我在C#上创建一个应用程序,生成一个hdf5文档,其中一行复合数据是一个时间戳(使用unix时间戳),我希望我可以在pandas中加载这个hdf5并加载timestamp列作为datetime64。我已经尝试从pandas创建文件,我看到它创建了具有许多属性的数据集,我认为pandas读取并在读取文件时做一些逻辑来转换它(从pandas创建的文件中的日期时间是也是一个时间戳),我无法弄清楚......
这是我的数据集创建代码和我调查过的一些截图
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));
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阅读(时间戳和日期时间):
是1-在jupyter笔记本中读取的值(由pandas处理) 2- HDF5文件中的实际值
这些是pandas创建的表的属性(我试图在我的代码中重新创建)