das2numpy 0.0.3__tar.gz → 0.0.4__tar.gz

{das2numpy-0.0.3/src/das2numpy.egg-info → das2numpy-0.0.4}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: das2numpy
-Version: 0.0.3
+Version: 0.0.4
 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://git.physnet.uni-hamburg.de/wave/das2numpy
@@ -10,6 +10,7 @@ Classifier: Operating System :: OS Independent
 Requires-Python: >=3.8
 Description-Content-Type: text/markdown
 License-File: LICENSE
+Dynamic: license-file
 
 # Module for loading Distributed Acoustic Sensing (DAS) data. SILIXA / OPTASENSE
 
@@ -80,12 +81,12 @@ For example, the above interfaces also exist with POSIX timestamps in millisecon
 
 ## Use as command line interface
 
-Example call (make sure that the current working directory is not inside idas2numpy):
+Example call:
 ```
-python -m idas2numpy "SILIXA" ~/iDAS/work/2024-05-10-desy/ 2024-05-10T10:01:00 2024-05-10T10:02:00 10 0 1000 10 default
+python -m das2numpy "SILIXA" /pnfs/desy.de/m/project/iDAS/raw/2025-DESY/2025-03-25-desy 2025-03-25T10:01:00 2025-03-25T10:02:00 10 0 1000 10 default
 ```
 
 For more information:
 ```
-python -m idas2numpy -h
+python -m das2numpy -h
 ```

{das2numpy-0.0.3 → das2numpy-0.0.4}/README.md

@@ -67,12 +67,12 @@ For example, the above interfaces also exist with POSIX timestamps in millisecon
 
 ## Use as command line interface
 
-Example call (make sure that the current working directory is not inside idas2numpy):
+Example call:
 ```
-python -m idas2numpy "SILIXA" ~/iDAS/work/2024-05-10-desy/ 2024-05-10T10:01:00 2024-05-10T10:02:00 10 0 1000 10 default
+python -m das2numpy "SILIXA" /pnfs/desy.de/m/project/iDAS/raw/2025-DESY/2025-03-25-desy 2025-03-25T10:01:00 2025-03-25T10:02:00 10 0 1000 10 default
 ```
 
 For more information:
 ```
-python -m idas2numpy -h
+python -m das2numpy -h
 ```

{das2numpy-0.0.3 → das2numpy-0.0.4}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "das2numpy"
-version = "0.0.3"
+version = "0.0.4"
 authors = [
   { name="Erik Genthe", email="erik.genthe@desy.de" },
 ]

{das2numpy-0.0.3 → das2numpy-0.0.4}/src/das2numpy/filefinder.py

@@ -109,7 +109,7 @@ class FileFinder():
         return self.__file_pathes[ first[0] : last[0] + 1 ]
 
 
-    def get_first(self) -> tuple:
+    def get_elem(self, index) -> tuple:
         if len(self.__file_pathes) == 0:
             raise Exception(f"No data files found in root directory: {self.__root_path}")
-        return self.__file_pathes[0]
+        return self.__file_pathes[index]

{das2numpy-0.0.3 → das2numpy-0.0.4}/src/das2numpy/setups/silixa.py

@@ -19,16 +19,12 @@ CALIBRATE = True
 
 def init(root_path, num_worker_threads):
     assert P.isdir(root_path)
-    file_time_sample_amount = 20000
     file_finder = FileFinder(root_path, ".tdms", filename_to_posix_timestamp)
-    example_file_path = file_finder.get_first()[1]
+    example_file_path = file_finder.get_elem(10)[1] # TODO get first instead of 10th
     tdms = TdmsReader(example_file_path)
     shape = tdms.get_mmap().shape
     file_time_sample_amount = shape[0]
     channel_amount = shape[1]
-    #channel_amount = tdms.fileinfo['n_channels']
-    #props = tdms.get_properties()
-    #fs = props.get('SamplingFrequency[Hz]') #TODO read sampling freq from file
     assert num_worker_threads >= 1
     multithreaded = num_worker_threads > 1
     return Chunk(
@@ -42,8 +38,10 @@ def init(root_path, num_worker_threads):
             )
 
