public void TestIDataViewSchemaInvalidate()
{
DataFrame df = DataFrameTests.MakeDataFrameWithAllMutableColumnTypes(10, withNulls: false);
IDataView dataView = df;
DataViewSchema schema = dataView.Schema;
Assert.Equal(14, schema.Count);
df.Columns.Remove("Bool");
schema = dataView.Schema;
Assert.Equal(13, schema.Count);
DataFrameColumn boolColumn = new PrimitiveDataFrameColumn <bool>("Bool", Enumerable.Range(0, (int)df.Rows.Count).Select(x => x % 2 == 1));
df.Columns.Insert(0, boolColumn);
schema = dataView.Schema;
Assert.Equal(14, schema.Count);
Assert.Equal("Bool", schema[0].Name);
DataFrameColumn boolClone = boolColumn.Clone();
boolClone.SetName("BoolClone");
df.Columns[1] = boolClone;
schema = dataView.Schema;
Assert.Equal("BoolClone", schema[1].Name);
}
public void TestWriteCsvWithSemicolonSeparator()
{
using MemoryStream csvStream = new MemoryStream();
DataFrame dataFrame = DataFrameTests.MakeDataFrameWithAllColumnTypes(10, true);
var separator = ';';
DataFrame.WriteCsv(dataFrame, csvStream, separator: separator);
csvStream.Seek(0, SeekOrigin.Begin);
DataFrame readIn = DataFrame.LoadCsv(csvStream, separator: separator);
Assert.Equal(dataFrame.Rows.Count, readIn.Rows.Count);
Assert.Equal(dataFrame.Columns.Count, readIn.Columns.Count);
Assert.Equal(1F, readIn[1, 0]);
Assert.Equal(1F, readIn[1, 1]);
Assert.Equal(1F, readIn[1, 2]);
Assert.Equal(1F, readIn[1, 3]);
Assert.Equal(1F, readIn[1, 4]);
Assert.Equal(1F, readIn[1, 5]);
Assert.Equal(1F, readIn[1, 6]);
Assert.Equal(1F, readIn[1, 7]);
Assert.Equal(1F, readIn[1, 8]);
Assert.Equal(1F, readIn[1, 9]);
Assert.Equal(1F, readIn[1, 10]);
}
public void TestWriteCsvWithCultureInfo()
{
using MemoryStream csvStream = new MemoryStream();
DataFrame dataFrame = DataFrameTests.MakeDataFrameWithNumericColumns(10, true);
dataFrame[1, 1] = 1.1M;
dataFrame[1, 2] = 1.2D;
dataFrame[1, 3] = 1.3F;
var cultureInfo = new CultureInfo("en-US");
DataFrame.WriteCsv(dataFrame, csvStream, cultureInfo: cultureInfo);
csvStream.Seek(0, SeekOrigin.Begin);
DataFrame readIn = DataFrame.LoadCsv(csvStream);
Assert.Equal(dataFrame.Rows.Count, readIn.Rows.Count);
Assert.Equal(dataFrame.Columns.Count, readIn.Columns.Count);
Assert.Equal(1F, readIn[1, 0]);
Assert.Equal(1.1F, readIn[1, 1]);
Assert.Equal(1.2F, readIn[1, 2]);
Assert.Equal(1.3F, readIn[1, 3]);
Assert.Equal(1F, readIn[1, 4]);
Assert.Equal(1F, readIn[1, 5]);
Assert.Equal(1F, readIn[1, 6]);
Assert.Equal(1F, readIn[1, 7]);
Assert.Equal(1F, readIn[1, 8]);
Assert.Equal(1F, readIn[1, 9]);
Assert.Equal(1F, readIn[1, 10]);
}
public void TestWriteCsvWithCultureInfoRomanianAndSemiColon()
{
DataFrame dataFrame = DataFrameTests.MakeDataFrameWithNumericColumns(10, true);
dataFrame[1, 1] = 1.1M;
dataFrame[1, 2] = 1.2D;
dataFrame[1, 3] = 1.3F;
using MemoryStream csvStream = new MemoryStream();
var cultureInfo = new CultureInfo("ro-RO");
var separator = ';';
DataFrame.WriteCsv(dataFrame, csvStream, separator: separator, cultureInfo: cultureInfo);
csvStream.Seek(0, SeekOrigin.Begin);
DataFrame readIn = DataFrame.LoadCsv(csvStream, separator: separator);
