def scrape(filename, ebcidc=False, trace_headers=False):
"""Scrape the file meta information and output it to text file.
If no options are specified both will be output. The output file will be
<filename>.txt for the EBCIDC and <filename>.csv for
trace headers.
The trace headers can be read back into Python using
pandas.read_csv(<filename>.csv, index_col=0)
"""
for file in tqdm(filename, desc="File"):
file = pathlib.Path(file)
ebcidc_name = file.with_suffix(".txt")
header_name = file.with_suffix(".csv")
if ebcidc == False and trace_headers == False:
ebcidc = True
trace_headers = True
if ebcidc:
txt = get_segy_texthead(file)
with open(ebcidc_name, "w") as txtfile:
txtfile.writelines(txt)
if trace_headers:
head_df = segy_header_scrape(file)
head_df.to_csv(header_name)
def test_segyiotests_2ds_wheaderscrap(segyio3d_test_files):
file, segyio_kwargs = segyio3d_test_files
scrape_args = dict()
try:
scrape_args["endian"] = segyio_kwargs["endian"]
except KeyError:
pass
header = segy_header_scrape(str(file), silent=True, **scrape_args)
ds = segy_loader(str(file), silent=True, **segyio_kwargs, head_df=header)
assert isinstance(ds, xr.Dataset)
def test_segy_header_scrape(temp_dir, temp_segy):
header = segy_header_scrape(temp_segy, silent=True)
assert isinstance(header, pd.DataFrame)
assert header.shape == (TEST_SEGY_SIZE**2, 89)
# to filter away blank values which can help us to understand the composition of the data. # # For instance, key values like **trace UTM coordinates** are located in bytes *73* for X & *77* for Y. We # can also see the byte positions of the **local grid** for INLINE_3D in byte *189* and for CROSSLINE_3D in byte *193*. # %% scan[scan["std"] > 0] # %% [markdown] # To retreive the raw header content use `segy_header_scrape`. Setting `partial_scan=None` will return the # full dataframe of trace header information. # %% from segysak.segy import segy_header_scrape scrape = segy_header_scrape(V3D_path, partial_scan=1000) scrape # %% [markdown] # ## Load SEG-Y data # %% [markdown] # All SEGY (2D, 2D gathers, 3D & 3D gathers) are ingested into `xarray.Dataset` objects through the # `segy_loader` function. It is best to be explicit about the byte locations of key information but # `segy_loader` can attempt to guess the shape of your dataset. Some standard byte positions are # defined in the `well_known_bytes` function and others can be added via pull requests to the Github # repository if desired. # %% from segysak.segy import segy_loader, well_known_byte_locs