| Version: | 0.1.5 |
| Date: | 2023-09-03 |
| Title: | Machine Learning Algorithms Fitting and Validation for Forestry |
| Description: | Fitting and validation of machine learning algorithms for volume prediction of trees, currently for conifer trees based on diameter at breast height and height as explanatory variables. |
| Depends: | R (≥ 4.1.0) |
| Imports: | stats (≥ 4.1.0), dplyr (≥ 1.1.2), rpart (≥ 4.1.19), caret (≥ 6.0-94), randomForest(≥ 4.7-1.1), e1071 (≥ 1.7-13), ggplot2 (≥ 3.4.2), rlang (≥ 1.1.1) |
| Maintainer: | Salvatore Mangiafico <mangiafico@njaes.rutgers.edu> |
| License: | GPL-3 |
| Encoding: | UTF-8 |
| LazyData: | true |
| RoxygenNote: | 7.2.3 |
| NeedsCompilation: | no |
| Packaged: | 2023-09-05 18:28:48 UTC; salva |
| Author: | M. Iqbal Jeelani [aut], Salvatore Mangiafico [aut, cre] |
| Repository: | CRAN |
| Date/Publication: | 2023-09-06 16:50:07 UTC |
Volume, height, and diameter of 300 pine trees in East Circle Jammu
Description
A data frame consisting of diameter (cm), height (m), and volume (m3) for 300 pine trees in East Circle, Jammu, Jammu and Kashmir Forest Department.
Usage
EastCirclePine
Format
An object of class data.frame with 300 rows and 3 columns.
Tree volume models based on height and diameter
Description
Decision tree, random forest, support vector machine, and linear models for fitting tree volume to height and diameter.
Usage
ImML(data, plotit = TRUE, setseed = NULL, verbose = FALSE, ...)
Arguments
data |
The data frame to use.
Must contain the numeric variables
|
plotit |
If |
setseed |
If not |
verbose |
If |
... |
Additional arguments, currently not used. |
Details
Calculates mean absolute error, root mean square error, root relative squared error, and prediction error rate for train and test partitions of a data frame using decision tree, random forest, support vector machine, and linear models for fitting tree volume to height and diameter.
Value
A data frame consisting of mean absolute error, root mean square error, root relative squared error, and prediction error rate for train and test partitions using decision tree, random forest, support vector machine, and linear model.
Note
The data frame must contain the numeric variables
Volume, Height, and Diameter.
Volume is used as the dependent variable.
The gray line in the plot is a 1:1 line.
Author(s)
M. Iqbal Jeelani, jeelani.miqbal@gmail.com, Salvatore Mangiafico, mangiafico@njaes.rutgers.edu
References
Jeelani, M.I., Tabassum, A., Rather, K and Gul,M.2023. Neural Network Modeling of Height Diameter Relationships for Himalayan Pine through Back Propagation Approach. Journal of The Indian Society of Agricultural Statistics. 76(3): 169–178.
Examples
data(EastCirclePine)
ImML(EastCirclePine, plotit=FALSE, setseed=123)