Assert.Equal(dataFrame.Rows.Count, readIn.Rows.Count);
Assert.Equal(dataFrame.Columns.Count, readIn.Columns.Count);
Assert.Equal(1F, readIn[1, 0]);
// LoadCsv does not support culture info, therefore decimal point comma (,) is seen as thousand separator and is ignored when read
Assert.Equal(11F, readIn[1, 1]);
Assert.Equal(12F, readIn[1, 2]);
Assert.Equal(129999992F, readIn[1, 3]);
Assert.Equal(1F, readIn[1, 4]);
Assert.Equal(1F, readIn[1, 5]);
Assert.Equal(1F, readIn[1, 6]);
Assert.Equal(1F, readIn[1, 7]);
Assert.Equal(1F, readIn[1, 8]);
Assert.Equal(1F, readIn[1, 9]);
Assert.Equal(1F, readIn[1, 10]);
}
public void TestWriteCsvWithCultureInfoRomanianAndComma()
{
using MemoryStream csvStream = new MemoryStream();
DataFrame dataFrame = DataFrameTests.MakeDataFrameWithNumericColumns(10, true);
var cultureInfo = new CultureInfo("ro-RO");
var separator = cultureInfo.NumberFormat.NumberDecimalSeparator.First();
Assert.Throws <ArgumentException>(() => DataFrame.WriteCsv(dataFrame, csvStream, separator: separator, cultureInfo: cultureInfo));
}
private DataFrame MakeTestDataFrameWithParityAndTensColumns(int length)
{
DataFrame df = DataFrameTests.MakeDataFrameWithNumericColumns(length, false);
DataFrameColumn parityColumn = new StringDataFrameColumn("Parity", Enumerable.Range(0, length).Select(x => x % 2 == 0 ? "even" : "odd"));
DataFrameColumn tensColumn = new Int32DataFrameColumn("Tens", Enumerable.Range(0, length).Select(x => x / 10));
df.Columns.Insert(df.Columns.Count, parityColumn);
df.Columns.Insert(df.Columns.Count, tensColumn);
return(df);
}
public void TestDataFrameFromIDataView_SelectColumns()
{
DataFrame df = DataFrameTests.MakeDataFrameWithAllColumnTypes(10, withNulls: false);
IDataView dfAsIDataView = df;
DataFrame newDf = dfAsIDataView.ToDataFrame("Int", "Double");
Assert.Equal(dfAsIDataView.GetRowCount(), newDf.Rows.Count);
Assert.Equal(2, newDf.Columns.Count);
Assert.True(df.Columns["Int"].ElementwiseEquals(newDf.Columns["Int"]).All());
Assert.True(df.Columns["Double"].ElementwiseEquals(newDf.Columns["Double"]).All());
}
public void TestDataFrameFromIDataView()
{
DataFrame df = DataFrameTests.MakeDataFrameWithAllColumnTypes(10, withNulls: false);
df.Columns.Remove("Char"); // Because chars are returned as uint16 by IDataView, so end up comparing CharDataFrameColumn to UInt16DataFrameColumn and fail asserts
IDataView dfAsIDataView = df;
DataFrame newDf = dfAsIDataView.ToDataFrame();
Assert.Equal(dfAsIDataView.GetRowCount(), newDf.Rows.Count);
Assert.Equal(dfAsIDataView.Schema.Count, newDf.Columns.Count);
for (int i = 0; i < df.Columns.Count; i++)
{
Assert.True(df.Columns[i].ElementwiseEquals(newDf.Columns[i]).All());
}
}
public void TestArrowIntegration()
{
RecordBatch originalBatch = new RecordBatch.Builder()
.Append("Column1", false, col => col.Int32(array => array.AppendRange(Enumerable.Range(0, 10))))
.Append("Column2", true, new Int32Array(
valueBuffer: new ArrowBuffer.Builder <int>().AppendRange(Enumerable.Range(0, 10)).Build(),
nullBitmapBuffer: new ArrowBuffer.Builder <byte>().Append(0xfd).Append(0xff).Build(),
length: 10,
nullCount: 1,
