create `CompressedNumpyList` from already-partitioned data.
 
         Args:
-            partitioned_data: List of arrays, each containing numpy data for one partition
-            partitioning: Partitioning object defining the boundaries
-            metadata: Optional metadata
+            partitioned_data:
+                List of arrays, each containing numpy data for one partition.
+
+            partitioning:
+                Partitioning object defining the boundaries.
+
+            metadata:
+                Optional metadata.
 
         Returns:
-            A new CompressedNumpyList
+            A new `CompressedNumpyList`.
         """
         import numpy as np
 
@@ -111,24 +116,16 @@ def _from_partitioned_data(
 @splitAsCompressedList.register
 def _(
     data: np.ndarray,
-    names: Optional[List[str]] = None,
+    groups_or_partitions: Union[list, Partitioning],
+    names: Optional[Sequence[str]] = None,
     metadata: Optional[dict] = None,
-    groups: Optional[list] = None,
-    partitions: Optional[Partitioning] = None,
-):
+) -> CompressedNumpyList:
     """Handle NumPy arrays."""
 
-    if groups is not None:
-        return _splitAsCompressedList_by_groups(data, groups, names, metadata)
-    elif partitions is not None:
-        return _splitAsCompressedList_by_partitions(data, partitions, names, metadata)
-    else:
-        # Original behavior: convert single array to list of arrays
-        if data.ndim == 1:
-            list_data = [data]
-        else:
-            list_data = [row for row in data]
-
-        from .numpy_list import CompressedNumpyList
+    partitioned_data, groups_or_partitions = _generic_register_helper(
+        data=data, groups_or_partitions=groups_or_partitions, names=names
+    )
 
-        return CompressedNumpyList.from_list(list_data, names, metadata)
+    return CompressedNumpyList.from_partitioned_data(
+        partitioned_data=partitioned_data, partitioning=groups_or_partitions, metadata=metadata
+    )
diff --git a/tests/test_comp_numpy.py b/tests/test_comp_numpy.py
index aebffb0..8611591 100644
--- a/tests/test_comp_numpy.py
+++ b/tests/test_comp_numpy.py
@@ -29,7 +29,7 @@ def test_creation(numpy_data):
 
 
 def test_creation_from_parts():
-    numpy_list = CompressedNumpyList([1, 2, 3, 4, 5, 6, 7, 8, 9], Partitioning(ends=[3, 5, 9]))
+    numpy_list = CompressedNumpyList(np.array([1, 2, 3, 4, 5, 6, 7, 8, 9]), Partitioning(ends=[3, 5, 9]))
 
     assert len(numpy_list) == 3
     assert isinstance(numpy_list.unlist_data, np.ndarray)

From 00e6c898086681d04bb8ce73a7355c0bc17d98f4 Mon Sep 17 00:00:00 2001
From: Jayaram Kancherla <jayaram.kancherla@gmail.com>
Date: Wed, 8 Oct 2025 11:04:50 -0700
Subject: [PATCH 19/28] more tests for the generic

---
 src/compressed_lists/__init__.py       |  1 +
 src/compressed_lists/biocframe_list.py | 72 ++++++++++++++++++++++++++
 src/compressed_lists/bool_list.py      | 14 ++---
 src/compressed_lists/float_list.py     | 14 ++---
 src/compressed_lists/integer_list.py   | 11 ++--
 src/compressed_lists/numpy_list.py     |  8 +--
 src/compressed_lists/split_generic.py  | 21 ++++----
 src/compressed_lists/string_list.py    | 14 ++---
 tests/test_comp_custom.py              | 12 +++--
 tests/test_generics.py                 | 26 ++++++++++
 10 files changed, 149 insertions(+), 44 deletions(-)
 create mode 100644 src/compressed_lists/biocframe_list.py
 create mode 100644 tests/test_generics.py

diff --git a/src/compressed_lists/__init__.py b/src/compressed_lists/__init__.py
index 3715ce0..114defd 100644
--- a/src/compressed_lists/__init__.py
+++ b/src/compressed_lists/__init__.py
@@ -22,3 +22,4 @@
 from .bool_list import CompressedBooleanList
 from .float_list import CompressedFloatList
 from .numpy_list import CompressedNumpyList
+from .split_generic import splitAsCompressedList
\ No newline at end of file
diff --git a/src/compressed_lists/biocframe_list.py b/src/compressed_lists/biocframe_list.py
new file mode 100644
index 0000000..bc320b0
--- /dev/null
+++ b/src/compressed_lists/biocframe_list.py
@@ -0,0 +1,72 @@
+from typing import List, Union
+
+from biocframe import BiocFrame
+
+from .base import CompressedList
+from .partition import Partitioning
+from .split_generic import splitAsCompressedList
+
+__author__ = "Jayaram Kancherla"
+__copyright__ = "Jayaram Kancherla"
+__license__ = "MIT"
+
+
+class CompressedBiocFrameList(CompressedList):
+    """CompressedList for BiocFrames."""
+
+    def __init__(
+        self,
+        unlist_data: BiocFrame,
+        partitioning: Partitioning,
+        element_metadata: dict = None,
+        metadata: dict = None,
+        **kwargs,
+    ):
+        super().__init__(
+            unlist_data, partitioning, element_type="BiocFrame", element_metadata=element_metadata, metadata=metadata
+        )
+
+    @classmethod
+    def from_list(cls, lst: List[BiocFrame], names: List[str] = None, metadata: dict = None):
+        partitioning = Partitioning.from_list(lst, names)
+        return cls(lst, partitioning, metadata=metadata)
+
+    def __getitem__(self, key: Union[int, str, slice]):
+        """Override to handle column extraction using `splitAsCompressedList`.
+
+        When extracting a column, this will automatically dispatch to the
+        appropriate `CompressedList` subclass based on the column data type.
+        """
+        if isinstance(key, str):
+            column_data = []
+            for df in self.unlist_data:
+                if key in df.columns:
+                    column_data.append(df[key].tolist())
+                else:
+                    column_data.append([])
+
+            return splitAsCompressedList(column_data, names=self.names, metadata=self.metadata)
+        else:
+            return super().__getitem__(key)
+
+    @classmethod
+    def _from_partitioned_data(cls, partitioned_data: List, partitioning: Partitioning, metadata: dict = None) -> "CompressedBiocFrameList":
+        """Create CompressedBiocFrameList from already-partitioned data.
+        
+        Args:
+            partitioned_data: List of BiocFrame objects (already partitioned)
+            partitioning: Partitioning object defining the boundaries  
+            metadata: Optional metadata
+            
+        Returns:
+            A new CompressedBiocFrameList
+        """
+        # For BiocFrame, the partitioned_data should already be a list of BiocFrame objects
+        # so we can use it directly as unlist_data
+        return cls(partitioned_data, partitioning, metadata=metadata)
+
+
+@splitAsCompressedList.register
+def _(data: List[BiocFrame], names: List[str] = None, metadata: dict = None) -> CompressedBiocFrameList:
+    """Handle lists of boolean."""
+    return CompressedBiocFrameList.from_list(data, names, metadata)
diff --git a/src/compressed_lists/bool_list.py b/src/compressed_lists/bool_list.py
index 19a0903..a3aed3f 100644
--- a/src/compressed_lists/bool_list.py
+++ b/src/compressed_lists/bool_list.py
@@ -1,4 +1,4 @@
-from typing import List, Optional, Sequence, Union
+from typing import Optional, Sequence, Union
 
 from biocutils.BooleanList import BooleanList
 
@@ -53,7 +53,7 @@ def __init__(
 
     @classmethod
     def from_partitioned_data(
-        cls, partitioned_data: List[List], partitioning: Partitioning, metadata: Optional[dict] = None
+        cls, partitioned_data: Sequence[BooleanList], partitioning: Partitioning, metadata: Optional[dict] = None
     ) -> "CompressedBooleanList":
         """Create `CompressedBooleanList` from already-partitioned data.
 
