graphdatascience 1.12__tar.gz → 1.13__tar.gz

{graphdatascience-1.12/graphdatascience.egg-info → graphdatascience-1.13}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: graphdatascience
-Version: 1.12
+Version: 1.13
 Summary: A Python client for the Neo4j Graph Data Science (GDS) library
 Home-page: https://neo4j.com/product/graph-data-science/
 Author: Neo4j
@@ -16,7 +16,6 @@ Classifier: License :: OSI Approved :: Apache Software License
 Classifier: Operating System :: OS Independent
 Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3 :: Only
-Classifier: Programming Language :: Python :: 3.8
 Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
@@ -25,24 +24,25 @@ Classifier: Topic :: Database
 Classifier: Topic :: Scientific/Engineering
 Classifier: Topic :: Software Development
 Classifier: Typing :: Typed
-Requires-Python: >=3.8
+Requires-Python: >=3.9
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: multimethod<2.0,>=1.0
 Requires-Dist: neo4j<6.0,>=4.4.12
 Requires-Dist: numpy<2.0
 Requires-Dist: pandas<3.0,>=1.0
-Requires-Dist: pyarrow<17.0,>=14.0.1
+Requires-Dist: pyarrow<19.0,>=15.0.2
 Requires-Dist: textdistance<5.0,>=4.0
 Requires-Dist: tqdm<5.0,>=4.0
 Requires-Dist: typing-extensions<5.0,>=4.0
 Requires-Dist: requests
+Requires-Dist: tenacity>=9.0
 Provides-Extra: ogb
 Requires-Dist: ogb<2.0,>=1.0; extra == "ogb"
 Provides-Extra: networkx
 Requires-Dist: networkx<4.0,>=2.0; extra == "networkx"
 Provides-Extra: rust-ext
-Requires-Dist: neo4j-rust-ext<6.0,>=4.4.2; extra == "rust-ext"
+Requires-Dist: neo4j-rust-ext<6.0,>=4.4.12; extra == "rust-ext"
 
 # Neo4j Graph Data Science Client
 

{graphdatascience-1.12 → graphdatascience-1.13}/graphdatascience/algo/algo_proc_runner.py

@@ -1,5 +1,5 @@
 from abc import ABC
-from typing import Any, Dict, Tuple
+from typing import Any
 
 from pandas import DataFrame, Series
 
@@ -12,7 +12,7 @@ from ..model.graphsage_model import GraphSageModel
 
 class AlgoProcRunner(IllegalAttrChecker, ABC):
     @graph_type_check
-    def _run_procedure(self, G: Graph, config: Dict[str, Any], with_logging: bool = True) -> DataFrame:
+    def _run_procedure(self, G: Graph, config: dict[str, Any], with_logging: bool = True) -> DataFrame:
         params = CallParameters(graph_name=G.name(), config=config)
 
         return self._query_runner.call_procedure(endpoint=self._namespace, params=params, logging=with_logging)
@@ -35,7 +35,7 @@ class StandardModeRunner(AlgoProcRunner):
 
 class GraphSageRunner(AlgoProcRunner):
     @graph_type_check
-    def __call__(self, G: Graph, **config: Any) -> Tuple[GraphSageModel, "Series[Any]"]:
+    def __call__(self, G: Graph, **config: Any) -> tuple[GraphSageModel, "Series[Any]"]:
         result = self._run_procedure(G, config).squeeze()
         model_name = result["modelInfo"]["modelName"]
 

{graphdatascience-1.12 → graphdatascience-1.13}/graphdatascience/call_parameters.py

@@ -1,4 +1,5 @@
-from typing import Any, OrderedDict
+from collections import OrderedDict
+from typing import Any
 
 
 class CallParameters(OrderedDict[str, Any]):

{graphdatascience-1.12 → graphdatascience-1.13}/graphdatascience/error/endpoint_suggester.py

@@ -1,11 +1,9 @@
-from typing import List
-
 import textdistance
 
 from ..ignored_server_endpoints import IGNORED_SERVER_ENDPOINTS
 
 
-def generate_suggestive_error_message(requested_endpoint: str, all_endpoints: List[str]) -> str:
+def generate_suggestive_error_message(requested_endpoint: str, all_endpoints: list[str]) -> str:
     MIN_SIMILARITY_FOR_SUGGESTION = 0.9
 
     closest_endpoint = None

{graphdatascience-1.12 → graphdatascience-1.13}/graphdatascience/graph/base_graph_proc_runner.py

