neo4j-viz 0.4.1__py3-none-any.whl → 0.5.0__py3-none-any.whl

neo4j_viz/gds.py

@@ -2,12 +2,11 @@ from __future__ import annotations
 
 import warnings
 from itertools import chain
-from typing import Optional
+from typing import Optional, cast
 from uuid import uuid4
 
 import pandas as pd
 from graphdatascience import Graph, GraphDataScience
-from pandas import Series
 
 from .pandas import _from_dfs
 from .visualization_graph import VisualizationGraph
@@ -24,22 +23,25 @@ def _fetch_node_dfs(
     }
 
 
-def _fetch_rel_df(gds: GraphDataScience, G: Graph) -> pd.DataFrame:
-    relationship_properties = G.relationship_properties()
-    assert isinstance(relationship_properties, Series)
+def _fetch_rel_dfs(gds: GraphDataScience, G: Graph) -> list[pd.DataFrame]:
+    rel_types = G.relationship_types()
 
-    relationship_properties_per_type = relationship_properties.tolist()
-    property_set: set[str] = set()
-    for props in relationship_properties_per_type:
-        if props:
-            property_set.update(props)
+    rel_props = {rel_type: G.relationship_properties(rel_type) for rel_type in rel_types}
 
-    if len(property_set) > 0:
-        return gds.graph.relationshipProperties.stream(
-            G, relationship_properties=list(property_set), separate_property_columns=True
-        )
+    rel_dfs: list[pd.DataFrame] = []
+    # Have to call per stream per relationship type as there was a bug in GDS < 2.21
+    for rel_type, props in rel_props.items():
+        assert isinstance(props, list)
+        if len(props) > 0:
+            rel_df = gds.graph.relationshipProperties.stream(
+                G, relationship_types=rel_type, relationship_properties=list(props), separate_property_columns=True
+            )
+        else:
+            rel_df = gds.graph.relationships.stream(G, relationship_types=[rel_type])
+
+        rel_dfs.append(rel_df)
 
-    return gds.graph.relationships.stream(G)
+    return rel_dfs
 
 
 def from_gds(
@@ -79,31 +81,32 @@ def from_gds(
     """
     node_properties_from_gds = G.node_properties()
     assert isinstance(node_properties_from_gds, pd.Series)
-    actual_node_properties = node_properties_from_gds.to_dict()
+    actual_node_properties: dict[str, list[str]] = cast(dict[str, list[str]], node_properties_from_gds.to_dict())
     all_actual_node_properties = list(chain.from_iterable(actual_node_properties.values()))
 
     if size_property is not None:
         if size_property not in all_actual_node_properties:
             raise ValueError(f"There is no node property '{size_property}' in graph '{G.name()}'")
 
+    node_properties_by_label_sets: dict[str, set[str]] = dict()
     if additional_node_properties is None:
-        node_properties_by_label = {k: set(v) for k, v in actual_node_properties.items()}
+        node_properties_by_label_sets = {k: set(v) for k, v in actual_node_properties.items()}
     else:
         for prop in additional_node_properties:
             if prop not in all_actual_node_properties:
                 raise ValueError(f"There is no node property '{prop}' in graph '{G.name()}'")
 
-        node_properties_by_label = {}
         for label, props in actual_node_properties.items():
-            node_properties_by_label[label] = {
+            node_properties_by_label_sets[label] = {
                 prop for prop in actual_node_properties[label] if prop in additional_node_properties
             }
 
     if size_property is not None:
-        for label, props in node_properties_by_label.items():
-            props.add(size_property)
+        # For some reason mypy are unable to understand that this is dict[str, set[str]]
+        for label, props in node_properties_by_label_sets.items():  # type: ignore
+            props.add(size_property)  # type: ignore
 
-    node_properties_by_label = {k: list(v) for k, v in node_properties_by_label.items()}
+    node_properties_by_label = {k: list(v) for k, v in node_properties_by_label_sets.items()}
 
     node_count = G.node_count()
     if node_count > max_node_count:
@@ -131,7 +134,7 @@ def from_gds(
             for df in node_dfs.values():
                 df.drop(columns=[property_name], inplace=True)
 
-        rel_df = _fetch_rel_df(gds, G_fetched)
+        rel_dfs = _fetch_rel_dfs(gds, G_fetched)
     finally:
         if G_fetched.name() != G.name():
             G_fetched.drop()
@@ -146,7 +149,10 @@ def from_gds(
     if size_property is not None:
         if "size" in all_actual_node_properties and size_property != "size":
             node_props_df.rename(columns={"size": "__size"}, inplace=True)
-        node_props_df.rename(columns={size_property: "size"}, inplace=True)
+        if additional_node_properties is not None and size_property not in additional_node_properties:
+            node_props_df.rename(columns={size_property: "size"}, inplace=True)
+        else:
+            node_props_df["size"] = node_props_df[size_property]
 
     for lbl, df in node_dfs.items():
         if "labels" in all_actual_node_properties:
@@ -161,12 +167,13 @@ def from_gds(
     if "caption" not in all_actual_node_properties:
         node_df["caption"] = node_df["labels"].astype(str)
 
-    if "caption" not in rel_df.columns:
-        rel_df["caption"] = rel_df["relationshipType"]
+    for rel_df in rel_dfs:
+        if "caption" not in rel_df.columns:
+            rel_df["caption"] = rel_df["relationshipType"]
 
     try:
         return _from_dfs(
-            node_df, rel_df, node_radius_min_max=node_radius_min_max, rename_properties={"__size": "size"}, dropna=True
+            node_df, rel_dfs, node_radius_min_max=node_radius_min_max, rename_properties={"__size": "size"}, dropna=True
         )
     except ValueError as e:
         err_msg = str(e)

neo4j_viz/pandas.py

@@ -74,7 +74,7 @@ def _parse_nodes(
     has_size = True
     nodes = []
     for node_df in node_dfs_iter:
-        has_size &= "size" in node_df.columns
+        has_size &= "size" in [c.lower() for c in node_df.columns]
         for _, row in node_df.iterrows():
             if dropna:
                 row = row.dropna(inplace=False)