offset: 0))
.Append("Column3", true, new Int32Array(
valueBuffer: new ArrowBuffer.Builder <int>().AppendRange(Enumerable.Range(0, 10)).Build(),
nullBitmapBuffer: new ArrowBuffer.Builder <byte>().Append(0x00).Append(0x00).Build(),
length: 10,
nullCount: 10,
offset: 0))
.Append("NullableBooleanColumn", true, new BooleanArray(
valueBuffer: new ArrowBuffer.Builder <byte>().Append(0xfd).Append(0xff).Build(),
nullBitmapBuffer: new ArrowBuffer.Builder <byte>().Append(0xed).Append(0xff).Build(),
length: 10,
nullCount: 2,
offset: 0))
.Append("StringDataFrameColumn", false, new StringArray.Builder().AppendRange(Enumerable.Range(0, 10).Select(x => x.ToString())).Build())
.Append("DoubleColumn", false, new DoubleArray.Builder().AppendRange(Enumerable.Repeat(1.0, 10)).Build())
.Append("FloatColumn", false, new FloatArray.Builder().AppendRange(Enumerable.Repeat(1.0f, 10)).Build())
.Append("ShortColumn", false, new Int16Array.Builder().AppendRange(Enumerable.Repeat((short)1, 10)).Build())
.Append("LongColumn", false, new Int64Array.Builder().AppendRange(Enumerable.Repeat((long)1, 10)).Build())
.Append("UIntColumn", false, new UInt32Array.Builder().AppendRange(Enumerable.Repeat((uint)1, 10)).Build())
.Append("UShortColumn", false, new UInt16Array.Builder().AppendRange(Enumerable.Repeat((ushort)1, 10)).Build())
.Append("ULongColumn", false, new UInt64Array.Builder().AppendRange(Enumerable.Repeat((ulong)1, 10)).Build())
.Append("ByteColumn", false, new Int8Array.Builder().AppendRange(Enumerable.Repeat((sbyte)1, 10)).Build())
.Append("UByteColumn", false, new UInt8Array.Builder().AppendRange(Enumerable.Repeat((byte)1, 10)).Build())
.Build();
DataFrame df = DataFrame.FromArrowRecordBatch(originalBatch);
DataFrameTests.VerifyColumnTypes(df, testArrowStringColumn: true);
IEnumerable <RecordBatch> recordBatches = df.ToArrowRecordBatches();
foreach (RecordBatch batch in recordBatches)
{
RecordBatchComparer.CompareBatches(originalBatch, batch);
}
}
public void TestDataFrameFromIDataView_SelectColumnsAndRows()
{
DataFrame df = DataFrameTests.MakeDataFrameWithAllColumnTypes(10, withNulls: false);
IDataView dfAsIDataView = df;
DataFrame newDf = dfAsIDataView.ToDataFrame(5, "Int", "Double");
Assert.Equal(5, newDf.Rows.Count);
for (int i = 0; i < newDf.Columns.Count; i++)
{
Assert.Equal(5, newDf.Columns[i].Length);
}
Assert.Equal(2, newDf.Columns.Count);
for (int r = 0; r < 5; r++)
{
Assert.Equal(df.Columns["Int"][r], newDf.Columns["Int"][r]);
Assert.Equal(df.Columns["Double"][r], newDf.Columns["Double"][r]);
}
}
public void TestDataFrameFromIDataView_SelectRows(int dataFrameSize, int rowSize)
{
DataFrame df = DataFrameTests.MakeDataFrameWithAllColumnTypes(dataFrameSize, withNulls: false);
df.Columns.Remove("Char"); // Because chars are returned as uint16 by DataViewSchema, so end up comparing CharDataFrameColumn to UInt16DataFrameColumn and fail asserts
df.Columns.Remove("Decimal"); // Because decimal is returned as double by DataViewSchema, so end up comparing DecimalDataFrameColumn to DoubleDataFrameColumn and fail asserts
IDataView dfAsIDataView = df;