@@ -1,8 +1,7 @@
 import os
 import pathlib
-import sys
 import warnings
-from typing import Any, Dict, List, Optional, Union
+from typing import Any, List, Optional, Union
 
 import pandas as pd
 from multimethod import multimethod
@@ -53,28 +52,22 @@ class BaseGraphProcRunner(UncallableNamespace, IllegalAttrChecker):
 
     @staticmethod
     def _path(package: str, resource: str) -> pathlib.Path:
-        if sys.version_info >= (3, 9):
-            from importlib.resources import files
+        from importlib.resources import files
 
-            # files() returns a Traversable, but usages require a Path object
-            return pathlib.Path(str(files(package) / resource))
-        else:
-            from importlib.resources import path
-
-            # we dont want to use a context manager here, so we need to call __enter__ manually
-            return path(package, resource).__enter__()
+        # files() returns a Traversable, but usages require a Path object
+        return pathlib.Path(str(files(package) / resource))
 
     @client_only_endpoint("gds.graph")
     @compatible_with("construct", min_inclusive=ServerVersion(2, 1, 0))
     def construct(
         self,
         graph_name: str,
-        nodes: Union[DataFrame, List[DataFrame]],
-        relationships: Optional[Union[DataFrame, List[DataFrame]]] = None,
+        nodes: Union[DataFrame, list[DataFrame]],
+        relationships: Optional[Union[DataFrame, list[DataFrame]]] = None,
         concurrency: int = 4,
-        undirected_relationship_types: Optional[List[str]] = None,
+        undirected_relationship_types: Optional[list[str]] = None,
     ) -> Graph:
-        nodes = nodes if isinstance(nodes, List) else [nodes]
+        nodes = nodes if isinstance(nodes, list) else [nodes]
 
         if isinstance(relationships, DataFrame):
             relationships = [relationships]
@@ -365,7 +358,7 @@ class BaseGraphProcRunner(UncallableNamespace, IllegalAttrChecker):
         G: Graph,
         properties: Strings,
         entities: Strings,
-        config: Dict[str, Any],
+        config: dict[str, Any],
     ) -> DataFrame:
         params = CallParameters(
             graph_name=G.name(),

{graphdatascience-1.12 → graphdatascience-1.13}/graphdatascience/graph/graph_alpha_proc_runner.py

@@ -1,5 +1,5 @@
 import os
-from typing import List, Optional, Union
+from typing import Optional, Union
 
 from pandas import DataFrame
 
@@ -36,13 +36,13 @@ class GraphAlphaProcRunner(UncallableNamespace, IllegalAttrChecker):
     def construct(
         self,
         graph_name: str,
-        nodes: Union[DataFrame, List[DataFrame]],
-        relationships: Union[DataFrame, List[DataFrame]],
+        nodes: Union[DataFrame, list[DataFrame]],
+        relationships: Union[DataFrame, list[DataFrame]],
         concurrency: int = 4,
-        undirected_relationship_types: Optional[List[str]] = None,
+        undirected_relationship_types: Optional[list[str]] = None,
     ) -> Graph:
-        nodes = nodes if isinstance(nodes, List) else [nodes]
-        relationships = relationships if isinstance(relationships, List) else [relationships]
+        nodes = nodes if isinstance(nodes, list) else [nodes]
+        relationships = relationships if isinstance(relationships, list) else [relationships]
 
         errors = []
 

{graphdatascience-1.12 → graphdatascience-1.13}/graphdatascience/graph/graph_beta_proc_runner.py

@@ -1,4 +1,4 @@
-from typing import Any, List, Union
+from typing import Any, Union
 
 from ..call_parameters import CallParameters
 from ..error.illegal_attr_checker import IllegalAttrChecker
@@ -9,7 +9,7 @@ from .graph_export_runner import GraphExportCsvEndpoints
 from .graph_object import Graph
 from .graph_project_runner import GraphProjectBetaRunner
 
