Change Description

The big data algorithm libraries are compatible with native Spark APIs, with optimizations on machine learning and graph analysis algorithms to greatly improve the computing performance in big data algorithm scenarios. The libraries support the Kunpeng processor architecture. Version 1.2.0 provides the following algorithms:

• Machine learning algorithms
  • Gradient Boosting Decision Tree (GBDT)
  • Random Forest
  • Support Vector Machine (SVM)
  • K-means Clustering (K-means)
  • DecisionTree
  • LinearRegression
  • LogisticRegression
  • Principle Component Analysis (PCA)
  • Singular Value Decomposition (SVD)
  • Latent Dirichlet Allocation (LDA)
  • Alternating Least Squares (ALS)
  • Prefix-projected Pattern Growth (PrefixSpan)
  • K-nearest Neighbors (KNN)

• Graph analysis algorithms
  • Maximal Clique Enumeration (MCE)
  • Weak Clique Enumeration (WCE)
  • Modularity
  • Triangle Count (TC)
  • Multiple Sources Shortest Path (MSSP)
  • PageRank
  • Strongly Connected Components (SCC)
  • Louvain (modularity-based community detection algorithm)
  • Label Propagation Algorithm (LPA)
  • Closeness
  • Cycle Detection (CD)
  • Connected Components (CC)
  • K-Core Decomposition (K-Core)
  • Degree Centrality (Degree)
  • Breadth-First-Search (BFS)