public void DataFrame()
{
var np = new NumPy <int>();
var pd = new Pandas();
var array = np.random.randint(low: 0, high: 10, size: new Shape(5, 5));
var df = pd.DataFrame(array, columns: new string[] { "a", "b", "c", "d", "e" });
}
public void SetColumn_Test()
{
var dict = new Dictionary <string, NDArray>
{
{ "one", np.arange(1000) },
{ "two", np.arange(1001, 2001) }
};
var pd = new Pandas();
var df1 = pd.DataFrame <string>(dict);
df1["three"] = new Series(np.arange(2001, 3001));
Assert.Equal(3000, df1.Size);
df1.SingleColumn("four", 1);
Assert.Equal(1, df1["four"][500]);
Assert.Equal(4000, df1.Size);
df1.SingleColumn(1, 1);
Assert.Equal(1, df1["two"][500]);
df1.Column("five", np.arange(3001, 4001));
Assert.Equal(3001, df1["five"][0]);
df1.SingleColumn(4, 1);
Assert.Equal(1, df1["five"][0]);
Assert.Equal(3000, df1["three"][999]);
df1["three"] = new Series(np.arange(1000));
Assert.Equal(999, df1["three"][999]);
}
private void CreateSliceModel()
{
int row = 10;
int col = 10;
var nd = np.random.randn(row, col);
NDArray array = nd;
//array.reshape(5, 4);
var pd = new Pandas();
List <string> indexs = new List <string>();
List <string> columns = new List <string>();
CreateRowAndCol(row, col, ref indexs, ref columns);
IDataFrame df1 = pd.DataFrame(array, indexs, columns, typeof(object));
_dataFrame = df1;
}
public void WriteCsvQuoted_ToFile_Test()
{
var filepath = "write_quoted_test.csv";
var array = np.arange(100).reshape(20, 5);
var columnNames = new string[] { "first", "second", "third",
"fourth", "fifth" };
var pd = new Pandas();
IDataFrame df1 = pd.DataFrame(array, null, columnNames, typeof(object));
df1.to_csv(filepath, quoting: 1);
using (var fr = File.OpenText(filepath))
{
Assert.Equal(string.Join(',', columnNames), fr.ReadLine());
for (var i = 0; i < array.shape[0]; i++)
{
Assert.Equal('"' + string.Join("\",\"", array[i].Data <int>()) + '"', fr.ReadLine());
}
}
}
public void Create_Group_Test()
{
var dict = new Dictionary <string, NDArray>
{
{ "col1", np.arange(5) },
{ "col2", np.arange(5) },
{ "col3", np.arange(5) },
{ "col4", np.arange(5) },
{ "col5", np.arange(5) },
};
var pd = new Pandas();
var df1 = pd.DataFrame <string>(dict, new string[] {
"row1", "row2", "row3", "row4", "row5"
});
var gro = df1.groupby("col2");
var group = gro.Groups;
var a = gro.Groups[1];
Assert.Equal("row2", a.Values[0]);
}
public void WriteCsvFormated_ToFile_Test()
{
var filepath = "write_quoted_test.csv";
var array = np.arange(0, 50, 0.5).reshape(20, 5);
var columnNames = new string[] { "first", "second", "third",
"fourth", "fifth" };
var floatFormat = "E03";
var pd = new Pandas();
IDataFrame df1 = pd.DataFrame(array, null, columnNames, typeof(object));
df1.to_csv(filepath, float_format: floatFormat);
using (var fr = File.OpenText(filepath))
{
Assert.Equal(string.Join(',', columnNames), fr.ReadLine());
for (var i = 0; i < array.shape[0]; i++)
{
var formattedData = array[i].Data <double>().Select(
x => x.ToString(floatFormat));
Assert.Equal(string.Join(",", formattedData), fr.ReadLine());
}
}
}
private static IDataFrame CreateDataFrame(IDataFrame df, List <int> indexs)
{
var value = df.Values.Array;
int colSize = df.Columns.Size;
int rowSize = df.Index.Size;
var cols = df.Columns.Values.Array;
var rows = df.Index.Values.Array;
var rowArray = Array.CreateInstance(df.Index.DType, rows.Length);
int index = 0;
foreach (var ind in indexs)
{
rowArray.SetValue(rows.GetValue(ind), index);
index++;
}
object[] objs = new object[df.Size];
int ins = 0;
for (int c = 0; c < colSize; c++)
{
for (int r = 0; r < rowSize; r++)
{
objs[ins] = value.GetValue(indexs[r] + c * rowSize);
ins++;
}
}
NDArray nDArray = new NDArray(df.DType, new Shape(rowSize, colSize));
nDArray.SetData(objs);
var pd = new Pandas();
IDataFrame dataFrame = pd.DataFrame(nDArray, null, null, df.DType);
dataFrame.Index.Values.SetData(rowArray);
dataFrame.Columns.Values.SetData(cols);
return(dataFrame);
}