public void TestIssues()
{
// case 1
var text = @"整併";
var extractor = new TfidfExtractor();
var keywords = extractor.ExtractTags(text, 10, Constants.NounPos);
foreach (var keyword in keywords)
{
Console.WriteLine(keyword);
}
keywords = extractor.ExtractTags(text, 10, Constants.VerbPos);
foreach (var keyword in keywords)
{
Console.WriteLine(keyword);
}
// case 2:
text = "開発支援工具FLEXITE";
keywords = extractor.ExtractTags(text, 10, Constants.NounPos);
foreach (var keyword in keywords)
{
Console.WriteLine(keyword);
}
}
public void wordCut()
{
string[] folders = Directory.GetDirectories(path);
string filePath = savePath + @"\分词结果.txt";
StreamWriter writer = new StreamWriter(filePath);
foreach (string folder in folders)
{
int index = folder.LastIndexOf('\\');
string folderName = folder.Substring(index + 1);
writer.Write("\"{0}\": [", folderName);
Console.WriteLine(folderName);
string[] files = Directory.GetFiles(folder);
string text = "";
foreach (string file in files)
{
text += File.ReadAllText(file);
}
var extractor = new TfidfExtractor();
var keywords = extractor.ExtractTagsWithWeight(text);
foreach (WordWeightPair w in keywords)
{
writer.Write("[\"{0}\", {1}],", w.Word, (int)(w.Weight * 100 * 2)); //将权重按照一定倍数放大并取整，便于后期处理
Console.WriteLine("{0}: {1}", w.Word, (int)(w.Weight * 100 * 2));
}
writer.WriteLine("],");
}
writer.Close();
}
private List <string> WordSplitResult(string strWords)
{
List <string> result = new List <string>();
IEnumerable <string> segments;
switch (comboBoxCutMode.SelectedIndex)
{
case 0:
segments = segmenter.Cut(strWords);
break;
case 1:
segments = segmenter.CutForSearch(strWords);
break;
case 2:
var idf = new TfidfExtractor();
segments = idf.ExtractTags(strWords, 20, Constants.NounAndVerbPos);
break;
default:
var textRank = new TextRankExtractor();
segments = textRank.ExtractTags(strWords, 20, Constants.NounAndVerbPos);
break;
}
foreach (string str in string.Join(" ", segments).Split(' '))
{
if (!stopwordsList.Contains(str))
{
result.Add(str);
}
}
return(result);
}
/// <summary>
/// 获取高频词
/// </summary>
/// <param name="userpaper"></param>
/// <returns></returns>
public List <string> GetKeyWord(string userpaper)
{
JiebaSegmenter segmenter = new JiebaSegmenter();
segmenter.LoadUserDict("THUOCL_it.txt");
var fc = new TfidfExtractor();
List <string> UserKeywords = fc.ExtractTags(userpaper, count: 6, allowPos: null).ToList <string>();
return(UserKeywords);
}
public void TestExtractTagsWithPos()
{
var tfidf = new TfidfExtractor();
var text = GetFileContents(TestHelper.GetResourceFilePath("article_social.txt"));
var result = tfidf.ExtractTags(text, 30, Constants.NounAndVerbPos);
foreach (var tag in result)
{
Console.WriteLine(tag);
}
}
public void TestExtractIdioms()
{
var tfidf = new TfidfExtractor();
var text = GetFileContents(@"Resources\article_social.txt");
var result = tfidf.ExtractTags(text, 50, Constants.IdiomPos);
foreach (var tag in result)
{
Console.WriteLine(tag);
}
}
public void TestExtractTagsWithWeights()
{
var tfidf = new TfidfExtractor();
var text = GetFileContents(@"Resources\article.txt");
