From 96744a133f3d421cdfcd9d18dd5f74981475fd5f Mon Sep 17 00:00:00 2001
From: schneefux <schneefux+commit@schneefux.xyz>
Date: Sat, 2 Apr 2016 21:33:19 +0200
Subject: integrate boston housing dataset and test values

---
 code/bostonset.js | 100 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 100 insertions(+)
 create mode 100644 code/bostonset.js

(limited to 'code/bostonset.js')

diff --git a/code/bostonset.js b/code/bostonset.js
new file mode 100644
index 0000000..50b9d38
--- /dev/null
+++ b/code/bostonset.js
@@ -0,0 +1,100 @@
+var Bostonset = (function() {
+    var attrs =
+        ["crim", "zn", "indus", "chas", "nox", "rm", "age", "dis", "rad", "tax", "ptratio", "black", "lstat", "medv"];
+
+    function Bostonset() {
+        this.data = [];
+        // fixed constants exported from training data
+        this.dataScaler = new MinMaxScaler();
+        this.dataScaler.setScales([[0.00632, 0.0, 0.46, 0.0, 0.385, 3.561, 2.9, 1.1296, 1.0, 187.0, 12.6, 0.32, 1.73], [88.9762, 100.0, 27.74, 1.0, 0.871, 8.78, 100.0, 12.1265, 24.0, 711.0, 22.0, 396.9, 37.97]]);
+        this.targetScaler = new MinMaxScaler();
+        this.targetScaler.setScales([5.0, 50.0]);
+    }
+
+    Bostonset.prototype.load = function(url) {
+        var self = this;
+        d3.csv(url).get(function(e, data) {
+            if (e) console.log(e);
+            data.forEach(function (el) {
+                var arr = [];
+                for (c=0; c<attrs.length; c++) {
+                    arr.push(parseFloat(el[attrs[c]]));
+                }
+                self.data.push(arr);
+            });
+        });
+    };
+
+    Bostonset.prototype.length = function() {
+        return this.data.length;
+    };
+
+    Bostonset.prototype.rawInputs = function(row) {
+        return this.data[row].slice(0, -1); // leave out MEDV
+    };
+
+    Bostonset.prototype.inputs = function(row) {
+        return this.dataScaler.scale(this.rawInputs(row));
+    };
+
+    Bostonset.prototype.asOutput = function(num) {
+        return this.targetScaler.unscale(num);
+    };
+
+    Bostonset.prototype.expectedOutput = function(row) {
+        return this.data[row][attrs.length-1];
+    };
+
+    return Bostonset;
+})();
+
+// TODO abstract for generic shapes?
+var MinMaxScaler = (function() {
+    function MinMaxScaler() {
+    }
+
+    MinMaxScaler.prototype.fit = function(arr) {
+        this.setScales(d3.extent(arr));
+    };
+
+    MinMaxScaler.prototype.setScales = function(fits) {
+        this.min = fits[0];
+        this.max = fits[1];
+    };
+
+    MinMaxScaler.prototype.scale = function(data) {
+        data = this._arrayDivide(this._arraySubtract(data, this.min), this._arraySubtract(this.max, this.min));
+        return data;
+    };
+
+    MinMaxScaler.prototype.unscale = function(data) {
+        data = this._arrayAdd(this._arrayMultiply(data, this._arraySubtract(this.max, this.min)), this.min);
+        return data;
+    };
+
+    MinMaxScaler.prototype._arraySubtract = function(one, two) {
+        if (one.constructor !== Array) return one - two;
+        for (i=0; i<one.length; one[i]-=two[i++]);
+        return one;
+    };
+
+    MinMaxScaler.prototype._arrayAdd = function(one, two) {
+        if (one.constructor !== Array) return one + two;
+        for (i=0; i<one.length; one[i]+=two[i++]);
+        return one;
+    };
+
+    MinMaxScaler.prototype._arrayMultiply = function(one, two) {
+        if (one.constructor !== Array) return one * two;
+        for (i=0; i<one.length; one[i]*=two[i++]);
+        return one;
+    };
+
+    MinMaxScaler.prototype._arrayDivide = function(one, two) {
+        if (one.constructor !== Array) return one / two;
+        for (i=0; i<one.length; one[i]/=two[i++]);
+        return one;
+    };
+
+    return MinMaxScaler;
+})();
-- 
cgit v1.3.1