Skip to content
Snippets Groups Projects
Commit 57014b2c authored by Gröne, Tjark Leon Raphael's avatar Gröne, Tjark Leon Raphael
Browse files

Update file maxwell_integrate_to_h5.py

parent 6a7aa2ee
No related branches found
No related tags found
No related merge requests found
Show whitespace changes
Inline Side-by-side
maxwell_integrate_to_h5.py
+ 58
− 190
View file @ 57014b2c
......@@ -15,7 +15,8 @@ from watchdog.observers.polling import PollingObserver
from watchdog.events import PatternMatchingEventHandler
from multiprocessing.pool import ThreadPool as Pool
import pandas as pd
from silx.io.dictdump import h5todict, dicttoh5
#from silx.io.dictdump import h5todict, dicttoh5
import h5py
import re
......@@ -124,198 +125,65 @@ def integrate_ims_in_dir(path_im, path_int, dtype_im=".tif", dtype_int=".dat"):
subdir_name = os.path.basename(os.path.normpath(subdir_path_int))
results_df.to_csv(os.path.join(subdir_path_int, f"{subdir_name}.csv"), index=False)
# Sort results_data by filename
def natural_sort_key(item):
return [int(text) if text.isdigit() else text.lower() for text in re.split(r'(\d+)', item["filename"])]
results_data = sorted(results_data, key=natural_sort_key)
# Prepare data for HDF5 file using silx
hdf5_data = {
subdir_name: {
"@NX_class": "NXentry",
"description": f"{subdir_name}",
"files": [
{
"name": f"{idx}.1",
"path": f"/{idx}.1",
"attributes": [
{
"name": "NX_class",
"shape": [],
"type": {
"class": "String",
"charSet": "UTF-8",
"strPad": "null-terminated"
},
"value": "NXentry"
},
{
"name": "default",
"shape": [],
"type": {
"class": "String",
"charSet": "UTF-8",
"strPad": "null-terminated"
},
"value": "measurement"
},
{
"name": "plotselect",
"shape": [],
"type": {
"class": "String",
"charSet": "UTF-8",
"strPad": "null-terminated"
},
"value": "q,I"
}
],
"kind": "group",
"children": [
{
"name": "measurement",
"path": f"/{idx}.1/measurement",
"attributes": [
{
"name": "NX_class",
"shape": [],
"type": {
"class": "String",
"charSet": "UTF-8",
"strPad": "null-terminated"
},
"value": "NXcollection"
}
],
"kind": "group",
"children": [
{
"name": "q",
"path": f"/{idx}.1/measurement/q",
"attributes": [],
"kind": "dataset",
"shape": [len(result["q"])],
"type": {
"class": "Float",
"endianness": "little-endian",
"size": 64
},
"chunks": [min(len(result["q"]), 1000)],
"filters": [],
"rawType": {
"signed": False,
"type": 1,
"vlen": False,
"littleEndian": True,
"size": 8,
"total_size": len(result["q"])
},
"value": result["q"]
},
{
"name": "I",
"path": f"/{idx}.1/measurement/I",
"attributes": [],
"kind": "dataset",
"shape": [len(result["I"])],
"type": {
"class": "Float",
"endianness": "little-endian",
"size": 64
},
"chunks": [min(len(result["I"]), 1000)],
"filters": [],
"rawType": {
"signed": False,
"type": 1,
"vlen": False,
"littleEndian": True,
"size": 8,
"total_size": len(result["I"])
},
"value": result["I"]
},
{
"name": "dI",
"path": f"/{idx}.1/measurement/dI",
"attributes": [],
"kind": "dataset",
"shape": [len(result["dI"])],
"type": {
"class": "Float",
"endianness": "little-endian",
"size": 64
},
"chunks": [min(len(result["dI"]), 1000)],
"filters": [],
"rawType": {
"signed": False,
"type": 1,
"vlen": False,
"littleEndian": True,
"size": 8,
"total_size": len(result["dI"])
},
"value": result["dI"]
}
]
},
{
"name": "plotselect",
"path": f"/{idx}.1/plotselect",
"attributes": [
{
"name": "NX_class",
"shape": [],
"type": {
"class": "String",
"charSet": "UTF-8",
"strPad": "null-terminated"
},
"value": "NXcollection"
},
{
"name": "axes",
"shape": [1],
"type": {
"class": "String",
"charSet": "UTF-8",
"strPad": "null-terminated"
},
"value": "q"
},
{
"name": "signal",
"shape": [],
"type": {
"class": "String",
"charSet": "UTF-8",
"strPad": "null-terminated"
},
"value": "I"
}
],
"kind": "group"
}
]
}
for idx, result in enumerate(results_data, start=1)
]
}
}
# Save to HDF5 file using silx
hdf5_file_path = os.path.join(subdir_path_int, f"{subdir_name}.h5")
dicttoh5(hdf5_data, hdf5_file_path, mode="w")
print(f"Results for subdirectory {subdir_name} saved to HDF5 file using silx.")