var result = tfidf.ExtractTagsWithWeight(text);
foreach (var tag in result)
{
Console.WriteLine("({0}, {1})", tag.Word, tag.Weight);
}
}
public void TestExtractTags()
{
var tfidf = new TfidfExtractor();
var text = GetFileContents(TestHelper.GetResourceFilePath("article.txt"));
var result = tfidf.ExtractTags(text, 30);
foreach (var tag in result)
{
Console.WriteLine(tag);
}
}
public void TestExtractTagsOfSportsNews()
{
var tfidf = new TfidfExtractor();
var text = GetFileContents(@"Resources\article_sports.txt");
var result = tfidf.ExtractTags(text);
foreach (var tag in result)
{
Console.WriteLine(tag);
}
}
/// <summary>
/// jieba.net分词，找关键词
/// </summary>
/// <param name="str">输入字符串</param>
/// <param name="strout">输出10个关键词</param>
/// <returns></returns>
public string JiebaKey(string str)
{
string strout = "";
var extractor = new TfidfExtractor().ExtractTags(str, 10, Constants.NounAndVerbPos);
// 提取前十个仅包含名词和动词的关键词
foreach (var keyword in extractor)
{
strout += (keyword + " ");
}
return(strout);
}
public void ExtractTagsDemo()
{
var text =
"程序员(英文Programmer)是从事程序开发、维护的专业人员。一般将程序员分为程序设计人员和程序编码人员，但两者的界限并不非常清楚，特别是在中国。软件从业人员分为初级程序员、高级程序员、系统分析员和项目经理四大类。";
var extractor = new TfidfExtractor();
var keywords = extractor.ExtractTags(text);
foreach (var keyword in keywords)
{
Console.WriteLine(keyword);
}
}
public async Task <string> Post([FromBody] MonitorRequestModel model)
{
var monitor = await _connection.QuerySingleOrDefaultAsync <Monitor>("SELECT * FROM [dbo].[Monitor] WHERE [Name]=@Name", new { model.Name });
if (monitor == null)
{
var name = model.Name;
if (model.Type == MonitorType.公司)
{
var extractor = new TfidfExtractor();
var keywords = extractor.ExtractTags(model.Name).ToArray();
name = keywords[0];
}
await _connection.ExecuteAsync(
@"INSERT INTO [dbo].[Monitor]([Type],[Name],[Tag],[Remarks]) VALUES(@Type, @Name, @Tag, @Remarks)", new { model.Type, model.Name, Tag = name, Remarks = model.NickName });
BackgroundJob.Enqueue <MonitorJob>(job => job.Monitor(name, null));
return($"@{model.NickName}:监控设置成功.");
}
else
{
await _connection.ExecuteAsync("UPDATE [dbo].[Monitor] SET [Remarks]=[Remarks]+','+@NickName WHERE [Id]=@Id",
new { monitor.Id, model.NickName });
var name = model.Name;
if (model.Type == MonitorType.公司)
{
var extractor = new TfidfExtractor();
var keywords = extractor.ExtractTags(model.Name).ToArray();
name = keywords[0];
}
var news = await _connection.QueryAsync <BaiduNews>("SELECT TOP 5 * FROM [dbo].[BaiduNews] WHERE [Keyword]=@Keyword ORDER BY [CreateDate] DESC",
new { Keyword = name });
var enumerable = news as BaiduNews[] ?? news.ToArray();
if (enumerable.Any())
{
//await _connection.ExecuteAsync("UPDATE [dbo].[BaiduNews] SET [IsPushed]=1 WHERE Id=@Id",
// enumerable.Where(p => p.IsPushed == false).Select(p => new { p.Id }));
var index = 1;
string content = enumerable.Aggregate("", (current, art) => current + $"{index++}.{art.Title}\r\n");
return($"@{model.NickName}:{model.Name}最新舆情:\r\n{content}点击查看更多详情http://syzb.qianjifang.com.cn/{HttpUtility.UrlEncode(name)}");
}
else
{
return($"@{model.NickName}:{model.Name}目前没有最新舆情!");
