Merge pull request #679 from FlorentinD/session-run-cypher-fixes

Reduce run_cypher calls for GDS endpoints

Author: FlorentinD

graphdatascience/model/link_prediction_model.py

@@ -41,5 +41,5 @@ def link_features(self) -> List[LinkFeature]:
             A list of LinkFeatures of the pipeline.
 
         """
-        steps: List[Dict[str, Any]] = self._list_info()["modelInfo"][0]["pipeline"]["featureSteps"]
+        steps: List[Dict[str, Any]] = self._list_info()["modelInfo"]["pipeline"]["featureSteps"]
         return [LinkFeature(s["name"], s["config"]) for s in steps]

graphdatascience/model/model.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 from abc import ABC, abstractmethod
 from typing import Any, Dict
 
@@ -21,34 +23,32 @@ def __init__(self, name: str, query_runner: QueryRunner, server_version: ServerV
     def _endpoint_prefix(self) -> str:
         pass
 
-    def _list_info(self) -> DataFrame:
+    def _list_info(self) -> Series[Any]:
+        params = CallParameters(name=self.name())
+
+        result: Series[Any]
         if self._server_version < ServerVersion(2, 5, 0):
-            query = "CALL gds.beta.model.list($name)"
+            result = self._query_runner.call_procedure(
+                "gds.beta.model.list", params=params, custom_error=False
+            ).squeeze()
         else:
-            query = """
-                    CALL gds.model.list($name)
-                    YIELD
-                      modelName, modelType, modelInfo,
-                      creationTime, trainConfig, graphSchema,
-                      loaded, stored, published
-                    RETURN
-                      modelName, modelType,
-                      modelInfo {.*, modelName: modelName, modelType: modelType} AS modelInfo,
-                      creationTime, trainConfig, graphSchema,
-                      loaded, stored, published, published AS shared
-                    """
-
-        params = {"name": self.name()}
-
-        # FIXME use call procedure + do post processing on the client side
-        info = self._query_runner.run_cypher(query, params, custom_error=False)
-
-        if len(info) == 0:
+            result = self._query_runner.call_procedure("gds.model.list", params=params, custom_error=False).squeeze()
+
+            if not result.empty:
+                #  2.5 compat format
+                result["modelInfo"] = {
+                    **result["modelInfo"],
+                    "modelName": result["modelName"],
+                    "modelType": result["modelType"],
+                }
+                result["shared"] = result["published"]
+
+        if result.empty:
             raise ValueError(f"There is no '{self.name()}' in the model catalog")
 
-        return info
+        return result
 
-    def _estimate_predict(self, predict_mode: str, graph_name: str, config: Dict[str, Any]) -> "Series[Any]":
+    def _estimate_predict(self, predict_mode: str, graph_name: str, config: Dict[str, Any]) -> Series[Any]:
         endpoint = f"{self._endpoint_prefix()}{predict_mode}.estimate"
         config["modelName"] = self.name()
         params = CallParameters(graph_name=graph_name, config=config)
@@ -76,28 +76,28 @@ def type(self) -> str:
             The type of the model.
 
         """
-        return self._list_info()["modelInfo"][0]["modelType"]  # type: ignore
+        return self._list_info()["modelInfo"]["modelType"]  # type: ignore
 
-    def train_config(self) -> "Series[Any]":
+    def train_config(self) -> Series[Any]:
         """
         Get the train config of the model.
 
         Returns:
             The train config of the model.
 
         """
-        train_config: "Series[Any]" = Series(self._list_info()["trainConfig"][0])
+        train_config: Series[Any] = Series(self._list_info()["trainConfig"])
         return train_config
 
-    def graph_schema(self) -> "Series[Any]":
+    def graph_schema(self) -> Series[Any]:
         """
         Get the graph schema of the model.
 
         Returns:
             The graph schema of the model.
 
         """
-        graph_schema: "Series[Any]" = Series(self._list_info()["graphSchema"][0])
+        graph_schema: Series[Any] = Series(self._list_info()["graphSchema"])
         return graph_schema
 
     def loaded(self) -> bool:
@@ -108,7 +108,7 @@ def loaded(self) -> bool:
             True if the model is loaded in memory, False otherwise.
 