-Strings = Union[str, List[str]]
+Strings = Union[str, list[str]]
 
 
 class GraphBetaProcRunner(UncallableNamespace, IllegalAttrChecker):

{graphdatascience-1.12 → graphdatascience-1.13}/graphdatascience/graph/graph_cypher_runner.py

@@ -2,7 +2,7 @@ from __future__ import annotations
 
 import re
 from itertools import chain, zip_longest
-from typing import Any, Dict, Optional
+from typing import Any, Optional
 
 from pandas import Series
 
@@ -45,7 +45,7 @@ class GraphCypherRunner(CallerBase):
 
         GraphCypherRunner._verify_query_ends_with_return_clause(self._namespace, query)
 
-        result: Optional[Dict[str, Any]] = self._query_runner.run_cypher(query, params, database, False).squeeze()
+        result: Optional[dict[str, Any]] = self._query_runner.run_cypher(query, params, database, False).squeeze()
 
         if not result:
             raise ValueError("Projected graph cannot be empty.")

{graphdatascience-1.12 → graphdatascience-1.13}/graphdatascience/graph/graph_entity_ops_runner.py

@@ -1,5 +1,5 @@
 from functools import reduce
-from typing import Any, Dict, List, Type, Union
+from typing import Any, Type, Union
 from warnings import filterwarnings
 
 import pandas as pd
@@ -18,7 +18,7 @@ from ..utils.util_proc_runner import UtilProcRunner
 from .graph_object import Graph
 from .graph_type_check import graph_type_check
 
-Strings = Union[str, List[str]]
+Strings = Union[str, list[str]]
 
 
 class TopologyDataFrame(DataFrame):
@@ -26,7 +26,7 @@ class TopologyDataFrame(DataFrame):
     def _constructor(self) -> "Type[TopologyDataFrame]":
         return TopologyDataFrame
 
-    def by_rel_type(self) -> Dict[str, List[List[int]]]:
+    def by_rel_type(self) -> dict[str, list[list[int]]]:
         # Pandas 2.2.0 deprecated an internal API used by DF.take(indices)
         filterwarnings(
             "ignore",
@@ -38,7 +38,7 @@ class TopologyDataFrame(DataFrame):
 
         output = {}
         for rel_type, indices in gb.groups.items():
-            one_rel_df = self.take(indices)
+            one_rel_df = self.take(list(indices))
             output[str(rel_type)] = [list(one_rel_df["sourceNodeId"]), list(one_rel_df["targetNodeId"])]
 
         return output
@@ -55,7 +55,7 @@ class GraphEntityOpsBaseRunner(UncallableNamespace, IllegalAttrChecker):
         G: Graph,
         properties: Strings,
         entities: Strings,
-        config: Dict[str, Any],
+        config: dict[str, Any],
     ) -> DataFrame:
         params = CallParameters(
             graph_name=G.name(),
@@ -78,11 +78,16 @@ class GraphNodePropertyRunner(GraphEntityOpsBaseRunner):
         G: Graph,
         node_property: str,
         node_labels: Strings = ["*"],
-        db_node_properties: List[str] = [],
+        db_node_properties: list[str] = [],
         **config: Any,
     ) -> DataFrame:
         self._namespace += ".stream"
 
+        if len(set(db_node_properties)) != len(db_node_properties):
+            raise ValueError(
+                f"The provided db_node_properties contain duplicate property names: `{db_node_properties}`."
+            )
+
         result = self._handle_properties(G, node_property, node_labels, config)
 
         return GraphNodePropertiesRunner._process_result(
@@ -96,14 +101,22 @@ class GraphNodePropertiesRunner(GraphEntityOpsBaseRunner):
     def stream(
         self,
         G: Graph,
-        node_properties: List[str],
+        node_properties: list[str],
         node_labels: Strings = ["*"],
         separate_property_columns: bool = False,
-        db_node_properties: List[str] = [],
+        db_node_properties: list[str] = [],
         **config: Any,
     ) -> DataFrame:
         self._namespace += ".stream"
 
