def createHDF5_file(signal, parm_dict, h5_path='', ds_name='FF_Raw'):
"""
Generates the HDF5 file given path to a specific file and a parameters dictionary
Parameters
----------
h5_path : string
Path to desired h5 file.
signal : str, ndarray
Path to the data file to be converted or a workspace array
parm_dict : dict
Scan parameters
Returns
-------
h5_path: str
The filename path to the H5 file create
"""
sg = signal
if 'str' in str(type(signal)):
sg = load.signal(signal)
if not any(h5_path): # if not passed, auto-generate name
fname = signal.replace('/', '\\')
h5_path = fname[:-4] + '.h5'
else:
fname = h5_path
hdf = px.ioHDF5(h5_path)
usid.hdf_utils.print_tree(hdf.file)
ff_group = px.MicroDataGroup('FF_Group', parent='/')
root_group = px.MicroDataGroup('/')
# fname = fname.split('\\')[-1][:-4]
sg = px.MicroDataset(ds_name, data=sg, dtype=np.float32, parent=ff_group)
if 'pnts_per_pixel' not in parm_dict.keys():
parm_dict['pnts_per_avg'] = signal.shape[1]
parm_dict['pnts_per_pixel'] = 1
parm_dict['pnts_per_line'] = parm_dict['num_cols']
ff_group.addChildren([sg])
ff_group.attrs = parm_dict
# Get reference for writing the data
h5_refs = hdf.writeData(ff_group, print_log=True)
hdf.flush()
# acquired from advanced atomic force microscopes. In this dataset, a spectra was colllected for each position in a two
# dimensional grid of spatial locations. Thus, this is a three dimensional dataset that has been flattened to a two
# dimensional matrix in accordance with the pycroscopy data format.
#
# Fortunately, all statistical analysis, machine learning, spectral unmixing algorithms, etc. only accept data that is
# formatted in the same manner of [position x spectra] in a two dimensional matrix.
#
# We will begin by downloading the BE-PFM dataset from Github
#
data_file_path = 'temp_um.h5'
# download the data file from Github:
url = 'https://raw.githubusercontent.com/pycroscopy/pycroscopy/master/data/BELine_0004.h5'
_ = wget.download(url, data_file_path, bar=None)
hdf = px.ioHDF5(data_file_path)
h5_file = hdf.file
print('Contents of data file:')
print('----------------------')
px.hdf_utils.print_tree(h5_file)
print('----------------------')
h5_meas_grp = h5_file['Measurement_000']
# Extracting some basic parameters:
num_rows = px.hdf_utils.get_attr(h5_meas_grp,'grid_num_rows')
num_cols = px.hdf_utils.get_attr(h5_meas_grp,'grid_num_cols')
# Getting a reference to the main dataset:
h5_main = h5_meas_grp['Channel_000/Raw_Data']
data_group.addChildren([ds_empty]) root_group.addChildren([ds_main, data_group]) ############################################################################## # The showTree method allows us to view the data structure before the hdf5 file is # created. root_group.showTree() ############################################################################## # Now that we have created the objects, we can write them to an hdf5 file # First we specify the path to the file h5_path = 'microdata_test.h5' # Then we use the ioHDF5 class to build the file from our objects. hdf = px.ioHDF5(h5_path) ############################################################################## # The writeData method builds the hdf5 file using the structure defined by the # MicroData objects. It returns a list of references to all h5py objects in the # new file. h5_refs = hdf.writeData(root_group, print_log=True) # We can use these references to get the h5py dataset and group objects h5_main = px.io.hdf_utils.getH5DsetRefs(['Main_Data'], h5_refs)[0] h5_empty = px.io.hdf_utils.getH5DsetRefs(['Empty_Data'], h5_refs)[0] ############################################################################## # Compare the data in our dataset to the original print(np.allclose(h5_main[()], data1))
""" ============ Load Dataset ============ Load a dataset from the hdf5 file. For this example, we will be loading the Raw_Data dataset. """ # Code source: pycroscopy # Liscense: MIT import h5py import pycroscopy as px h5_path = px.uiGetFile(caption='Select .h5 file', filter='HDF5 file (*.h5)') # Load the dataset with h5py h5_file1 = h5py.File(h5_path, 'r') h5_raw1 = h5_file1['Measurement_000\Channel_000\Raw_Data'] # Load the dataset with pycroscopy h5_file2 = px.ioHDF5(h5_path) h5_raw2 = h5_file2['Measurement_000\Channel_000\Raw_Data']