@@ -70,11 +70,13 @@ def from_partitioned_data(
         Returns:
             A new `CompressedBooleanList`.
         """
-        flat_data = []
-        for partition in partitioned_data:
-            flat_data.extend(partition)
+        unlist_data = partitioned_data
+        if isinstance(partitioned_data, list):
+            flat_data = []
+            for partition in partitioned_data:
+                flat_data.extend(partition)
 
-        unlist_data = BooleanList(flat_data)
+            unlist_data = BooleanList(flat_data)
 
         return cls(unlist_data, partitioning, metadata=metadata)
 
diff --git a/src/compressed_lists/float_list.py b/src/compressed_lists/float_list.py
index 2b56884..6c97c5b 100644
--- a/src/compressed_lists/float_list.py
+++ b/src/compressed_lists/float_list.py
@@ -1,4 +1,4 @@
-from typing import List, Optional, Sequence, Union
+from typing import Optional, Sequence, Union
 
 from biocutils.FloatList import FloatList
 
@@ -53,7 +53,7 @@ def __init__(
 
     @classmethod
     def from_partitioned_data(
-        cls, partitioned_data: List[List], partitioning: Partitioning, metadata: Optional[dict] = None
+        cls, partitioned_data: Sequence[FloatList], partitioning: Partitioning, metadata: Optional[dict] = None
     ) -> "CompressedFloatList":
         """Create `CompressedFloatList` from already-partitioned data.
 
@@ -70,11 +70,13 @@ def from_partitioned_data(
         Returns:
             A new `CompressedFloatList`.
         """
-        flat_data = []
-        for partition in partitioned_data:
-            flat_data.extend(partition)
+        unlist_data = partitioned_data
+        if isinstance(partitioned_data, list):
+            flat_data = []
+            for partition in partitioned_data:
+                flat_data.extend(partition)
 
-        unlist_data = FloatList(flat_data)
+            unlist_data = FloatList(flat_data)
 
         return cls(unlist_data, partitioning, metadata=metadata)
 
diff --git a/src/compressed_lists/integer_list.py b/src/compressed_lists/integer_list.py
index 10410a1..3739d76 100644
--- a/src/compressed_lists/integer_list.py
+++ b/src/compressed_lists/integer_list.py
@@ -70,12 +70,13 @@ def from_partitioned_data(
         Returns:
             A new `CompressedIntegerList`.
         """
+        unlist_data = partitioned_data
+        if isinstance(partitioned_data, list):
+            flat_data = []
+            for partition in partitioned_data:
+                flat_data.extend(partition)
 
-        flat_data = []
-        for partition in partitioned_data:
-            flat_data.extend(partition)
-
-        unlist_data = IntegerList(flat_data)
+            unlist_data = IntegerList(flat_data)
 
         return cls(unlist_data, partitioning, metadata=metadata)
 
diff --git a/src/compressed_lists/numpy_list.py b/src/compressed_lists/numpy_list.py
index 74becd0..5f7aeeb 100644
--- a/src/compressed_lists/numpy_list.py
+++ b/src/compressed_lists/numpy_list.py
@@ -71,11 +71,8 @@ def from_list(
         Returns:
             A new `CompressedNumpyList`.
         """
-
-        # Create partitioning
         partitioning = Partitioning.from_list(lst, names)
 
-        # Create unlist_data
         if len(lst) == 0:
             unlist_data = np.array([])
         else:
@@ -85,7 +82,7 @@ def from_list(
 
     @classmethod
     def from_partitioned_data(
-        cls, partitioned_data: List[List], partitioning: Partitioning, metadata: Optional[dict] = None
+        cls, partitioned_data: Sequence[np.ndarray], partitioning: Partitioning, metadata: Optional[dict] = None
     ) -> "CompressedNumpyList":
         """Create `CompressedNumpyList` from already-partitioned data.
 
@@ -102,9 +99,6 @@ def from_partitioned_data(
         Returns:
             A new `CompressedNumpyList`.
         """
-        import numpy as np
-
-        # Concatenate the numpy arrays
         if not partitioned_data or not partitioned_data[0]:
             unlist_data = np.array([])
         else:
diff --git a/src/compressed_lists/split_generic.py b/src/compressed_lists/split_generic.py
index bfe9cae..d63e55e 100644
--- a/src/compressed_lists/split_generic.py
+++ b/src/compressed_lists/split_generic.py
@@ -96,19 +96,22 @@ def _generic_register_helper(data, groups_or_partitions, names=None):
     if not data:
         raise ValueError("'data' cannot be empty.")
 
-    if isinstance(groups_or_partitions, (list, np.ndarray)):
+    if isinstance(groups_or_partitions, Partitioning):
+        if names is not None:
+            groups_or_partitions = groups_or_partitions.set_names(names, in_place=False)
+
+        # TODO: probably not necessary to split when groups is a partition object.
+        # unless ordering matters
+        # partitioned_data = []
+        # for i in range(len(groups_or_partitions)):
+        #     start, end = groups_or_partitions.get_partition_range(i)
+        #     partitioned_data.append(data[start:end])
+        partitioned_data = data
+    elif isinstance(groups_or_partitions, (list, np.ndarray)):
         partitioned_data, groups_or_partitions = groups_to_partition(data, groups=groups_or_partitions, names=names)
 
         if len(partitioned_data) == 0:
             raise ValueError("No data after grouping")
-    elif isinstance(groups_or_partitions, Partitioning):
-        if names is not None:
-            groups_or_partitions = groups_or_partitions.set_names(names, in_place=False)
-
-        partitioned_data = []
-        for i in range(len(groups_or_partitions)):
-            start, end = groups_or_partitions.get_partition_range(i)
-            partitioned_data.append(data[start:end])
     else:
         raise ValueError("'groups_or_paritions' must be a group vector or a Partition object.")
 
diff --git a/src/compressed_lists/string_list.py b/src/compressed_lists/string_list.py
index b7cbd4d..19fb82e 100644
--- a/src/compressed_lists/string_list.py
+++ b/src/compressed_lists/string_list.py
@@ -1,4 +1,4 @@
-from typing import List, Optional, Sequence, Union
+from typing import Optional, Sequence, Union
 
 from biocutils.StringList import StringList
 
@@ -52,7 +52,7 @@ def __init__(
 
     @classmethod
     def from_partitioned_data(
-        cls, partitioned_data: List[List], partitioning: Partitioning, metadata: Optional[dict] = None
+        cls, partitioned_data: Sequence[StringList], partitioning: Partitioning, metadata: Optional[dict] = None
     ) -> "CompressedStringList":
         """Create `CompressedStringList` from already-partitioned data.
 
@@ -69,11 +69,13 @@ def from_partitioned_data(
         Returns:
             A new `CompressedStringList`.
         """
-        flat_data = []
-        for partition in partitioned_data:
-            flat_data.extend(partition)
+        unlist_data = partitioned_data
+        if isinstance(partitioned_data, list):
+            flat_data = []
+            for partition in partitioned_data:
+                flat_data.extend(partition)
 
-        unlist_data = StringList(flat_data)
+            unlist_data = StringList(flat_data)
 
         return cls(unlist_data, partitioning, metadata=metadata)
 
diff --git a/tests/test_comp_custom.py b/tests/test_comp_custom.py
index aa4f582..82bd860 100644
--- a/tests/test_comp_custom.py
+++ b/tests/test_comp_custom.py
@@ -1,4 +1,4 @@
-from typing import List
+from typing import Any, List, Optional, Sequence
 
 import pytest
 
@@ -14,10 +14,12 @@ def CompressedCustomFloatList():
     class CompressedCustomFloatList(CompressedList):
         def __init__(
             self,
-            unlist_data: List[float],
+            unlist_data: Any,
             partitioning: Partitioning,
-            element_metadata: dict = None,
-            metadata: dict = None,
+            element_type: Any = None,
+            element_metadata: Optional[dict] = None,
+            metadata: Optional[dict] = None,
+            validate: bool = True,
         ):
             super().__init__(
                 unlist_data, partitioning, element_type="float", element_metadata=element_metadata, metadata=metadata
@@ -28,7 +30,7 @@ def extract_range(self, start: int, end: int) -> List[float]:
 