+        # find if list contain duplicates
+        if len(set(node_properties)) != len(node_properties):
+            raise ValueError(f"The provided node_properties contain duplicate property names: `{node_properties}`.")
+        if len(set(db_node_properties)) != len(db_node_properties):
+            raise ValueError(
+                f"The provided db_node_properties contain duplicate property names: `{db_node_properties}`."
+            )
+
         result = self._handle_properties(G, node_properties, node_labels, config)
 
         return GraphNodePropertiesRunner._process_result(
@@ -113,11 +126,11 @@ class GraphNodePropertiesRunner(GraphEntityOpsBaseRunner):
     @staticmethod
     def _process_result(
         query_runner: QueryRunner,
-        node_properties: List[str],
+        node_properties: list[str],
         separate_property_columns: bool,
-        db_node_properties: List[str],
+        db_node_properties: list[str],
         result: DataFrame,
-        config: Dict[str, Any],
+        config: dict[str, Any],
     ) -> DataFrame:
         # new format was requested, but the query was run via Cypher
         if separate_property_columns and "propertyValue" in result.keys():
@@ -125,7 +138,11 @@ class GraphNodePropertiesRunner(GraphEntityOpsBaseRunner):
             if "listNodeLabels" in config.keys():
                 # nodeLabels cannot be an index column of the pivot as its not hashable
                 # so we need to manually join it back in
-                labels_df = result[["nodeId", "nodeLabels"]].set_index("nodeId")
+                labels_df = result[["nodeId", "nodeLabels"]]
+                # drop duplicates as for each property we would have one row for each nodeId
+                labels_df = labels_df.drop_duplicates(ignore_index=False, subset=["nodeId"])
+                labels_df.set_index("nodeId", inplace=True)
+
                 wide_result = wide_result.join(labels_df, on="nodeId")
             result = wide_result.reset_index()
             result.columns.name = None
@@ -161,7 +178,7 @@ class GraphNodePropertiesRunner(GraphEntityOpsBaseRunner):
         return result
 
     @staticmethod
-    def _build_query(db_node_properties: List[str]) -> str:
+    def _build_query(db_node_properties: list[str]) -> str:
         query_prefix = "MATCH (n) WHERE id(n) IN $ids RETURN id(n) AS nodeId"
 
         def add_property(query: str, prop: str) -> str:
@@ -176,7 +193,7 @@ class GraphNodePropertiesRunner(GraphEntityOpsBaseRunner):
 
     @compatible_with("drop", min_inclusive=ServerVersion(2, 2, 0))
     @graph_type_check
-    def drop(self, G: Graph, node_properties: List[str], **config: Any) -> "Series[Any]":
+    def drop(self, G: Graph, node_properties: list[str], **config: Any) -> "Series[Any]":
         self._namespace += ".drop"
         params = CallParameters(
             graph_name=G.name(),
@@ -205,7 +222,7 @@ class GraphRelationshipPropertiesRunner(GraphEntityOpsBaseRunner):
     def stream(
         self,
         G: Graph,
-        relationship_properties: List[str],
+        relationship_properties: list[str],
         relationship_types: Strings = ["*"],
         separate_property_columns: bool = False,
         **config: Any,
@@ -239,7 +256,7 @@ class GraphRelationshipPropertiesRunner(GraphEntityOpsBaseRunner):
         self,
         G: Graph,
         relationship_type: str,
-        relationship_properties: List[str],
+        relationship_properties: list[str],
         **config: Any,
     ) -> "Series[Any]":
         self._namespace += ".write"
@@ -319,7 +336,7 @@ class GraphRelationshipsRunner(GraphEntityOpsBaseRunner):
 
