NEWS.md
In LearnSL: Learn Supervised Classification Methods Through Examples and Code

LearnSL 1.0.0

New decission_tree() function to create a perfect decision tree based on a set of observations and (if selected) see the step-by-step procedure;
New multivariate_linear_regression() function to generate linear equation lines that approximate the values on a set of observations and (if selected) see the step-by-step procedure;
New polynomial_regression() function to generate polynomial equation lines that approximate the values on a set of observations to selected degree and (if selected) see the step-by-step procedure;
New perceptron() function to calculate the weights of a perceptron and predict values on a set of observations and (if selected) see the step-by-step procedure;
New knn() function to perform k-nearest neighbors classification on a set of observations and (if selected) see the step-by-step procedure;
New print.tree_struct() function that prints a tree with the structure of the output of the decision_tree() function;
New act_method() function that calculates the selected activation function to a given input;
New db1rl data.frame with 20 observations (4 features). Values form different types of lines (linear, exponential, logarithmic, sine);
New db_per_and data.frame with 8 observations (2 features). "AND" logic gate;
New db_per_or data.frame with 8 observations (2 features). "OR" logic gate;
New db_per_xor data.frame with 8 observations (2 features). "XOR" logic gate;
New db_flowers data.frame with 25 observations (4 features) containing values about flowers;
New db2 data.frame with 10 observations (4 features) containing values about vehicles;
New db3 data.frame with 12 observations (5 features) containing values about vehicles.
New db_tree_struct data.frame with 12 observations (5 features) containing values about vehicles.
Initial CRAN submission.