cbrkit 0.18.0__tar.gz → 0.18.2__tar.gz

{cbrkit-0.18.0 → cbrkit-0.18.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: cbrkit
-Version: 0.18.0
+Version: 0.18.2
 Summary: Customizable Case-Based Reasoning (CBR) toolkit for Python with a built-in API and CLI.
 Home-page: https://wi2trier.github.io/cbrkit/
 License: MIT
@@ -18,6 +18,7 @@ Classifier: Natural Language :: English
 Classifier: Operating System :: OS Independent
 Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
 Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Classifier: Topic :: Scientific/Engineering :: Information Analysis
 Classifier: Topic :: Software Development :: Libraries :: Python Modules
@@ -144,7 +145,7 @@ import pandas as pd
 import cbrkit
 
 df = pd.read_csv("path/to/cases.csv")
-casebase = cbrkit.loaders.dataframe(df)
+casebase = cbrkit.loaders.pandas(df)
 ```
 
 When dealing with formats like JSON, the files can be loaded directly:
@@ -169,7 +170,7 @@ If you have a collection of queries, you can load them using the same loader fun
 
 ```python
  # for pandas
-queries = cbrkit.loaders.dataframe(pd.read_csv("path/to/queries.csv"))
+queries = cbrkit.loaders.pandas(pd.read_csv("path/to/queries.csv"))
 # for json
 queries = cbrkit.loaders.json("path/to/queries.json")
 ```

{cbrkit-0.18.0 → cbrkit-0.18.2}/README.md

@@ -76,7 +76,7 @@ import pandas as pd
 import cbrkit
 
 df = pd.read_csv("path/to/cases.csv")
-casebase = cbrkit.loaders.dataframe(df)
+casebase = cbrkit.loaders.pandas(df)
 ```
 
 When dealing with formats like JSON, the files can be loaded directly:
@@ -101,7 +101,7 @@ If you have a collection of queries, you can load them using the same loader fun
 
 ```python
  # for pandas
-queries = cbrkit.loaders.dataframe(pd.read_csv("path/to/queries.csv"))
+queries = cbrkit.loaders.pandas(pd.read_csv("path/to/queries.csv"))
 # for json
 queries = cbrkit.loaders.json("path/to/queries.json")
 ```

{cbrkit-0.18.0 → cbrkit-0.18.2}/cbrkit/loaders.py

@@ -20,7 +20,6 @@ from cbrkit.typing import Casebase, FilePath
 
 __all__ = [
     "csv",
-    "dataframe",
     "pandas",
     "file",
     "folder",
@@ -62,17 +61,20 @@ def python(import_name: str) -> Any:
 class pandas(Mapping[int, pd.Series]):
     df: pd.DataFrame
 
-    def __getitem__(self, key: int) -> pd.Series:
-        return self.df.iloc[key]
+    def __getitem__(self, key: int | str) -> pd.Series:
+        if isinstance(key, str):
+            return cast(pd.Series, self.df.loc[key])
+        elif isinstance(key, int):
+            return self.df.iloc[key]
+
+        raise TypeError(f"Invalid key type: {type(key)}")
 
     def __iter__(self) -> Iterator[int]:
-        return iter(range(len(self.df)))
+        return iter(range(self.df.shape[0]))
 
     def __len__(self) -> int:
-        return len(self.df)
-
+        return self.df.shape[0]
 
-dataframe = pandas
 
 # @dataclass(slots=True)
 # class dataframe(Mapping[int, tuple[Any, ...]]):
@@ -95,17 +97,22 @@ try:
     import polars as pl
 
     @dataclass(slots=True, frozen=True)
-    class polars(Mapping[int, pl.DataFrame]):
+    class polars(Mapping[int, pl.Series]):
         df: pl.DataFrame
 
