Represents the linear function y = m * x + c.
Created by Jennifer Thompson on 3/17/16.
Created by Jennifer Thompson on 3/17/16.
Model that will replace null values in the input row with specified values.
Model that will replace null values in the input row with specified values.
Assumes replacement values are either numeric or string.
One hot encoding for a single feature.
One hot encoding for a single feature. The baseValue is encoded as all 0s to ensure a linear independence of the range.
values to be encoded as 1 at the corresponding index, 0s elsewhere.
value to be encoded as a vector as 0s.
Model to apply one-hot encoding to categorical input features.
Model to apply one-hot encoding to categorical input features. Result will be a sequence of 1s and 0s.
Model that creates output features that are polynomial combinations of the input features.
Model that creates output features that are polynomial combinations of the input features.
We use java.lang.Double for the type of the numeric values, because the scala Double type information is lost by scala/Gson and the deserialization fails badly for edge cases (e.g. Double.NaN).
If the exponents are a matrix
[[1,2,0], [0.5,3,2]]
Then the transformation of a row (x1, x2, x3) will be
(y1, y2) = (x1 * x2 pow 2, sqrt(x1) * x2 pow 3 * x3 pow 2).
Interface for real-valued functions (functions that map the real (double) numbers to real (double) numbers) to be used in RealValuedFunctionsModel
Added in SDK 1.9 (Alpine-Chorus 6.3).
Added in SDK 1.9 (Alpine-Chorus 6.3).
This is like the unit model, except that it takes a list of names to be used for the output features. It passes along the content of its input as output.
Created by Jennifer Thompson on 1/5/17.
Applies One-hot encoding for a single feature.
Applies One-hot encoding for a single feature. e.g. if hotValues = Seq["apple", "raspberry"] baseValue = "orange"
apply("apple") = [1,0] apply("raspberry") = [0,1] apply("orange") = [0,0]
apply("banana") throws exception "banana is an unrecognised value".
case class wrapping hot values and base values.
Represents the linear function y = m * x + c. Can be constructed out of Add and Multiply functions, but included for convenience.
Added in SDK 1.9 (Alpine-Chorus 6.3).
multiplier
constant offset