Question

我有很多文件的格式为YYYYMMDD_HHmmss_goals.csv

现在我有一个容器有一天，所有文件列表合并在一个文件中。

CSV具有不同ID，X，Y的倍数。现在我希望将它们合并为一天，使用一个ID并将该ID的x和y相加并按单日存储它们。我也不希望它们在一个文件中合并，只是动态，保存合并的单日 - ＆gt;一行CVS格式的ID，x，y。它有点像将它们排序一天和ID并将它们的x，y相加，但仅限于该ID。

更新：

public class XY_Values
{
    public int X { get; set; }
    public int Y { get; set; }
}


 public class ImageKey
    {
        public int mLocationId;
        public int mFormatId;
        public int mEditionId;

        public ImageKey(int LocationId, int FormatId, int EditionId)
        {
            mLocationId = LocationId;
            mFormatId = FormatId;
            mEditionId = EditionId;
        }

        public bool Equals(ImageKey x, ImageKey y)
        {
            return x.mLocationId == y.mLocationId && x.mFormatId == y.mFormatId && x.mEditionId == y.mEditionId;
        }

        public int GetHashCode(ImageKey obj)
        {
            return obj.mLocationId ^ obj.mFormatId ^ obj.mEditionId;
        }

    }


    static void MergeFilesForDay(string dir, DateTime date, List<string> files)
{
    var idValues = new Dictionary<string, XY_Values>();
    foreach (string fn in files)
    {
        foreach (string line in File.ReadAllLines(fn))
        {
            string[] fields = line.Split(new string[] { "," }, StringSplitOptions.None);
            if (fields.Length < 5) continue; // skip invalid data

            int LocationId, FormatID,EditionId;
            int x, y;
            bool LocationIdValid = int.TryParse(fields[0].Trim(), out x);
            bool FormatIDValid = int.TryParse(fields[1].Trim(), out y);
            bool EditionIdValid = int.TryParse(fields[2].Trim(), out x);
            bool xValid = int.TryParse(fields[3].Trim(), out x);
            bool yValid = int.TryParse(fields[4].Trim(), out y);


            if (xValid && yValid && LocationIdValid &&FormatIDValid && EditionIdValid)
            {
               ImageKey key = new ImageKey(LocationId, FormatID, EditionId);
                            bool knownId = enteries.ContainsKey(key);
                            if (!knownId)
                            {
                                enteries.Add(key, new XY_Values());
                            }

                            XY_Values entry = enteries[key];
                            entry.X += x;
                            entry.Y += y;

            }
        }
    }

    // don't know how would I combine them like to output cvs
    //LocationId, FormatID, EditionID, x,y   ... items 
    //Date:  
}

Answer 1

此方法使用Dictionary<string, XY_Values>按ID进行分组：

public class XY_Values
{
    public int X { get; set; }
    public int Y { get; set; }
}

static void MergeFilesForDay(string dir, DateTime date, List<string> files)
{
    var idValues = new Dictionary<string, XY_Values>();
    foreach (string fn in files)
    {
        foreach (string line in File.ReadAllLines(fn))
        {
            string[] fields = line.Split(new string[] { "," }, StringSplitOptions.None);
            if (fields.Length < 3) continue; // skip invalid data
            string id = fields[0].Trim();
            int x, y;
            bool xValid = int.TryParse(fields[1].Trim(), out x);
            bool yValid = int.TryParse(fields[2].Trim(), out y);
            if (xValid && yValid)
            {
                bool knownID = idValues.ContainsKey(id);
                if (!knownID) idValues.Add(id, new XY_Values());
                XY_Values values = idValues[id];
                values.X += x;
                values.Y += y;
            }
        }
    }

    string file = Path.Combine(dir, date.ToString("yyyyMMdd") + ".csv");
    using (var stream = File.CreateText(file))
    {
        foreach (KeyValuePair<string, XY_Values> idValue in idValues)
        {
            string line = string.Format("{0},{1},{2}", idValue.Key, idValue.Value.X, idValue.Value.Y);
            stream.WriteLine(line);
        }
    }
}

该方法取代旧的in my last answer。

Answer 2

您可以创建一个类：

class ItemXY
{
    int X;
    int Y;    
}

然后创建一个词典：

Dictionary<int, ItemXY> dict = new Dictionary();

和foreach文件组，读取所有文件以填充dict：

string [] path_tab; //a tab of path, grouping all one day files

foreach (string path in path_tab)
{
  System.IO.StreamReader file = new System.IO.StreamReader(path, Encoding.Default);

  while (!file.EndOfStream)
  {
    string [] tab;
    string s = file.ReadLine();
    tab = s.split(',');
    if (dict.Contains(tab[0]) //ID
    {
      ((ItemXY)dict[tab[0]]).X += tab[1];
      ((ItemXY)dict[tab[0]]).Y += tab[2];
    }
    else
    {
        ItemXY newItem = new ItemXY();
        newItem.X = tab[1];
        newItem.Y = tab[2];
        dict.Add(tab[0], newItem);
    }
  }
  file.Close();
}

之后，使用dict值创建新的CSV。

按日期和ID合并和排序CSV格式的数据

2 个答案: