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_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 TestDataFrameFromIDataView_MLData_SelectColumnsAndRows()
{
IDataView data = GetASampleIDataView();
DataFrame df = data.ToDataFrame(3, "Name", "Value");
Assert.Equal(3, df.Rows.Count);
Assert.Equal(2, df.Columns.Count);
foreach (var column in df.Columns)
{
Assert.Equal(3, column.Length);
}
VerifyDataFrameColumnAndDataViewColumnValues <string>("Name", data, df, 3);
VerifyDataFrameColumnAndDataViewColumnValues <float>("Value", data, df, 3);
}
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 TestDataFrameFromIDataView_MLData_SelectRows(int maxRows)
{
IDataView data = GetASampleIDataView();
DataFrame df = data.ToDataFrame(maxRows);
Assert.Equal(maxRows, df.Rows.Count);
Assert.Equal(3, df.Columns.Count);
foreach (var column in df.Columns)
{
Assert.Equal(maxRows, column.Length);
}
VerifyDataFrameColumnAndDataViewColumnValues <string>("Name", data, df, maxRows);
VerifyDataFrameColumnAndDataViewColumnValues <bool>("FilterNext", data, df, maxRows);
VerifyDataFrameColumnAndDataViewColumnValues <float>("Value", data, df, maxRows);
}
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]);
}
}
