make_feature_from_data_frame: Create a feature vector for a classifier from a data frame

In fosterlab/PrInCE-R: Predicting Interactomes from Co-Elution

Description

Convert a data frame containing pairwise interactions, and a score or other data associated with each interaction, into a feature vector that matches the dimensions of a data frame used as input to a classifier, such as a naive Bayes, random forests, or support vector machine classifier.

Usage

make_feature_from_data_frame(
  dat,
  target,
  dat_node_cols = c(1, 2),
  target_node_cols = c(1, 2),
  feature_col = 3,
  default_value = NA
)

Arguments

dat	a data frame containing pairwise interactions and a feature to be converted to a vector in a third column
target	the data frame of features that will be provided as input to a classifier
dat_node_cols	a vector of length two, denoting either the indices (integer vector) or column names (character vector) of the columns within the feature data frame; defaults to the first two columns of the data frame (c(1, 2))
target_node_cols	a vector of length two, denoting either the indices (integer vector) or column names (character vector) of the columns within the target data frame; defaults to the first two columns of the data frame (c(1, 2))
feature_col	the name or index of the column in the first data frame that contains a feature for each interaction
default_value	the default value for protein pairs that are not in the first data frame (set, by default, to NA)

Value

a vector matching the dimensions and order of the feature data frame, to use as input for a classifier in interaction prediction

fosterlab/PrInCE-R documentation built on Dec. 11, 2020, 3:51 p.m.