DimensionReducerFunction
represents a function generated by DimensionReduction that projects data onto a lower-dimensional approximating manifold.
Details and Options
- DimensionReducerFunction works like Function.
- DimensionReducerFunction[…][example] projects the single example example onto the approximating manifold.
- DimensionReducerFunction[…][{example1,example2,…}] projects all the examplei.
- DimensionReducerFunction[…][data,prop] gives the specified property of the dimension reduction associated with data.
- Possible properties include:
-
"ReducedVectors" reduction of the vectors given "OriginalData" deduced original examples given reduced vectors "ReconstructedData" reconstruction by reduction and inversion "ImputedData" missing values replaced by imputed ones - DimensionReduction[DimensionReducerFunction[…],FeatureExtractorfe] can be used to prepend the FeatureExtractorFunction[…] fe to the existing feature extractor.
Examples
open all close allBasic Examples (3)
Generate a DimensionReducerFunction from a list of vectors:
dr = DimensionReduction[{{1, 2, 3}, {2, 3, 5}, {3, 5, 8}, {4, 5, 8.5}}]Use this reducer function on a new vector:
dr[{6, 7, 14}]Use this reducer function on a list of new vectors:
dr[{{6, 7, 14}, {5, 6, 11}, {1, 3, 4}}]The vectors can also contain missing values:
dr[{{6, Missing[], 14}, {5, 6, Missing[]}, {Missing[], 3, 4}}]Generate a DimensionReducerFunction from a list of vectors:
dr = DimensionReduction[{{Missing[], 2, 3}, {2, 3, 5}, {3, Missing[], 8}, {4, 5, 8.5}}]Use this reducer function on a list of new vectors:
newvectors = {{6, 7, 14}, {5, 6, 11}, {1, 3, Missing[]}};reduced = dr[newvectors]Try to reconstruct the original vectors from the reduced ones:
dr[reduced, "OriginalVectors"]The reconstructed vectors can be directly obtained from the original vectors:
dr[newvectors, "ReconstructedVectors"]Generate a dimension reducer on a mixed-type dataset:
dr = DimensionReduction[{{1.4, "A"}, {1.5, "A"}, {2.3, "B"}, {5.4, "B"}}]Reduce the dimension of a new example:
dr[{2.4, "A"}]Scope (1)
Generate a DimensionReducerFunction from a list of vectors:
dr = DimensionReduction[{{1, 2, 3}, {2, 3, 5}, {3, 5, 8}, {4, 5, 8.5}}]Use the reducer function to impute missing values in other vectors:
newvectors = {{6, 7, Missing[]}, {5, Missing[], 11}};dr[newvectors, "ImputedVectors"]Text
Wolfram Research (2015), DimensionReducerFunction, Wolfram Language function, https://reference.wolfram.com/language/ref/DimensionReducerFunction.html (updated 2018).
CMS
Wolfram Language. 2015. "DimensionReducerFunction." Wolfram Language & System Documentation Center. Wolfram Research. Last Modified 2018. https://reference.wolfram.com/language/ref/DimensionReducerFunction.html.
APA
Wolfram Language. (2015). DimensionReducerFunction. Wolfram Language & System Documentation Center. Retrieved from https://reference.wolfram.com/language/ref/DimensionReducerFunction.html