return 4.8
def datetime64_str(time_str: Optional[str] = None) -> np.ndarray:
"""
Reformat time_str to ISO 8601 or to 'NaT'. Used here for input in funcs that converts str to numpy.datetime64
:param time_str: May be 'NaT'
:return: ndarray of strings (tested for 1 element only) formatted by numpy.
"""
return np.datetime_as_string(np.datetime64(time_str, 's'))
probes = probes or range(
9, 40) # sets default range, specify your values before line ---
if st(
1
): # Can not find additional not corrected files for same probe if already have any corrected in search path (move them out if need)
i_proc_probe = 0 # counter of processed probes
i_proc_file = 0 # counter of processed files
# patten to identify only _probe_'s raw data files that need to correct '*INKL*{:0>2}*.[tT][xX][tT]':
raw_pattern = f'*{prefix.replace("incl","inkl").upper()}_{{:0>3}}*.[tT][xX][tT]'
raw_parent = path_cruise / dir_incl / '_raw'
for probe in probes:
correct_fun = partial(correct_kondrashov_txt
if prefix == 'incl' else correct_baranov_txt,
dir_out=raw_parent)
raw_found = []
if not raw_archive_name:
raw_found = list(raw_parent.glob(raw_pattern.format(probe)))
if not raw_found:
# Check if already have corrected files for probe generated by correct_kondrashov_txt(). If so then just use them
# Stop before steps that need manual preparings (70) i.e. set end < 70 at first
# Gridding (last step) needs debugging if interactive filtering is needed
# ---------------------------------------------------------------------------------------------
# if st(1, 'Save gpx navigation to DB'):
# # Save navigation to DB
# gpx2h5(['',
# '--db_path', str(path_db),
# '--path', str(path_cruise / r'navigation\_raw\*.gpx'),
# '--tables_list', ',navigation,', # skip waypoints
# '--table_prefix', r'',
# # '--min_date', '2019-07-17T14:00:00',
# '--b_interact', '0',
# ])
if st(5, "Save Supervisor's navigation to DB"):
# Save navigation to DB
csv2h5([
'ini/csv_nav_supervisor.ini',
'--db_path',
str(path_db),
'--path',
str(path_cruise / r'navigation\bridge\??????.txt'),
'--table',
'navigation', # skip waypoints
#'--b_remove_duplicates', 'True',
#'--csv_specific_param_dict', 'DepEcho_add:4.5',
'--min_dict',
'DepEcho:6',
'--b_interact',
'0',
def main(new_arg=None, **kwargs):
"""
:param new_arg: list of strings, command line arguments
:kwargs: dicts of dictcts (for each ini section): specified values overwrites ini values
"""
# global l
cfg = cfg_from_args(my_argparser(), new_arg, **kwargs)
cfg['in']['db_coefs'] = Path(cfg['in']['db_coefs'])
for path_field in ['db_coefs', 'path_cruise']:
if not cfg['in'][path_field].is_absolute():
cfg['in'][path_field] = (
cfg['in']['cfgFile'].parent / cfg['in'][path_field]
).resolve().absolute() # cfg['in']['cfgFile'].parent /
def constant_factory(val):
def default_val():
return val
return default_val
for lim in ('min_date', 'max_date'):
cfg['filter'][lim] = defaultdict(
constant_factory(cfg['filter'][lim].get(
'0', cfg['filter'][lim].get(0))), cfg['filter'][lim])
l = init_logging(logging, None, None, 'INFO')
#l = init_logging(logging, None, cfg['program']['log'], cfg['program']['verbose'])
if True: # False. Experimental speedup but takes memory
from dask.cache import Cache
cache = Cache(2e9) # Leverage two gigabytes of memory
cache.register() # Turn cache on globally
if cfg['program']['dask_scheduler']:
if cfg['program']['dask_scheduler'] == 'distributed':
from dask.distributed import Client
client = Client(
processes=False
) # navigate to http://localhost:8787/status to see the diagnostic dashboard if you have Bokeh installed