}
}
}
public void TestSetStopWords()
{
var tfidf = new TfidfExtractor();
tfidf.SetStopWords(@"Resources\stop_words_test.txt");
var text = GetFileContents(@"Resources\article_sports.txt");
var result = tfidf.ExtractTags(text, 30);
foreach (var tag in result)
{
Console.WriteLine(tag);
}
}
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);
}
}
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);
}
}
void init()
{
if (Extractor == null)
{
TextRankExtractor = new TextRankExtractor();
TfidfExtractor = new TfidfExtractor();
}
if (Algorithm == ExtractAlgorithm.TextRank)
{
Extractor = TextRankExtractor;
}
if (Algorithm == ExtractAlgorithm.TF_IDF)
{
Extractor = TfidfExtractor;
}
}
private async void Button1_Click(object sender, EventArgs e)
{
if (textBox1.Text == "")
{
return;
}
_query = textBox1.Text;
var result = "";
var client = new HttpClient();
var uri = Host + "cx=" + Cx + "&key=" + Key + "&num=" + Num + "&start=" + Start + "&q=" + System.Net.WebUtility.UrlEncode(_query);
var response = await client.GetAsync(uri);
var contentString = await response.Content.ReadAsStringAsync();
dynamic parsedJson = JsonConvert.DeserializeObject(contentString);
var items = parsedJson?.items;
for (var i = Start; i < Num; i++)
{
result += items?[i].snippet.ToString();
}
var extractor = new TfidfExtractor();
var pairs = extractor.ExtractTagsWithWeight(result, 30);
var words = new List <string>();
var freqs = new List <int>();
foreach (var pair in pairs)
{
if (pair.Word.Equals("..."))
{
continue;
}
words.Add(pair.Word);
freqs.Add(Convert.ToInt32(pair.Weight * Math.Pow(10, 6)));
}
var wc = new WordCloud.WordCloud(1920, 1080);
var image = wc.Draw(words, freqs);
pictureBox1.Image = image;
button2.Enabled = true;
button2.Visible = true;
}
/// <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();
}
public double CalcTFIDFSimilarity(string paperText1, string paperText2)
{
ObjectArgs arg = new ObjectArgs();
//去掉分隔符，。...
string txt1 = paperText1;
txt1 = Regex.Replace(txt1, @"[^a-zA-Z0-9\u4e00-\u9fa5\s]", "");
string txt2 = paperText2;
txt2 = Regex.Replace(txt2, @"[^a-zA-Z0-9\u4e00-\u9fa5\s]", "");
var segmenter = new JiebaSegmenter();
JiebaNet.Analyser.TfidfExtractor tfd = new TfidfExtractor(segmenter);
arg.ObjData = "开始分词";
OnRaiseReporting(arg);
Console.WriteLine("开始分词");
Stopwatch sw = new Stopwatch();
sw.Start();
IEnumerable <string> segment1 = segmenter.Cut(txt1);
IEnumerable <string> segment2 = segmenter.Cut(txt2);
int num1 = segment1.Count();
int num2 = segment2.Count();
Console.WriteLine("文档1分词数:" + num1);
Console.WriteLine("文档2分词数:" + num2);
arg.ObjData = "文档1分词数:" + num1 + "\r\n文档2分词数: " + num2;
OnRaiseReporting(arg);
IEnumerable <string> seg1 = null; //多的
IEnumerable <string> seg2 = null; //少的
if (num1 > num2)
{
seg1 = segment1;
seg2 = segment2;
}
else
{
seg2 = segment1;
seg1 = segment2;
}
int maxLength = seg1.Count();
int minLength = seg2.Count();
double similar = 0;
//Dictionary<string, double> seg2Dic = CalcTF(seg2);
string str2 = GetText(seg2);
for (int i = 0; i + minLength <= maxLength; i++)
{
//0-interval
//1-interval+1
//2-interval+2 ...
