decision_tree: Decision Tree

In stschn/deepANN: Neural Network Toolbox

Decision Tree

Description

Decision Tree

Usage

decision_tree(object, ...)

## S3 method for class 'formula'
decision_tree(formula, data, maxdepth = 100L, ...)

treeheight(node)

treedepth(node)

## Default S3 method:
decision_tree(x, y, maxdepth = 100L, ...)

is.decisiontree(object)

Arguments

object	R object.
...	Optional arguments.
formula	A model formula.
data	A data frame, containing the variables in formula. Neither a matrix nor an array will be accepted.
maxdepth	The maximum depth of the resulting tree. If this value, default 100, is reached, the algorithm will stop.
x	A matrix or data frame with feature values.
y	A factor variable with categorical values for x.

Details

A decision tree is a type of model that puts a certain feature from x onto a node, called split node, of the tree structure on the basis of operations (e.g. gini impurity, information gain) and also uses a calculated value of the feature for each node for further separations into left and right subnodes. At the end of the tree are the leaf nodes, each of which has a resulting level of y.
treeheight() computes the height of a tree. The height of a tree is the number of nodes from the starting node on the path to its deepest leaf node.
treedepth() computes the depth of a tree. The depth of a tree is the number of edges or arcs from the starting node on the path to its deepest leaf node.

Value

A list from class decisiontree with split nodes and leaf nodes.

See Also

Other Machine Learning: cross_validation_split(), k_nearest_neighbors(), moving_average(), naive_bayes(), naive_forecast(), predict.decisiontree(), predict.kmeans(), predict.naivebayes()

Examples

  df <- data.frame(Outlook = factor(c("Sunny", "Sunny", "Overcast", "Rain", "Rain", "Rain", "Overcast", "Sunny", "Sunny", "Rain", "Sunny", "Overcast", "Overcast", "Rain")),
                   Temperature = factor(c("Hot", "Hot", "Hot", "Mild", "Cool", "Cool", "Cool", "Mild", "Cool", "Mild", "Mild", "Mild", "Hot", "Mild")),
                   Humidity = factor(c("High", "High", "High", "High", "Normal", "Normal", "Normal", "High", "Normal", "Normal", "Normal", "High", "Normal", "High")),
                   Wind = factor(c("Weak", "Strong", "Weak", "Weak", "Weak", "Strong", "Strong", "Weak", "Weak", "Weak", "Strong", "Strong", "Weak", "Strong")),
                   PlayTennis = factor(c("No", "No", "Yes", "Yes", "Yes", "No", "Yes", "No", "Yes", "Yes", "Yes", "Yes", "Yes", "No")))

  x <- df[, -5L]
  y <- df[[5L]]
  # Build up decision tree
  tree <- decision_tree(as.formula(PlayTennis ~ .), data = df)
  # Compute height and depth of the tree
  treeheight(tree); treedepth(tree)
  # Predict labels of the features
  yhat <- predict(tree, x)
  accuracy(y, yhat)

stschn/deepANN documentation built on June 25, 2024, 7:27 a.m.