das2numpy 1.1.2__tar.gz → 1.2.0__tar.gz

{das2numpy-1.1.2/src/das2numpy.egg-info → das2numpy-1.2.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: das2numpy
-Version: 1.1.2
+Version: 1.2.0
 Summary: A simple and universal package for loading large amounts of distributed acoustic sensing (DAS) data.
 Author-email: Erik Genthe <erik.genthe@desy.de>
 Project-URL: Homepage, https://gitlab.desy.de/wave/tools/das2numpy

{das2numpy-1.1.2 → das2numpy-1.2.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "das2numpy"
-version = "1.1.2"
+version = "1.2.0"
 authors = [
   { name="Erik Genthe", email="erik.genthe@desy.de" },
 ]

{das2numpy-1.1.2 → das2numpy-1.2.0}/src/das2numpy/__init__.py

@@ -26,6 +26,9 @@ def loader(root_path:str, predefined_setup:str, num_worker_threads):
     elif predefined_setup.upper() == "FLAC_200HZ":
         from .setups import flac_200hz
         chunk = flac_200hz.init(root_path, num_worker_threads)
+    elif predefined_setup.upper() == "HDAS":
+        from .setups import hdas
+        chunk = hdas.init(root_path, num_worker_threads)
     elif predefined_setup.upper() == "OPTASENSE":
         from .setups import optasense_b35idefix
         chunk = optasense_b35idefix.init()

das2numpy-1.2.0/src/das2numpy/setups/hdas.py

@@ -0,0 +1,106 @@
+""" Setup file for hDAS.
+"""
+
+import sys as SYS
+from os import path as P
+import datetime as DT
+import numpy as NP
+import h5py as H5PY
+from ..filefinder import FileFinder, to_posix_timestamp_ms
+from ..chunk import Chunk
+from .light_tdms_reader import TdmsReader
+from ..utils import bin
+
+
+CALIBRATE = True
+
+
+
+
+def init(root_path, num_worker_threads):
+    assert P.isdir(root_path)
+    file_finder = FileFinder(root_path, ".h5", filename_to_posix_timestamp)
+    assert num_worker_threads >= 1
+    multithreaded = num_worker_threads > 1
+    sample_rate = 1000
+    return Chunk(
+                file_finder,
+                sample_rate,
+                multithreaded,
+                num_worker_threads,
+                False,
+                load_file
+            )
+
+def filename_to_posix_timestamp(file_name:str) -> int:
+    # Example path: 2026_05_08_15h02m22s_HDAS_StrainRate_ch1.h5
+    # TODO Known bug: The timestamps array in the file has milliseconds! So the milliseonds are missing in the file name! h5['Timestamps']['Timestamps_Data']
+    timestamp_dt = DT.datetime.strptime(file_name.split("s_")[0], "%Y_%m_%d_%Hh%Mm%S")
+    timestamp_ms = to_posix_timestamp_ms(timestamp_dt)
+    return timestamp_ms
+
+
+def load_file(file_path, file_timestamp, t_start, t_end, t_step, channel_start, channel_end, channel_step) -> NP.ndarray:
+    """ Loads a single file, trims it. And returns the trimmed data as a numpy array. Downsampling (t_step, channel_step) is also possible!
+    """
+    
+    with H5PY.File(file_path, "r") as h5:
+        # Known bug: The file_timestamp is not accurate to milliseconds, because milliseconds are missing in the file name
+        #timestamps_unix_sec = h5['Timestamps']['Timestamps_Data']
+        #print(file_timestamp)
+        #file_timestamp = int(timestamps_unix_sec[0][0] * 1000.0) # Overwrite inaccurate file_timestamp
+        #file_timestamp -= 7200000 # TODO: This is a dirty fix: Internal timestamp is CEST, when hDAS system time is CEST.
+        data = NP.array(h5["StrainRate"]["StrainRate_Data"])
+        #print(file_timestamp)
+
+        # Trim data
+        rel_t_start = 0
+        if t_start > file_timestamp: # Check if beginning should be trimmed.
+            rel_t_start = t_start - file_timestamp
+        rel_t_end = -1 
+        if t_end < file_timestamp + data.shape[0]: # Check if end should be trimmed
+            rel_t_end = t_end - file_timestamp
+        if rel_t_start == rel_t_end:
+            return NP.zeros(shape=[0, 0]) # No data should be loaded. Do nothing
+        if file_timestamp + data.shape[0] <= t_start:
+            print("Warning: File does not contain any parts of the requested data.",
+                    "This can happen if there are leaks in the data. The corresponding output will be left filled with zeros.\n",
+                    f"    Requested range (Posixtimestamps in ms): [{t_start}, {t_end}[\n",
+                    f"    Filepath: {file_path}.")
+            return NP.zeros(shape=[0, 0])
+        assert rel_t_end == -1 or rel_t_end > rel_t_start, f"rel_t_start={rel_t_start}, rel_t_end={rel_t_end}."
+        if channel_end == -1: # Avoids that last channel is missing when channel_end == -1
+            channel_end = None
+        data = data[rel_t_start:rel_t_end, channel_start:channel_end]
+
+
+        # Downsample data
+        if t_step != 1 or channel_step != 1:
+            data = bin(data, (t_step, channel_step))
+        #if t_step != 1:
+        #    data = data[::t_step]
+        #if channel_step != 1:
+        #    data = data[:, ::channel_step]
+        assert len(data) > 0
+
+        if CALIBRATE:
+            data = calibrate(data)
+
+    return data
+
+
+
+
+
+def calibrate(data:NP.ndarray) -> NP.ndarray:
+    """ Convert raw data to strain rate data. """
+    if data.dtype not in (float, NP.float32, NP.float64):
+        NEW_TYPE = NP.float32
+        #print("Warning: For calibration the data has to be of type float. Converting from {data.dtype} to {NEW_TYPE}")
+        data = data.astype(NEW_TYPE)
+    factor = 10 * 1e-9
+    return data * factor # Result: 1 / s
+
+
+
+