         @classmethod
         def from_list(
-            cls, lst: List[List[float]], names: list = None, metadata: dict = None
+            cls, lst: List[Any], names: Optional[Sequence[str]] = None, metadata: Optional[dict] = None
         ) -> "CompressedCustomFloatList":
             flat_data = []
             for sublist in lst:
diff --git a/tests/test_generics.py b/tests/test_generics.py
new file mode 100644
index 0000000..8ec5b0e
--- /dev/null
+++ b/tests/test_generics.py
@@ -0,0 +1,26 @@
+import biocutils as ut
+import numpy as np
+import pytest
+
+from compressed_lists import CompressedFloatList, CompressedIntegerList, Partitioning, splitAsCompressedList
+
+__author__ = "Jayaram Kancherla"
+__copyright__ = "Jayaram Kancherla"
+__license__ = "MIT"
+
+
+def test_groups():
+    float_vec = ut.FloatList([1.1, 1.2, 2.1, 2.2, 2.3, 3.0])
+    groups = [1, 2, 3, 1, 2, 3]
+
+    clist = splitAsCompressedList(float_vec, groups_or_partitions=groups)
+
+    assert isinstance(clist, CompressedFloatList)
+
+
+def test_partitions():
+    int_list = splitAsCompressedList(
+        ut.IntegerList([1, 2, 3, 4, 5, 6, 7, 8, 9]), groups_or_partitions=Partitioning(ends=[3, 5, 9])
+    )
+
+    assert isinstance(int_list, CompressedIntegerList)

From 155e8aa58f3d575bd9768bf88c9046715ed6b85d Mon Sep 17 00:00:00 2001
From: "pre-commit-ci[bot]"
 <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Date: Wed, 8 Oct 2025 18:05:09 +0000
Subject: [PATCH 20/28] [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci
---
 src/compressed_lists/__init__.py       |  2 +-
 src/compressed_lists/biocframe_list.py | 10 ++++++----
 tests/test_generics.py                 |  2 --
 3 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/src/compressed_lists/__init__.py b/src/compressed_lists/__init__.py
index 114defd..6f94bef 100644
--- a/src/compressed_lists/__init__.py
+++ b/src/compressed_lists/__init__.py
@@ -22,4 +22,4 @@
 from .bool_list import CompressedBooleanList
 from .float_list import CompressedFloatList
 from .numpy_list import CompressedNumpyList
-from .split_generic import splitAsCompressedList
\ No newline at end of file
+from .split_generic import splitAsCompressedList
diff --git a/src/compressed_lists/biocframe_list.py b/src/compressed_lists/biocframe_list.py
index bc320b0..0870d2c 100644
--- a/src/compressed_lists/biocframe_list.py
+++ b/src/compressed_lists/biocframe_list.py
@@ -50,14 +50,16 @@ def __getitem__(self, key: Union[int, str, slice]):
             return super().__getitem__(key)
 
     @classmethod
-    def _from_partitioned_data(cls, partitioned_data: List, partitioning: Partitioning, metadata: dict = None) -> "CompressedBiocFrameList":
+    def _from_partitioned_data(
+        cls, partitioned_data: List, partitioning: Partitioning, metadata: dict = None
+    ) -> "CompressedBiocFrameList":
         """Create CompressedBiocFrameList from already-partitioned data.
-        
+
         Args:
             partitioned_data: List of BiocFrame objects (already partitioned)
-            partitioning: Partitioning object defining the boundaries  
+            partitioning: Partitioning object defining the boundaries
             metadata: Optional metadata
-            
+
         Returns:
             A new CompressedBiocFrameList
         """
diff --git a/tests/test_generics.py b/tests/test_generics.py
index 8ec5b0e..ae45e43 100644
--- a/tests/test_generics.py
+++ b/tests/test_generics.py
@@ -1,6 +1,4 @@
 import biocutils as ut
-import numpy as np
-import pytest
 
 from compressed_lists import CompressedFloatList, CompressedIntegerList, Partitioning, splitAsCompressedList
 

From 7c7ecba90f7da07418499cd732cd5387bc41b60b Mon Sep 17 00:00:00 2001
From: Jayaram Kancherla <jayaram.kancherla@gmail.com>
Date: Wed, 8 Oct 2025 19:25:43 -0700
Subject: [PATCH 21/28] more biocutils methods, getting rid of from_partitioned
 data

---
 src/compressed_lists/biocframe_list.py | 107 ++++++++++++++++---------
 src/compressed_lists/bool_list.py      |  50 +++---------
 src/compressed_lists/float_list.py     |  50 +++---------
 src/compressed_lists/integer_list.py   |  52 +++---------
 src/compressed_lists/numpy_list.py     |  36 ++-------
 src/compressed_lists/split_generic.py  |   5 +-
 src/compressed_lists/string_list.py    |  50 +++---------
 7 files changed, 128 insertions(+), 222 deletions(-)

diff --git a/src/compressed_lists/biocframe_list.py b/src/compressed_lists/biocframe_list.py
index 0870d2c..ec1c423 100644
--- a/src/compressed_lists/biocframe_list.py
+++ b/src/compressed_lists/biocframe_list.py
@@ -1,10 +1,11 @@
-from typing import List, Union
+from typing import List, Optional, Sequence, Union
 
+import biocutils as ut
 from biocframe import BiocFrame
 
 from .base import CompressedList
 from .partition import Partitioning
-from .split_generic import splitAsCompressedList
+from .split_generic import _generic_register_helper, splitAsCompressedList
 
 __author__ = "Jayaram Kancherla"
 __copyright__ = "Jayaram Kancherla"
@@ -18,57 +19,87 @@ def __init__(
         self,
         unlist_data: BiocFrame,
         partitioning: Partitioning,
-        element_metadata: dict = None,
-        metadata: dict = None,
+        element_metadata: Optional[dict] = None,
+        metadata: Optional[dict] = None,
         **kwargs,
     ):
+        """Initialize a CompressedBiocFrameList.
+
+        Args:
+            unlist_data:
+                BiocFrame object.
+
+            partitioning:
+                Partitioning object defining element boundaries.
+
+            element_metadata:
+                Optional metadata for elements.
+
+            metadata:
+                Optional general metadata.
+
+            kwargs:
+                Additional arguments.
+        """
+        if not isinstance(unlist_data, BiocFrame):
+            raise TypeError("'unlist_data' is not a `BiocFrame` object.")
+
         super().__init__(
             unlist_data, partitioning, element_type="BiocFrame", element_metadata=element_metadata, metadata=metadata
         )
 
     @classmethod
-    def from_list(cls, lst: List[BiocFrame], names: List[str] = None, metadata: dict = None):
-        partitioning = Partitioning.from_list(lst, names)
-        return cls(lst, partitioning, metadata=metadata)
+    def from_list(
+        cls, lst: List[BiocFrame], names: Optional[Sequence[str]] = None, metadata: Optional[dict] = None
+    ) -> "CompressedBiocFrameList":
+        """Create a `CompressedBiocFrameList` from a regular list.
 
-    def __getitem__(self, key: Union[int, str, slice]):
-        """Override to handle column extraction using `splitAsCompressedList`.
+        This concatenates the list of `BiocFrame` objects.
+
+        Args:
+            lst:
+                List of `BiocFrame` objects.
 
