Context Navigation

HeuristicLab.Problems.Instances.DataAnalysis

Timestamp:

11/29/15 16:59:52 (9 years ago)

Author:

gkronber

Message:

#2071: added progress reporting when importing regression problem data from csv files.

Location:

Files:

-                      r12012
+                      r13414
 using System.Collections;
 using System.Collections.Generic;
+using System.ComponentModel;
+using System.Drawing;
 using System.Globalization;
 using System.IO;
 …
     where ImportType : DataAnalysisImportType {
+    public event ProgressChangedEventHandler ProgressChanged;
     public TData ImportData(string path, ImportType type, DataAnalysisCSVFormat csvFormat) {
       TableFileParser csvFileParser = new TableFileParser();
+      long fileSize = new FileInfo(path).Length;
+      csvFileParser.ProgressChanged += (sender, e) => {
+        OnProgressChanged(e / (double)fileSize);
+      };
       csvFileParser.Parse(path, csvFormat.NumberFormatInfo, csvFormat.DateTimeFormatInfo, csvFormat.Separator, csvFormat.VariableNamesAvailable);
       return ImportData(path, type, csvFileParser);
+    }
+    protected virtual void OnProgressChanged(double d) {
+      var handler = ProgressChanged;
+      if (handler != null)
+        handler(this, new ProgressChangedEventArgs((int)(100*d), null));
+    }

-                      r13413
+                      r13414
 namespace HeuristicLab.Problems.Instances.DataAnalysis {
   public class TableFileParser {
+  public class TableFileParser : Progress<long> { // reports the number of bytes read
     private const int BUFFER_SIZE = 65536;
     // char used to symbolize whitespaces (no missing values can be handled with whitespaces)
 …
         private set { currentLine = value; }
+      }
+      public long BytesRead {
+        get;
+        private set;
+      }
       public Tokenizer(StreamReader reader, NumberFormatInfo numberFormatInfo, DateTimeFormatInfo dateTimeFormatInfo, char separator) {
 …
         if (!reader.EndOfStream) {
           CurrentLine = reader.ReadLine();
+          try {
+            BytesRead = reader.BaseStream.Position;
+          } catch (IOException) {
+            BytesRead += CurrentLine.Length + 2; // guess
+          } catch (NotSupportedException) {
+            BytesRead += CurrentLine.Length + 2;
+          }
           int i = 0;
           foreach (var tok in Split(CurrentLine)) {
 …
           rowValues.Add(row);
+        }
+        OnReport(tokenizer.BytesRead);
+      }
+    }

Note: See TracChangeset for help on using the changeset viewer.