rf = import('https://cdn.skypack.dev/ml-random-forest@2.1.0?min')
trainingSet = formattedData.map((d) => d.slice(0, 5));
predictions = formattedData.map((d) => d[5])
options = ({
seed: 3,
maxFeatures: 5,
replacement: false,
nEstimators: 100
})
regression = new rf.RandomForestRegression(options)
a = await regression.train(trainingSet, predictions);
result3 = a, regression.predict([[numericData[0],numericData[1],numericData[2],125,numericData[3]]]);
numericData[3]
viewof endofLife = Inputs.select([null].concat("Landfill","Recycle","Reuse"), {label: "End of Life"})
viewof pctRecovered = Inputs.select(["0%","50%","100%"], {label: "Percent Recovered"})
viewof dist = Inputs.range([100, 1000], {step: 1, label: "Distance Traveled"})
viewof quant = Inputs.range([100, 1000], {step: 1, label: "Quantity"})
viewof set = Inputs.button("Set Data")
viewof dist.value
numericData = {
var data =[]
var eol
var rcvrd
var distance
var quantity
if(viewof endofLife.value=="Landfill"){eol = 1}
if(viewof endofLife.value=="Recycle"){eol = 2}
if(viewof endofLife.value=="Reuse"){eol = 3}
if(viewof pctRecovered.value=="0%"){rcvrd = 1}
if(viewof pctRecovered.value=="50%"){rcvrd = 2}
if(viewof pctRecovered.value=="100%"){rcvrd = 3}
distance = viewof dist.value
quantity = viewof quant.value
data.push(quantity)
data.push(rcvrd)
data.push(distance)
data.push(eol)
data.push(set)
return data
}
a, regression.featureImportance()
a, regression.toJSON()
Glass- Systems Protypting - Sheet1@1.csv
Type Table, then Shift-Enter. Ctrl-space for more options.
spMaterialsForMachineLearningSheet3
fullDataSet = {
return spMaterialsForMachineLearningSheet3
}
formattedData = {
var fullSet = []
for (let i = 0; i < fullDataSet.length; i++) {
var currentLine = [Number(fullDataSet[i].col1),Number(fullDataSet[i].col2),Number(fullDataSet[i].col3),Number(fullDataSet[i].col4),Number(fullDataSet[i].col5),Number(fullDataSet[i].result)]
fullSet.push(currentLine)
}
return fullSet
}
One platform to build and deploy the best data apps
Experiment and prototype by building visualizations in live JavaScript notebooks. Collaborate with your team and decide which concepts to build out.
Use Observable Framework to build data apps locally. Use data loaders to build in any language or library, including Python, SQL, and R.
Seamlessly deploy to Observable. Test before you ship, use automatic deploy-on-commit, and ensure your projects are always up-to-date.