         """
-        return self._list_info()["loaded"].squeeze()  # type: ignore
+        return self._list_info()["loaded"]  # type: ignore
 
     def stored(self) -> bool:
         """
@@ -118,7 +118,7 @@ def stored(self) -> bool:
             True if the model is stored on disk, False otherwise.
 
         """
-        return self._list_info()["stored"].squeeze()  # type: ignore
+        return self._list_info()["stored"]  # type: ignore
 
     def creation_time(self) -> Any:  # neo4j.time.DateTime not exported
         """
@@ -128,7 +128,7 @@ def creation_time(self) -> Any:  # neo4j.time.DateTime not exported
             The creation time of the model.
 
         """
-        return self._list_info()["creationTime"].squeeze()
+        return self._list_info()["creationTime"]
 
     def shared(self) -> bool:
         """
@@ -138,7 +138,7 @@ def shared(self) -> bool:
             True if the model is shared, False otherwise.
 
         """
-        return self._list_info()["shared"].squeeze()  # type: ignore
+        return self._list_info()["shared"]  # type: ignore
 
     @compatible_with("published", min_inclusive=ServerVersion(2, 5, 0))
     def published(self) -> bool:
@@ -149,17 +149,17 @@ def published(self) -> bool:
             True if the model is published, False otherwise.
 
         """
-        return self._list_info()["published"].squeeze()  # type: ignore
+        return self._list_info()["published"]  # type: ignore
 
-    def model_info(self) -> "Series[Any]":
+    def model_info(self) -> Dict[str, Any]:
         """
         Get the model info of the model.
 
         Returns:
             The model info of the model.
 
         """
-        return Series(self._list_info()["modelInfo"].squeeze())
+        return Series(self._list_info()["modelInfo"])  # type: ignore
 
     def exists(self) -> bool:
         """
@@ -179,7 +179,7 @@ def exists(self) -> bool:
             endpoint=endpoint, params=params, yields=yields, custom_error=False
         ).squeeze()
 
-    def drop(self, failIfMissing: bool = False) -> "Series[Any]":
+    def drop(self, failIfMissing: bool = False) -> Series[Any]:
         """
         Drop the model.
 
@@ -190,36 +190,38 @@ def drop(self, failIfMissing: bool = False) -> "Series[Any]":
             The result of the drop operation.
 
         """
+        params = CallParameters(model_name=self._name, fail_if_missing=failIfMissing)
         if self._server_version < ServerVersion(2, 5, 0):
-            query = "CALL gds.beta.model.drop($model_name, $fail_if_missing)"
+            return self._query_runner.call_procedure(  # type: ignore
+                "gds.beta.model.drop", params=params, custom_error=False
+            ).squeeze()
         else:
-            query = """
-                    CALL gds.model.drop($model_name, $fail_if_missing)
-                    YIELD
-                      modelName, modelType, modelInfo,
-                      creationTime, trainConfig, graphSchema,
-                      loaded, stored, published
-                    RETURN
-                      modelName, modelType,
-                      modelInfo {.*, modelName: modelName, modelType: modelType} AS modelInfo,
-                      creationTime, trainConfig, graphSchema,
-                      loaded, stored, published, published AS shared
-                    """
-
-        params = {"model_name": self._name, "fail_if_missing": failIfMissing}
-        # FIXME use call procedure + do post processing on the client side
-        return self._query_runner.run_cypher(query, params, custom_error=False).squeeze()  # type: ignore
-
-    def metrics(self) -> "Series[Any]":
+            result: Series[Any] = self._query_runner.call_procedure(
+                "gds.model.drop", params=params, custom_error=False
+            ).squeeze()
+
+            if result.empty:
+                return Series()
+
+            #  modelInfo {.*, modelName: modelName, modelType: modelType} AS modelInfo
+            result["modelInfo"] = {
+                **result["modelInfo"],
+                "modelName": result["modelName"],
+                "modelType": result["modelType"],
+            }
+            result["shared"] = result["published"]
+            return result
+
+    def metrics(self) -> Series[Any]:
         """
         Get the metrics of the model.
 
         Returns:
             The metrics of the model.
 
