decision-tree | Based on decision tree | Rule Engine library

Introduction

I'm learning the basics of AI. I have created a .csv file with random data to test Decision Trees. I'm currently using R in Jupyther Notebook.

Problem

Temperature, Humidity and Wind are the variables which determine if you are allowed to fly or not.

When I execute ctree(vuelo~., data=vuelo.csv) the output it's just a single node when I was expecting a full tree with the variables (Temperatura, Humdedad, Viento), as I resolved on paper.

Snippet of the result

The data used is the next table:

My company's main page doesn't have a H1 and having content order in mind the best solution would be having the logo encapsuled inside the heading, although not ideal, it should be acceptable. Here's the code I have so far:

While viewing this question scikit learn - feature importance calculation in decision trees, I have trouble understanding the value list of the Decision Tree. For example, the top node has value=[1,3]. What exactly are 1 and 3? Does it mean if X[2]<= 0.5, then 1 false, 3 true? If so, the value list is [number of false cases, number of true cases]. If so, what about the value lists of the leaves?

1. Why do three right leaves have [0,1] and one left leaf has [1,0]?
2. What does [1,0] or [0,1] mean anyway? One false zero true or zero false one true? But there's no condition on the leaves (like something <=.5). Then what is true what is false?

Your advice is highly appreciated!

I have been using this tutorial to learn decision tree learning, and am now trying to understand how it works with higher dimensional datasets.

Currently my regressor predicts a Z value for an (x,y) pair that you pass to it.

In this tutorial, I tried to use another method for converting categorical variables to factor.

In the article, the following method is used.

Overview

I am following a tutorial (see below) to find the best fit models from bagged trees, random forests, boosted trees, and general linear models.

Tutorial (see examples below)

https://bcullen.rbind.io/post/2020-06-02-tidymodels-decision-tree-learning-in-r/

Issue

In this case, I would like to explore the data further and visualise the most important predictors (see diagram below) for my data in the random forest model.

My data frame is called FID and the predictors in the random forest model involve:

1. Year (numeric)
2. Month (Factor)
3. Days (numeric)

The dependent variable is Frequency (numeric)

When I try to run the plot to visualise the most important predictor, I keep on getting this error message:-

Overview:

I am following a tutorial (see below) to find the best fit models from bagged trees, random forests, boosted trees and general linear models.

Tutorial (see examples below)

https://bcullen.rbind.io/post/2020-06-02-tidymodels-decision-tree-learning-in-r/

Issue

In this case, I would like to explore the data further and visualise the most important predictors (see diagram below) for my data.

My data frame is called FID and the predictors in the bagged tree model involve:

1. Year (numeric)
2. Month (Factor)
3. Days (numeric)

The dependent variable is Frequency (numeric)

When I try to run the plot to visualise the most important predictor, I keep on getting this error message:-

Error Message

Issue

I am attempting to undertake an analysis using the Tidymodels Package in R. I am following this tutorial below regarding decision tree learning in R:-

Tutorial

https://bcullen.rbind.io/post/2020-06-02-tidymodels-decision-tree-learning-in-r/

I have a data frame called FID (see below) where the dependent variable is the frequency (numeric), and the predictor variables are:- Year (numeric), Month (factor), Monsoon (factor), and Days (numeric).

I believe I have successfully followed the tutorial named "Tidymodels: Decision Tree Learning in R" by building a bagged tree, random forest, and boosted tree model.

For this analysis, I would also like to construct a general linear model (glm) in order to make model comparisons between all models (i.e the random forest, bagged tree, boosted tree, and general linear models) to establish the best model fit. All models are subject to 10-fold cross-validation to decrease the bias of overfitting.

Problem

Subsequently, I have attempted to adapt the code (please see below) from the tutorial to fit a glm model, but I am confused whether I have tuned the model appropriately. I am unsure if this element of glm R-code is producing the error message below when I am attempting to produce the rmse values after the models have all been fit:-

Error message