DataFrame newDf;
if (rowSize == 100)
{
// Test default
newDf = dfAsIDataView.ToDataFrame();
}
else
{
newDf = dfAsIDataView.ToDataFrame(rowSize);
}
if (rowSize == -1)
{
rowSize = dataFrameSize;
}
Assert.Equal(rowSize, newDf.Rows.Count);
Assert.Equal(df.Columns.Count, newDf.Columns.Count);
for (int i = 0; i < newDf.Columns.Count; i++)
{
Assert.Equal(rowSize, newDf.Columns[i].Length);
Assert.Equal(df.Columns[i].Name, newDf.Columns[i].Name);
}
Assert.Equal(dfAsIDataView.Schema.Count, newDf.Columns.Count);
for (int c = 0; c < df.Columns.Count; c++)
{
for (int r = 0; r < rowSize; r++)
{
Assert.Equal(df.Columns[c][r], newDf.Columns[c][r]);
}
}
}
public void TestIDataView()
{
IDataView dataView = DataFrameTests.MakeDataFrameWithAllColumnTypes(10, withNulls: false);
DataDebuggerPreview preview = dataView.Preview();
Assert.Equal(10, preview.RowView.Length);
Assert.Equal(15, preview.ColumnView.Length);
Assert.Equal("Byte", preview.ColumnView[0].Column.Name);
Assert.Equal((byte)0, preview.ColumnView[0].Values[0]);
Assert.Equal((byte)1, preview.ColumnView[0].Values[1]);
Assert.Equal("Decimal", preview.ColumnView[1].Column.Name);
Assert.Equal((double)0, preview.ColumnView[1].Values[0]);
Assert.Equal((double)1, preview.ColumnView[1].Values[1]);
Assert.Equal("Double", preview.ColumnView[2].Column.Name);
Assert.Equal((double)0, preview.ColumnView[2].Values[0]);
Assert.Equal((double)1, preview.ColumnView[2].Values[1]);
Assert.Equal("Float", preview.ColumnView[3].Column.Name);
Assert.Equal((float)0, preview.ColumnView[3].Values[0]);
Assert.Equal((float)1, preview.ColumnView[3].Values[1]);
Assert.Equal("Int", preview.ColumnView[4].Column.Name);
Assert.Equal((int)0, preview.ColumnView[4].Values[0]);
Assert.Equal((int)1, preview.ColumnView[4].Values[1]);
Assert.Equal("Long", preview.ColumnView[5].Column.Name);
Assert.Equal((long)0, preview.ColumnView[5].Values[0]);
Assert.Equal((long)1, preview.ColumnView[5].Values[1]);
Assert.Equal("Sbyte", preview.ColumnView[6].Column.Name);
Assert.Equal((sbyte)0, preview.ColumnView[6].Values[0]);
Assert.Equal((sbyte)1, preview.ColumnView[6].Values[1]);
Assert.Equal("Short", preview.ColumnView[7].Column.Name);
Assert.Equal((short)0, preview.ColumnView[7].Values[0]);
Assert.Equal((short)1, preview.ColumnView[7].Values[1]);
Assert.Equal("Uint", preview.ColumnView[8].Column.Name);
Assert.Equal((uint)0, preview.ColumnView[8].Values[0]);
Assert.Equal((uint)1, preview.ColumnView[8].Values[1]);
Assert.Equal("Ulong", preview.ColumnView[9].Column.Name);
Assert.Equal((ulong)0, preview.ColumnView[9].Values[0]);
Assert.Equal((ulong)1, preview.ColumnView[9].Values[1]);
Assert.Equal("Ushort", preview.ColumnView[10].Column.Name);
Assert.Equal((ushort)0, preview.ColumnView[10].Values[0]);
Assert.Equal((ushort)1, preview.ColumnView[10].Values[1]);
Assert.Equal("String", preview.ColumnView[11].Column.Name);
Assert.Equal("0".ToString(), preview.ColumnView[11].Values[0].ToString());
Assert.Equal("1".ToString(), preview.ColumnView[11].Values[1].ToString());
Assert.Equal("Char", preview.ColumnView[12].Column.Name);
Assert.Equal((ushort)65, preview.ColumnView[12].Values[0]);
