Best way to read csv file in C# to improve time efficiency

Next Door Engineer picture Next Door Engineer · Aug 10, 2012 · Viewed 13.8k times · Source

I have the following code to read in a large file, say with over a million rows. I am using Parallel and Linq approaches. Is there a better way to do it? If yes, then how?

        private static void ReadFile()
        {
            float floatTester = 0;
            List<float[]> result = File.ReadLines(@"largedata.csv")
                .Where(l => !string.IsNullOrWhiteSpace(l))
                .Select(l => new { Line = l, Fields = l.Split(new[] { ',' }, StringSplitOptions.RemoveEmptyEntries) })
                .Select(x => x.Fields
                              .Where(f => Single.TryParse(f, out floatTester))
                              .Select(f => floatTester).ToArray())
                .ToList();

            // now get your totals
            int numberOfLinesWithData = result.Count;
            int numberOfAllFloats = result.Sum(fa => fa.Length);
            MessageBox.Show(numberOfAllFloats.ToString());
        }

        private static readonly char[] Separators = { ',', ' ' };

        private static void ProcessFile()
        {
            var lines = File.ReadAllLines("largedata.csv");
            var numbers = ProcessRawNumbers(lines);

            var rowTotal = new List<double>();
            var totalElements = 0;

            foreach (var values in numbers)
            {
                var sumOfRow = values.Sum();
                rowTotal.Add(sumOfRow);
                totalElements += values.Count;
            }
            MessageBox.Show(totalElements.ToString());
        }

        private static List<List<double>> ProcessRawNumbers(IEnumerable<string> lines)
        {
            var numbers = new List<List<double>>();
            /*System.Threading.Tasks.*/
            Parallel.ForEach(lines, line =>
            {
                lock (numbers)
                {
                    numbers.Add(ProcessLine(line));
                }
            });
            return numbers;
        }

        private static List<double> ProcessLine(string line)
        {
            var list = new List<double>();
            foreach (var s in line.Split(Separators, StringSplitOptions.RemoveEmptyEntries))
            {
                double i;
                if (Double.TryParse(s, out i))
                {
                    list.Add(i);
                }
            }
            return list;
        }

        private void button1_Click(object sender, EventArgs e)
        {
            Stopwatch stopWatchParallel = new Stopwatch();
            stopWatchParallel.Start();
            ProcessFile();
            stopWatchParallel.Stop();
            // Get the elapsed time as a TimeSpan value.
            TimeSpan ts = stopWatchParallel.Elapsed;

            // Format and display the TimeSpan value.
            string elapsedTime = String.Format("{0:00}:{1:00}:{2:00}.{3:00}",
                ts.Hours, ts.Minutes, ts.Seconds,
                ts.Milliseconds / 10);
            MessageBox.Show(elapsedTime);

            Stopwatch stopWatchLinQ = new Stopwatch();
            stopWatchLinQ.Start();
            ReadFile();
            stopWatchLinQ.Stop();
            // Get the elapsed time as a TimeSpan value.
            TimeSpan ts2 = stopWatchLinQ.Elapsed;

            // Format and display the TimeSpan value.
            string elapsedTimeLinQ = String.Format("{0:00}:{1:00}:{2:00}.{3:00}",
                ts2.Hours, ts.Minutes, ts.Seconds,
                ts2.Milliseconds / 10);
            MessageBox.Show(elapsedTimeLinQ);
        }

Answer

Robin Maben picture Robin Maben · Aug 10, 2012

You can the built-in OleDb for that..

public void ImportCsvFile(string filename)
{
    FileInfo file = new FileInfo(filename);

    using (OleDbConnection con = 
            new OleDbConnection("Provider=Microsoft.Jet.OLEDB.4.0;Data Source=\"" +
            file.DirectoryName + "\";
            Extended Properties='text;HDR=Yes;FMT=Delimited(,)';"))
    {
        using (OleDbCommand cmd = new OleDbCommand(string.Format
                                  ("SELECT * FROM [{0}]", file.Name), con))
        {
            con.Open();

            // Using a DataTable to process the data
            using (OleDbDataAdapter adp = new OleDbDataAdapter(cmd))
            {
                DataTable tbl = new DataTable("MyTable");
                adp.Fill(tbl);

                //foreach (DataRow row in tbl.Rows)

                //Or directly make a list
                List<DataRow> list = dt.AsEnumerable().ToList();
            }
        }
    }
} 

See this and this for further reference.