 def filename_to_posix_timestamp(file_name:str) -> int:
-    return to_posix_timestamp_ms(DT.datetime.strptime(file_name[-24:], "%Y%m%d_%H%M%S.%f.tdms"))
-
+    timestamp_str = file_name.split("_UTC_")[1][:19]
+    timestamp_dt = DT.datetime.strptime(timestamp_str, "%Y%m%d_%H%M%S.%f")
+    timestamp_ms = to_posix_timestamp_ms(timestamp_dt)
+    return timestamp_ms
 
 
 def load_file(file_path, rel_t_start, rel_t_end, t_step, channel_start, channel_end, channel_step) -> NP.ndarray:
@@ -76,7 +74,7 @@ def calibrate(data:NP.ndarray) -> NP.ndarray:
     """ Convert raw data to strain rate data. 
     As the resulting values are decimals, the datatype should be float. Otherwise an assertion fails. """
     #assert data.dtype in (NP.float, NP.float32, NP.float64), f"The data should be floating point. It is {data.dtype}"
-    if data.dtype not in (NP.float, NP.float32, NP.float64):
+    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)

{das2numpy-0.0.3 → das2numpy-0.0.4}/src/das2numpy/utils.py

@@ -41,25 +41,7 @@ def differentiate(data: NP.ndarray, axis: int) -> NP.ndarray:
             data[:,i] = data[:,i+1] - data[:,i]
     return data
 
-#@njit
-#def integrate(data: NP.ndarray, axis: int) -> NP.ndarray:
-#    """Integrate the 2-dimensional signal over one axis
-#     A 2-d array is expected as input
-#     The return-value is None. The array is copied, modified and returned.
-#     :return: integrated array
-#    """
-#    assert axis == 0 or axis == 1
-#    data = data.copy()
-#
-#    if data.shape[axis] < 2:
-#        raise Exception("Integration with less then two samples makes no sense.")
-#    if axis == 0:
-#        for i in range(1, data.shape[0]):
-#            data[i] = data[i] + data[i-1]
-#    elif axis == 1:
-#        for i in range(1, data.shape[1]):
-#            data[:, i] = data[:, i] + data[:, i-1]
-#    return data
+
 def integrate(data: NP.ndarray, axis: int, sample_rate_hz:float) -> NP.ndarray:
     """Integrate the 2-dimensional signal over one axis
        A 2-d array is expected as input
@@ -85,12 +67,58 @@ def butterworth_filter(
     array = SS.sosfiltfilt(sos, array, axis=TIME_AXIS, padtype='odd', padlen=None)
     return array
 
-#https://numpy.org/doc/stable/reference/generated/numpy.fft.fft.html#numpy.fft.fft
-def fft(array):
-    raise NotImplementedError("Not implemented yet")
-    return None
 
 
+def spectrum_smoothing(frequencies:NP.ndarray, psd:NP.ndarray, n:int):
+    """
+    Perform 1/n decade smoothing on the power spectral density (PSD) data.
+    See also:  https://dsp.stackexchange.com/questions/9967/1-n-octave-smoothing
+
+    Parameters:
+    frequencies : numpy.ndarray
+        Array containing the frequency values.
+    psd : numpy.ndarray
+        Array containing the power spectral density values corresponding to the frequencies.
+    n : int
+        The number of divisions per decade (e.g., n=10 for 1/10 decade smoothing).
+    
+    Returns:
+    numpy.ndarray, numpy.ndarray
+        Smoothed frequencies and PSD.
+    """
+    frequencies = NP.array(frequencies)
+    psd = NP.array(psd)
+    if frequencies[0] == 0.0:
+        frequencies = frequencies[1:]
+        psd = psd[1:]
+
+
+    # Generate new frequency points:
+    min_freq = frequencies[0]
+    max_freq = frequencies[-1]
+    min_freq_new_log = NP.floor(NP.log10(min_freq))
+    max_freq_new_log = NP.ceil(NP.log10(max_freq))
+    n_decades = int(max_freq_new_log - min_freq_new_log)
+    freq_new = NP.logspace(min_freq_new_log, max_freq_new_log, num=n_decades*n+1, base=10)
+    freq_new_log = NP.log10(freq_new)
+    step_log = freq_new_log[1] - freq_new_log[0]
+
+    freq_new_actual = []
+    psd_new = []
+    for i in range(len(freq_new)):
+        f_log = freq_new_log[i]
+        f_lower = 10**(f_log - step_log / 2)
+        f_higher = 10**(f_log + step_log / 2)
+
+        # Find the indices within this log decade interval
+        mask = (frequencies >= f_lower) & (frequencies < f_higher)
+        #print(freq_new[i], f_lower, f_higher, mask)
+        if NP.any(mask):
+            freq_new_actual.append(NP.mean(frequencies[mask]))
+            psd_new.append(NP.mean(psd[mask]))
+
+    return NP.array(freq_new_actual), NP.array(psd_new)
+
 