# processes=False: avoide inter-worker communication for computations releases the GIL (numpy, da.array) # without is error
else:
if cfg['program']['dask_scheduler'] == 'synchronous':
l.warning('using "synchronous" scheduler for debugging')
import dask
dask.config.set(scheduler=cfg['program']['dask_scheduler'])
# Run steps :
st.start = cfg['program']['step_start']
st.end = cfg['program']['step_end']
st.go = True
if not cfg['out'][
'db_name']: # set name by 'path_cruise' name or parent if it has digits at start. priority for name is "*inclinometer*"
for p in (lambda p: [p, p.parent])(cfg['in']['path_cruise']):
m = re.match('(^[\d_]*).*', p.name)
if m:
break
cfg['out']['db_name'] = f"{m.group(1).strip('_')}incl.h5"
cfg['in']['path_cruise'].glob('*inclinometer*')
dir_incl = next((d for d in cfg['in']['path_cruise'].glob('*inclinometer*')
if d.is_dir()), cfg['in']['path_cruise'])
db_path = dir_incl / cfg['out']['db_name']
# ---------------------------------------------------------------------------------------------
def fs(probe, name):
return 5
# if 'w' in name.lower(): # Baranov's wavegauge electronic
# return 5 # 10
# if probe < 20 or probe in [23, 29, 30, 32, 33]: # 30 [4, 11, 5, 12] + [1, 7, 13, 30]
# return 5
# if probe in [21, 25, 26] + list(range(28, 35)):
# return 8.2
# return 4.8
def datetime64_str(time_str: Optional[str] = None) -> np.ndarray:
"""
Reformat time_str to ISO 8601 or to 'NaT'. Used here for input in funcs that converts str to numpy.datetime64
:param time_str: May be 'NaT'
:return: ndarray of strings (tested for 1 element only) formatted by numpy.
"""
return np.datetime_as_string(np.datetime64(time_str, 's'))
probes = cfg['in']['probes'] or range(
1, 41) # sets default range, specify your values before line ---
raw_root, subs_made = re.subn('INCL_?', 'INKL_',
cfg['in']['probes_prefix'].upper())
if st(
1
): # Can not find additional not corrected files for same probe if already have any corrected in search path (move them out if need)
i_proc_probe = 0 # counter of processed probes
i_proc_file = 0 # counter of processed files
# patten to identify only _probe_'s raw data files that need to correct '*INKL*{:0>2}*.[tT][xX][tT]':
raw_parent = dir_incl / '_raw'
dir_out = raw_parent / re.sub(
r'[.\\/ ]', '_', cfg['in']['raw_subdir']
) # sub replaces multilevel subdirs to 1 level that correct_fun() can only make
raw_parent /= cfg['in']['raw_subdir']
for probe in probes:
raw_found = []
raw_pattern_file = cfg['in']['raw_pattern'].format(prefix=raw_root,
number=probe)
correct_fun = partial(
correct_kondrashov_txt if subs_made else correct_baranov_txt,
dir_out=dir_out)
# if not archive:
if (not '.zip' in cfg['in']['raw_subdir'].lower() and not '.rar'
in cfg['in']['raw_subdir'].lower()) or raw_parent.is_dir():
raw_found = list(raw_parent.glob(raw_pattern_file))
if not raw_found:
# Check if already have corrected files for probe generated by correct_kondrashov_txt(). If so then just use them
raw_found = list(
raw_parent.glob(
f"{cfg['in']['probes_prefix']}{probe:0>2}.txt"))
if raw_found:
print('corrected csv file', [r.name for r in raw_found],
'found')
correct_fun = lambda x: x
elif not cfg['in']['raw_subdir']:
continue
for file_in in (raw_found or open_csv_or_archive_of_them(
raw_parent, binary_mode=False, pattern=raw_pattern_file)):
file_in = correct_fun(file_in)
if not file_in:
continue
tbl = f"{cfg['in']['probes_prefix']}{probe:0>2}"
# tbl = re.sub('^((?P<i>inkl)|w)_0', lambda m: 'incl' if m.group('i') else 'w', # correct name
# re.sub('^[\d_]*|\*', '', file_in.stem).lower()), # remove date-prefix if in name
csv2h5(
[
str(
Path(__file__).parent / 'ini' /
f"csv_inclin_{'Kondrashov' if subs_made else 'Baranov'}.ini"