-        When extracting a column, this will automatically dispatch to the
-        appropriate `CompressedList` subclass based on the column data type.
+            names:
+                Optional names for list elements.
+
+            metadata:
+                Optional metadata.
+
+        Returns:
+            A new `CompressedList`.
         """
+        unlist_data = ut.relaxed_combine_rows(*lst)
+        partitioning = Partitioning.from_list(lst, names)
+        return cls(unlist_data, partitioning, metadata=metadata)
+
+    def __getitem__(self, key: Union[int, str, slice]):
+        """Override to handle column extraction using `splitAsCompressedList`."""
         if isinstance(key, str):
-            column_data = []
-            for df in self.unlist_data:
-                if key in df.columns:
-                    column_data.append(df[key].tolist())
-                else:
-                    column_data.append([])
-
-            return splitAsCompressedList(column_data, names=self.names, metadata=self.metadata)
+            column_data = self._unlist_data.get_column(key)
+            return splitAsCompressedList(
+                column_data, partition=self._partitioning, names=self.names, metadata=self.metadata
+            )
         else:
             return super().__getitem__(key)
 
-    @classmethod
-    def _from_partitioned_data(
-        cls, partitioned_data: List, partitioning: Partitioning, metadata: dict = None
-    ) -> "CompressedBiocFrameList":
-        """Create CompressedBiocFrameList from already-partitioned data.
 
-        Args:
-            partitioned_data: List of BiocFrame objects (already partitioned)
-            partitioning: Partitioning object defining the boundaries
-            metadata: Optional metadata
+@splitAsCompressedList.register
+def _(
+    data: BiocFrame,
+    groups_or_partitions: Union[list, Partitioning],
+    names: Optional[Sequence[str]] = None,
+    metadata: Optional[dict] = None,
+) -> CompressedBiocFrameList:
+    """Handle lists of BiocFrame objects."""
 
-        Returns:
-            A new CompressedBiocFrameList
-        """
-        # For BiocFrame, the partitioned_data should already be a list of BiocFrame objects
-        # so we can use it directly as unlist_data
-        return cls(partitioned_data, partitioning, metadata=metadata)
+    partitioned_data, groups_or_partitions = _generic_register_helper(
+        data=data, groups_or_partitions=groups_or_partitions, names=names
+    )
 
+    if not isinstance(partitioned_data, BiocFrame):
+        partitioned_data = ut.relaxed_combine_rows(*partitioned_data)
 
-@splitAsCompressedList.register
-def _(data: List[BiocFrame], names: List[str] = None, metadata: dict = None) -> CompressedBiocFrameList:
-    """Handle lists of boolean."""
-    return CompressedBiocFrameList.from_list(data, names, metadata)
+    return CompressedBiocFrameList(
+        unlist_data=partitioned_data, partitioning=groups_or_partitions, metadata=metadata
+    )
diff --git a/src/compressed_lists/bool_list.py b/src/compressed_lists/bool_list.py
index a3aed3f..8ca8f29 100644
--- a/src/compressed_lists/bool_list.py
+++ b/src/compressed_lists/bool_list.py
@@ -1,6 +1,7 @@
 from typing import Optional, Sequence, Union
+from warnings import warn
 
-from biocutils.BooleanList import BooleanList
+import biocutils as ut
 
 from .base import CompressedList
 from .partition import Partitioning
@@ -16,7 +17,7 @@ class CompressedBooleanList(CompressedList):
 
     def __init__(
         self,
-        unlist_data: BooleanList,
+        unlist_data: ut.BooleanList,
         partitioning: Partitioning,
         element_metadata: Optional[dict] = None,
         metadata: Optional[dict] = None,
@@ -41,49 +42,21 @@ def __init__(
                 Additional arguments.
         """
 
-        if not isinstance(unlist_data, BooleanList):
+        if not isinstance(unlist_data, ut.BooleanList):
             try:
-                unlist_data = BooleanList(unlist_data)
+                warn("trying to coerce 'unlist_data' to `BooleanList`..")
+                unlist_data = ut.BooleanList(unlist_data)
             except Exception as e:
                 raise TypeError("'unlist_data' must be an `BooleanList`, provided ", type(unlist_data)) from e
 
         super().__init__(
-            unlist_data, partitioning, element_type=BooleanList, element_metadata=element_metadata, metadata=metadata
+            unlist_data, partitioning, element_type=ut.BooleanList, element_metadata=element_metadata, metadata=metadata
         )
 
-    @classmethod
-    def from_partitioned_data(
-        cls, partitioned_data: Sequence[BooleanList], partitioning: Partitioning, metadata: Optional[dict] = None
-    ) -> "CompressedBooleanList":
-        """Create `CompressedBooleanList` from already-partitioned data.
-
-        Args:
-            partitioned_data:
-                List of `BooleanList`'s, each containing booleans for one partition.
-
-            partitioning:
-                Partitioning object defining the boundaries.
-
-            metadata:
-                Optional metadata.
-
-        Returns:
-            A new `CompressedBooleanList`.
-        """
-        unlist_data = partitioned_data
-        if isinstance(partitioned_data, list):
-            flat_data = []
-            for partition in partitioned_data:
-                flat_data.extend(partition)
-
-            unlist_data = BooleanList(flat_data)
-
-        return cls(unlist_data, partitioning, metadata=metadata)
-
 
 @splitAsCompressedList.register
 def _(
-    data: BooleanList,
+    data: ut.BooleanList,
     groups_or_partitions: Union[list, Partitioning],
     names: Optional[Sequence[str]] = None,
     metadata: Optional[dict] = None,
@@ -94,6 +67,7 @@ def _(
         data=data, groups_or_partitions=groups_or_partitions, names=names
     )
 
-    return CompressedBooleanList.from_partitioned_data(
-        partitioned_data=partitioned_data, partitioning=groups_or_partitions, metadata=metadata
-    )
+    if not isinstance(partitioned_data, ut.BooleanList):
+        partitioned_data = ut.combine_sequences(*partitioned_data)
+
+    return CompressedBooleanList(unlist_data=partitioned_data, partitioning=groups_or_partitions, metadata=metadata)
diff --git a/src/compressed_lists/float_list.py b/src/compressed_lists/float_list.py
index 6c97c5b..006f767 100644
--- a/src/compressed_lists/float_list.py
+++ b/src/compressed_lists/float_list.py
@@ -1,6 +1,7 @@
 from typing import Optional, Sequence, Union
+from warnings import warn
 
-from biocutils.FloatList import FloatList
+import biocutils as ut
 
 from .base import CompressedList
 from .partition import Partitioning
@@ -16,7 +17,7 @@ class CompressedFloatList(CompressedList):
 
     def __init__(
         self,
-        unlist_data: FloatList,
+        unlist_data: ut.FloatList,
         partitioning: Partitioning,
         element_metadata: Optional[dict] = None,
         metadata: Optional[dict] = None,
@@ -41,49 +42,21 @@ def __init__(
                 Additional arguments.
         """
 
-        if not isinstance(unlist_data, FloatList):
+        if not isinstance(unlist_data, ut.FloatList):
             try:
-                unlist_data = FloatList(unlist_data)
+                warn("trying to coerce 'unlist_data' to `FloatList`..")
+                unlist_data = ut.FloatList(unlist_data)
             except Exception as e:
                 raise TypeError("'unlist_data' must be an `FloatList`, provided ", type(unlist_data)) from e
 
         super().__init__(
-            unlist_data, partitioning, element_type=FloatList, element_metadata=element_metadata, metadata=metadata
+            unlist_data, partitioning, element_type=ut.FloatList, element_metadata=element_metadata, metadata=metadata
         )
 
-    @classmethod
-    def from_partitioned_data(
-        cls, partitioned_data: Sequence[FloatList], partitioning: Partitioning, metadata: Optional[dict] = None
-    ) -> "CompressedFloatList":
-        """Create `CompressedFloatList` from already-partitioned data.
-
-        Args:
-            partitioned_data:
-                List of lists, each containing floats for one partition.
-
-            partitioning:
-                Partitioning object defining the boundaries.
-
-            metadata:
-                Optional metadata.
-
-        Returns:
-            A new `CompressedFloatList`.
-        """
-        unlist_data = partitioned_data
-        if isinstance(partitioned_data, list):
-            flat_data = []
-            for partition in partitioned_data:
-                flat_data.extend(partition)
-
-            unlist_data = FloatList(flat_data)
-
-        return cls(unlist_data, partitioning, metadata=metadata)
-
 
