Ignore data/ folder
[agghoo.git] / R / R6_Model.R
CommitLineData
c5946158
BA
1#' @title R6 class representing a (generic) model.
2#'
3#' @description
4#' "Model" class, containing a (generic) learning function, which from
5#' data + target [+ params] returns a prediction function X --> y.
6#' Parameters for cross-validation are either provided or estimated.
7#' Model family can be chosen among "rf", "tree", "ppr" and "knn" for now.
8#'
d9a139b5
BA
9#' @importFrom FNN knn.reg
10#' @importFrom class knn
11#' @importFrom stats ppr
12#' @importFrom randomForest randomForest
13#' @importFrom rpart rpart
14#' @importFrom caret var_seq
15#'
c5946158
BA
16#' @export
17Model <- R6::R6Class("Model",
18 public = list(
19 #' @field nmodels Number of parameters (= number of [predictive] models)
20 nmodels = NA,
21 #' @description Create a new generic model.
22 #' @param data Matrix or data.frame
23 #' @param target Vector of targets (generally numeric or factor)
24 #' @param task "regression" or "classification"
25 #' @param gmodel Generic model returning a predictive function; chosen
26 #' automatically given data and target nature if not provided.
27 #' @param params List of parameters for cross-validation (each defining a model)
d9a139b5
BA
28 initialize = function(data, target, task, gmodel = NULL, params = NULL) {
29 if (is.null(gmodel)) {
c5946158
BA
30 # (Generic) model not provided
31 all_numeric <- is.numeric(as.matrix(data))
32 if (!all_numeric)
33 # At least one non-numeric column: use random forests or trees
34 # TODO: 4 = arbitrary magic number...
35 gmodel = ifelse(ncol(data) >= 4, "rf", "tree")
36 else
37 # Numerical data
38 gmodel = ifelse(task == "regression", "ppr", "knn")
39 }
d9a139b5 40 if (is.null(params))
c5946158
BA
41 # Here, gmodel is a string (= its family),
42 # because a custom model must be given with its parameters.
43 params <- as.list(private$getParams(gmodel, data, target))
44 private$params <- params
45 if (is.character(gmodel))
46 gmodel <- private$getGmodel(gmodel, task)
47 private$gmodel <- gmodel
48 self$nmodels <- length(private$params)
49 },
50 #' @description
51 #' Returns the model at index "index", trained on dataHO/targetHO.
52 #' index is between 1 and self$nmodels.
53 #' @param dataHO Matrix or data.frame
54 #' @param targetHO Vector of targets (generally numeric or factor)
55 #' @param index Index of the model in 1...nmodels
56 get = function(dataHO, targetHO, index) {
57 private$gmodel(dataHO, targetHO, private$params[[index]])
58 }
59 ),
60 private = list(
61 # No need to expose model or parameters list
d9a139b5
BA
62 gmodel = NULL,
63 params = NULL,
c5946158
BA
64 # Main function: given a family, return a generic model, which in turn
65 # will output a predictive model from data + target + params.
66 getGmodel = function(family, task) {
67 if (family == "tree") {
68 function(dataHO, targetHO, param) {
69 require(rpart)
70 method <- ifelse(task == "classification", "class", "anova")
71 df <- data.frame(cbind(dataHO, target=targetHO))
d9a139b5 72 model <- rpart::rpart(target ~ ., df, method=method, control=list(cp=param))
c5946158
BA
73 function(X) predict(model, X)
74 }
75 }
76 else if (family == "rf") {
77 function(dataHO, targetHO, param) {
78 require(randomForest)
79 if (task == "classification" && !is.factor(targetHO))
80 targetHO <- as.factor(targetHO)
81 model <- randomForest::randomForest(dataHO, targetHO, mtry=param)
82 function(X) predict(model, X)
83 }
84 }
85 else if (family == "ppr") {
86 function(dataHO, targetHO, param) {
87 model <- stats::ppr(dataHO, targetHO, nterms=param)
88 function(X) predict(model, X)
89 }
90 }
91 else if (family == "knn") {
d9a139b5
BA
92 if (task == "classification") {
93 function(dataHO, targetHO, param) {
94 require(class)
95 function(X) class::knn(dataHO, X, cl=targetHO, k=param)
96 }
97 }
98 else {
99 function(dataHO, targetHO, param) {
100 require(FNN)
101 function(X) FNN::knn.reg(dataHO, X, y=targetHO, k=param)$pred
102 }
c5946158
BA
103 }
104 }
105 },
106 # Return a default list of parameters, given a gmodel family
107 getParams = function(family, data, target) {
108 if (family == "tree") {
109 # Run rpart once to obtain a CV grid for parameter cp
110 require(rpart)
111 df <- data.frame(cbind(data, target=target))
112 ctrl <- list(
113 minsplit = 2,
114 minbucket = 1,
115 maxcompete = 0,
116 maxsurrogate = 0,
117 usesurrogate = 0,
118 xval = 0,
119 surrogatestyle = 0,
120 maxdepth = 30)
121 r <- rpart(target ~ ., df, method="class", control=ctrl)
122 cps <- r$cptable[-1,1]
123 if (length(cps) <= 11)
124 return (cps)
125 step <- (length(cps) - 1) / 10
126 cps[unique(round(seq(1, length(cps), step)))]
127 }
128 else if (family == "rf") {
129 p <- ncol(data)
130 # Use caret package to obtain the CV grid of mtry values
131 require(caret)
132 caret::var_seq(p, classification = (task == "classificaton"),
133 len = min(10, p-1))
134 }
135 else if (family == "ppr")
136 # This is nterms in ppr() function
137 1:10
138 else if (family == "knn") {
139 n <- nrow(data)
140 # Choose ~10 NN values
141 K <- length(unique(target))
142 if (n <= 10)
143 return (1:(n-1))
144 sqrt_n <- sqrt(n)
145 step <- (2*sqrt_n - 1) / 10
146 grid <- unique(round(seq(1, 2*sqrt_n, step)))
147 if (K == 2) {
148 # Common binary classification case: odd number of neighbors
149 for (i in 2:11) {
150 if (grid[i] %% 2 == 0)
151 grid[i] <- grid[i] + 1 #arbitrary choice
152 }
153 }
154 grid
155 }
156 }
157 )
158)