Wolfram Language & System 10.3 (2015)|Legacy Documentation

This is documentation for an earlier version of the Wolfram Language.View current documentation (Version 11.2)

DimensionReduce

DimensionReduce[{vec1,vec2,}]
projects the vectors onto an approximating manifold in lower-dimensional space.

DimensionReduce[vecs,n]
projects onto an approximating manifold in n-dimensional space.

DimensionReduce[vecs,n,data]
applies the projection deduced from vecs to the list of vectors data.

DimensionReduce[vecs,n,data,prop]
gives the specified property of the reduction associated with data.

Details and OptionsDetails and Options

  • The vectors must be numerical and must all be of the same length.
  • DimensionReduce[vecs] automatically chooses an appropriate dimension for the approximating manifold.
  • DimensionReduce[vecs] is equivalent to DimensionReduce[vecs,Automatic].
  • The vectors in the list data must be the same length as the .
  • DimensionReduce only works on numerical vectors all having the same length.
  • In DimensionReduce[vecs,n,data,prop], possible properties include:
  • "ReducedVectors"reduction of the vectors given
    "OriginalVectors"deduced original vectors given reduced vectors
    "ReconstructedVectors"reconstruction by reduction and inversion
    "ImputedVectors"missing values replaced by imputed ones
  • The following options can be given:
  • MethodAutomaticwhich reduction algorithm to use
    PerformanceGoalAutomaticaspect of performance to optimize
  • Possible settings for PerformanceGoal include:
  • "Quality"maximize reduction quality
    "Speed"maximize reduction speed
  • Possible settings for Method include:
  • Automaticautomatically chosen method
    "PrincipalComponentsAnalysis"principal components analysis method
    "LatentSemanticAnalysis"latent semantic analysis method
    "LowRankMatrixFactorization"use a low-rank matrix factorization algorithm

ExamplesExamplesopen allclose all

Basic Examples  (2)Basic Examples  (2)

Reduce the dimension of vectors:

In[1]:=
Click for copyable input
In[2]:=
Click for copyable input
Out[2]=

Specify that the target dimension should be 1:

In[3]:=
Click for copyable input
Out[3]=

Create a dimensionality reducer using vectors, and reduce the dimension of other vectors in one step:

In[1]:=
Click for copyable input
In[2]:=
Click for copyable input
In[3]:=
Click for copyable input
Out[3]=

Perform the reduction, then the inverse operation:

In[4]:=
Click for copyable input
Out[4]=
Introduced in 2015
(10.1)