vgplot 0.29.0__tar.gz → 0.29.1__tar.gz

{vgplot-0.29.0 → vgplot-0.29.1}/PKG-INFO

@@ -1,9 +1,10 @@
 Metadata-Version: 2.4
 Name: vgplot
-Version: 0.29.0
+Version: 0.29.1
 Summary: A Python API for authoring Mosaic vgplot visualizations
 Project-URL: homepage, https://github.com/uwdata/mosaic
 Requires-Python: >=3.10
+Requires-Dist: narwhals>=2.8.0
 Description-Content-Type: text/markdown
 
 # vgplot

{vgplot-0.29.0 → vgplot-0.29.1}/package.json

@@ -1,6 +1,6 @@
 {
   "name": "vgplot-python",
-  "version": "0.29.0",
+  "version": "0.29.1",
   "private": true,
   "scripts": {
     "prerelease": "uv run ruff check && uv run ruff format --check",

{vgplot-0.29.0 → vgplot-0.29.1}/pyproject.toml

@@ -4,7 +4,7 @@ dynamic = ["version"]
 description = "A Python API for authoring Mosaic vgplot visualizations"
 readme = "README.md"
 requires-python = ">=3.10"
-dependencies = []
+dependencies = ["narwhals>=2.8.0"]
 
 [project.urls]
 homepage = "https://github.com/uwdata/mosaic"

{vgplot-0.29.0 → vgplot-0.29.1}/test/test_python_api.py

@@ -79,3 +79,32 @@ class TestAutoNaming:
         assert d["params"]["_param0"] == 1
         assert d["params"]["_param1"] == 2
         assert d["plot"][0]["x"] == "$_param1"
+
+
+class TestDataFrames:
+    """A DataFrame passed directly to a mark is discovered by variable name,
+    referenced as a table, and carried in the spec's data section for the host
+    (e.g. the widget) to register."""
+
+    def test_frame_is_referenced_and_named_after_variable(self):
+        import pyarrow as pa
+
+        weather = pa.table({"a": [1, 2, 3]})
+        view = vg.plot(vg.dot(weather, x="a"))
+        d = view.to_dict()
+
+        assert d["plot"][0]["data"] == {"from": "weather"}
+        assert d["data"]["weather"] is weather
+
+    def test_frame_and_datadef_share_the_data_section(self):
+        import pyarrow as pa
+
+        weather = pa.table({"a": [1]})
+        athletes = vg.csv("athletes.csv")
+        view = vg.plot(vg.dot(weather, x="a"), vg.dot(athletes, x="a"))
+        d = view.to_dict()
+
+        assert d["plot"][0]["data"] == {"from": "weather"}
+        assert d["plot"][1]["data"] == {"from": "athletes"}
+        assert d["data"]["weather"] is weather
+        assert d["data"]["athletes"] == {"type": "csv", "file": "athletes.csv"}

{vgplot-0.29.0 → vgplot-0.29.1}/vgplot/data.py

@@ -3,6 +3,8 @@ from __future__ import annotations
 from dataclasses import dataclass
 from typing import Any
 
+import narwhals as nw
+
 
 @dataclass
 class DataDef:
@@ -12,6 +14,19 @@ class DataDef:
         return self.payload
 
 
+def is_frame(obj: Any) -> bool:
+    """True if `obj` is a dataframe-like object (pandas/polars/Arrow/...)."""
+    if obj is None or isinstance(
+        obj, (str, bytes, int, float, bool, dict, list, tuple)
+    ):
+        return False
+    try:
+        nw.from_native(obj)
+    except TypeError:
+        return False
+    return True
+
+
 def parquet(file: str, select: Any = None, where: Any = None, **kwargs: Any) -> DataDef:
     payload: dict[str, Any] = {"type": "parquet", "file": file}
     if select is not None:

{vgplot-0.29.0 → vgplot-0.29.1}/vgplot/plot.py

@@ -6,7 +6,7 @@ from typing import Any
 
 from .util import camelize, omit_none
 from .params import _ParamBase
-from .data import DataDef
+from .data import DataDef, is_frame
 
 
 class FromRef:
@@ -47,7 +47,7 @@ class Mark:
                 data_dict: Any = {"from": self.data}
             elif isinstance(self.data, FromRef):
                 data_dict = dict(self.data.to_dict())
-            elif isinstance(self.data, DataDef):
+            elif isinstance(self.data, DataDef) or is_frame(self.data):
                 data_dict = {"from": self.data}
             else:
                 data_dict = self.data
@@ -84,6 +84,10 @@ def encode_value(
         return [encode_value(x, param_names, data_names) for x in v]
     if isinstance(v, dict):
         return {k: encode_value(val, param_names, data_names) for k, val in v.items()}
+    if is_frame(v):
+        if data_names and id(v) in data_names:
+            return data_names[id(v)]
+        return v
     return v
 
