KNN - Lua

knn.lua

-- Vamos guardar as nossas features
X={}
-- Petal length
X[1]={1.4,1.4,1.3,1.5,1.4,1.7,1.4,1.5,1.4,1.5,1.5,1.6,1.4,1.1,1.2,1.5,1.3,1.4,1.7,1.5,1.7,1.5,1.0,1.7,1.9,1.6,1.6,1.5,1.4,1.6,1.6,1.5,1.5,1.4,1.5,1.2,1.3,1.4,1.3,1.5,1.3,1.3,1.3,1.6,1.9,1.4,1.6,1.4,1.5,1.4,4.7,4.5,4.9,4.0,4.6,4.5,4.7,3.3,4.6,3.9,3.5,4.2,4.0,4.7,3.6,4.4,4.5,4.1,4.5,3.9,4.8,4.0,4.9,4.7,4.3,4.4,4.8,5.0,4.5,3.5,3.8,3.7,3.9,5.1,4.5,4.5,4.7,4.4,4.1,4.0,4.4,4.6,4.0,3.3,4.2,4.2,4.2,4.3,3.0,4.1,6.0,5.1,5.9,5.6,5.8,6.6,4.5,6.3,5.8,6.1,5.1,5.3,5.5,5.0,5.1,5.3,5.5,6.7,6.9,5.0,5.7,4.9,6.7,4.9,5.7,6.0,4.8,4.9,5.6,5.8,6.1,6.4,5.6,5.1,5.6,6.1,5.6,5.5,4.8,5.4,5.6,5.1,5.1,5.9,5.7,5.2,5.0,5.2,5.4,5.1}
-- Petal width
X[2]={0.2,0.2,0.2,0.2,0.2,0.4,0.3,0.2,0.2,0.1,0.2,0.2,0.1,0.1,0.2,0.4,0.4,0.3,0.3,0.3,0.2,0.4,0.2,0.5,0.2,0.2,0.4,0.2,0.2,0.2,0.2,0.4,0.1,0.2,0.2,0.2,0.2,0.1,0.2,0.2,0.3,0.3,0.2,0.6,0.4,0.3,0.2,0.2,0.2,0.2,1.4,1.5,1.5,1.3,1.5,1.3,1.6,1.0,1.3,1.4,1.0,1.5,1.0,1.4,1.3,1.4,1.5,1.0,1.5,1.1,1.8,1.3,1.5,1.2,1.3,1.4,1.4,1.7,1.5,1.0,1.1,1.0,1.2,1.6,1.5,1.6,1.5,1.3,1.3,1.3,1.2,1.4,1.2,1.0,1.3,1.2,1.3,1.3,1.1,1.3,2.5,1.9,2.1,1.8,2.2,2.1,1.7,1.8,1.8,2.5,2.0,1.9,2.1,2.0,2.4,2.3,1.8,2.2,2.3,1.5,2.3,2.0,2.0,1.8,2.1,1.8,1.8,1.8,2.1,1.6,1.9,2.0,2.2,1.5,1.4,2.3,2.4,1.8,1.8,2.1,2.4,2.3,1.9,2.3,2.5,2.3,1.9,2.0,2.3,1.8}

-- Guardando os nossas target values (species): 0 = setosa, 1 = versicolor, 2 = virginica
Y={0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2}

-- Vamos fazer o nosso modelo
model = {
    ['test'] = {},
    ['train'] = {},
    ['split'] = 20, -- Definimos em quantos % vamos fazer 'split' no nosso modelo,
    ["k"] = 7
}

function split(X, Y, model)
    local splitOnI = #Y * ((100 - model.split) / 100)
    local testI = 0

    for i in pairs(Y) do
        local tableLocation = 'train'
        local currentI = i

        if i >= splitOnI then
            currentI = (i - #model.train)
            tableLocation = 'test'
        end

        model[tableLocation][currentI] = {
            ['label'] = Y[i],
            ['coord'] = {}
        }

        for k in pairs(X) do
            table.insert(model[tableLocation][currentI]['coord'], X[k][i])
        end
    end

    return model
end

function value_to_label(value)
    if value == 0 then
        return 'setosa'
    elseif value == 1 then
        return 'versicolor'
    end

    return 'virginica'
end

function KNN_predict(input, model)
    local distances = {}
    local predicted = 0

    for i in pairs(model.train) do
        local currentDistance = 0
        local coords = model.train[i]['coord']

        for _,v in pairs(input) do
            currentDistance = currentDistance + ((v - coords[_]) * (v - coords[_]))
        end

        currentDistance = math.sqrt(currentDistance)

        table.insert(distances, {
            ['value'] = currentDistance,
            ['label'] = model.train[i]['label']
        })
    end

    table.sort(distances, function(a, b) return a.value < b.value end)

    local knn = {}

    for i = 1,model.k do
        if knn[distances[i].label] then
            knn[distances[i].label] = knn[distances[i].label] + 1
        else
            knn[distances[i].label] = 1
        end
    end

    local knnMax = -1
    local index = 1
    for i in pairs(knn) do
        if knn[i] > knnMax then
            knnMax = knn[i]
            index = i
        end
    end

    return index
end

function KNN_score(inputs, model)
    local tries = #inputs
    local correntPredictions = 0

    for i,v in pairs(inputs) do
        local predictedValue = KNN_predict(v.coord, model)

        print(predictedValue, v.label)

        if predictedValue == v.label then
            correntPredictions = correntPredictions + 1
        end
    end

    return correntPredictions / tries
end

model = split(X, Y, model)

toPredict = {1.4, 0.2}
print('Predição de {1.4, 0.2}: ' .. KNN_predict(toPredict, model) .. '')
print('Acurácia do modelo: ' .. KNN_score(model.test, model))