     @compatible_with("stream", min_inclusive=ServerVersion(2, 5, 0))
     @graph_type_check
-    def stream(self, G: Graph, relationship_types: List[str] = ["*"], **config: Any) -> TopologyDataFrame:
+    def stream(self, G: Graph, relationship_types: list[str] = ["*"], **config: Any) -> TopologyDataFrame:
         self._namespace += ".stream"
         params = CallParameters(graph_name=G.name(), relationship_types=relationship_types, config=config)
         result = self._query_runner.call_procedure(endpoint=self._namespace, params=params)
@@ -336,7 +353,7 @@ class GraphRelationshipsRunner(GraphEntityOpsBaseRunner):
 class GraphRelationshipsBetaRunner(GraphEntityOpsBaseRunner):
     @compatible_with("stream", min_inclusive=ServerVersion(2, 2, 0))
     @graph_type_check
-    def stream(self, G: Graph, relationship_types: List[str] = ["*"], **config: Any) -> TopologyDataFrame:
+    def stream(self, G: Graph, relationship_types: list[str] = ["*"], **config: Any) -> TopologyDataFrame:
         self._namespace += ".stream"
         params = CallParameters(graph_name=G.name(), relationship_types=relationship_types, config=config)
 

{graphdatascience-1.12 → graphdatascience-1.13}/graphdatascience/graph/graph_export_runner.py

@@ -1,4 +1,4 @@
-from typing import Any, Dict
+from typing import Any
 
 from pandas import Series
 
@@ -15,7 +15,7 @@ class GraphExportCsvRunner(IllegalAttrChecker):
         return self._export_call(G, config)
 
     @graph_type_check
-    def _export_call(self, G: Graph, config: Dict[str, Any]) -> "Series[Any]":
+    def _export_call(self, G: Graph, config: dict[str, Any]) -> "Series[Any]":
         params = CallParameters(graph_name=G.name(), config=config)
         return self._query_runner.call_procedure(endpoint=self._namespace, params=params).squeeze()  # type: ignore
 
@@ -39,7 +39,7 @@ class GraphExportRunner(IllegalAttrChecker):
         return self._export_call(G, config)
 
     @graph_type_check
-    def _export_call(self, G: Graph, config: Dict[str, Any]) -> "Series[Any]":
+    def _export_call(self, G: Graph, config: dict[str, Any]) -> "Series[Any]":
         params = CallParameters(graph_name=G.name(), config=config)
         return self._query_runner.call_procedure(endpoint=self._namespace, params=params).squeeze()  # type: ignore
 

{graphdatascience-1.12 → graphdatascience-1.13}/graphdatascience/graph/graph_object.py

@@ -1,7 +1,7 @@
 from __future__ import annotations
 
 from types import TracebackType
-from typing import Any, List, Optional, Type, Union
+from typing import Any, Optional, Type, Union
 
 from pandas import Series
 
@@ -39,7 +39,7 @@ class Graph:
         """
         return self._name
 
-    def _graph_info(self, yields: List[str] = []) -> "Series[Any]":
+    def _graph_info(self, yields: list[str] = []) -> Series[Any]:
         yield_db = "database" in yields
         yields_with_db = yields if yield_db else yields + ["database"]
 
@@ -90,21 +90,21 @@ class Graph:
         """
         return self._graph_info(["relationshipCount"])  # type: ignore
 
-    def node_labels(self) -> List[str]:
+    def node_labels(self) -> list[str]:
         """
         Returns:
             the node labels in the graph
         """
         return list(self._graph_info(["schema"])["nodes"].keys())
 
-    def relationship_types(self) -> List[str]:
+    def relationship_types(self) -> list[str]:
         """
         Returns:
             the relationship types in the graph
         """
         return list(self._graph_info(["schema"])["relationships"].keys())
 
-    def node_properties(self, label: Optional[str] = None) -> Union["Series[str]", List[str]]:
+    def node_properties(self, label: Optional[str] = None) -> Union[Series[str], list[str]]:
         """
         Args:
             label: the node label to get the properties for
@@ -123,7 +123,7 @@ class Graph:
 
         return list(labels_to_props[label].keys())
 
-    def relationship_properties(self, type: Optional[str] = None) -> Union["Series[str]", List[str]]:
+    def relationship_properties(self, type: Optional[str] = None) -> Union[Series[str], list[str]]:
         """
         Args:
             type: the relationship type to get the properties for

{graphdatascience-1.12 → graphdatascience-1.13}/graphdatascience/graph/graph_remote_project_runner.py

