k-nearest-neighbors

README.md

@@ -2,14 +2,16 @@
 
 You don't need ~~Python~~ to train your own models and perform Machine Learning.
 
-This repository is linked to a series I have been writing about on Medium.com, regarding _ML in JS_. [Machine Learning with Javascript : Part 1](https://hackernoon.com/machine-learning-with-javascript-part-1-9b97f3ed4fe5)
+This repository is linked to a series I have been writing about on Medium.com, regarding _ML in JS_. 
+
+[Machine Learning with Javascript : Part 1](https://hackernoon.com/machine-learning-with-javascript-part-1-9b97f3ed4fe5)
 
 ## Repository Info
 
 The repository is organized as follows:
 
-1. **Linear Regression** has its own branch named `**linear-regression**`
-2. The upcoming tutorials will follow the same strategy.
+1. **Linear Regression** | [linear-regression](https://github.com/abhisheksoni27/machine-learning-with-js/tree/master/linear-regression)
+2. **k Nearest Neighbors** | [knn](https://github.com/abhisheksoni27/machine-learning-with-js/tree/master/knn)
 
 ## Get started
 

knn/README.md

@@ -0,0 +1,2 @@
+# k Nearest Neighbours
+For a walk through, please refer to the article on Medium. [Machine Learning with Javascript : Part 2 (k Nearest Neighbours)](https://hackernoon.com/machine-learning-with-javascript-part-1-9b97f3ed4fe5)

knn/index.js

@@ -0,0 +1,120 @@
+const KNN = require('ml-knn');
+const csv = require('csvtojson');
+const prompt = require('prompt');
+const knn = new KNN();
+
+const csvFilePath = 'iris.csv'; // Data
+const names = ['sepalLength', 'sepalWidth', 'petalLength', 'petalWidth', 'type']; // For header
+
+let seperationSize; // To seperate training and test data
+
+let data = [], X = [], y = [];
+
+let trainingSetX = [], trainingSetY = [], testSetX = [], testSetY = [];
+
+csv({noheader: true, headers: names})
+    .fromFile(csvFilePath)
+    .on('json', (jsonObj) => {
+        data.push(jsonObj); // Push each object to data Array
+    })
+    .on('done', (error) => {
+        seperationSize = 0.7 * data.length;
+        data = shuffleArray(data);
+        dressData();
+    });
+
+function dressData() {
+
+    /**
+     * There are three different types of Iris flowers
+     * that this dataset classifies.
+     *
+     * 1. Iris Setosa (Iris-setosa)
+     * 2. Iris Versicolor (Iris-versicolor)
+     * 3. Iris Virginica (Iris-virginica)
+     *
+     * We are going to change these classes from Strings to numbers.
+     * Such that, a value of type equal to
+     * 0 would mean setosa,
+     * 1 would mean versicolor, and
+     * 3 would mean virginica
+     */
+
+    let types = new Set(); // To gather UNIQUE classes
+
+    data.forEach((row) => {
+        types.add(row.type);
+    });
+
+    typesArray = [...types]; // To save the different types of classes.
+
+    data.forEach((row) => {
+        let rowArray, typeNumber;
+
+        rowArray = Object.keys(row).map(key => parseFloat(row[key])).slice(0, 4);
+
+        typeNumber = typesArray.indexOf(row.type); // Convert type(String) to type(Number)
+
+        X.push(rowArray);
+        y.push(typeNumber);
+    });
+
+    trainingSetX = X.slice(0, seperationSize);
+    trainingSetY = y.slice(0, seperationSize);
+    testSetX = X.slice(seperationSize);
+    testSetY = y.slice(seperationSize);
+
+    train();
+}
+
+function train() {
+    knn.train(trainingSetX, trainingSetY, { k:7 });
+    test();
+}
+
+function test() {
+    const result = knn.predict(testSetX);
+    const testSetLength = testSetX.length;
+    const predictionError = error(result, testSetY);
+    console.log(`Test Set Size = ${testSetLength} and number of Misclassifications = ${predictionError}`);
+    predict();
+}
+
+function error(predicted, expected) {
+    let misclassifications = 0;
+    for (var index = 0; index < predicted.length; index++) {
+        if (predicted[index] !== expected[index]) {
+            misclassifications++;
+        }
+    }
+    return misclassifications;
+}
+
+function predict() {
+    let temp = [];
+    prompt.start();
+
+    prompt.get(['Sepal Length', 'Sepal Width', 'Petal Length', 'Petal Width'], function (err, result) {
+        if (!err) {
+            for (var key in result) {
+                temp.push(parseFloat(result[key]));
+            }
+            console.log(`With ${temp} -- type =  ${knn.getSinglePrediction(temp)}`);
+        }
+    });
+}
+
+/**
+ * https://stackoverflow.com/a/12646864
+ * Randomize array element order in-place.
+ * Using Durstenfeld shuffle algorithm.
+ */
+function shuffleArray(array) {
+    for (var i = array.length - 1; i > 0; i--) {
+        var j = Math.floor(Math.random() * (i + 1));
+        var temp = array[i];
+        array[i] = array[j];
+        array[j] = temp;
+    }
+    return array;
+}

