In [1]:

# DAL ToolBox
# version 1.1.727

source("https://raw.githubusercontent.com/cefet-rj-dal/daltoolbox/main/jupyter.R")

#loading DAL
load_library("daltoolbox")

Loading required package: daltoolbox

Registered S3 method overwritten by 'quantmod':
  method            from
  as.zoo.data.frame zoo 


Attaching package: ‘daltoolbox’


The following object is masked from ‘package:base’:

    transform

Classification¶

In [2]:

iris <- datasets::iris
head(iris)

A data.frame: 6 × 5
	Sepal.Length	Sepal.Width	Petal.Length	Petal.Width	Species
	<dbl>	<dbl>	<dbl>	<dbl>	<fct>
1	5.1	3.5	1.4	0.2	setosa
2	4.9	3.0	1.4	0.2	setosa
3	4.7	3.2	1.3	0.2	setosa
4	4.6	3.1	1.5	0.2	setosa
5	5.0	3.6	1.4	0.2	setosa
6	5.4	3.9	1.7	0.4	setosa

In [3]:

#extracting the levels for the dataset
slevels <- levels(iris$Species)
slevels

'setosa'
'versicolor'
'virginica'

Building samples (training and testing)¶

In [4]:

# preparing dataset for random sampling
set.seed(1)
sr <- sample_random()
sr <- train_test(sr, iris)
iris_train <- sr$train
iris_test <- sr$test

In [5]:

tbl <- rbind(table(iris[,"Species"]), 
             table(iris_train[,"Species"]), 
             table(iris_test[,"Species"]))
rownames(tbl) <- c("dataset", "training", "test")
head(tbl)

A matrix: 3 × 3 of type int
	setosa	versicolor	virginica
dataset	50	50	50
training	39	38	43
test	11	12	7

Model training¶

In [6]:

model <- cla_majority("Species", slevels)
model <- fit(model, iris_train)
train_prediction <- predict(model, iris_train)

Model adjustement¶

In [7]:

iris_train_predictand <- adjust_class_label(iris_train[,"Species"])
train_eval <- evaluate(model, iris_train_predictand, train_prediction)
print(train_eval$metrics)

   accuracy TP TN FP FN precision recall sensitivity specificity  f1
1 0.3583333  0 81  0 39       NaN      0           0           1 NaN

Model testing¶

In [8]:

# Test  
test_prediction <- predict(model, iris_test)
  
iris_test_predictand <- adjust_class_label(iris_test[,"Species"])
test_eval <- evaluate(model, iris_test_predictand, test_prediction)
print(test_eval$metrics)

   accuracy TP TN FP FN precision recall sensitivity specificity  f1
1 0.2333333  0 19  0 11       NaN      0           0           1 NaN

In [ ]: