C#中使用jieba.NET、WordCloudSharp制作词云图的步骤

/// <summary>
/// 从指定文本中抽取关键词的同时得到其权重
/// </summary>
/// <param name="text"></param>
/// <returns></returns>
static WordWeightPair[] ExtractTagsWithWeight(string text)
{
    var extractor = new TfidfExtractor();
    var wordWeight = extractor.ExtractTagsWithWeight(text, 50);
    StringBuilder sbr = new StringBuilder();
    sbr.Append("词语");
    sbr.Append(",");
    sbr.Append("权重");
    sbr.AppendLine(",");
    foreach (var item in wordWeight)
    {
        sbr.Append(item.Word);
        sbr.Append(",");
        sbr.Append(item.Weight);
        sbr.AppendLine(",");
    }
    string filename = "关键词权重统计.csv";
    File.WriteAllText(filename, sbr.ToString(), Encoding.UTF8);
    Console.WriteLine("关键词提取完成：" + filename);
    return wordWeight.ToArray();
}

/// <summary>
/// 分词并统计词频：默认为精确模式，同时也使用HMM模型
/// </summary>
/// <param name="text"></param>
/// <param name="wordWeightAry"></param>
/// <returns></returns>
static KeyValuePair<string, int>[] Counter(string text, WordWeightPair[] wordWeightAry)
{
    var segmenter = new JiebaSegmenter();
    var segments = segmenter.Cut(text);
    var freqs = new Counter<string>(segments);
    KeyValuePair<string, int>[] countAry = new KeyValuePair<string, int>[wordWeightAry.Length];
    for (int i = 0; i < wordWeightAry.Length; i++)
    {
        string key = wordWeightAry[i].Word;
        countAry[i] = new KeyValuePair<string, int>(key, freqs[key]);
    }
    StringBuilder sbr = new StringBuilder();
    sbr.Append("词语");
    sbr.Append(",");
    sbr.Append("词频");
    sbr.AppendLine(",");
    foreach (var pair in countAry)
    {
        sbr.Append(pair.Key);
        sbr.Append(",");
        sbr.Append(pair.Value);
        sbr.AppendLine(",");
    }
    string filename = "词频统计结果.csv";
    File.WriteAllText(filename, sbr.ToString(), Encoding.UTF8);
    Console.WriteLine("词频统计完成：" + filename);
    return countAry;
}

/// <summary>
/// 创建词云图
/// </summary>
/// <param name="countAry"></param>
static void CreateWordCloud(KeyValuePair<string, int>[] countAry)
{            
    string markPath = "mask.jpg";
    string resultPath = "result.jpg";
    Console.WriteLine("开始生成图片，读取蒙版：" + markPath);
    Image mask = Image.FromFile(markPath);
    //使用蒙版图片
    var wordCloud = new WordCloud(mask.Width, mask.Height, mask: mask, allowVerical: true, fontname: "YouYuan");
    //不使用蒙版图片
    //var wordCloud = new WordCloud(1000, 1000,false, null,-1,1,null, false);
    var result = wordCloud.Draw(countAry.Select(it => it.Key).ToList(), countAry.Select(it => it.Value).ToList());
    result.Save(resultPath);
    Console.WriteLine("图片生成完成，保存图片：" + resultPath);
}

static void Main(string[] args)
{
    string text = File.ReadAllText("待处理数据.txt");
    var wordWeight = ExtractTagsWithWeight(text);
    var wordFreqs = Counter(text, wordWeight);
    CreateWordCloud(wordFreqs);
    Console.Read();
}