),
'--path',
str(file_in),
'--blocksize_int',
'50_000_000', # 50Mbt
'--table',
tbl,
'--db_path',
str(db_path),
# '--log', str(scripts_path / 'log/csv2h5_inclin_Kondrashov.log'),
# '--b_raise_on_err', '0', # ?
'--b_interact',
'0',
'--fs_float',
f'{fs(probe, file_in.stem)}',
'--dt_from_utc_seconds',
str(cfg['in']['dt_from_utc'].total_seconds()),
'--b_del_temp_db',
'1',
] +
(['--csv_specific_param_dict', 'invert_magnitometr: True']
if subs_made else
['--cols_load_list', "yyyy,mm,dd,HH,MM,SS,P,U"]),
**{
'filter': {
'min_date': cfg['filter']['min_date'][probe],
'max_date': cfg['filter']['max_date'][probe],
}
})
# Get coefs:
l.info(
f"Adding coefficients to {db_path}/{tbl} from {cfg['in']['db_coefs']}"
)
try:
h5copy_coef(cfg['in']['db_coefs'], db_path, tbl)
except KeyError as e: # Unable to open object (component not found)
l.warning(
'No coefs to copy?'
) # write some dummy coefficients to can load Veusz patterns:
h5copy_coef(None,
db_path,
tbl,
dict_matrices=dict_matrices_for_h5(tbl=tbl))
except OSError as e:
l.warning(
'Not found DB with coefs?'
) # write some dummy coefficients to can load Veusz patterns:
h5copy_coef(None,
db_path,
tbl,
dict_matrices=dict_matrices_for_h5(tbl=tbl))
i_proc_file += 1
else:
print('no', raw_pattern_file, end=', ')
i_proc_probe += 1
print('Ok:', i_proc_probe, 'probes,', i_proc_file, 'files processed.')
# Calculate velocity and average
if st(2):
# if aggregate_period_s is None then not average and write to *_proc_noAvg.h5 else loading from that h5 and writing to _proc.h5
if not cfg['out']['aggregate_period_s']:
cfg['out']['aggregate_period_s'] = [
None, 2, 600,
3600 if 'w' in cfg['in']['probes_prefix'] else 7200
]
if cfg['in']['azimuth_add']:
if 'Lat' in cfg['in']['azimuth_add']:
from datetime import datetime
# add magnetic declination,° for used coordinates
# todo: get time
azimuth_add = mag_dec(cfg['in']['azimuth_add']['Lat'],
cfg['in']['azimuth_add']['Lon'],
datetime(2020, 9, 10),
depth=-1)
else:
azimuth_add = 0
if 'constant' in cfg['in']['azimuth_add']:
# and add constant. For example, subtruct declination at the calibration place if it was applied
azimuth_add += cfg['in']['azimuth_add'][
'constant'] # add -6.65644183° to account for calibration in Kaliningrad
for aggregate_period_s in cfg['out']['aggregate_period_s']:
if aggregate_period_s is None:
db_path_in = db_path
db_path_out = db_path.with_name(
f'{db_path.stem}_proc_noAvg.h5')
else:
db_path_in = db_path.with_name(f'{db_path.stem}_proc_noAvg.h5')
db_path_out = f'{db_path.stem}_proc.h5' # or separately: '_proc{aggregate_period_s}.h5'
args = [
Path(incl_h5clc.__file__).with_name(
f'incl_h5clc_{db_path.stem}.yaml'),
# if no such file all settings are here
'--db_path',
str(db_path_in),
# ! 'incl.*|w\d*' inclinometers or wavegauges w\d\d # 'incl09':
'--tables_list',
'incl.*' if not cfg['in']['probes'] else
f"incl.*(?:{'|'.join('{:0>2}'.format(p) for p in cfg['in']['probes'])})",
'--aggregate_period',
f'{aggregate_period_s}S' if aggregate_period_s else '',
'--out.db_path',
str(db_path_out),
'--table',
f'V_incl_bin{aggregate_period_s}'
if aggregate_period_s else 'V_incl',
'--verbose',
'INFO', #'DEBUG' get many numba messages
'--b_del_temp_db',
'1',
# '--calc_version', 'polynom(force)', # depreshiated
# '--chunksize', '20000',
# '--not_joined_h5_path', f'{db_path.stem}_proc.h5',
]
# if aggregate_period_s <= 5: # [s], do not need split csv for big average interval
# args += (['--split_period', '1D'])
if aggregate_period_s is None: # proc. parameters (if we have saved proc. data then when aggregating we are not processing)
args += ([
'--max_dict',
'M[xyz]:4096',
# Note: for Baranov's prog 4096 is not suited
# '--timerange_zeroing_dict', "incl19: '2019-11-10T13:00:00', '2019-11-10T14:00:00'\n," # not works - use kwarg
# '--timerange_zeroing_list', '2019-08-26T04:00:00, 2019-08-26T05:00:00'
'--split_period',
'1D'
] if subs_made else [
'--bad_p_at_bursts_starts_peroiod',
'1H',
])
# csv splitted by 1day (default for no avg) and monolith csv if aggregate_period_s==600
if aggregate_period_s not in cfg['out'][
'aggregate_period_s_not_to_text']: # , 300, 600]:
args += ['--text_path', str(db_path.parent / 'text_output')]
kwarg = {
'in': {
'min_date': cfg['filter']['min_date'][0],
'max_date': cfg['filter']['max_date'][0],
'timerange_zeroing': cfg['in']['timerange_zeroing'],
'azimuth_add': azimuth_add
}
}
# If need all data to be combined one after one:
# set_field_if_no(kwarg, 'in', {})
# kwarg['in'].update({
#
# 'tables': [f'incl{i:0>2}' for i in min_date.keys() if i!=0],
# 'dates_min': min_date.values(), # in table list order
# 'dates_max': max_date.values(), #
# })
# set_field_if_no(kwarg, 'out', {})
# kwarg['out'].update({'b_all_to_one_col': 'True'})
incl_h5clc.main(args, **kwarg)