# Create the HDF5 file
with h5py.File("output_silx_format.h5", "w") as f:
# Create top-level group (e.g., subdir_name)
subdir_grp = f.create_group(subdir_name)
subdir_grp.attrs["NX_class"] = np.string_("NXentry")
subdir_grp.attrs["description"] = np.string_(subdir_name)
for idx, result in enumerate(results_data, start=1):
scan_name = f"{idx}.1"
scan_grp = subdir_grp.create_group(scan_name)
# --- Group-level attributes ---
scan_grp.attrs["NX_class"] = np.string_("NXentry")
scan_grp.attrs["default"] = np.string_("measurement")
scan_grp.attrs["plotselect"] = np.string_("q,I")
# --- Measurement group ---
meas_grp = scan_grp.create_group("measurement")
meas_grp.attrs["NX_class"] = np.string_("NXcollection")
# Datasets: q, I, dI
for name in ["q", "I", "dI"]:
data = result[name]
meas_grp.create_dataset(name, data=data, chunks=(min(len(data), 1000),), dtype='f8')
# --- Plotselect group ---
plotselect_grp = scan_grp.create_group("plotselect")
plotselect_grp.attrs["NX_class"] = np.string_("NXcollection")
plotselect_grp.attrs["axes"] = np.string_("q")
plotselect_grp.attrs["signal"] = np.string_("I")
# # Sort results_data by filename
# def natural_sort_key(item):
# return [int(text) if text.isdigit() else text.lower() for text in re.split(r'(\d+)', item["filename"])]
# results_data = sorted(results_data, key=natural_sort_key)
# # Prepare data for HDF5 file using silx
# hdf5_data = {}
# for idx, result in enumerate(results_data, start=1):
# hdf5_data[f"{idx}.1"] = {
# "@NX_class": "NXentry",
# "measurement": {
# "@NX_class": "NXcollection",
# "q": result["q"].tolist(), # Convert numpy arrays to lists for HDF5 compatibility
# "I": result["I"].tolist(),
# "dI": result["dI"].tolist(),
# },
# "plotselect": {
# "@NX_class": "NXcollection",
# "axes": "q",
# "signal": "I",
# },
# }
print(f"Results for subdirectory {subdir_name} saved to HDF5 file using h5py.")
# Save to HDF5 file using silx
hdf5_file_path = os.path.join(subdir_path_int, f"{subdir_name}.h5")
dicttoh5(hdf5_data, hdf5_file_path, mode="w")
# hdf5_file_path = os.path.join(subdir_path_int, f"{subdir_name}.h5")
# dicttoh5(hdf5_data, hdf5_file_path, mode="w")
print(f"Results for subdirectory {subdir_name} saved to CSV and HDF5 files using silx.")
del results_df
else:
print(f"No images were integrated in subdirectory {subdir}. No results DataFrame created.")
......
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Please register or to comment