HashGNN 的节点分类

# Install necessary Python dependencies
%pip install "graphdatascience>=1.6"

# Import our dependencies
import os

from graphdatascience import GraphDataScience

# Get Neo4j DB URI, credentials and name from environment if applicable
NEO4J_URI = os.environ.get("NEO4J_URI", "bolt://localhost:7687")
NEO4J_AUTH = None
NEO4J_DB = os.environ.get("NEO4J_DB", "neo4j")
if os.environ.get("NEO4J_USER") and os.environ.get("NEO4J_PASSWORD"):
    NEO4J_AUTH = (
        os.environ.get("NEO4J_USER"),
        os.environ.get("NEO4J_PASSWORD"),
    )
gds = GraphDataScience(NEO4J_URI, auth=NEO4J_AUTH, database=NEO4J_DB)

from graphdatascience import ServerVersion

assert gds.server_version() >= ServerVersion(2, 5, 0)

# Run the loading to obtain a `Graph` object representing our GDS projection
G = gds.graph.load_imdb()

print(f"Overview of G: {G}")
print(f"Node labels in G: {G.node_labels()}")
print(f"Relationship types in G: {G.relationship_types()}")

print(f"Node properties per label:\n{G.node_properties()}")

# Create an empty node classification pipeline
pipe, _ = gds.beta.pipeline.nodeClassification.create("genre-predictor-pipe")

# Set the test set size to be 79.6 % of the entire set of `Movie` nodes
_ = pipe.configureSplit(testFraction=0.796)

# Add a HashGNN node property step to the pipeline
_ = pipe.addNodeProperty(
    "hashgnn",
    mutateProperty="embedding",
    iterations=4,
    heterogeneous=True,
    embeddingDensity=512,
    neighborInfluence=0.7,
    featureProperties=["plot_keywords"],
    randomSeed=41,
    contextNodeLabels=G.node_labels(),
)

# Set the embeddings vectors produced by HashGNN as feature input to our ML algorithm
_ = pipe.selectFeatures("embedding")

# Add logistic regression as a candidate ML algorithm for the training
# Provide an interval for the `penalty` parameter to enable autotuning for it
_ = pipe.addLogisticRegression(penalty=(0.1, 1.0), maxEpochs=1000, patience=5, tolerance=0.0001, learningRate=0.01)

# Add random forest as a candidate ML algorithm for the training
# Provide an interval for the `minSplitSize` parameter to enable autotuning for it
_ = pipe.addRandomForest(minSplitSize=(2, 100), criterion="ENTROPY")

# Call train on our pipeline object to run the entire training pipeline and produce a model
model, _ = pipe.train(
    G,
    modelName="genre-predictor-model",
    targetNodeLabels=["Movie"],
    targetProperty="genre",
    metrics=["F1_MACRO"],
    randomSeed=42,
)

print(f"Accuracy scores of trained model:\n{model.metrics()['F1_MACRO']}")

print(f"Winning ML algorithm candidate config:\n{model.best_parameters()}")

# Predict `genre` for `UnclassifiedMovie` nodes and stream the results
predictions = model.predict_stream(G, targetNodeLabels=["UnclassifiedMovie"], includePredictedProbabilities=True)

print(f"First predictions of unclassified movie nodes:\n{predictions.head()}")

# Drop the GDS graph represented by `G` from the GDS graph catalog
_ = G.drop()

# Drop the GDS training pipeline represented by `pipe` from the GDS pipeline catalog
_ = pipe.drop()

# Drop the GDS model represented by `model` from the GDS model catalog
_ = model.drop()