 @splitAsCompressedList.register
 def _(
-    data: FloatList,
+    data: ut.FloatList,
     groups_or_partitions: Union[list, Partitioning],
     names: Optional[Sequence[str]] = None,
     metadata: Optional[dict] = None,
@@ -94,6 +67,7 @@ def _(
         data=data, groups_or_partitions=groups_or_partitions, names=names
     )
 
-    return CompressedFloatList.from_partitioned_data(
-        partitioned_data=partitioned_data, partitioning=groups_or_partitions, metadata=metadata
-    )
+    if not isinstance(partitioned_data, ut.FloatList):
+        partitioned_data = ut.combine_sequences(*partitioned_data)
+
+    return CompressedFloatList(unlist_data=partitioned_data, partitioning=groups_or_partitions, metadata=metadata)
diff --git a/src/compressed_lists/integer_list.py b/src/compressed_lists/integer_list.py
index 3739d76..e79a9f1 100644
--- a/src/compressed_lists/integer_list.py
+++ b/src/compressed_lists/integer_list.py
@@ -1,10 +1,11 @@
 from typing import Optional, Sequence, Union
+from warnings import warn
 
-from biocutils.IntegerList import IntegerList
+import biocutils as ut
 
 from .base import CompressedList
 from .partition import Partitioning
-from .split_generic import splitAsCompressedList, _generic_register_helper
+from .split_generic import _generic_register_helper, splitAsCompressedList
 
 __author__ = "Jayaram Kancherla"
 __copyright__ = "Jayaram Kancherla"
@@ -16,7 +17,7 @@ class CompressedIntegerList(CompressedList):
 
     def __init__(
         self,
-        unlist_data: IntegerList,
+        unlist_data: ut.IntegerList,
         partitioning: Partitioning,
         element_metadata: Optional[dict] = None,
         metadata: Optional[dict] = None,
@@ -41,49 +42,21 @@ def __init__(
                 Additional arguments.
         """
 
-        if not isinstance(unlist_data, IntegerList):
+        if not isinstance(unlist_data, ut.IntegerList):
             try:
-                unlist_data = IntegerList(unlist_data)
+                warn("trying to coerce 'unlist_data' to `IntegerList`..")
+                unlist_data = ut.IntegerList(unlist_data)
             except Exception as e:
                 raise TypeError("'unlist_data' must be an `IntegerList`, provided ", type(unlist_data)) from e
 
         super().__init__(
-            unlist_data, partitioning, element_type=IntegerList, element_metadata=element_metadata, metadata=metadata
+            unlist_data, partitioning, element_type=ut.IntegerList, element_metadata=element_metadata, metadata=metadata
         )
 
-    @classmethod
-    def from_partitioned_data(
-        cls, partitioned_data: Sequence[IntegerList], partitioning: Partitioning, metadata: Optional[dict] = None
-    ) -> "CompressedIntegerList":
-        """Create `CompressedIntegerList` from already-partitioned data.
-
-        Args:
-            partitioned_data:
-                List of `IntegerList`'s, each containing integers for one partition.
-
-            partitioning:
-                Partitioning object defining the boundaries.
-
-            metadata:
-                Optional metadata.
-
-        Returns:
-            A new `CompressedIntegerList`.
-        """
-        unlist_data = partitioned_data
-        if isinstance(partitioned_data, list):
-            flat_data = []
-            for partition in partitioned_data:
-                flat_data.extend(partition)
-
-            unlist_data = IntegerList(flat_data)
-
-        return cls(unlist_data, partitioning, metadata=metadata)
-
 
 @splitAsCompressedList.register
 def _(
-    data: IntegerList,
+    data: ut.IntegerList,
     groups_or_partitions: Union[list, Partitioning],
     names: Optional[Sequence[str]] = None,
     metadata: Optional[dict] = None,
@@ -94,6 +67,7 @@ def _(
         data=data, groups_or_partitions=groups_or_partitions, names=names
     )
 
-    return CompressedIntegerList.from_partitioned_data(
-        partitioned_data=partitioned_data, partitioning=groups_or_partitions, metadata=metadata
-    )
+    if not isinstance(partitioned_data, ut.IntegerList):
+        partitioned_data = ut.combine_sequences(*partitioned_data)
+
+    return CompressedIntegerList(unlist_data=partitioned_data, partitioning=groups_or_partitions, metadata=metadata)
diff --git a/src/compressed_lists/numpy_list.py b/src/compressed_lists/numpy_list.py
index 5f7aeeb..1e70f2b 100644
--- a/src/compressed_lists/numpy_list.py
+++ b/src/compressed_lists/numpy_list.py
@@ -1,5 +1,7 @@
 from typing import List, Optional, Sequence, Union
+from warnings import warn
 
+import biocutils as ut
 import numpy as np
 
 from .base import CompressedList
@@ -43,6 +45,7 @@ def __init__(
 
         if not isinstance(unlist_data, np.ndarray):
             try:
+                warn("trying to concatenate/coerce 'unlist_data' to a `np.ndarray`..")
                 unlist_data = np.concatenate(unlist_data)
             except Exception as e:
                 raise TypeError("'unlist_data' must be an `np.ndarray`, provided ", type(unlist_data)) from e
@@ -80,32 +83,6 @@ def from_list(
 
         return cls(unlist_data, partitioning, metadata=metadata)
 
-    @classmethod
-    def from_partitioned_data(
-        cls, partitioned_data: Sequence[np.ndarray], partitioning: Partitioning, metadata: Optional[dict] = None
-    ) -> "CompressedNumpyList":
-        """Create `CompressedNumpyList` from already-partitioned data.
-
-        Args:
-            partitioned_data:
-                List of arrays, each containing numpy data for one partition.
-
-            partitioning:
-                Partitioning object defining the boundaries.
-
-            metadata:
-                Optional metadata.
-
-        Returns:
-            A new `CompressedNumpyList`.
-        """
-        if not partitioned_data or not partitioned_data[0]:
-            unlist_data = np.array([])
-        else:
-            unlist_data = np.concatenate(partitioned_data)
-
-        return cls(unlist_data, partitioning, metadata=metadata)
-
 
 @splitAsCompressedList.register
 def _(
@@ -120,6 +97,7 @@ def _(
         data=data, groups_or_partitions=groups_or_partitions, names=names
     )
 
-    return CompressedNumpyList.from_partitioned_data(
-        partitioned_data=partitioned_data, partitioning=groups_or_partitions, metadata=metadata
-    )
+    if not isinstance(partitioned_data, np.ndarray):
+        partitioned_data = ut.combine_sequences(*partitioned_data)
+
+    return CompressedNumpyList(unlist_data=partitioned_data, partitioning=groups_or_partitions, metadata=metadata)
diff --git a/src/compressed_lists/split_generic.py b/src/compressed_lists/split_generic.py
index d63e55e..78aea5e 100644
--- a/src/compressed_lists/split_generic.py
+++ b/src/compressed_lists/split_generic.py
@@ -30,7 +30,7 @@ def groups_to_partition(
     Returns:
         Tuple of (partitioned_data_list, partitioning_object)
     """
-
+    print(data, groups)
     if len(data) != len(groups):
         raise ValueError(f"Length of data ({len(data)}) must match length of groups ({len(groups)})")
 
