i’m creating an application on C# that generates a hdf5 document with one row of the compound data being a timestamp (using unix timestamp), and i wish i could load this hdf5 in pandas and it load the timestamp column as a datetime64. I’ve tried to create the file from pandas and i saw it creates the dataset with a lot of attributes that i assume pandas read and do some logic to convert it while reading the file (the datetime inside the file created from pandas is a timestamp too), i can’t figure it out…
Here is my dataset creation code and some screenshots of what i had investigated
public void CriaHDF5Customizado(PackingConfigFile pf)
{
// PopulaOPC(pf);
H5FileId arquivoHDF5 = H5F.create("C:/Users/arthuro/Desktop/timestampteste.h5", H5F.CreateMode.ACC_TRUNC);
H5GroupId datasetGroup = H5G.create(arquivoHDF5, "Datasets");
H5GroupId infosGroup = H5G.create(arquivoHDF5, "Informations");
H5G.close(infosGroup);
opcSt opHelper = new opcSt();
opHelper.dt = (Int64)DateTime.Parse("1996-11-9").Subtract(new DateTime(1970, 1, 1,12,00,00, DateTimeKind.Utc)).TotalSeconds;
opHelper.qlt = (Int64)DateTime.Now.Subtract(new DateTime(1970, 1, 1, 0, 0, 0, DateTimeKind.Utc)).TotalSeconds;
opHelper.vl = 123456.7f;
int structsize = Marshal.SizeOf(opHelper);
H5DataTypeId myOPCType = H5T.create(H5T.CreateClass.COMPOUND, structsize);
//H5T.insert(myOPCType, "TimeStamp", 0, new H5DataTypeId(H5T.H5Type.NATIVE_LONG));
H5T.insert(myOPCType, "Quality", 8, new H5DataTypeId(H5T.H5Type.NATIVE_LONG));
H5T.insert(myOPCType, "Value", 16, new H5DataTypeId(H5T.H5Type.NATIVE_FLOAT));
long[] ds = new long[1];
ds[0] = 1;
H5DataTypeId dtDatetime = H5T.create_array(new H5DataTypeId(H5T.H5Type.NATIVE_LLONG), ds);
H5T.insert(myOPCType, "TimeStamp", 0, dtDatetime);
foreach (BasicVariable bv in pf.basicVariableList.bvList)
{
bv.PopulateOPCUA();
var bvnow = bv;
var bvNro = pf.basicVariableList.bvList.IndexOf(bv);
long[] dims = new long[1];
dims[0] = bv.bvData.Count;
H5DataSpaceId myDataSpace = H5S.create_simple(1, dims);
H5DataSetId bvDset = H5D.create(datasetGroup, bv.bvTag, myOPCType, myDataSpace);
var arrayaux = new List<opcSt>();
foreach (OPC_UA opc in bv.bvData)
{
var aux = new opcSt(opc.timeStamp, opc.quality, (float)opc.data);
arrayaux.Add(aux);
}
H5D.write(bvDset, myOPCType, new H5Array<opcSt>(arrayaux.ToArray()));
string[] stringteste = { "datetime64" };
H5DataTypeId attrDt = H5T.copy(H5T.H5Type.C_S1);
H5T.setSize(attrDt, stringteste[0].Length);
var longsz = new long[] { 1 };
var enc = new System.Text.ASCIIEncoding();
var array1 = enc.GetBytes(stringteste[0]);
var charArray = new byte[stringteste[0].Length + 1];
array1.CopyTo(charArray, 0);
charArray[stringteste[0].Length] = 0;
H5DataSpaceId atribDS = H5S.create_simple(1, longsz);
H5AttributeId Attribs = H5A.create(bvDset, "TimeStamp_dtype", attrDt, atribDS);
H5A.write(Attribs, attrDt, new H5Array<byte>(charArray));
stringteste[0] = "(lp0L0La.";
H5T.setSize(attrDt, stringteste[0].Length);
longsz = new long[] { 1 };
enc = new System.Text.ASCIIEncoding();
array1 = enc.GetBytes(stringteste[0]);
charArray = new byte[stringteste[0].Length + 1];
array1.CopyTo(charArray, 0);
charArray[stringteste[0].Length] = 0;
atribDS = H5S.create_simple(1, longsz);
H5AttributeId Attribs2 = H5A.create(bvDset, "TimeStamp_kind", attrDt, atribDS);
H5A.write(Attribs2, attrDt, new H5Array<byte>(charArray));
stringteste[0] = "N.";
H5T.setSize(attrDt, stringteste[0].Length);
longsz = new long[] { 1 };
enc = new System.Text.ASCIIEncoding();
array1 = enc.GetBytes(stringteste[0]);
charArray = new byte[stringteste[0].Length + 1];
array1.CopyTo(charArray, 0);
charArray[stringteste[0].Length] = 0;
atribDS = H5S.create_simple(1, longsz);
H5AttributeId Attribs3 = H5A.create(bvDset, "TimeStamp_meta", attrDt, atribDS);
H5A.write(Attribs3, attrDt, new H5Array<byte>(charArray));
H5S.close(atribDS);
H5A.close(Attribs);
H5A.close(Attribs2);
H5A.close(Attribs3);
H5D.close(bvDset);
H5S.close(myDataSpace);
bv.bvData = new List<OPC_UA>();
}
H5G.close(datasetGroup);
H5F.close(arquivoHDF5);
}
Pandas reading (timestamp and datetime):
being
1- The value read inside jupyter notebook (processed by pandas)
2- The real value inside the HDF5 File
https://i.stack.imgur.com/ZZJ3A.png
And these are the attributes of the table created by pandas (that i’ve tried to recreate in my code)
