Playing with smile and california housing dataset / published by https://github.com/dacr/code-examples-manager #a532819f-03fb-429b-90b2-02babad00863/f2245ae45258e1b0f870e0008e4128981166b83f

cal_housing.sc

// summary : Playing with smile and california housing dataset
// keywords : smile, machine-learning, cal_housing, ai, @testable
// publish : gist
// authors : David Crosson
// license : Apache NON-AI License Version 2.0 (https://raw.githubusercontent.com/non-ai-licenses/non-ai-licenses/main/NON-AI-APACHE2)
// id : a532819f-03fb-429b-90b2-02babad00863
// created-on : 2021-03-05T09:23:01Z
// managed-by : https://github.com/dacr/code-examples-manager
// execution : scala ammonite script (http://ammonite.io/) - run as follow 'amm scriptname.sc'

// run-with : scala-cli $file

// ---------------------
//> using scala "3.4.2"
//> using dep "com.github.pathikrit::better-files:3.9.2"
//> using dep "com.github.haifengl::smile-scala:3.1.1"
//> using dep "org.bytedeco:javacpp-platform:1.5.10"
//> using dep "org.bytedeco:javacpp:1.5.10,classifier=linux-x86_64"
//> using dep "org.bytedeco:arpack-ng:3.9.1-1.5.10,classifier=linux-x86_64"
//> using dep "org.bytedeco:openblas:0.3.26-1.5.10,classifier=linux-x86_64"
//> using dep "org.slf4j:slf4j-nop:2.0.13"
//> using dep "com.lihaoyi::requests:0.9.0"
// ---------------------

import better.files.*
import scala.language.postfixOps
import smile.*
import smile.util.*
import smile.math.*
import smile.math.MathEx.*
import smile.math.distance.*
import smile.data.formula.*
import smile.regression.OLS


//import smile.plot.vega.* // FOR VEGA RENDERING
import smile.plot.swing.* // FOR SWING RENDERING
import smile.plot.show

// =====================================================================
// Normalize input data in the same way as for python

/*
 datasets :
 * http://lib.stat.cmu.edu/datasets/

 used dataset :
 * original data : https://www.dcc.fc.up.pt/~ltorgo/Regression/cal_housing.tgz
   + with some adaptations :
     - https://github.com/scikit-learn/scikit-learn/blob/95d4f0841/sklearn/datasets/_california_housing.py#L51
     - CaliforniaHousing/cal_housing.data
 * https://github.com/crhodes2/Get-Rich/blob/master/tensorflow/Lib/site-packages/sklearn/datasets/descr/california_housing.rst
*/


val infile=file"cal_housing.data"
if (infile.notExists) {
  val url = "https://gist.githubusercontent.com/dacr/4dd9b6cf55154559684f96aeeed33f64/raw/68989aefc9c483601439aeb4e8a0c49b8e2de0db/cal_housing.data"
  for {out <- infile.newOutputStream.autoClosed} {requests.get(url).writeBytesTo(out)}
}

val outfile=file"cal_housing.csv"
if (!outfile.exists) {
  val columnsIndex = List(8, 7, 2, 3, 4, 5, 6, 1, 0)
  val featureNames = List("Price", "MedInc", "HouseAge", "AveRooms", "AveBedrms", "Population", "AveOccup", "Latitude", "Longitude")
  val it =
    infile
      .lineIterator
      .map{_.split(",")}
      .map{a => columnsIndex.map(i => a(i).toDouble)}
      .map{
        case List(ct,c0,c1,c2,c3,c4,c5,c6,c7) =>
          List(ct/100000d,c0, c1, c2/c5, c3/c5, c4, c4/c5, c6, c7)
      }
  outfile.append(featureNames.mkString(",")).append("\n")
  it.foreach{ a => outfile.append(a.mkString(",")).append("\n") }
}

// =====================================================================
// SMILE PART - using linear regression

val houses = read.csv("cal_housing.csv")
val model = OLS.fit("Price".~(), houses)

println(model)

val tuple = houses(0)
val predicted = model.predict(tuple)
println(s"predicted : $predicted")
// TODO - to be continued...