-        def __getitem__(self, key: int) -> pl.DataFrame:
-            return self.df.slice(key, 1)
+        def __getitem__(self, key: int | str) -> pl.Series:
+            if isinstance(key, str):
+                return self.df[key]
+            elif isinstance(key, int):
+                return pl.Series(self.df.row(key))
+
+            raise TypeError(f"Invalid key type: {type(key)}")
 
         def __iter__(self) -> Iterator[int]:
-            return iter(range(len(self.df)))
+            return iter(range(self.df.shape[0]))
 
         def __len__(self) -> int:
-            return len(self.df)
+            return self.df.shape[0]
 
         __all__ += ["polars"]
 
@@ -141,7 +148,7 @@ def csv(path: FilePath) -> dict[int, dict[str, str]]:
 def _csv_pandas(path: FilePath) -> dict[int, pd.Series]:
     df = pd.read_csv(path)
 
-    return cast(dict[int, pd.Series], dataframe(df))
+    return cast(dict[int, pd.Series], pandas(df))
 
 
 def json(path: FilePath) -> dict[Any, Any]:
@@ -401,7 +408,7 @@ def validate(data: Casebase[Any, Any] | Any, validation_model: BaseModel):
         >>> validate(data, Car)
         >>> import pandas as pd
         >>> df = pd.read_csv("data/cars-1k.csv")
-        >>> data = dataframe(df)
+        >>> data = pandas(df)
         >>> validate(data, Car)
     """
     assert data is not None

{cbrkit-0.18.0 → cbrkit-0.18.2}/cbrkit/retrieval.py

@@ -160,7 +160,7 @@ def apply[K, V, S: Float](
         >>> import cbrkit
         >>> import pandas as pd
         >>> df = pd.read_csv("./data/cars-1k.csv")
-        >>> casebase = cbrkit.loaders.dataframe(df)
+        >>> casebase = cbrkit.loaders.pandas(df)
         >>> query = casebase[42]
         >>> retriever = cbrkit.retrieval.build(
         ...     cbrkit.sim.attribute_value(

{cbrkit-0.18.0 → cbrkit-0.18.2}/cbrkit/sim/graphs/_model.py

@@ -160,3 +160,49 @@ try:
 
 except ImportError:
     pass
+
+try:
+    import networkx as nx
+
+    def to_networkx[N, E](g: Graph[Any, N, E, Any]) -> "nx.DiGraph":
+        ng = nx.DiGraph()
+        # Set graph attributes
+        ng.graph.update(g.data)
+
+        # Add nodes with their data
+        for node in g.nodes.values():
+            ng.add_node(node.key, data=node.data)
+
+        # Add edges with their data
+        for edge in g.edges.values():
+            ng.add_edge(edge.source.key, edge.target.key, key=edge.key, data=edge.data)
+
+        return ng
+
+    def from_networkx[N, E](g: "nx.DiGraph") -> Graph[Any, N, E, Any]:
+        # Create nodes
+        nodes = immutables.Map(
+            (node_id, Node(node_id, g.nodes[node_id].get("data")))
+            for node_id in g.nodes
+        )
+
+        # Create edges
+        edges = immutables.Map(
+            (
+                edge_data.get("key", idx),
+                Edge(
+                    edge_data.get("key", idx),
+                    nodes[source],
+                    nodes[target],
+                    edge_data.get("data"),
+                ),
+            )
+            for idx, (source, target, edge_data) in enumerate(g.edges(data=True))
+        )
+
+        return Graph(nodes, edges, dict(g.graph))
+
+    __all__ += ["to_networkx", "from_networkx"]
+
+except ImportError:
+    pass

{cbrkit-0.18.0 → cbrkit-0.18.2}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "cbrkit"
-version = "0.18.0"
+version = "0.18.2"
 description = "Customizable Case-Based Reasoning (CBR) toolkit for Python with a built-in API and CLI."
 authors = ["Mirko Lenz <mirko@mirkolenz.com>"]
 license = "MIT"
@@ -79,7 +79,7 @@ xmltodict = ">=0.13, <1.0"
 
 [tool.poetry.group.dev.dependencies]
 pytest = "^8.0"
-pytest-cov = "^5.0"
+pytest-cov = "^6.0"
 
 [tool.poetry.group.docs.dependencies]
 pdoc = "^15"