@@ -39,8 +39,9 @@ def groups_to_partition(
         group_dict[group].append(item)
 
     sorted_groups = sorted(group_dict.keys())
+    print(sorted_groups)
     partitioned_data = [group_dict[group] for group in sorted_groups]
-
+    print("pdata", partitioned_data)
     if names is None:
         group_names = [str(group) for group in sorted_groups]
     else:
diff --git a/src/compressed_lists/string_list.py b/src/compressed_lists/string_list.py
index 19fb82e..f612747 100644
--- a/src/compressed_lists/string_list.py
+++ b/src/compressed_lists/string_list.py
@@ -1,6 +1,7 @@
 from typing import Optional, Sequence, Union
+from warnings import warn
 
-from biocutils.StringList import StringList
+import biocutils as ut
 
 from .base import CompressedList
 from .partition import Partitioning
@@ -16,7 +17,7 @@ class CompressedStringList(CompressedList):
 
     def __init__(
         self,
-        unlist_data: StringList,
+        unlist_data: ut.StringList,
         partitioning: Partitioning,
         element_metadata: Optional[dict] = None,
         metadata: Optional[dict] = None,
@@ -40,45 +41,17 @@ def __init__(
             kwargs:
                 Additional arguments.
         """
-        if not isinstance(unlist_data, StringList):
+        if not isinstance(unlist_data, ut.StringList):
             try:
-                unlist_data = StringList(unlist_data)
+                warn("trying to coerce 'unlist_data' to `StringList`..")
+                unlist_data = ut.StringList(unlist_data)
             except Exception as e:
                 raise TypeError("'unlist_data' must be an `StringList`, provided ", type(unlist_data)) from e
 
         super().__init__(
-            unlist_data, partitioning, element_type=StringList, element_metadata=element_metadata, metadata=metadata
+            unlist_data, partitioning, element_type=ut.StringList, element_metadata=element_metadata, metadata=metadata
         )
 
-    @classmethod
-    def from_partitioned_data(
-        cls, partitioned_data: Sequence[StringList], partitioning: Partitioning, metadata: Optional[dict] = None
-    ) -> "CompressedStringList":
-        """Create `CompressedStringList` from already-partitioned data.
-
-        Args:
-            partitioned_data:
-                List of lists, each containing strings for one partition.
-
-            partitioning:
-                Partitioning object defining the boundaries.
-
-            metadata:
-                Optional metadata.
-
-        Returns:
-            A new `CompressedStringList`.
-        """
-        unlist_data = partitioned_data
-        if isinstance(partitioned_data, list):
-            flat_data = []
-            for partition in partitioned_data:
-                flat_data.extend(partition)
-
-            unlist_data = StringList(flat_data)
-
-        return cls(unlist_data, partitioning, metadata=metadata)
-
 
 class CompressedCharacterList(CompressedStringList):
     pass
@@ -86,7 +59,7 @@ class CompressedCharacterList(CompressedStringList):
 
 @splitAsCompressedList.register
 def _(
-    data: StringList,
+    data: ut.StringList,
     groups_or_partitions: Union[list, Partitioning],
     names: Optional[Sequence[str]] = None,
     metadata: Optional[dict] = None,
@@ -97,6 +70,7 @@ def _(
         data=data, groups_or_partitions=groups_or_partitions, names=names
     )
 
-    return CompressedStringList.from_partitioned_data(
-        partitioned_data=partitioned_data, partitioning=groups_or_partitions, metadata=metadata
-    )
+    if not isinstance(partitioned_data, ut.StringList):
+        partitioned_data = ut.combine_sequences(*partitioned_data)
+
+    return CompressedStringList(unlist_data=partitioned_data, partitioning=groups_or_partitions, metadata=metadata)

From b799d710aca9de35b1c6f54c8871ba71d2f9fa4e Mon Sep 17 00:00:00 2001
From: "pre-commit-ci[bot]"
 <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Date: Thu, 9 Oct 2025 02:25:52 +0000
Subject: [PATCH 22/28] [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci
---
 src/compressed_lists/biocframe_list.py | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/src/compressed_lists/biocframe_list.py b/src/compressed_lists/biocframe_list.py
index ec1c423..c716597 100644
--- a/src/compressed_lists/biocframe_list.py
+++ b/src/compressed_lists/biocframe_list.py
@@ -100,6 +100,4 @@ def _(
     if not isinstance(partitioned_data, BiocFrame):
         partitioned_data = ut.relaxed_combine_rows(*partitioned_data)
 
-    return CompressedBiocFrameList(
-        unlist_data=partitioned_data, partitioning=groups_or_partitions, metadata=metadata
-    )
+    return CompressedBiocFrameList(unlist_data=partitioned_data, partitioning=groups_or_partitions, metadata=metadata)

From 7d916a3954e751d208975a1866051a8c6545a2c5 Mon Sep 17 00:00:00 2001
From: Jayaram Kancherla <jayaram.kancherla@gmail.com>
Date: Wed, 8 Oct 2025 19:43:52 -0700
Subject: [PATCH 23/28] tests for compressed biocframe

---
 setup.cfg                              |  1 +
 src/compressed_lists/__init__.py       |  3 ++-
 src/compressed_lists/biocframe_list.py | 23 +++++++++++++++++++
 tests/test_comp_biocframe.py           | 31 ++++++++++++++++++++++++++
 4 files changed, 57 insertions(+), 1 deletion(-)
 create mode 100644 tests/test_comp_biocframe.py

diff --git a/setup.cfg b/setup.cfg
index 72798f5..6cdfdec 100644
--- a/setup.cfg
+++ b/setup.cfg
@@ -51,6 +51,7 @@ install_requires =
     importlib-metadata; python_version<"3.8"
     biocutils
     numpy
+    biocframe
 
 
 [options.packages.find]
diff --git a/src/compressed_lists/__init__.py b/src/compressed_lists/__init__.py
index 6f94bef..7d4f677 100644
--- a/src/compressed_lists/__init__.py
+++ b/src/compressed_lists/__init__.py
@@ -22,4 +22,5 @@
 from .bool_list import CompressedBooleanList
 from .float_list import CompressedFloatList
 from .numpy_list import CompressedNumpyList
-from .split_generic import splitAsCompressedList
+from .biocframe_list import CompressedBiocFrameList
+from .split_generic import splitAsCompressedList
\ No newline at end of file
diff --git a/src/compressed_lists/biocframe_list.py b/src/compressed_lists/biocframe_list.py
index c716597..4832804 100644
--- a/src/compressed_lists/biocframe_list.py
+++ b/src/compressed_lists/biocframe_list.py
@@ -83,6 +83,29 @@ def __getitem__(self, key: Union[int, str, slice]):
         else:
             return super().__getitem__(key)
 
+    def extract_range(self, start: int, end: int) -> BiocFrame:
+        """Extract a range from `unlist_data`.
+
+        This method must be implemented by subclasses to handle
+        type-specific extraction from `unlist_data`.
+
+        Args:
+            start:
+                Start index (inclusive).
+
+            end:
+                End index (exclusive).
+
+        Returns:
+            Extracted element.
+        """
+        try:
+            return self._unlist_data[start:end, :]
+        except Exception as e:
+            raise NotImplementedError(
+                "Custom classes should implement their own `extract_range` method for slice operations"
+            ) from e
+
 
 @splitAsCompressedList.register
 def _(
diff --git a/tests/test_comp_biocframe.py b/tests/test_comp_biocframe.py
new file mode 100644
index 0000000..65345b8
--- /dev/null
+++ b/tests/test_comp_biocframe.py
@@ -0,0 +1,31 @@
+import pytest
+from biocframe import BiocFrame
+
+from compressed_lists import CompressedBiocFrameList, Partitioning
+
+__author__ = "Jayaram Kancherla"
+__copyright__ = "Jayaram Kancherla"
+__license__ = "MIT"
+
+
+@pytest.fixture
+def frame_data():
+    return BiocFrame(
+        {
+            "ensembl": ["ENS00001", "ENS00002", "ENS00003"],
+            "symbol": ["MAP1A", "BIN1", "ESR1"],
+        }
+    )
+
+
+def test_creation(frame_data):
+    frame_list = CompressedBiocFrameList(frame_data, partitioning=Partitioning.from_lengths([1, 2]))
+
+    assert isinstance(frame_list, CompressedBiocFrameList)
+    assert len(frame_list) == 2
+    assert isinstance(frame_list.unlist_data, BiocFrame)
+    assert len(frame_list.get_unlist_data()) == 3
+    assert list(frame_list.get_element_lengths()) == [1,2]
+    print(frame_list._unlist_data)
+    print(frame_list[0])
+    assert frame_list[0].get_column("symbol") == ["MAP1A"]

