官术网_书友最值得收藏!

The FeatureExtractor class

This newly added class provides our feature extraction for the given folder of filesOnce extraction is complete, the classification and strings data is written out to the sampledata file:

using System;
using System.IO;

using chapter03_logistic_regression.Common;
using chapter03_logistic_regression.ML.Base;

namespace chapter03_logistic_regression.ML
{
public class FeatureExtractor : BaseML
{
public void Extract(string folderPath)
{
var files = Directory.GetFiles(folderPath);

using (var streamWriter =
new StreamWriter(Path.Combine(AppContext.BaseDirectory, $"../../../Data/{Constants.SAMPLE_DATA}")))
{
foreach (var file in files)
{
var strings = GetStrings(File.ReadAllBytes(file));

streamWriter.WriteLine($"{file.ToLower().Contains("malicious")}\t{strings}");
}
}

Console.WriteLine($"Extracted {files.Length} to {Constants.SAMPLE_DATA}");
}
}
}
主站蜘蛛池模板: 谷城县| 易门县| 禄丰县| 丰都县| 大渡口区| 玉屏| 安远县| 台东市| 柳林县| 二连浩特市| 晋州市| 木里| 吉安县| 德格县| 奉新县| 兰州市| 东安县| 天津市| 安平县| 裕民县| 临武县| 铜梁县| 克拉玛依市| 洞口县| 安新县| 东海县| 玉门市| 吉林市| 麻栗坡县| 布尔津县| 遂川县| 稷山县| 锡林郭勒盟| 洪江市| 黑龙江省| 黑水县| 资兴市| 五河县| 田林县| 建阳市| 新闻|