IEnumerable <string> seg = seg1.Where((item, index) => index > i && index < i + minLength);//取i 到 i+minLength
//从seg1 中截取与seg2相同数量的词集合seg
//分别计算词频 seg2的词频只需要计算一次
//计算cos ===相似度
//Dictionary<string, double> dic = CalcTF(seg);
//double s = CalcSimilar(dic, seg2Dic);
string str = GetText(seg);
int topNum = 500;
IEnumerable <WordWeightPair> tf_a = tfd.ExtractTagsWithWeight(str2, topNum);
IEnumerable <WordWeightPair> tf_b = tfd.ExtractTagsWithWeight(str, topNum);
double molecular = 0; // 分子
double denominator_a = 0; // 分母
double denominator_b = 0;
Dictionary <string, WordWeightPair> dic_a = new Dictionary <string, WordWeightPair>();
Dictionary <string, WordWeightPair> dic_b = new Dictionary <string, WordWeightPair>();
foreach (var a in tf_a)
{
dic_a.Add(a.Word, a);
}
foreach (var b in tf_b)
{
dic_b.Add(b.Word, b);
}
//Console.WriteLine("两篇文档相似的词有：");
foreach (var k in dic_a.Keys)
{
WordWeightPair a = dic_a[k];
WordWeightPair b;
dic_b.TryGetValue(k, out b);
denominator_a += a.Weight * a.Weight;
molecular += a.Weight * (null == b ? 0 : b.Weight);
//if (a != null && b != null)
//{
// Console.WriteLine(a.Word + " TF-IDF词频统计 文档一：" + a.Weight + "|文档二："
// + b.Weight);
//}
}
foreach (var k in dic_b.Keys)
{
WordWeightPair b = dic_b[k];
denominator_b += b.Weight * b.Weight;
}
double s = 0;
if (denominator_a != 0 && denominator_b != 0)
{
s = (molecular / (Math.Sqrt(denominator_a) * Math.Sqrt(denominator_b)));
}
//Console.WriteLine("两篇文档相似度：" + s * 100 + "%");
if ((i + 1) % 50 == 0)
{
Console.WriteLine(string.Format("第{0}次计算出的相似度：{1}", i + 1, s));
arg.ObjData = string.Format("第{0}次计算出的相似度：{1}", i + 1, s);
OnRaiseReporting(arg);
}
if (s > similar)
{
similar = s;
}
if (s >= 0.99)
{
//极高相似度
Console.WriteLine(string.Format("第{0}次计算出的相似度：{1}", i + 1, s));
arg.ObjData = string.Format("第{0}次计算出的相似度：{1}", i + 1, s);
OnRaiseReporting(arg);
}
//Console.WriteLine("第"+i+"次花费时间：" + sw.ElapsedMilliseconds / 1000 + "秒");
}
sw.Stop();
Console.WriteLine("两篇文章的相似度：" + similar);
Console.WriteLine("花费时间：" + sw.ElapsedMilliseconds + "ms");
arg.ObjData = string.Format("两篇文章的相似度：" + similar + "\r\n花费时间：" + sw.ElapsedMilliseconds + "ms");
OnRaiseReporting(arg);
return(similar);
}
/// <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
}
/// <summary> /// 获取关键词权重（名/动词） /// </summary> /// <param name="str"></param> /// <param name="count">数量</param> /// <param name="tfidf">词典（不提供则使用默认分词词典）</param> /// <returns></returns> public static IEnumerable <WordWeightPair> GetKeyWordsWegihtNounAndVerb(this string str, int count = 20, TfidfExtractor tfidf = null) => (tfidf ?? TfidfExtractor).ExtractTagsWithWeight(str, count, Constants.NounAndVerbPos);
/// <summary> /// 获取关键词权重 /// </summary> /// <param name="str"></param> /// <param name="count">数量</param> /// <param name="tfidf">词典（不提供则使用默认分词词典）</param> /// <returns></returns> public static IEnumerable <WordWeightPair> GetKeyWordsWegiht(this string str, int count = 20, TfidfExtractor tfidf = null) => (tfidf ?? TfidfExtractor).ExtractTagsWithWeight(str, count);