 

{vgplot-0.29.0 → vgplot-0.29.1}/vgplot/spec.py

@@ -6,7 +6,7 @@ from typing import Any
 
 from .util import omit_none
 from .params import _ParamBase
-from .data import DataDef
+from .data import DataDef, is_frame
 from .plot import _encode_component
 
 
@@ -41,25 +41,38 @@ def _collect_params(node: Any) -> list[_ParamBase]:
     return []
 
 
-def _collect_datadefs(node: Any) -> list[DataDef]:
-    """Recursively collect all DataDef instances in a view tree."""
-    if isinstance(node, DataDef):
+def _collect_data_sources(node: Any) -> list[Any]:
+    """Recursively collect all data sources (DataDefs and DataFrames) in a view tree."""
+    if isinstance(node, DataDef) or is_frame(node):
         return [node]
     if isinstance(node, View):
-        return _collect_datadefs(node._view)
+        return _collect_data_sources(node._view)
     if isinstance(node, dict):
         found = []
         for v in node.values():
-            found.extend(_collect_datadefs(v))
+            found.extend(_collect_data_sources(v))
         return found
     if isinstance(node, list):
         found = []
         for item in node:
-            found.extend(_collect_datadefs(item))
+            found.extend(_collect_data_sources(item))
         return found
     return []
 
 
+def _frame_data_names(caller_locals: dict[str, Any]) -> dict[int, str]:
+    """Map id->name for DataFrames bound to non-underscore caller variables.
+
+    A frame bound to several variables resolves to just one name (the last),
+    which becomes its registered table name.
+    """
+    return {
+        id(obj): name
+        for name, obj in caller_locals.items()
+        if is_frame(obj) and not name.startswith("_")
+    }
+
+
 class Spec:
     def __init__(
         self,
@@ -73,7 +86,7 @@ class Spec:
         view: dict[str, Any] | None = None,
         **extra: Any,
     ) -> None:
-        # Serialize any DataDef values in data and build id→name mapping
+        # Serialize any DataDef values in data and build id->name mapping
         resolved_data: dict[str, Any] = {}
         resolved_data_names: dict[int, str] = dict(data_names or {})
         for name, val in (data or {}).items():
@@ -123,19 +136,22 @@ class Spec:
             else:
                 serialized_params[name] = p
 
-        # Build data_names lookup and auto-register any unnamed DataDefs in the view
         data_names = dict(self.data_names)
         extra_data: dict[str, Any] = {}
         used = set(data_names.values()) | set(self.data or {})
         counter = 0
-        for obj in _collect_datadefs(self.view):
-            if id(obj) not in data_names:
+        for obj in _collect_data_sources(self.view):
+            name = data_names.get(id(obj))
+            if name is None:
                 while f"_data{counter}" in used:
                     counter += 1
-                auto_name = f"_data{counter}"
-                data_names[id(obj)] = auto_name
-                extra_data[auto_name] = obj.to_dict()
+                name = f"_data{counter}"
                 counter += 1
+                data_names[id(obj)] = name
+                used.add(name)
+            if name in (self.data or {}) or name in extra_data:
+                continue
+            extra_data[name] = obj.to_dict() if isinstance(obj, DataDef) else obj
         merged_data = {**(self.data or {}), **extra_data} or None
 
         base: dict[str, Any] = {}
@@ -214,6 +230,7 @@ class View:
         }
         return Spec(
             data=merged_data,
+            data_names=_frame_data_names(caller_locals) or None,
             params=frame_params or None,
             plotDefaults=self._plotDefaults,
             config=self._config,
@@ -295,6 +312,7 @@ def spec(
 
     return Spec(
         data=merged_data,
+        data_names=_frame_data_names(caller_locals) or None,
         params=params,
         plotDefaults=plotDefaults,
         plot_defaults=plot_defaults,