# Calculate spectrograms.
if st(3): # Can be done at any time after step 1
def raise_ni():
raise NotImplementedError(
'Can not proc probes having different fs in one run: you need to do it separately'
)
args = [
Path(incl_h5clc.__file__).with_name(
f'incl_h5spectrum{db_path.stem}.yaml'),
# if no such file all settings are here
'--db_path',
str(db_path.with_name(f'{db_path.stem}_proc_noAvg.h5')),
'--tables_list',
f"{cfg['in']['probes_prefix']}.*", # inclinometers or wavegauges w\d\d ## 'w02', 'incl.*',
# '--aggregate_period', f'{aggregate_period_s}S' if aggregate_period_s else '',
'--min_date',
datetime64_str(cfg['filter']['min_date'][0]),
'--max_date',
datetime64_str(cfg['filter']['max_date']
[0]), # '2019-09-09T16:31:00', #17:00:00
# '--max_dict', 'M[xyz]:4096', # use if db_path is not ends with _proc_noAvg.h5 i.e. need calc velocity
'--out.db_path',
f"{db_path.stem.replace('incl', cfg['in']['probes_prefix'])}_proc_psd.h5",
# '--table', f'psd{aggregate_period_s}' if aggregate_period_s else 'psd',
'--fs_float',
f"{fs(probes[0], cfg['in']['probes_prefix'])}",
# (lambda x: x == x[0])(np.vectorize(fs)(probes, prefix))).all() else raise_ni()
#
# '--timerange_zeroing_list', '2019-08-26T04:00:00, 2019-08-26T05:00:00'
# '--verbose', 'DEBUG',
# '--chunksize', '20000',
'--b_interact',
'0',
]
if 'w' in cfg['in']['probes_prefix']:
args += [
'--split_period',
'1H',
'--dt_interval_minutes',
'10', # burst mode
'--fmin',
'0.0001',
'--fmax',
'4'
]
else:
args += [
'--split_period',
'2H',
'--fmin',
'0.0004', #0.0004
'--fmax',
'1.05'
]
incl_h5spectrum.main(args)
# Draw in Veusz
if st(4):
b_images_only = True # False
pattern_path = db_path.parent / r'vsz_5min\191119_0000_5m_incl19.vsz' # r'vsz_5min\191126_0000_5m_w02.vsz'
if not b_images_only:
pattern_bytes_slice_old = re.escape(b'((5828756, 5830223, None),)')
# Length of not adjacent intervals, s (set None to not allow)
period = '1D'
length = '5m' # period # '1D'
dt_custom_s = pd_period_to_timedelta(
length) if length != period else None # None # 60 * 5
if True:
# Load starts and assign ends
t_intervals_start = pd.read_csv(
cfg['in']['path_cruise'] /
r'vsz+h5_proc\intervals_selected.txt',
converters={
'time_start': lambda x: np.datetime64(x, 'ns')
},
index_col=0).index
edges = (pd.DatetimeIndex(t_intervals_start),
pd.DatetimeIndex(t_intervals_start + dt_custom_s)
) # np.zeros_like()
else:
# Generate periodic intervals
t_interval_start, t_intervals_end = intervals_from_period(
datetime_range=np.array(
[
cfg['filter']['min_date']['0'],
cfg['filter']['max_date']['0']
],
# ['2018-08-11T18:00:00', '2018-09-06T00:00:00'],
# ['2019-02-11T13:05:00', '2019-03-07T11:30:00'],
# ['2018-11-16T15:19', '2018-12-14T14:35'],
# ['2018-10-22T12:30', '2018-10-27T06:30:00'],
'datetime64[s]'),
period=period)
edges = (pd.DatetimeIndex([t_interval_start
]).append(t_intervals_end[:-1]),
pd.DatetimeIndex(t_intervals_end))
for i, probe in enumerate(probes):
probe_name = f"{cfg['in']['probes_prefix']}{probe:02}" # table name in db
l.info('Draw %s in Veusz: %d intervals...', probe_name,
edges[0].size)
# for i_interval, (t_interval_start, t_interval_end) in enumerate(zip(pd.DatetimeIndex([t_interval_start]).append(t_intervals_end[:-1]), t_intervals_end), start=1):
cfg_vp = {'veusze': None}
