Items in cluster improvements #1
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,5 +1,5 @@ | ||
| /** | ||
| * Copyright 2014-2015 BigML | ||
| * | ||
| * Licensed under the Apache License, Version 2.0 (the "License"); you may | ||
| * not use this file except in compliance with the License. You may obtain | ||
|
|
@@ -27,6 +27,62 @@ var LocalCentroid = require(PATH + 'LocalCentroid'); | |
| var constants = require(PATH + 'constants'); | ||
|
|
||
|
|
||
| function countItemsMatches(text, items) { | ||
| /** | ||
| * Check if a word is contained or not | ||
| * @param {string} text Input text (single word) | ||
| * @param {string} items to match | ||
| */ | ||
| for (indx = 0; indx < items.length; indx++) { | ||
| if (text === items[indx][0]) { | ||
| return 1; | ||
| } | ||
| } | ||
| return 0; | ||
| } | ||
|
|
||
|
|
||
| function itemMatches(text, summaryItems) { | ||
| /** | ||
| * Computes item matches depending on the chosen items analysis options | ||
|
There was a problem hiding this comment. are numerical segments taken into account in this code? There was a problem hiding this comment. Sorry, as @joseribes pointed out, the items field has only text separated by a user-given separator or regular expression, so either you have a list of text tokens or you tokenize using the user-given information. I was mixing the "Item" concept in association rules in my comment. |
||
| * | ||
| * @param {string} text Input text (array or string) | ||
| * @param {string} items to match | ||
| */ | ||
|
|
||
| var inputItems = [], | ||
| itemMatchesList = [], | ||
| singleItem, | ||
| indx, | ||
| itemText, | ||
| regexp; | ||
|
|
||
| if ((typeof text).indexOf('object') > -1) { | ||
| //Array case | ||
| inputItems = text; | ||
| inputItems[0] = text[0] || [""]; | ||
| } else { | ||
| //Text string case | ||
| regexp = new RegExp('(\\b|_)([^\\b_\\s]+?)(\\b|_)', 'g'); | ||
| inputItems = text.match(regexp); | ||
| } | ||
| if (inputItems[0] == "") return []; | ||
|
|
||
| //Text array here | ||
| for (indx = 0; indx < inputItems.length; indx++) { | ||
| singleItem = inputItems[indx]; | ||
|
|
||
| if (countItemsMatches(singleItem, summaryItems) > 0) { | ||
| itemMatchesList.push(singleItem); | ||
| } | ||
| } | ||
| return itemMatchesList; | ||
|
|
||
| } | ||
|
|
||
|
|
||
|
|
||
|
|
||
| function parseTerms(text, caseSensitive) { | ||
| /** | ||
| * Parses the text into words | ||
|
|
@@ -123,7 +179,7 @@ function LocalCluster(resource, connection) { | |
| * @param {object} resource Model's resource info | ||
| */ | ||
| var status, fields, field, fieldId, fieldInfo, clusters, i, clustersLength, | ||
| centroid, summaryFields, index; | ||
| if (error) { | ||
| throw new Error('Cannot create the Cluster instance. Could not' + | ||
| ' retrieve the resource: ' + error); | ||
|
|
@@ -145,7 +201,12 @@ function LocalCluster(resource, connection) { | |
| self.termForms = {}; | ||
| self.tagClouds = {}; | ||
| self.termAnalysis = {}; | ||
| self.items = {}; | ||
| fields = resource.clusters.fields; | ||
| summaryFields = resource['summary_fields']; | ||
| for (index = 0; index < summaryFields.length; index++) { | ||
| delete fields[summaryFields[index]]; | ||
| } | ||
| for (fieldId in fields) { | ||
| if (fields.hasOwnProperty(fieldId)) { | ||
| field = fields[fieldId]; | ||
|
|
@@ -154,6 +215,9 @@ function LocalCluster(resource, connection) { | |
| self.tagClouds[fieldId] = field.summary.tag_cloud; | ||
| self.termAnalysis[fieldId] = field.term_analysis; | ||
| } | ||
| if (field.optype === 'items') { | ||
| self.items[fieldId] = field.summary.items; | ||
| } | ||
| } | ||
| } | ||
| self.fields = fields; | ||
|
|
@@ -196,7 +260,7 @@ LocalCluster.prototype.computeNearest = function (inputData) { | |
| * | ||
| * @param {object} data Input data to predict from | ||
| */ | ||
| var uniqueTerms = {}, terms, items, caseSensitive, tokenMode, inputDataField, | ||
| fieldId, nearest, distance2, i, clustersLength, centroid; | ||
| for (fieldId in this.tagClouds) { | ||
| if (inputData.hasOwnProperty(fieldId)) { | ||
|
|
@@ -210,7 +274,7 @@ LocalCluster.prototype.computeNearest = function (inputData) { | |
| } else { | ||
| terms = []; | ||
| } | ||
|
|
||
| if (tokenMode !== constants.TM_TOKENS) { | ||
| terms.push((caseSensitive) ? inputDataField : | ||
| inputDataField.toLowerCase()); | ||
|
|
@@ -223,12 +287,24 @@ LocalCluster.prototype.computeNearest = function (inputData) { | |
| } | ||
| } | ||
|
|
||
| //items fields | ||
| items = []; | ||
| for (fieldId in this.items) { | ||
| if (inputData.hasOwnProperty(fieldId)) { | ||
| if (inputData.hasOwnProperty(fieldId)) { | ||
| inputDataField = inputData[fieldId]; | ||
| items[fieldId] = itemMatches(inputDataField, this.items[fieldId]); | ||
| delete inputData[fieldId]; | ||
| } | ||
| } | ||
| } | ||
|
|
||
| nearest = {'centroidId': null, 'centroidName': null, | ||
| 'distance': Infinity}; | ||
| clustersLength = this.centroids.length; | ||
| for (i = 0; i < clustersLength; i++) { | ||
| centroid = this.centroids[i]; | ||
| distance2 = centroid.distance2(inputData, uniqueTerms, items, this.scales, | ||
| nearest.distance); | ||
| if (distance2 < nearest.distance) { | ||
| nearest = {'centroidId': centroid.centroidId, | ||
|
|
@@ -290,6 +366,7 @@ LocalCluster.prototype.validateInput = function (inputData, cb) { | |
| if (this.fields.hasOwnProperty(fieldId)) { | ||
| field = this.fields[fieldId]; | ||
| if (field.optype !== "categorical" && field.optype !== "text" && | ||
| field.optype !== "items" && | ||
| !inputData.hasOwnProperty(fieldId) && | ||
| !inputData.hasOwnProperty(field.name)) { | ||
| throw new Error("The input data lacks some numeric fields values." + | ||
|
|
||
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I guess you define a separate function in order not to mix with the existing one, but I think they can be merged into one. Maybe in a later PR...