@@ -1,6 +1,6 @@
 from __future__ import annotations
 
-from typing import List, Optional
+from typing import Optional
 
 from ..call_parameters import CallParameters
 from ..error.illegal_attr_checker import IllegalAttrChecker
@@ -17,9 +17,10 @@ class GraphProjectRemoteRunner(IllegalAttrChecker):
         self,
         graph_name: str,
         query: str,
+        job_id: Optional[str] = None,
         concurrency: int = 4,
-        undirected_relationship_types: Optional[List[str]] = None,
-        inverse_indexed_relationship_types: Optional[List[str]] = None,
+        undirected_relationship_types: Optional[list[str]] = None,
+        inverse_indexed_relationship_types: Optional[list[str]] = None,
         batch_size: Optional[int] = None,
     ) -> GraphCreateResult:
         if inverse_indexed_relationship_types is None:
@@ -34,6 +35,7 @@ class GraphProjectRemoteRunner(IllegalAttrChecker):
         params = CallParameters(
             graph_name=graph_name,
             query=query,
+            job_id=job_id,
             concurrency=concurrency,
             undirected_relationship_types=undirected_relationship_types,
             inverse_indexed_relationship_types=inverse_indexed_relationship_types,

{graphdatascience-1.12 → graphdatascience-1.13}/graphdatascience/graph/nx_loader.py

@@ -1,5 +1,5 @@
 from collections import defaultdict
-from typing import Any, Dict, List, Optional, Set, Tuple
+from typing import Any, Optional
 
 import networkx as nx
 from pandas import DataFrame
@@ -28,8 +28,8 @@ class NXLoader(UncallableNamespace, IllegalAttrChecker):
         return Graph(graph_name, self._query_runner)
 
     @staticmethod
-    def _attr_to_labels_key(labels_attr: Any, node_id: Any, no_node_labels: Optional[bool]) -> Tuple[str, ...]:
-        node_labels: List[str]
+    def _attr_to_labels_key(labels_attr: Any, node_id: Any, no_node_labels: Optional[bool]) -> tuple[str, ...]:
+        node_labels: list[str]
         if no_node_labels:
             node_labels = ["N"]
         elif isinstance(labels_attr, str):
@@ -45,9 +45,9 @@ class NXLoader(UncallableNamespace, IllegalAttrChecker):
         return tuple(sorted(node_labels))
 
     @staticmethod
-    def _parse_nodes(nx_G: nx.Graph) -> List[DataFrame]:
-        node_dicts_by_labels: Dict[Tuple[str, ...], Dict[str, List[Any]]] = defaultdict(lambda: defaultdict(list))
-        node_props_schema: Dict[Tuple[str, ...], Set[str]] = defaultdict(set)
+    def _parse_nodes(nx_G: nx.Graph) -> list[DataFrame]:
+        node_dicts_by_labels: dict[tuple[str, ...], dict[str, list[Any]]] = defaultdict(lambda: defaultdict(list))
+        node_props_schema: dict[tuple[str, ...], set[str]] = defaultdict(set)
 
         no_node_labels = None
 
@@ -84,9 +84,9 @@ class NXLoader(UncallableNamespace, IllegalAttrChecker):
         return "R" if type_attr is None else type_attr
 
     @staticmethod
-    def _parse_rels(nx_G: nx.Graph) -> List[DataFrame]:
-        rel_dicts_by_types: Dict[str, Dict[str, List[Any]]] = defaultdict(lambda: defaultdict(list))
-        rel_props_schema: Dict[str, Set[str]] = defaultdict(set)
+    def _parse_rels(nx_G: nx.Graph) -> list[DataFrame]:
+        rel_dicts_by_types: dict[str, dict[str, list[Any]]] = defaultdict(lambda: defaultdict(list))
+        rel_props_schema: dict[str, set[str]] = defaultdict(set)
         no_rel_types = None
 
         for edge_data in nx_G.edges(data=True):
@@ -129,7 +129,7 @@ class NXLoader(UncallableNamespace, IllegalAttrChecker):
         ]
 
     @staticmethod
-    def _parse(nx_G: nx.Graph) -> Tuple[List[DataFrame], List[DataFrame]]:
+    def _parse(nx_G: nx.Graph) -> tuple[list[DataFrame], list[DataFrame]]:
         nodes = NXLoader._parse_nodes(nx_G)
         rels = NXLoader._parse_rels(nx_G)