for i_interval, (t_interval_start,
t_interval_end) in enumerate(zip(*edges),
start=1):
# if i_interval < 23: #<= 0: # TEMPORARY Skip this number of intervals
# continue
if period != length:
t_interval_start = t_interval_end - pd.Timedelta(
dt_custom_s, 's')
try: # skipping absent probes
start_end = h5q_interval2coord(
db_path=str(db_path),
table=f'/{probe_name}',
t_interval=(t_interval_start, t_interval_end))
if not len(start_end):
break # no data
except KeyError:
break # device name not in specified range, go to next name
pattern_path_new = pattern_path.with_name(
f"{t_interval_start:%y%m%d_%H%M}_{length}_{probe_name}.vsz"
)
# Modify pattern file
if not b_images_only:
probe_name_old = re.match('.*((?:incl|w)\d*).*',
pattern_path.name).groups()[0]
bytes_slice = bytes(
'(({:d}, {:d}, None),)'.format(*(start_end +
np.int32([-1, 1]))),
'ascii')
def f_replace(line):
"""
Replace in file
1. probe name
2. slice
"""
# if i_interval == 1:
line, ok = re.subn(bytes(probe_name_old, 'ascii'),
bytes(probe_name, 'ascii'), line)
if ok: # can be only in same line
line = re.sub(pattern_bytes_slice_old, bytes_slice,
line)
return line
if not rep_in_file(pattern_path,
pattern_path_new,
f_replace=f_replace):
l.warning('Veusz pattern not changed!')
# break
elif cfg_vp['veusze']:
cfg_vp['veusze'].Load(str(pattern_path_new))
elif cfg_vp['veusze']:
cfg_vp['veusze'].Load(str(pattern_path_new))
txt_time_range = \
"""
"[['{:%Y-%m-%dT%H:%M}', '{:%Y-%m-%dT%H:%M}']]" \
""".format(t_interval_start, t_interval_end)
print(f'{i_interval}. {txt_time_range}', end=' ')
cfg_vp = veuszPropagate.main(
[
Path(veuszPropagate.__file__).parent.with_name(
'veuszPropagate.ini'),
# '--data_yield_prefix', '-',
'--path',
str(
db_path
), # use for custom loading from db and some source is required
'--tables_list',
f'/{probe_name}', # 181022inclinometers/ \d*
'--pattern_path',
str(pattern_path_new),
# fr'd:\workData\BalticSea\190801inclinometer_Schuka\{probe_name}_190807_1D.vsz',
# str(db_path.parent / dir_incl / f'{probe_name}_190211.vsz'), #warning: create file with small name
# '--before_next', 'restore_config',
# '--add_to_filename', f"_{t_interval_start:%y%m%d_%H%M}_{length}",
'--filename_fun',
f'lambda tbl: "{pattern_path_new.name}"',
'--add_custom_list',
'USEtime', # nAveragePrefer',
'--add_custom_expressions_list',
txt_time_range,
# + """
# ", 5"
# """,
'--b_update_existed',
'True',
'--export_pages_int_list',
'1, 2', # 0 for all '6, 7, 8', #'1, 2, 3'
# '--export_dpi_int', '200',
'--export_format',
'emf',
'--b_interact',
'0',
'--b_images_only',
f'{b_images_only}',
'--return',
'<embedded_object>', # reuse to not bloat memory
],
veusze=cfg_vp['veusze'])
def main(config: ConfigType) -> None:
"""
----------------------------
Save data to Pandas HDF5 store*.h5
----------------------------
The store contains tables for each device and each device table contains log with metadata of recording sessions
:param config: with fields:
- in - mapping with fields:
- tables_log: - log table name or pattern str for it: in pattern '{}' will be replaced by data table name
- cols_good_data: -