/// <summary> /// 获取关键词（名/动词） /// </summary> /// <param name="str"></param> /// <param name="count">数量</param> /// <param name="tfidf">词典（不提供则使用默认分词词典）</param> /// <returns></returns> public static IEnumerable <string> GetKeyWordsNounAndVerb(this string str, int count = 20, TfidfExtractor tfidf = null) => (tfidf ?? TfidfExtractor).ExtractTags(str, count, Constants.NounAndVerbPos);
/// <summary> /// 获取关键词 /// </summary> /// <param name="str"></param> /// <param name="count">数量</param> /// <param name="tfidf">词典（不提供则使用默认分词词典）</param> /// <returns></returns> public static IEnumerable <string> GetKeyWords(this string str, int count = 20, TfidfExtractor tfidf = null) => (tfidf ?? TfidfExtractor).ExtractTags(str, count);
private void button3_Click(object sender, EventArgs e)
{
try
{
//进行计时
Stopwatch time = new Stopwatch();
time.Start();
//将inform,normal,spam三个文件夹下的文件汇入gather文件夹下的collect.txt文档
File.Create(@"..\Debug\textgather\gather\collect.txt").Close();
string[] subdirectory = Directory.GetFiles(@"..\Debug\textgather\spam\");
foreach (string path in subdirectory)
{
StreamReader sr = new StreamReader(path, Encoding.Default);
string content = sr.ReadLine();
sr.Close();
StreamWriter sw = new StreamWriter(@"..\Debug\textgather\gather\collect.txt", true, Encoding.Default);
sw.WriteLine(content);
sw.Close();
}
subdirectory = Directory.GetFiles(@"..\Debug\textgather\inform\");
foreach (string path in subdirectory)
{
StreamReader sr = new StreamReader(path, Encoding.Default);
string content = sr.ReadLine();
sr.Close();
StreamWriter sw = new StreamWriter(@"..\Debug\textgather\gather\collect.txt", true, Encoding.Default);
sw.WriteLine(content);
sw.Close();
}
subdirectory = Directory.GetFiles(@"..\Debug\textgather\normal\");
foreach (string path in subdirectory)
{
StreamReader sr = new StreamReader(path, Encoding.Default);
string content = sr.ReadLine();
sr.Close();
StreamWriter sw = new StreamWriter(@"..\Debug\textgather\gather\collect.txt", true, Encoding.Default);
sw.WriteLine(content);
sw.Close();
}
//将collect文本中的词语进行分词，以及用TF-IDF算法提取关键词保存在collectok文本
StreamReader srt = new StreamReader(@"..\Debug\textgather\gather\collect.txt", Encoding.Default);
string cont = srt.ReadToEnd();
srt.Close();
//调用jieba提取仅包含名词和动词的关键词
var extractor = new TfidfExtractor();
var keywords = extractor.ExtractTagsWithWeight(cont, 6000, Constants.NounAndVerbPos);
File.Create(@"..\Debug\textgather\gather\collecto.txt").Close();
StreamWriter swt = new StreamWriter(@"..\Debug\textgather\gather\collecto.txt", true, Encoding.Default);
string strline = null;
foreach (var keyword in keywords)
{
strline = keyword.Word + " " + keyword.Weight;
swt.WriteLine(strline);
}
swt.Close();
//计时
time.Stop();
TimeSpan ts2 = time.Elapsed;
listBox1.Items.Clear();
listBox1.Items.Add("文本预处理完成，总耗时：" + ts2.TotalSeconds + "秒");
}
catch (Exception ex)
{
MessageBox.Show(ex.Message);
}
}