Assert.Equal((ushort)66, preview.ColumnView[12].Values[1]);
Assert.Equal("Bool", preview.ColumnView[13].Column.Name);
Assert.Equal(true, preview.ColumnView[13].Values[0]);
Assert.Equal(false, preview.ColumnView[13].Values[1]);
Assert.Equal("ArrowString", preview.ColumnView[14].Column.Name);
Assert.Equal("foo".ToString(), preview.ColumnView[14].Values[0].ToString());
Assert.Equal("foo".ToString(), preview.ColumnView[14].Values[1].ToString());
}
public void TestIDataViewWithNulls()
{
int length = 10;
IDataView dataView = DataFrameTests.MakeDataFrameWithAllColumnTypes(length, withNulls: true);
DataDebuggerPreview preview = dataView.Preview();
Assert.Equal(length, preview.RowView.Length);
Assert.Equal(15, preview.ColumnView.Length);
Assert.Equal("Byte", preview.ColumnView[0].Column.Name);
Assert.Equal((byte)0, preview.ColumnView[0].Values[0]);
Assert.Equal((byte)1, preview.ColumnView[0].Values[1]);
Assert.Equal((byte)4, preview.ColumnView[0].Values[4]);
Assert.Equal((byte)0, preview.ColumnView[0].Values[5]); // null row
Assert.Equal((byte)6, preview.ColumnView[0].Values[6]);
Assert.Equal("Decimal", preview.ColumnView[1].Column.Name);
Assert.Equal((double)0, preview.ColumnView[1].Values[0]);
Assert.Equal((double)1, preview.ColumnView[1].Values[1]);
Assert.Equal((double)4, preview.ColumnView[1].Values[4]);
Assert.Equal(double.NaN, preview.ColumnView[1].Values[5]); // null row
Assert.Equal((double)6, preview.ColumnView[1].Values[6]);
Assert.Equal("Double", preview.ColumnView[2].Column.Name);
Assert.Equal((double)0, preview.ColumnView[2].Values[0]);
Assert.Equal((double)1, preview.ColumnView[2].Values[1]);
Assert.Equal((double)4, preview.ColumnView[2].Values[4]);
Assert.Equal(double.NaN, preview.ColumnView[2].Values[5]); // null row
Assert.Equal((double)6, preview.ColumnView[2].Values[6]);
Assert.Equal("Float", preview.ColumnView[3].Column.Name);
Assert.Equal((float)0, preview.ColumnView[3].Values[0]);
Assert.Equal((float)1, preview.ColumnView[3].Values[1]);
Assert.Equal((float)4, preview.ColumnView[3].Values[4]);
Assert.Equal(float.NaN, preview.ColumnView[3].Values[5]); // null row
Assert.Equal((float)6, preview.ColumnView[3].Values[6]);
Assert.Equal("Int", preview.ColumnView[4].Column.Name);
Assert.Equal((int)0, preview.ColumnView[4].Values[0]);
Assert.Equal((int)1, preview.ColumnView[4].Values[1]);
Assert.Equal((int)4, preview.ColumnView[4].Values[4]);
Assert.Equal((int)0, preview.ColumnView[4].Values[5]); // null row
Assert.Equal((int)6, preview.ColumnView[4].Values[6]);
Assert.Equal("Long", preview.ColumnView[5].Column.Name);
Assert.Equal((long)0, preview.ColumnView[5].Values[0]);
Assert.Equal((long)1, preview.ColumnView[5].Values[1]);
Assert.Equal((long)4, preview.ColumnView[5].Values[4]);
Assert.Equal((long)0, preview.ColumnView[5].Values[5]); // null row
Assert.Equal((long)6, preview.ColumnView[5].Values[6]);
Assert.Equal("Sbyte", preview.ColumnView[6].Column.Name);
Assert.Equal((sbyte)0, preview.ColumnView[6].Values[0]);
Assert.Equal((sbyte)1, preview.ColumnView[6].Values[1]);
Assert.Equal((sbyte)4, preview.ColumnView[6].Values[4]);