{das2numpy-1.1.2 → das2numpy-1.2.0/src/das2numpy.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: das2numpy
-Version: 1.1.2
+Version: 1.2.0
 Summary: A simple and universal package for loading large amounts of distributed acoustic sensing (DAS) data.
 Author-email: Erik Genthe <erik.genthe@desy.de>
 Project-URL: Homepage, https://gitlab.desy.de/wave/tools/das2numpy

{das2numpy-1.1.2 → das2numpy-1.2.0}/src/das2numpy.egg-info/SOURCES.txt

@@ -13,6 +13,7 @@ src/das2numpy.egg-info/dependency_links.txt
 src/das2numpy.egg-info/requires.txt
 src/das2numpy.egg-info/top_level.txt
 src/das2numpy/setups/flac_200hz.py
+src/das2numpy/setups/hdas.py
 src/das2numpy/setups/light_tdms_reader.py
 src/das2numpy/setups/optasense_b35idefix.py
 src/das2numpy/setups/silixa.py

{das2numpy-1.1.2 → das2numpy-1.2.0}/src/example.py

@@ -11,6 +11,7 @@ t_end   = datetime(2024, 7, 23, 1, 1, 0)
 channel_start = 0
 channel_end = -1
 #loader = loader("/pnfs/desy.de/m/project/iDAS/raw/2024-DESY/2024-07-23-desy", "SILIXA", 1) # 1000 Hz
+#loader = loader("/pnfs/desy.de/m/project/iDAS/raw/2026-DESY/2026_das_comparison/hdas", "HDAS", 1) # 1000 Hz
 loader = loader("/pnfs/desy.de/m/project/iDAS/work/IDAS_200HZ/", "FLAC_200HZ", 1) # 200 Hz
 data = loader.load_array(t_start, t_end, channel_start, channel_end)