         """
-        model_info = self._list_info()["modelInfo"][0]
-        metrics: "Series[Any]" = Series(model_info["metrics"])
+        model_info = self._list_info()["modelInfo"]
+        metrics: Series[Any] = Series(model_info["metrics"])
         return metrics
 
     @graph_type_check
@@ -242,7 +244,7 @@ def predict_stream(self, G: Graph, **config: Any) -> DataFrame:
         return self._query_runner.call_procedure(endpoint=endpoint, params=params, logging=True)
 
     @graph_type_check
-    def predict_stream_estimate(self, G: Graph, **config: Any) -> "Series[Any]":
+    def predict_stream_estimate(self, G: Graph, **config: Any) -> Series[Any]:
         """
         Estimate the prediction on the given graph using the model and stream the results as DataFrame
 
@@ -257,7 +259,7 @@ def predict_stream_estimate(self, G: Graph, **config: Any) -> "Series[Any]":
         return self._estimate_predict("stream", G.name(), config)
 
     @graph_type_check
-    def predict_mutate(self, G: Graph, **config: Any) -> "Series[Any]":
+    def predict_mutate(self, G: Graph, **config: Any) -> Series[Any]:
         """
         Predict on the given graph using the model and mutate the graph with the results.
 
@@ -278,7 +280,7 @@ def predict_mutate(self, G: Graph, **config: Any) -> "Series[Any]":
         ).squeeze()
 
     @graph_type_check
-    def predict_mutate_estimate(self, G: Graph, **config: Any) -> "Series[Any]":
+    def predict_mutate_estimate(self, G: Graph, **config: Any) -> Series[Any]:
         """
         Estimate the memory needed to predict on the given graph using the model.
 

graphdatascience/model/model_proc_runner.py

@@ -1,4 +1,6 @@
-from typing import Any, Dict, List, Optional, Tuple
+from __future__ import annotations
+
+from typing import Any, Dict, List, Optional, Tuple, Union
 
 from pandas import DataFrame, Series
 
@@ -49,23 +51,29 @@ def create(
 class ModelProcRunner(ModelResolver):
     @client_only_endpoint("gds.model")
     def get(self, model_name: str) -> Model:
+        params = CallParameters(model_name=model_name)
         if self._server_version < ServerVersion(2, 5, 0):
-            query = "CALL gds.beta.model.list($model_name) YIELD modelInfo RETURN modelInfo.modelType AS modelType"
+            endpoint = "gds.beta.model.list"
+            yields = ["modelInfo"]
+            result_25: Series[Any] = self._query_runner.call_procedure(
+                endpoint=endpoint, params=params, yields=yields, custom_error=False
+            ).squeeze()
+            model_type = str(result_25["modelInfo"]["modelType"]) if not result_25.empty else None
         else:
-            query = "CALL gds.model.list($model_name) YIELD modelType"
-
-        params = {"model_name": model_name}
-        # FIXME use call procedure + do post processing on the client side
-        result = self._query_runner.run_cypher(query, params, custom_error=False)
-
-        if len(result) == 0:
+            endpoint = "gds.model.list"
+            yields = ["modelType"]
+            result: Union[str, Series[Any]] = self._query_runner.call_procedure(
+                endpoint=endpoint, params=params, yields=yields, custom_error=False
+            ).squeeze()
+            model_type = result if isinstance(result, str) else None
+
+        if model_type is None:
             raise ValueError(f"No loaded model named '{model_name}' exists")
 
-        model_type = str(result["modelType"].squeeze())
         return self._resolve_model(model_type, model_name)
 
     @compatible_with("store", min_inclusive=ServerVersion(2, 5, 0))
-    def store(self, model: Model, failIfUnsupportedType: bool = True) -> "Series[Any]":
+    def store(self, model: Model, failIfUnsupportedType: bool = True) -> Series[Any]:
         self._namespace += ".store"
         params = CallParameters(model_name=model.name(), fail_flag=failIfUnsupportedType)
 
@@ -88,7 +96,7 @@ def publish(self, model: Model) -> Model:
         return self._resolve_model(model_type, model_name)
 
     @compatible_with("load", min_inclusive=ServerVersion(2, 5, 0))
-    def load(self, model_name: str) -> Tuple[Model, "Series[Any]"]:
+    def load(self, model_name: str) -> Tuple[Model, Series[Any]]:
         self._namespace += ".load"
 
         params = CallParameters(model_name=model_name)
@@ -101,7 +109,7 @@ def load(self, model_name: str) -> Tuple[Model, "Series[Any]"]:
         return proc_runner.get(result["modelName"]), result
 