From 06a2a2e866bfce3905117986bdd5ad7f879d2d18 Mon Sep 17 00:00:00 2001
From: "pre-commit-ci[bot]"
 <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Date: Thu, 9 Oct 2025 02:44:00 +0000
Subject: [PATCH 24/28] [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci
---
 src/compressed_lists/__init__.py | 2 +-
 tests/test_comp_biocframe.py     | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/src/compressed_lists/__init__.py b/src/compressed_lists/__init__.py
index 7d4f677..e9497e6 100644
--- a/src/compressed_lists/__init__.py
+++ b/src/compressed_lists/__init__.py
@@ -23,4 +23,4 @@
 from .float_list import CompressedFloatList
 from .numpy_list import CompressedNumpyList
 from .biocframe_list import CompressedBiocFrameList
-from .split_generic import splitAsCompressedList
\ No newline at end of file
+from .split_generic import splitAsCompressedList
diff --git a/tests/test_comp_biocframe.py b/tests/test_comp_biocframe.py
index 65345b8..ff54102 100644
--- a/tests/test_comp_biocframe.py
+++ b/tests/test_comp_biocframe.py
@@ -25,7 +25,7 @@ def test_creation(frame_data):
     assert len(frame_list) == 2
     assert isinstance(frame_list.unlist_data, BiocFrame)
     assert len(frame_list.get_unlist_data()) == 3
-    assert list(frame_list.get_element_lengths()) == [1,2]
+    assert list(frame_list.get_element_lengths()) == [1, 2]
     print(frame_list._unlist_data)
     print(frame_list[0])
     assert frame_list[0].get_column("symbol") == ["MAP1A"]

From 04ac7ca097f519ea894500224f2df54df9a8bb46 Mon Sep 17 00:00:00 2001
From: Jayaram Kancherla <jayaram.kancherla@gmail.com>
Date: Wed, 8 Oct 2025 19:46:24 -0700
Subject: [PATCH 25/28] remove prints

---
 src/compressed_lists/split_generic.py | 4 +---
 tests/test_comp_biocframe.py          | 2 --
 tests/test_comp_int.py                | 1 -
 tests/test_comp_numpy.py              | 1 -
 4 files changed, 1 insertion(+), 7 deletions(-)

diff --git a/src/compressed_lists/split_generic.py b/src/compressed_lists/split_generic.py
index 78aea5e..1bcd9c8 100644
--- a/src/compressed_lists/split_generic.py
+++ b/src/compressed_lists/split_generic.py
@@ -30,7 +30,6 @@ def groups_to_partition(
     Returns:
         Tuple of (partitioned_data_list, partitioning_object)
     """
-    print(data, groups)
     if len(data) != len(groups):
         raise ValueError(f"Length of data ({len(data)}) must match length of groups ({len(groups)})")
 
@@ -39,9 +38,8 @@ def groups_to_partition(
         group_dict[group].append(item)
 
     sorted_groups = sorted(group_dict.keys())
-    print(sorted_groups)
     partitioned_data = [group_dict[group] for group in sorted_groups]
-    print("pdata", partitioned_data)
+
     if names is None:
         group_names = [str(group) for group in sorted_groups]
     else:
diff --git a/tests/test_comp_biocframe.py b/tests/test_comp_biocframe.py
index ff54102..5306206 100644
--- a/tests/test_comp_biocframe.py
+++ b/tests/test_comp_biocframe.py
@@ -26,6 +26,4 @@ def test_creation(frame_data):
     assert isinstance(frame_list.unlist_data, BiocFrame)
     assert len(frame_list.get_unlist_data()) == 3
     assert list(frame_list.get_element_lengths()) == [1, 2]
-    print(frame_list._unlist_data)
-    print(frame_list[0])
     assert frame_list[0].get_column("symbol") == ["MAP1A"]
diff --git a/tests/test_comp_int.py b/tests/test_comp_int.py
index daac5d5..479bf34 100644
--- a/tests/test_comp_int.py
+++ b/tests/test_comp_int.py
@@ -87,7 +87,6 @@ def test_getitem_by_slice(int_list):
 
 def test_iteration(int_list, int_data):
     items = list(int_list)
-    print(items, int_data)
     for i, lst in enumerate(items):
         assert np.allclose(list(lst), int_data[i])
 
diff --git a/tests/test_comp_numpy.py b/tests/test_comp_numpy.py
index 8611591..99afb8b 100644
--- a/tests/test_comp_numpy.py
+++ b/tests/test_comp_numpy.py
@@ -86,7 +86,6 @@ def test_getitem_by_slice(numpy_list):
 
 def test_iteration(numpy_list, numpy_data):
     items = list(numpy_list)
-    print(items, numpy_data)
     for i, lst in enumerate(items):
         assert np.allclose(lst, numpy_data[i])
 

From fea4835985bface7ff50d11970e57c96f35f7513 Mon Sep 17 00:00:00 2001
From: Jayaram Kancherla <jayaram.kancherla@gmail.com>
Date: Wed, 8 Oct 2025 20:06:52 -0700
Subject: [PATCH 26/28] update readme and docs

---
 README.md        | 14 +++++++------
 docs/tutorial.md | 54 +++++++++++++++++++++++++++---------------------
 2 files changed, 38 insertions(+), 30 deletions(-)

diff --git a/README.md b/README.md
index 96c0fc1..1c1ce09 100644
--- a/README.md
+++ b/README.md
@@ -17,9 +17,8 @@ pip install compressed-lists
 
 ## Usage
 
-
 ```py
-from compressed_lists import CompressedIntegerList, CompressedStringList
+from compressed_lists import CompressedIntegerList, CompressedStringList, Partitioning
 
 # Create a CompressedIntegerList
 int_data = [[1, 2, 3], [4, 5], [6, 7, 8, 9]]
@@ -38,9 +37,12 @@ print(squared[0])       # [1, 4, 9]
 # Convert to a regular Python list
 regular_list = int_list.to_list()
 
-# Create a CompressedStringList
-char_data = [["apple", "banana"], ["cherry", "date", "elderberry"], ["fig"]]
-char_list = CompressedStringList.from_list(char_data)
+# Create a CompressedStringList from lengths
+import biocutils as ut
+char_data = ut.StringList(["apple", "banana", "cherry", "date", "elderberry", "fig"])
+
+char_list = CompressedStringList(char_data, partitioning=Partitioning.from_lengths([2,3,1]))
+print(char_list)
 ```
 
 ### Partitioning
@@ -61,7 +63,7 @@ start, end = part[1]  # Returns (3, 5)
 
 > [!NOTE]
 >
-> Check out the [documentation](https://biocpy.github.io/compressed-lists) for extending CompressedLists to custom data types.
+> Check out the [documentation](https://biocpy.github.io/compressed-lists) for available compressed list implementations and extending `CompressedLists` to custom data types.
 
