krann_main.cpp File Reference

#include <mlpack/prereqs.hpp>
#include <mlpack/core/util/io.hpp>
#include <mlpack/core/util/mlpack_main.hpp>
#include "ra_search.hpp"
#include "ra_model.hpp"
#include <mlpack/methods/neighbor_search/unmap.hpp>

Include dependency graph for krann_main.cpp:

This graph shows which files directly or indirectly include this file:

Functions
	BINDING_NAME ("K-Rank-Approximate-Nearest-Neighbors (kRANN)")
	BINDING_SHORT_DESC ("An implementation of rank-approximate k-nearest-neighbor search (kRANN) " " using single-tree and dual-tree algorithms. Given a set of reference " "points and query points, this can find the k nearest neighbors in the " "reference set of each query point using trees; trees that are built can " "be saved for future use.")
	BINDING_LONG_DESC ("This program will calculate the k rank-approximate-nearest-neighbors of a " "set of points. You may specify a separate set of reference points and " "query points, or just a reference set which will be used as both the " "reference and query set. You must specify the rank approximation (in %) " "(and optionally the success probability).")
	BINDING_EXAMPLE ("For example, the following will return 5 neighbors from the top 0.1% of " "the data (with probability 0.95) for each point in "+PRINT_DATASET("input")+" and store the distances in "+PRINT_DATASET("distances")+" and the neighbors in "+PRINT_DATASET("neighbors.csv")+":" "\"+PRINT_CALL("krann", "reference", "input", "k", 5, "distances", "distances", "neighbors", "neighbors", "tau", 0.1)+"\" "Note that tau must be set such that the number of points in the " "corresponding percentile of the data is greater than k. Thus, if we " "choose tau = 0.1 with a dataset of 1000 points and k = 5, then we are " "attempting to choose 5 nearest neighbors out of the closest 1 point -- " "this is invalid and the program will terminate with an error message." "\" "The output matrices are organized such that row i and column j in the " "neighbors output file corresponds to the index of the point in the " "reference set which is the i'th nearest neighbor from the point in the " "query set with index j. Row i and column j in the distances output file " "corresponds to the distance between those two points.")
	BINDING_SEE_ALSO ("@knn", "#knn")
	BINDING_SEE_ALSO ("@lsh", "#lsh")
	BINDING_SEE_ALSO ("Rank-approximate nearest neighbor search: Retaining meaning" " and speed in high dimensions (pdf)", "https://papers.nips.cc/paper/" "3864-rank-approximate-nearest-neighbor-search-retaining-meaning-and" "-speed-in-high-dimensions.pdf")
	BINDING_SEE_ALSO ("mlpack::neighbor::RASearch C++ class documentation", "@doxygen/classmlpack_1_1neighbor_1_1RASearch.html")
	PARAM_MATRIX_IN ("reference", "Matrix containing the reference dataset.", "r")
	PARAM_MATRIX_OUT ("distances", "Matrix to output distances into.", "d")
	PARAM_UMATRIX_OUT ("neighbors", "Matrix to output neighbors into.", "n")
	PARAM_MODEL_IN (RAModel, "input_model", "Pre-trained kNN model.", "m")
	PARAM_MODEL_OUT (RAModel, "output_model", "If specified, the kNN model will be" " output here.", "M")
	PARAM_MATRIX_IN ("query", "Matrix containing query points (optional).", "q")
	PARAM_INT_IN ("k", "Number of nearest neighbors to find.", "k", 0)
	PARAM_STRING_IN ("tree_type", "Type of tree to use: 'kd', 'ub', 'cover', 'r', " "'x', 'r-star', 'hilbert-r', 'r-plus', 'r-plus-plus', 'oct'.", "t", "kd")
	PARAM_INT_IN ("leaf_size", "Leaf size for tree building (used for kd-trees, " "UB trees, R trees, R* trees, X trees, Hilbert R trees, R+ trees, " "R++ trees, and octrees).", "l", 20)
	PARAM_FLAG ("random_basis", "Before tree-building, project the data onto a " "random orthogonal basis.", "R")
	PARAM_INT_IN ("seed", "Random seed (if 0, std::time(NULL) is used).", "s", 0)
	PARAM_DOUBLE_IN ("tau", "The allowed rank-error in terms of the percentile of " "the data.", "T", 5)
	PARAM_DOUBLE_IN ("alpha", "The desired success probability.", "a", 0.95)
	PARAM_FLAG ("naive", "If true, sampling will be done without using a tree.", "N")
	PARAM_FLAG ("single_mode", "If true, single-tree search is used (as opposed to " "dual-tree search.", "S")
	PARAM_FLAG ("sample_at_leaves", "The flag to trigger sampling at leaves.", "L")
	PARAM_FLAG ("first_leaf_exact", "The flag to trigger sampling only after " "exactly exploring the first leaf.", "X")
	PARAM_INT_IN ("single_sample_limit", "The limit on the maximum number of " "samples (and hence the largest node you can approximate).", "z", 20)

Detailed Description

Author

Parikshit Ram

Implementation of the kRANN executable. Allows some number of standard options.

mlpack is free software; you may redistribute it and/or modify it under the terms of the 3-clause BSD license. You should have received a copy of the 3-clause BSD license along with mlpack. If not, see http://www.opensource.org/licenses/BSD-3-Clause for more information.