/// <summary>
/// Reads CSV data passed in as a string into a DataFrame.
/// </summary>
/// <param name="csvString">csv data passed in as a string</param>
/// <param name="separator">column separator</param>
/// <param name="header">has a header or not</param>
/// <param name="columnNames">column names (can be empty)</param>
/// <param name="dataTypes">column types (can be empty)</param>
/// <param name="numberOfRowsToRead">number of rows to read not including the header(if present)</param>
/// <param name="guessRows">number of rows used to guess types</param>
/// <param name="addIndexColumn">add one column with the row index</param>
/// <returns><see cref="DataFrame"/></returns>
public static DataFrame LoadCsvFromString(string csvString,
char separator = ',', bool header = true,
string[] columnNames = null, Type[] dataTypes = null,
long numberOfRowsToRead = -1, int guessRows = 10, bool addIndexColumn = false)
{
WrappedStreamReaderOrStringReader wrappedStreamReaderOrStringReader = new WrappedStreamReaderOrStringReader(csvString);
return(ReadCsvLinesIntoDataFrame(wrappedStreamReaderOrStringReader, separator, header, columnNames, dataTypes, numberOfRowsToRead, guessRows, addIndexColumn));
}
/// <summary>
/// Reads a seekable stream of CSV data into a DataFrame.
/// </summary>
/// <param name="csvStream">stream of CSV data to be read in</param>
/// <param name="separator">column separator</param>
/// <param name="header">has a header or not</param>
/// <param name="columnNames">column names (can be empty)</param>
/// <param name="dataTypes">column types (can be empty)</param>
/// <param name="numberOfRowsToRead">number of rows to read not including the header(if present)</param>
/// <param name="guessRows">number of rows used to guess types</param>
/// <param name="addIndexColumn">add one column with the row index</param>
/// <param name="encoding">The character encoding. Defaults to UTF8 if not specified</param>
/// <returns><see cref="DataFrame"/></returns>
public static DataFrame LoadCsv(Stream csvStream,
char separator = ',', bool header = true,
string[] columnNames = null, Type[] dataTypes = null,
long numberOfRowsToRead = -1, int guessRows = 10, bool addIndexColumn = false,
Encoding encoding = null)
{
if (!csvStream.CanSeek)
{
throw new ArgumentException(Strings.NonSeekableStream, nameof(csvStream));
}
if (dataTypes == null && guessRows <= 0)
{
throw new ArgumentException(string.Format(Strings.ExpectedEitherGuessRowsOrDataTypes, nameof(guessRows), nameof(dataTypes)));
}
WrappedStreamReaderOrStringReader wrappedStreamReaderOrStringReader = new WrappedStreamReaderOrStringReader(csvStream, encoding ?? Encoding.UTF8);
return(ReadCsvLinesIntoDataFrame(wrappedStreamReaderOrStringReader, separator, header, columnNames, dataTypes, numberOfRowsToRead, guessRows, addIndexColumn));
}
private static DataFrame ReadCsvLinesIntoDataFrame(WrappedStreamReaderOrStringReader wrappedReader,
char separator = ',', bool header = true,
string[] columnNames = null, Type[] dataTypes = null,
long numberOfRowsToRead = -1, int guessRows = 10, bool addIndexColumn = false
)
{
if (dataTypes == null && guessRows <= 0)
{
throw new ArgumentException(string.Format(Strings.ExpectedEitherGuessRowsOrDataTypes, nameof(guessRows), nameof(dataTypes)));
}
List <DataFrameColumn> columns;
string[] fields;
using (var textReader = wrappedReader.GetTextReader())
{
TextFieldParser parser = new TextFieldParser(textReader);
parser.SetDelimiters(separator.ToString());
var linesForGuessType = new List <string[]>();
long rowline = 0;
int numberOfColumns = dataTypes?.Length ?? 0;
if (header == true && numberOfRowsToRead != -1)
{
numberOfRowsToRead++;
}
// First pass: schema and number of rows.
while ((fields = parser.ReadFields()) != null)
{
if ((numberOfRowsToRead == -1) || rowline < numberOfRowsToRead)
{
if (linesForGuessType.Count < guessRows || (header && rowline == 0))
{
if (header && rowline == 0)
{
if (columnNames == null)
{
columnNames = fields;
}
}
else
{
linesForGuessType.Add(fields);
numberOfColumns = Math.Max(numberOfColumns, fields.Length);
}
}
}
++rowline;
if (rowline == guessRows || guessRows == 0)
{
break;
}
}
if (rowline == 0)
{
throw new FormatException(Strings.EmptyFile);
}
columns = new List <DataFrameColumn>(numberOfColumns);
// Guesses types or looks up dataTypes and adds columns.
for (int i = 0; i < numberOfColumns; ++i)
{
Type kind = dataTypes == null?GuessKind(i, linesForGuessType) : dataTypes[i];
columns.Add(CreateColumn(kind, columnNames, i));
}
}
DataFrame ret = new DataFrame(columns);
// Fill values.
using (var textReader = wrappedReader.GetTextReader())
{
TextFieldParser parser = new TextFieldParser(textReader);
parser.SetDelimiters(separator.ToString());
long rowline = 0;
while ((fields = parser.ReadFields()) != null && (numberOfRowsToRead == -1 || rowline < numberOfRowsToRead))
{
if (header && rowline == 0)
{
// Skips.
}
else
{
ret.Append(fields, inPlace: true);
}
++rowline;
}
if (addIndexColumn)
{
PrimitiveDataFrameColumn <int> indexColumn = new PrimitiveDataFrameColumn <int>("IndexColumn", columns[0].Length);
for (int i = 0; i < columns[0].Length; i++)
{
indexColumn[i] = i;
}
columns.Insert(0, indexColumn);
}
}
return(ret);
}
