Move spotlight.io.pandas to spotlight.dataset.pandas

renumics/spotlight/dataset/__init__.py

@@ -32,12 +32,7 @@
 from typing_extensions import TypeGuard
 
 from renumics.spotlight.__version__ import __version__
-from renumics.spotlight.io.pandas import (
-    infer_dtypes,
-    prepare_column,
-    is_string_mask,
-    stringify_columns,
-)
+from .pandas import create_typed_series, infer_dtypes, is_string_mask, prepare_column
 from renumics.spotlight.typing import (
     BoolType,
     IndexType,
@@ -47,7 +42,6 @@
     is_integer,
     is_iterable,
 )
-from renumics.spotlight.io.pandas import create_typed_series
 from renumics.spotlight.dtypes.conversion import prepare_path_or_url
 from renumics.spotlight import dtypes as spotlight_dtypes
 
@@ -738,7 +732,7 @@ def from_pandas(
             df = df.reset_index(level=df.index.names)  # type: ignore
         else:
             df = df.copy()
-        df.columns = pd.Index(stringify_columns(df))
+        df.columns = pd.Index([str(column) for column in df.columns])
 
         if dtypes is None:
             dtypes = {}

renumics/spotlight/dtypes/__init__.py

@@ -9,6 +9,8 @@
 
 __all__ = [
     "CategoryDType",
+    "ArrayDType",
+    "EmbeddingDType",
     "Sequence1DDType",
     "bool_dtype",
     "int_dtype",
@@ -83,7 +85,7 @@ def __init__(
 
     def __eq__(self, other: Any) -> bool:
         if isinstance(other, CategoryDType):
-            return other._name == self._name and other._categories == self._categories
+            return other._categories == self._categories
         return False
 
     def __hash__(self) -> int:
@@ -117,7 +119,7 @@ def __init__(self, shape: Optional[Tuple[Optional[int], ...]] = None):
 
     def __eq__(self, other: Any) -> bool:
         if isinstance(other, ArrayDType):
-            return other._name == self._name and other.shape == self.shape
+            return other.shape == self.shape
         return False
 
     def __hash__(self) -> int:
@@ -145,7 +147,7 @@ def __init__(self, length: Optional[int] = None):
 
     def __eq__(self, other: Any) -> bool:
         if isinstance(other, EmbeddingDType):
-            return other._name == self._name and other.length == self.length
+            return other.length == self.length
         return False
 
     def __hash__(self) -> int:
@@ -165,6 +167,14 @@ def __init__(self, x_label: str = "x", y_label: str = "y"):
         self.x_label = x_label
         self.y_label = y_label
 
+    def __eq__(self, other: Any) -> bool:
+        if isinstance(other, Sequence1DDType):
+            return other.x_label == self.x_label and other.y_label == self.y_label
+        return False
+
+    def __hash__(self) -> int:
+        return hash(self._name) ^ hash(self.x_label) ^ hash(self.y_label)
+
 
 ALIASES: Dict[Any, DType] = {}
 

renumics/spotlight/io/__init__.py

@@ -1,6 +1,9 @@
 """
 Reading and writing of different data formats.
 """
+import ast
+from contextlib import suppress
+from typing import Any
 
 from .audio import (
     get_format_codec,
@@ -19,6 +22,8 @@
     decode_gltf_arrays,
     encode_gltf_array,
 )
+from .huggingface import prepare_hugging_face_dict
+
 
 __all__ = [
     "get_format_codec",
@@ -34,4 +39,15 @@
     "check_gltf",
     "decode_gltf_arrays",
     "encode_gltf_array",
+    "prepare_hugging_face_dict",
+    "try_literal_eval",
 ]
+
+
+def try_literal_eval(x: str) -> Any:
+    """
+    Try to evaluate a literal expression, otherwise return value as is.
+    """
+    with suppress(Exception):
+        return ast.literal_eval(x)
+    return x