dbscan   54

« earlier    

Frequently Asked Questions — scikit-learn 0.18.1 documentation
Firstly, many estimators take precomputed distance/similarity matrices, so if the dataset is not too large, you can compute distances for all pairs of inputs. If the dataset is large, you can use feature vectors with only one “feature”, which is an index into a separate data structure, and supply a custom metric function that looks up the actual data in this data structure. E.g., to use DBSCAN with Levenshtein distances:
dbscan  distance  estimator 
june 2017 by pskomoroch

« earlier    

related tags

algorithm  algorithms  analytics  anomaly  applications  assignment  autoencoder  book  c++  cesiumterrainbuilder  cluster  cluster_analysis  clustering  code  convnet  course  ctb  data-mining  data  data_science  databases  datamining  datascience  debacl  demo  density-estimation  density  distance  estimator  fuzzy-clustering  genomics  geo  geospatial  gis  hdbscan  hiccomp  iate  ipython  java  k-means  kmeans  knn  large  lectures  level-set  machine-learning  machine_learning  machinelearning  matlab  metric  minibatch  ml  netflix  neural-net  numpy  octave  optics  paper  parallel  performance  points  programming  pseudo-metric  python  research-article  scikit  scipy  sklearn  software  spatial  statistics  treo  ufl  umn  unsupervised  visualization  word2vec 

Copy this bookmark: