Most of the working based on Random Forest is to achieve regression or classification tasks without clearifing the underlying structure of trees that make up the forest. However, is there a way to derive the summarized or balanced unique tree structure to represent the whole batch of decision trees without minimizing the effectiveness and generalizing ability?
Dear Zixuan Zhou :
Random forest is a great algorithm to train early in the model development process, to see how it performs. Its simplicity makes building a “bad” random forest a tough proposition. The algorithm is also a great choice for anyone who needs to develop a model quickly. On top of that, it provides a pretty good indicator of the importance it assigns to your features.
Random forests are also very hard to beat performance-wise. Of course, you can probably always find a model that can perform better, like a neural network for example, but these usually take more time to develop, though they can handle a lot of different feature types, like binary, categorical and numerical.
Overall, random forest is a (mostly) fast, simple and flexible tool, but not without some limitations. Please have look at these below-mentioned links:
- https://www.analyticsvidhya.com/blog/2020/05/decision-tree-vs-random-forest-algorithm/
- https://builtin.com/data-science/random-forest-algorithm
- https://towardsdatascience.com/understanding-random-forest-58381e0602d2
Regards
Ehtisham
I have the same question. I'm studying the relation between primary productivity and an array of environmental variables (e.g. topoedaphic, irradiation), in a data set with obvious nonlinearities in NPP. Random forest gives me a basic tree structure (what variables branch when), but I want mean values at the branch points. Previously I've gone thru the laborious process of extracting a number of individual trees ("gettree" in RF), and averaging tree results for a given variable. But there must be a simpler way.
Dear Zixuan Zhou
Have a look at the following links :
- https://www.keboola.com/blog/random-forest-regression
- https://www.analyticsvidhya.com/blog/2020/05/decision-tree-vs-random-forest-algorithm
- https://builtin.com/data-science/random-forest-algorithm
All the best,
Samawel JABALLI
Random forest tree is a best algorithm. Random Forest is suitable for situations when we have a large dataset, and interpretability is not a major concern.
- Badges
- Science topic
- Similar topics
- Mathematics
- Statistics
- Sampling Design
- Sample Size