Assert.Equal((sbyte)0, preview.ColumnView[6].Values[5]); // null row
Assert.Equal((sbyte)6, preview.ColumnView[6].Values[6]);
Assert.Equal("Short", preview.ColumnView[7].Column.Name);
Assert.Equal((short)0, preview.ColumnView[7].Values[0]);
Assert.Equal((short)1, preview.ColumnView[7].Values[1]);
Assert.Equal((short)4, preview.ColumnView[7].Values[4]);
Assert.Equal((short)0, preview.ColumnView[7].Values[5]); // null row
Assert.Equal((short)6, preview.ColumnView[7].Values[6]);
Assert.Equal("Uint", preview.ColumnView[8].Column.Name);
Assert.Equal((uint)0, preview.ColumnView[8].Values[0]);
Assert.Equal((uint)1, preview.ColumnView[8].Values[1]);
Assert.Equal((uint)4, preview.ColumnView[8].Values[4]);
Assert.Equal((uint)0, preview.ColumnView[8].Values[5]); // null row
Assert.Equal((uint)6, preview.ColumnView[8].Values[6]);
Assert.Equal("Ulong", preview.ColumnView[9].Column.Name);
Assert.Equal((ulong)0, preview.ColumnView[9].Values[0]);
Assert.Equal((ulong)1, preview.ColumnView[9].Values[1]);
Assert.Equal((ulong)4, preview.ColumnView[9].Values[4]);
Assert.Equal((ulong)0, preview.ColumnView[9].Values[5]); // null row
Assert.Equal((ulong)6, preview.ColumnView[9].Values[6]);
Assert.Equal("Ushort", preview.ColumnView[10].Column.Name);
Assert.Equal((ushort)0, preview.ColumnView[10].Values[0]);
Assert.Equal((ushort)1, preview.ColumnView[10].Values[1]);
Assert.Equal((ushort)4, preview.ColumnView[10].Values[4]);
Assert.Equal((ushort)0, preview.ColumnView[10].Values[5]); // null row
Assert.Equal((ushort)6, preview.ColumnView[10].Values[6]);
Assert.Equal("String", preview.ColumnView[11].Column.Name);
Assert.Equal("0", preview.ColumnView[11].Values[0].ToString());
Assert.Equal("1", preview.ColumnView[11].Values[1].ToString());
Assert.Equal("4", preview.ColumnView[11].Values[4].ToString());
Assert.Equal("", preview.ColumnView[11].Values[5].ToString()); // null row
Assert.Equal("6", preview.ColumnView[11].Values[6].ToString());
Assert.Equal("Char", preview.ColumnView[12].Column.Name);
Assert.Equal((ushort)65, preview.ColumnView[12].Values[0]);
Assert.Equal((ushort)66, preview.ColumnView[12].Values[1]);
Assert.Equal((ushort)69, preview.ColumnView[12].Values[4]);
Assert.Equal((ushort)0, preview.ColumnView[12].Values[5]); // null row
Assert.Equal((ushort)71, preview.ColumnView[12].Values[6]);
Assert.Equal("Bool", preview.ColumnView[13].Column.Name);
Assert.Equal(true, preview.ColumnView[13].Values[0]);
Assert.Equal(false, preview.ColumnView[13].Values[1]);
Assert.Equal(true, preview.ColumnView[13].Values[4]);
Assert.Equal(false, preview.ColumnView[13].Values[5]); // null row
Assert.Equal(true, preview.ColumnView[13].Values[6]);
Assert.Equal("ArrowString", preview.ColumnView[14].Column.Name);
Assert.Equal("foo", preview.ColumnView[14].Values[0].ToString());
Assert.Equal("foo", preview.ColumnView[14].Values[1].ToString());
Assert.Equal("foo", preview.ColumnView[14].Values[4].ToString());
Assert.Equal("", preview.ColumnView[14].Values[5].ToString()); // null row
Assert.Equal("foo", preview.ColumnView[14].Values[6].ToString());
}