knn/iris.csv

@@ -0,0 +1,150 @@
+5.1,3.5,1.4,0.2,Iris-setosa
+4.9,3.0,1.4,0.2,Iris-setosa
+4.7,3.2,1.3,0.2,Iris-setosa
+4.6,3.1,1.5,0.2,Iris-setosa
+5.0,3.6,1.4,0.2,Iris-setosa
+5.4,3.9,1.7,0.4,Iris-setosa
+4.6,3.4,1.4,0.3,Iris-setosa
+5.0,3.4,1.5,0.2,Iris-setosa
+4.4,2.9,1.4,0.2,Iris-setosa
+4.9,3.1,1.5,0.1,Iris-setosa
+5.4,3.7,1.5,0.2,Iris-setosa
+4.8,3.4,1.6,0.2,Iris-setosa
+4.8,3.0,1.4,0.1,Iris-setosa
+4.3,3.0,1.1,0.1,Iris-setosa
+5.8,4.0,1.2,0.2,Iris-setosa
+5.7,4.4,1.5,0.4,Iris-setosa
+5.4,3.9,1.3,0.4,Iris-setosa
+5.1,3.5,1.4,0.3,Iris-setosa
+5.7,3.8,1.7,0.3,Iris-setosa
+5.1,3.8,1.5,0.3,Iris-setosa
+5.4,3.4,1.7,0.2,Iris-setosa
+5.1,3.7,1.5,0.4,Iris-setosa
+4.6,3.6,1.0,0.2,Iris-setosa
+5.1,3.3,1.7,0.5,Iris-setosa
+4.8,3.4,1.9,0.2,Iris-setosa
+5.0,3.0,1.6,0.2,Iris-setosa
+5.0,3.4,1.6,0.4,Iris-setosa
+5.2,3.5,1.5,0.2,Iris-setosa
+5.2,3.4,1.4,0.2,Iris-setosa
+4.7,3.2,1.6,0.2,Iris-setosa
+4.8,3.1,1.6,0.2,Iris-setosa
+5.4,3.4,1.5,0.4,Iris-setosa
+5.2,4.1,1.5,0.1,Iris-setosa
+5.5,4.2,1.4,0.2,Iris-setosa
+4.9,3.1,1.5,0.1,Iris-setosa
+5.0,3.2,1.2,0.2,Iris-setosa
+5.5,3.5,1.3,0.2,Iris-setosa
+4.9,3.1,1.5,0.1,Iris-setosa
+4.4,3.0,1.3,0.2,Iris-setosa
+5.1,3.4,1.5,0.2,Iris-setosa
+5.0,3.5,1.3,0.3,Iris-setosa
+4.5,2.3,1.3,0.3,Iris-setosa
+4.4,3.2,1.3,0.2,Iris-setosa
+5.0,3.5,1.6,0.6,Iris-setosa
+5.1,3.8,1.9,0.4,Iris-setosa
+4.8,3.0,1.4,0.3,Iris-setosa
+5.1,3.8,1.6,0.2,Iris-setosa
+4.6,3.2,1.4,0.2,Iris-setosa
+5.3,3.7,1.5,0.2,Iris-setosa
+5.0,3.3,1.4,0.2,Iris-setosa
+7.0,3.2,4.7,1.4,Iris-versicolor
+6.4,3.2,4.5,1.5,Iris-versicolor
+6.9,3.1,4.9,1.5,Iris-versicolor
+5.5,2.3,4.0,1.3,Iris-versicolor
+6.5,2.8,4.6,1.5,Iris-versicolor
+5.7,2.8,4.5,1.3,Iris-versicolor
+6.3,3.3,4.7,1.6,Iris-versicolor
+4.9,2.4,3.3,1.0,Iris-versicolor
+6.6,2.9,4.6,1.3,Iris-versicolor
+5.2,2.7,3.9,1.4,Iris-versicolor
+5.0,2.0,3.5,1.0,Iris-versicolor
+5.9,3.0,4.2,1.5,Iris-versicolor
+6.0,2.2,4.0,1.0,Iris-versicolor
+6.1,2.9,4.7,1.4,Iris-versicolor
+5.6,2.9,3.6,1.3,Iris-versicolor
+6.7,3.1,4.4,1.4,Iris-versicolor
+5.6,3.0,4.5,1.5,Iris-versicolor
+5.8,2.7,4.1,1.0,Iris-versicolor
+6.2,2.2,4.5,1.5,Iris-versicolor
+5.6,2.5,3.9,1.1,Iris-versicolor
+5.9,3.2,4.8,1.8,Iris-versicolor
+6.1,2.8,4.0,1.3,Iris-versicolor
+6.3,2.5,4.9,1.5,Iris-versicolor
+6.1,2.8,4.7,1.2,Iris-versicolor
+6.4,2.9,4.3,1.3,Iris-versicolor
+6.6,3.0,4.4,1.4,Iris-versicolor
+6.8,2.8,4.8,1.4,Iris-versicolor
+6.7,3.0,5.0,1.7,Iris-versicolor
+6.0,2.9,4.5,1.5,Iris-versicolor
+5.7,2.6,3.5,1.0,Iris-versicolor
+5.5,2.4,3.8,1.1,Iris-versicolor
+5.5,2.4,3.7,1.0,Iris-versicolor
+5.8,2.7,3.9,1.2,Iris-versicolor
+6.0,2.7,5.1,1.6,Iris-versicolor