     @compatible_with("delete", min_inclusive=ServerVersion(2, 5, 0))
-    def delete(self, model: Model) -> "Series[Any]":
+    def delete(self, model: Model) -> Series[Any]:
         self._namespace += ".delete"
         params = CallParameters(model_name=model.name())
         return self._query_runner.call_procedure(endpoint=self._namespace, params=params).squeeze()  # type: ignore
@@ -117,15 +125,15 @@ def list(self, model: Optional[Model] = None) -> DataFrame:
         return self._query_runner.call_procedure(endpoint=self._namespace, params=params)
 
     @compatible_with("exists", min_inclusive=ServerVersion(2, 5, 0))
-    def exists(self, model_name: str) -> "Series[Any]":
+    def exists(self, model_name: str) -> Series[Any]:
         self._namespace += ".exists"
 
         return self._query_runner.call_procedure(  # type: ignore
             endpoint=self._namespace, params=CallParameters(model_name=model_name)
         ).squeeze()
 
     @compatible_with("drop", min_inclusive=ServerVersion(2, 5, 0))
-    def drop(self, model: Model) -> "Series[Any]":
+    def drop(self, model: Model) -> Series[Any]:
         self._namespace += ".drop"
 
         return self._query_runner.call_procedure(  # type: ignore

graphdatascience/model/node_classification_model.py

@@ -62,7 +62,7 @@ def classes(self) -> List[int]:
             The classes of the model.
 
         """
-        return self._list_info()["modelInfo"][0]["classes"]  # type: ignore
+        return self._list_info()["modelInfo"]["classes"]  # type: ignore
 
     def feature_properties(self) -> List[str]:
         """
@@ -72,5 +72,5 @@ def feature_properties(self) -> List[str]:
             The feature properties of the model.
 
         """
-        features: List[Dict[str, Any]] = self._list_info()["modelInfo"][0]["pipeline"]["featureProperties"]
+        features: List[Dict[str, Any]] = self._list_info()["modelInfo"]["pipeline"]["featureProperties"]
         return [f["feature"] for f in features]

graphdatascience/model/node_regression_model.py

@@ -21,5 +21,5 @@ def feature_properties(self) -> List[str]:
             The feature properties of the model.
 
         """
-        features: List[Dict[str, Any]] = self._list_info()["modelInfo"][0]["pipeline"]["featureProperties"]
+        features: List[Dict[str, Any]] = self._list_info()["modelInfo"]["pipeline"]["featureProperties"]
         return [f["feature"] for f in features]

graphdatascience/model/pipeline_model.py

@@ -75,7 +75,7 @@ def best_parameters(self) -> "Series[Any]":
             The best parameters for the pipeline model.
 
         """
-        best_params: Dict[str, Any] = self._list_info()["modelInfo"][0]["bestParameters"]
+        best_params: Dict[str, Any] = self._list_info()["modelInfo"]["bestParameters"]
         return Series(best_params)
 
     def node_property_steps(self) -> List[NodePropertyStep]:
@@ -86,7 +86,7 @@ def node_property_steps(self) -> List[NodePropertyStep]:
             The node property steps for the pipeline model.
 
         """
-        steps: List[Dict[str, Any]] = self._list_info()["modelInfo"][0]["pipeline"]["nodePropertySteps"]
+        steps: List[Dict[str, Any]] = self._list_info()["modelInfo"]["pipeline"]["nodePropertySteps"]
         return [NodePropertyStep(s["name"], s["config"]) for s in steps]
 
     def metrics(self) -> "Series[Any]":
@@ -97,6 +97,6 @@ def metrics(self) -> "Series[Any]":
             The metrics for the pipeline model.
 
         """
-        model_metrics: Dict[str, Any] = self._list_info()["modelInfo"][0]["metrics"]
+        model_metrics: Dict[str, Any] = self._list_info()["modelInfo"]["metrics"]
         metric_scores: Dict[str, MetricScores] = {k: MetricScores.create(v) for k, v in (model_metrics.items())}
         return Series(metric_scores)