文件名称：ML_with_GDS：Marvel Universe演示
文件大小：15KB
文件格式：ZIP
更新时间：2024-03-06 01:32:37
Neo4j的图数据科学图书馆进行机器学习 该库包含Neo4j的新节点分类和链接预测算法的演示-适用于Marvel Universe。 它建立在Tomasnojo的Marvel Graph Gist之上，可。 此演示演示如何： 准备使用ML模型的数据 训练图嵌入作为模型的输入 预测缺少的节点标签（在这种情况下，是X战警） 预测失落的人际关系（他们将一起出现在未来的漫画书中） 我将添加一个演示模型的演示，然后稍后在Bloom中查看结果
【文件预览】：
ML_with_GDS-main
----5. Make some predictions!()
--------1-lets-predict-node-classes-aka-can-we-find-more-x-men.cypher(526B)
--------2-lets-predict-some-new-links-aka-can-we-find-more-x-men.cypher(480B)
--------4-check-predicted-links.cypher(118B)
--------3-check-our-predicted-node-classes.cypher(311B)
----1. Data Prep for Marvel()
--------4-one-hot-encode-group-membership-i-ended-up-not-using-this-but-useful-to-know-how-to.cypher(347B)
--------2-move-character-traits-to-character-nodes.cypher(431B)
--------3-create-an-appeared-together-relationship.cypher(253B)
--------1-load-data-from-https-gist-github-com-tomasonjo-fbc-6-d-617-c-3-f-6476-a-3-a-825-b-5-dd-22-fd-29-a.cypher(2KB)
----2. Feature Engineering()
--------5-drop-extra-graphs.cypher(71B)
--------1-load-graph-with-features.cypher(1KB)
--------4-compute-fast-rp-extended-embedding.cypher(778B)
--------2-run-centrality-algos-to-add-more-features.cypher(2KB)
--------3-mutate-the-in-memory-graph-rather-than-reload.cypher(2KB)
----README.md(679B)
----4. Link Prediction()
--------4-train-a-link-prediction-model.cypher(698B)
--------1-split-the-graph-into-the-data-we-want-to-use-for-the-model-and-data-to-hold-out-to-test-afterwards.cypher(789B)
--------3-add-test-train-splits-to-in-memory-graph.cypher(617B)
--------2-load-graph-for-class-prediction.cypher(1KB)
--------5-train-a-link-prediction-model-without-an-embedding.cypher(761B)
----3. Node Classification()
--------2-load-graph-for-class-prediction.cypher(1KB)
--------1-select-label-the-data-for-the-model.cypher(930B)
--------4-compare-to-tabular-properties.cypher(923B)
--------3-train-node-classifier-to-find-x-men-fast-rp.cypher(896B)