+5.4,3.0,4.5,1.5,Iris-versicolor
+6.0,3.4,4.5,1.6,Iris-versicolor
+6.7,3.1,4.7,1.5,Iris-versicolor
+6.3,2.3,4.4,1.3,Iris-versicolor
+5.6,3.0,4.1,1.3,Iris-versicolor
+5.5,2.5,4.0,1.3,Iris-versicolor
+5.5,2.6,4.4,1.2,Iris-versicolor
+6.1,3.0,4.6,1.4,Iris-versicolor
+5.8,2.6,4.0,1.2,Iris-versicolor
+5.0,2.3,3.3,1.0,Iris-versicolor
+5.6,2.7,4.2,1.3,Iris-versicolor
+5.7,3.0,4.2,1.2,Iris-versicolor
+5.7,2.9,4.2,1.3,Iris-versicolor
+6.2,2.9,4.3,1.3,Iris-versicolor
+5.1,2.5,3.0,1.1,Iris-versicolor
+5.7,2.8,4.1,1.3,Iris-versicolor
+6.3,3.3,6.0,2.5,Iris-virginica
+5.8,2.7,5.1,1.9,Iris-virginica
+7.1,3.0,5.9,2.1,Iris-virginica
+6.3,2.9,5.6,1.8,Iris-virginica
+6.5,3.0,5.8,2.2,Iris-virginica
+7.6,3.0,6.6,2.1,Iris-virginica
+4.9,2.5,4.5,1.7,Iris-virginica
+7.3,2.9,6.3,1.8,Iris-virginica
+6.7,2.5,5.8,1.8,Iris-virginica
+7.2,3.6,6.1,2.5,Iris-virginica
+6.5,3.2,5.1,2.0,Iris-virginica
+6.4,2.7,5.3,1.9,Iris-virginica
+6.8,3.0,5.5,2.1,Iris-virginica
+5.7,2.5,5.0,2.0,Iris-virginica
+5.8,2.8,5.1,2.4,Iris-virginica
+6.4,3.2,5.3,2.3,Iris-virginica
+6.5,3.0,5.5,1.8,Iris-virginica
+7.7,3.8,6.7,2.2,Iris-virginica
+7.7,2.6,6.9,2.3,Iris-virginica
+6.0,2.2,5.0,1.5,Iris-virginica
+6.9,3.2,5.7,2.3,Iris-virginica
+5.6,2.8,4.9,2.0,Iris-virginica
+7.7,2.8,6.7,2.0,Iris-virginica
+6.3,2.7,4.9,1.8,Iris-virginica
+6.7,3.3,5.7,2.1,Iris-virginica
+7.2,3.2,6.0,1.8,Iris-virginica
+6.2,2.8,4.8,1.8,Iris-virginica
+6.1,3.0,4.9,1.8,Iris-virginica
+6.4,2.8,5.6,2.1,Iris-virginica
+7.2,3.0,5.8,1.6,Iris-virginica
+7.4,2.8,6.1,1.9,Iris-virginica
+7.9,3.8,6.4,2.0,Iris-virginica
+6.4,2.8,5.6,2.2,Iris-virginica
+6.3,2.8,5.1,1.5,Iris-virginica
+6.1,2.6,5.6,1.4,Iris-virginica
+7.7,3.0,6.1,2.3,Iris-virginica
+6.3,3.4,5.6,2.4,Iris-virginica
+6.4,3.1,5.5,1.8,Iris-virginica
+6.0,3.0,4.8,1.8,Iris-virginica
+6.9,3.1,5.4,2.1,Iris-virginica
+6.7,3.1,5.6,2.4,Iris-virginica
+6.9,3.1,5.1,2.3,Iris-virginica
+5.8,2.7,5.1,1.9,Iris-virginica
+6.8,3.2,5.9,2.3,Iris-virginica
+6.7,3.3,5.7,2.5,Iris-virginica
+6.7,3.0,5.2,2.3,Iris-virginica
+6.3,2.5,5.0,1.9,Iris-virginica
+6.5,3.0,5.2,2.0,Iris-virginica
+6.2,3.4,5.4,2.3,Iris-virginica
+5.9,3.0,5.1,1.8,Iris-virginica

linear-regression/README.md

@@ -0,0 +1,2 @@
+# Linear Regression
+For a walk through, please refer to the article on Medium. [Machine Learning with Javascript : Part 1 (Linear Regression)](https://hackernoon.com/machine-learning-with-javascript-part-1-9b97f3ed4fe5)

package.json

@@ -11,6 +11,8 @@
   "license": "ISC",
   "dependencies": {
     "csvtojson": "^1.1.6",
-    "ml-regression": "^4.2.1"
+    "ml-knn": "^1.0.0",
+    "ml-regression": "^4.2.1",
+    "prompt": "^1.0.0"
   }
 }