 <!-- biocsetup-notes -->
 
diff --git a/docs/tutorial.md b/docs/tutorial.md
index fdd1f0b..7092129 100644
--- a/docs/tutorial.md
+++ b/docs/tutorial.md
@@ -7,7 +7,7 @@ kernelspec:
 # Basic Usage
 
 ```{code-cell}
-from compressed_lists import CompressedIntegerList, CompressedStringList
+from compressed_lists import CompressedIntegerList, CompressedStringList, Partitioning
 
 # Create a CompressedIntegerList
 int_data = [[1, 2, 3], [4, 5], [6, 7, 8, 9]]
@@ -15,20 +15,23 @@ names = ["A", "B", "C"]
 int_list = CompressedIntegerList.from_list(int_data, names)
 
 # Access elements
-print(int_list[0])      # [1, 2, 3]
-print(int_list["B"])    # [4, 5]
-print(int_list[1:3])    # Slice of elements
+print(int_list[0])
+print(int_list["B"])
+print(int_list[1:3])
 
 # Apply a function to each element
 squared = int_list.lapply(lambda x: [i**2 for i in x])
-print(squared[0])       # [1, 4, 9]
+print(squared[0])
 
 # Convert to a regular Python list
 regular_list = int_list.to_list()
 
-# Create a CompressedStringList
-char_data = [["apple", "banana"], ["cherry", "date", "elderberry"], ["fig"]]
-char_list = CompressedStringList.from_list(char_data)
+# Create a CompressedStringList from lengths
+import biocutils as ut
+char_data = ut.StringList(["apple", "banana", "cherry", "date", "elderberry", "fig"])
+
+char_list = CompressedStringList(char_data, partitioning=Partitioning.from_lengths([2,3,1]))
+print(char_list)
 ```
 
 ## Partitioning
@@ -57,7 +60,7 @@ print(start, end)
 Create a new class that inherits from `CompressedList` with appropriate type annotations:
 
 ```python
-from typing import List, TypeVar, Generic
+from typing import List
 from compressed_lists import CompressedList, Partitioning
 import numpy as np
 
@@ -72,31 +75,32 @@ The constructor should initialize the superclass with the appropriate data:
 
 ```python
 def __init__(self,
-             unlist_data: Any,  # Replace with your data type
-             partitioning: Partitioning,
-             element_metadata: dict = None,
-             metadata: dict = None):
+        unlist_data: Any,  # Replace with your data type
+        partitioning: Partitioning,
+        element_type: Any = None,
+        element_metadata: Optional[dict] = None,
+        metadata: Optional[dict] = None):
     super().__init__(unlist_data, partitioning,
-                    element_type="custom_type",  # Set your element type
-                    element_metadata=element_metadata,
-                    metadata=metadata)
+        element_type="custom_type",  # Set your element type
+        element_metadata=element_metadata,
+        metadata=metadata)
 ```
 
-## 3. Implement _extract_range Method
+## 3. Implement `extract_range` Method
 
 This method defines how to extract a range of elements from your unlisted data:
 
 ```python
-def _extract_range(self, start: int, end: int) -> List[T]:
+def extract_range(self, start: int, end: int) -> List[T]:
     """Extract a range from unlisted data."""
     # For example, with numpy arrays:
-    return self.unlist_data[start:end].tolist()
+    return self.unlist_data[start:end]
 
     # Or for other data types:
-    # return self.unlist_data[start:end]
+    # return self.unlist_data[start:end, :]
 ```
 
-## 4. Implement from_list Class Method
+## 4. Implement `from_list` Class Method
 
 This factory method creates a new instance from a list:
 
@@ -140,7 +144,7 @@ class CompressedFloatList(CompressedList):
                         element_metadata=element_metadata,
                         metadata=metadata)
 
-    def _extract_range(self, start: int, end: int) -> List[float]:
+    def extract_range(self, start: int, end: int) -> List[float]:
         return self.unlist_data[start:end].tolist()
 
     @classmethod
@@ -176,10 +180,10 @@ class MyObject:
     def __init__(self, value):
         self.value = value
 
-class CompressedMyObjectList(CompressedList[List[MyObject]]):
+class CompressedMyObjectList(CompressedList):
     # Implementation details...
 
-    def _extract_range(self, start: int, end: int) -> List[MyObject]:
+    def extract_range(self, start: int, end: int) -> List[MyObject]:
         return self.unlist_data[start:end]
 
     @classmethod
@@ -187,3 +191,5 @@ class CompressedMyObjectList(CompressedList[List[MyObject]]):
         # Custom flattening and storage logic
         # ...
 ```
+
+Check out the `CompressedBiocFrameList` for a complete example of this usecase.

From 0dd56eda8ef26daa08916a24f323aa4be7fd9a08 Mon Sep 17 00:00:00 2001
From: Jayaram Kancherla <jayaram.kancherla@gmail.com>
Date: Wed, 8 Oct 2025 21:21:02 -0700
Subject: [PATCH 27/28] more tests and update changelog

---
 CHANGELOG.md                           |  2 +-
 src/compressed_lists/biocframe_list.py |  2 +-
 tests/test_comp_biocframe.py           | 18 +++++++++++++++++-
 3 files changed, 19 insertions(+), 3 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index fb081ab..ee0980a 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -2,7 +2,7 @@
 
 ## Version 0.2.0
 
-- Switch to typed lists from the biocutils package.
+- Major changes to the package; Switch to typed lists from the biocutils package.
 
 ## Version 0.1.0 - 0.1.1
 
diff --git a/src/compressed_lists/biocframe_list.py b/src/compressed_lists/biocframe_list.py
index 4832804..b06c68d 100644
--- a/src/compressed_lists/biocframe_list.py
+++ b/src/compressed_lists/biocframe_list.py
@@ -78,7 +78,7 @@ def __getitem__(self, key: Union[int, str, slice]):
         if isinstance(key, str):
             column_data = self._unlist_data.get_column(key)
             return splitAsCompressedList(
-                column_data, partition=self._partitioning, names=self.names, metadata=self.metadata
+                column_data, groups_or_partitions=self._partitioning, names=self.names, metadata=self.metadata
             )
         else:
             return super().__getitem__(key)
diff --git a/tests/test_comp_biocframe.py b/tests/test_comp_biocframe.py
index 5306206..1d37f28 100644
--- a/tests/test_comp_biocframe.py
+++ b/tests/test_comp_biocframe.py
@@ -1,7 +1,8 @@
 import pytest
 from biocframe import BiocFrame
+import biocutils as ut
 
-from compressed_lists import CompressedBiocFrameList, Partitioning
+from compressed_lists import CompressedBiocFrameList, Partitioning, CompressedStringList
 
 __author__ = "Jayaram Kancherla"
 __copyright__ = "Jayaram Kancherla"
@@ -27,3 +28,18 @@ def test_creation(frame_data):
     assert len(frame_list.get_unlist_data()) == 3
     assert list(frame_list.get_element_lengths()) == [1, 2]
     assert frame_list[0].get_column("symbol") == ["MAP1A"]
+
+
+def test_bframe_typed_list_column():
+    bframe = BiocFrame(
+        {
+            "ensembl": ut.StringList(["ENS00001", "ENS00002", "ENS00003"]),
+            "symbol": ["MAP1A", "BIN1", "ESR1"],
+        }
+    )
+    frame_list = CompressedBiocFrameList(bframe, partitioning=Partitioning.from_lengths([1, 2]))
+
+    ens_col = frame_list["ensembl"]
+    assert isinstance(ens_col, CompressedStringList)
+    assert len(ens_col) == 2
+

From 423ea911be30bf91c87342555bc1a6a5393fb092 Mon Sep 17 00:00:00 2001
From: "pre-commit-ci[bot]"
 <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Date: Thu, 9 Oct 2025 04:21:11 +0000
Subject: [PATCH 28/28] [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci
---
 tests/test_comp_biocframe.py | 1 -
 1 file changed, 1 deletion(-)

diff --git a/tests/test_comp_biocframe.py b/tests/test_comp_biocframe.py
index 1d37f28..64691b6 100644
--- a/tests/test_comp_biocframe.py
+++ b/tests/test_comp_biocframe.py
@@ -42,4 +42,3 @@ def test_bframe_typed_list_column():
     ens_col = frame_list["ensembl"]
     assert isinstance(ens_col, CompressedStringList)
     assert len(ens_col) == 2
-