public void Build(IEnumerable <ProcessInfoLabeledItem> items) { var words = items.Select(d => d.Title + " " + d.Process).Select(_filter).ToArray(); if (_vocabulary == null) { _vocabulary = items.Select(d => d.Title + " " + d.Process).SelectMany(_filter).GroupBy(str => str).Where(grp => grp.Count() > 2).OrderByDescending(grp => grp.Count()).Select(grp => grp.Key).Take(2500).OrderBy(str => str).ToArray(); } _x = TransformTextUtils.TransformTextToX(words, _vocabulary); _y = items.Select(d => (int)d.Category).ToArray(); }
public void Build(IEnumerable <ProcessInfo> inputs) { var testWordsOrigin = inputs.Select(d => d.MainWindowTitle + " " + d.ProcessName).ToArray(); _x = TransformTextUtils.TransformTextToX(testWordsOrigin.Select(TransformTextUtils.Filter).ToArray(), _featureSchema); }