 def bin(arr: NP.ndarray, bin_factors:tuple):
     """ Returns a binned version of arr. If factors were 1, the original array is returned."""

{das2numpy-0.0.3 → das2numpy-0.0.4/src/das2numpy.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: das2numpy
-Version: 0.0.3
+Version: 0.0.4
 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://git.physnet.uni-hamburg.de/wave/das2numpy
@@ -10,6 +10,7 @@ Classifier: Operating System :: OS Independent
 Requires-Python: >=3.8
 Description-Content-Type: text/markdown
 License-File: LICENSE
+Dynamic: license-file
 
 # Module for loading Distributed Acoustic Sensing (DAS) data. SILIXA / OPTASENSE
 
@@ -80,12 +81,12 @@ For example, the above interfaces also exist with POSIX timestamps in millisecon
 
 ## Use as command line interface
 
-Example call (make sure that the current working directory is not inside idas2numpy):
+Example call:
 ```
-python -m idas2numpy "SILIXA" ~/iDAS/work/2024-05-10-desy/ 2024-05-10T10:01:00 2024-05-10T10:02:00 10 0 1000 10 default
+python -m das2numpy "SILIXA" /pnfs/desy.de/m/project/iDAS/raw/2025-DESY/2025-03-25-desy 2025-03-25T10:01:00 2025-03-25T10:02:00 10 0 1000 10 default
 ```
 
 For more information:
 ```
-python -m idas2numpy -h
+python -m das2numpy -h
 ```

{das2numpy-0.0.3 → das2numpy-0.0.4}/src/example.py

@@ -1,3 +1,4 @@
+import numpy as NP
 import sys
 from datetime import datetime
 import matplotlib.pyplot as PP
@@ -5,19 +6,21 @@ from das2numpy import loader, utils
 
 
 print("Load data to numpy-array")
-t_start = datetime(2024,  5, 11, 1, 0, 0)
-t_end   = datetime(2024,  5, 11, 1, 0, 5)
+t_start = datetime(2025,  3, 25, 1, 0, 0)
+t_end   = datetime(2025,  3, 25, 1, 1, 0)
 channel_start = 0
 channel_end = -1
-loader = loader("/pnfs/desy.de/m/project/iDAS/work/2024-05-11-desy", "SILIXA", 1)
+loader = loader("/pnfs/desy.de/m/project/iDAS/raw/2025-DESY/2025-03-25-desy", "SILIXA", 1)
 data = loader.load_array(t_start, t_end, channel_start, channel_end)
 
 print("Reduce data by binning (mean averaging)")
-bin_factors = (10, 10)
-data = utils.bin(data, bin_factors) # Reduce time sampling and spatial sampling by a factor of 10 by averaging each.
+bin_factors = (100, 10)
+data = utils.bin(data, bin_factors) # Reduce time sampling and spatial sampling by averaging.
 sampling_hz = 1000.0 / bin_factors[0]
 channel_spacing = 1.0 * bin_factors[1]
 
+NP.save("data.npy", data)
+
 print("Create plot with pyplot")
 PP.title(f"{t_start.isoformat()}")
 PP.imshow(
@@ -25,9 +28,8 @@ PP.imshow(
     cmap = "seismic",
     aspect = "auto",
     interpolation = "nearest",
-    origin = "lower",
-    vmin = -2e-6,
-    vmax = +2e-6,
+    vmin = -1e-7,
+    vmax = +1e-7,
     extent = (
         channel_start, channel_start + (data.shape[1] * channel_spacing), 
         data.shape[0] / sampling_hz, 0