['dt_from_utc', 'db', 'db_path', 'table_nav']
- out - mapping with fields:
- cols: can use i - data row number and i_log_row - log row number that is used to load data range
- cols_log: can use i - log row number
- text_date_format
- file_name_fun, file_name_fun_log - {fun} part of "lambda rec_num, t_st, t_en: {fun}" string to compile function
for name of data and log text files
- sep
"""
global cfg
cfg = to_vaex_hdf5.cfg_dataclasses.main_init(config, cs_store_name)
cfg_in = cfg.pop('input')
cfg_in['cfgFile'] = cs_store_name
cfg['in'] = cfg_in
# try:
# cfg = to_vaex_hdf5.cfg_dataclasses.main_init_input_file(cfg, cs_store_name, )
# except Ex_nothing_done:
# pass # existed db is not mandatory
device_path, cfg['out']['db_path'] = device_in_out_paths(
db_path=cfg['out'].get('db_path'),
path_cruise=cfg['in']['path_cruise'],
device_short_name=cfg['in']['probes_prefix'],
device_dir_pattern='*inclinometer*')
out = cfg['out']
# h5init(cfg['in'], out)
probes = cfg['in']['probes'] or range(
1, 41) # sets default range, specify your values before line ---
raw_root, probe_is_incl = re.subn('INCL_?', 'INKL_',
cfg['in']['probes_prefix'].upper())
# some parameters that depends of probe type (indicated by probes_prefix)
p_type = defaultdict(
# baranov's format
constant_factory({
'correct_fun':
partial(correct_txt,
mod_file_name=mod_incl_name,
sub_str_list=[
b'^\r?(?P<use>20\d{2}(\t\d{1,2}){5}(\t\d{5}){8}).*',
b'^.+'
]),
'fs':
10,
'format':
'Baranov',
}),
{
'incl': {
'correct_fun':
partial(
correct_txt,
mod_file_name=mod_incl_name,
sub_str_list=[
b'^(?P<use>20\d{2}(,\d{1,2}){5}(,\-?\d{1,6}){6}(,\d{1,2}\.\d{2})(,\-?\d{1,3}\.\d{2})).*',
b'^.+'
]),
'fs':
5,
'format':
'Kondrashov',
},
'voln': {
'correct_fun':
partial(
correct_txt,
mod_file_name=mod_incl_name,
sub_str_list=[
b'^(?P<use>20\d{2}(,\d{1,2}){5}(,\-?\d{1,8})(,\-?\d{1,2}\.\d{2}){2}).*',
b'^.+'
]),
'fs':
5,
#'tbl_prefix': 'w',
'format':
'Kondrashov',
}
})
if st(1, 'Save inclinometer or wavegage data from ASCII to HDF5'):
# Note: Can not find additional not corrected files for same probe if already have any corrected in search path (move them out if need)
i_proc_probe = 0 # counter of processed probes
i_proc_file = 0 # counter of processed files
# patten to identify only _probe_'s raw data files that need to correct '*INKL*{:0>2}*.[tT][xX][tT]':
raw_parent = dir_incl / '_raw' # raw_parent /=
if cfg['in']['raw_subdir'] is None:
cfg['in']['raw_subdir'] = ''
dir_out = raw_parent / re.sub(r'[.\\/ *?]', '_',
cfg['in']['raw_subdir'])
# sub replaces multilevel subdirs to 1 level that correct_fun() can only make
def dt_from_utc_2000(probe):
""" Correct time of probes started without time setting. Raw date must start from 2000-01-01T00:00"""
return (
datetime(year=2000, month=1, day=1) -
cfg['in']['time_start_utc'][probe]
) if cfg['in']['time_start_utc'].get(probe) else timedelta(0)
# convert cfg['in']['dt_from_utc'] keys to int
cfg['in']['dt_from_utc'] = {
int(p): v
for p, v in cfg['in']['dt_from_utc'].items()
}
# convert cfg['in']['t_start_utc'] to cfg['in']['dt_from_utc'] and keys to int
cfg['in']['dt_from_utc'].update( # overwriting the 'time_start_utc' where already exist
