public void ExtractTagsDemo2()
{
var text = @"在数学和计算机科学/算学之中，算法/算则法（Algorithm）为一个计算的具体步骤，常用于计算、数据处理和自动推理。精确而言，算法是一个表示为有限长列表的有效方法。算法应包含清晰定义的指令用于计算函数。
算法中的指令描述的是一个计算，当其运行时能从一个初始状态和初始输入（可能为空）开始，经过一系列有限而清晰定义的状态最终产生输出并停止于一个终态。一个状态到另一个状态的转移不一定是确定的。随机化算法在内的一些算法，包含了一些随机输入。
形式化算法的概念部分源自尝试解决希尔伯特提出的判定问题，并在其后尝试定义有效计算性或者有效方法中成形。这些尝试包括库尔特·哥德尔、雅克·埃尔布朗和斯蒂芬·科尔·克莱尼分别于1930年、1934年和1935年提出的递归函数，阿隆佐·邱奇于1936年提出的λ演算，1936年Emil Leon Post的Formulation 1和艾伦·图灵1937年提出的图灵机。即使在当前，依然常有直觉想法难以定义为形式化算法的情况。";
var extractor = new TfidfExtractor();
var keywords = extractor.ExtractTags(text, 10, Constants.NounAndVerbPos);
foreach (var keyword in keywords)
{
Console.WriteLine(keyword);
}
}
public void TestSetStopWords()
{
var tfidf = new TfidfExtractor();
// Use less stopwords than default stopword list.
tfidf.SetStopWords(TestHelper.GetResourceFilePath("stop_words_test.txt"));
var text = GetFileContents(TestHelper.GetResourceFilePath("article.txt"));
var result = tfidf.ExtractTags(text, 30);
foreach (var tag in result)
{
Console.WriteLine(tag);
}
}
/// <summary>
/// 获取num个核心句
/// </summary>
/// <param name="text">文本</param>
/// <param name="num">核心句数</param>
/// <param name="type">抽取类型</param>
public void GetList(string text, int num, int type)
{
keywordList.Clear();
//获取核心关键词列表
switch (type)
{
case 1:
{
TfidfExtractor te = new TfidfExtractor();
keywordList = te.ExtractTags(text, num).ToList();
}
break;
case 2:
{
TextRankExtractor te = new TextRankExtractor();
keywordList = te.ExtractTags(text, num).ToList();
}
break;
}
AllsentenceList.Clear();
keySentenceList.Clear();
//将文章拆为句子列表，并分词
text = text.Replace(Environment.NewLine.ToString(), " 。");
//text = text.Replace(" ", "");
AllsentenceList = text.Split('。', '？').Where(x => !string.IsNullOrEmpty(x) && x != "undefined").Select(x => x.Trim()).ToList();
List <Sentence> temp = new List <Sentence>();
for (int i = 0; i < AllsentenceList.Count; i++)
{
AllsentenceList[i] = AllsentenceList[i] + "。";
var sentence = segmenter.Cut(AllsentenceList[i]);
Sentence v = new Sentence();
v.Sen = string.Join(" ", sentence);
v.Index = i;
temp.Add(v);
}
GetSentenceList(keywordList, temp);
}
public static decimal GetHousePrice(string text)
{
//var seg = new JiebaSegmenter();
//var li = seg.Cut(text).ToList();
decimal housePrice = 0;
var extractor = new TfidfExtractor();
var keywords = extractor.ExtractTags(text, 20, new List <string>()
{
"m"
});
if (keywords != null)
{
var lstProce = keywords.Distinct().Where(s => s.Length <= 5 && s.Length >= 3).OrderByDescending(s => s.Length);
var price = lstProce.FirstOrDefault();
decimal.TryParse(price, out housePrice);
}
return(housePrice);
}
public static int GetHousePrice(string text)
{
int housePrice = 0;
var extractor = new TfidfExtractor();
var keywords = extractor.ExtractTags(text, 20, new List <string>()
{
"m"
});
if (keywords != null)
{
var prices = keywords.Distinct().Select(p =>
{
var price = 0;
int.TryParse(p, out price);
return(price);
}).Where(p => p >= 500 && p <= 30000);
return(prices.FirstOrDefault());
}
return(housePrice);
}
private static void oprateJieBa(string filename)
{
string[] filenames = filename.Split('\\');
string filename1 = "E:\\词云\\JieBaResult\\" + filenames[2] + ".csv"; //用来存储jieba分析后的结果
string text = File.ReadAllText(filename);
var segmenter = new JiebaSegmenter();
var segments = segmenter.Cut(text);
var extractor = new TfidfExtractor();
var keywords = extractor.ExtractTags(text, 30, Constants.NounAndVerbPos);
Console.WriteLine(filename);
string str = null;
foreach (var keyword in keywords)
{
str = str + keyword + "\n";
Console.WriteLine(keyword);
}
StreamWriter fz = new StreamWriter(filename1, true);
fz.Write(str);
fz.Close();
}
/// <summary>
/// 提取文章关键词集合
/// </summary>
/// <param name="objStr"></param>
/// <returns></returns>
public static IEnumerable <string> GetArticleKeywords(string objStr)
{
var idf = new TfidfExtractor();
return(idf.ExtractTags(objStr, 10, Constants.NounAndVerbPos));//名词和动词
}