{int(p): dt_from_utc_2000(p) for p, v in cfg['in']['time_start_utc'].items()}
)
# make cfg['in']['dt_from_utc'][0] be default value
cfg['in']['dt_from_utc'] = defaultdict(
constant_factory(cfg['in']['dt_from_utc'].pop(0, timedelta(0))),
cfg['in']['dt_from_utc'])
for probe in probes:
raw_found = []
raw_pattern_file = str(
Path(glob.escape(cfg['in']['raw_subdir'])) /
cfg['in']['raw_pattern'].format(prefix=raw_root, number=probe))
correct_fun = p_type[cfg['in']['probes_prefix']]['correct_fun']
# if not archive:
if (not re.match(r'.*(\.zip|\.rar)$', cfg['in']['raw_subdir'],
re.IGNORECASE)) and raw_parent.is_dir():
raw_found = list(raw_parent.glob(raw_pattern_file))
if not raw_found:
# Check if already have corrected files for probe generated by correct_txt(). If so then just use them
raw_found = list(
dir_out.glob(
f"{cfg['in']['probes_prefix']}{probe:0>2}.txt"))
if raw_found:
print('corrected csv file', [r.name for r in raw_found],
'found')
correct_fun = lambda x, dir_out: x
elif not cfg['in']['raw_subdir']:
continue
for file_in in (raw_found or open_csv_or_archive_of_them(
raw_parent, binary_mode=False, pattern=raw_pattern_file)):
file_in = correct_fun(file_in, dir_out=dir_out)
if not file_in:
continue
tbl = file_in.stem # f"{cfg['in']['probes_prefix']}{probe:0>2}"
# tbl = re.sub('^((?P<i>inkl)|w)_0', lambda m: 'incl' if m.group('i') else 'w', # correct name
# re.sub('^[\d_]*|\*', '', file_in.stem).lower()), # remove date-prefix if in name
csv2h5(
[
str(
Path(__file__).parent / 'ini' /
f"csv_{'inclin' if probe_is_incl else 'wavegage'}_{p_type[cfg['in']['probes_prefix']]['format']}.ini"
),
'--path',
str(file_in),
'--blocksize_int',
'50_000_000', # 50Mbt
'--table',
tbl,
'--db_path',
str(db_path),
# '--log', str(scripts_path / 'log/csv2h5_inclin_Kondrashov.log'),
# '--b_raise_on_err', '0', # ?
'--b_interact',
'0',
'--fs_float',
str(p_type[cfg['in']['probes_prefix']]
['fs']), #f'{fs(probe, file_in.stem)}',
'--dt_from_utc_seconds',
str(cfg['in']['dt_from_utc'][probe].total_seconds()),
'--b_del_temp_db',
'1',
] +
(['--csv_specific_param_dict', 'invert_magnitometr: True']
if probe_is_incl else []),
**{
'filter': {
'min_date':
cfg['filter']['min_date'].get(
probe, np.datetime64(0, 'ns')),
'max_date':
cfg['filter']['max_date'].get(
probe, np.datetime64('now', 'ns')
), # simple 'now' works in sinchronious mode
}
})
# Get coefs:
l.info(
f"Adding coefficients to {db_path}/{tbl} from {cfg['in']['db_coefs']}"
)
try:
h5copy_coef(cfg['in']['db_coefs'], db_path, tbl)
except KeyError as e: # Unable to open object (component not found)
l.warning(
'No coefs to copy?'
) # write some dummy coefficients to can load Veusz patterns:
h5copy_coef(None,
db_path,
tbl,
dict_matrices=dict_matrices_for_h5(tbl=tbl))
except OSError as e:
l.warning(
'Not found DB with coefs?'
) # write some dummy coefficients to can load Veusz patterns:
h5copy_coef(None,
db_path,
tbl,
dict_matrices=dict_matrices_for_h5(tbl=tbl))
i_proc_file += 1
else:
print('no', raw_pattern_file, end=', ')
i_proc_probe += 1
print('Ok:', i_proc_probe, 'probes,', i_proc_file, 'files processed.')
cfg_in['tables'] = ['incl30']
from inclinometer.incl_h5clc import h5_names_gen
from inclinometer.h5inclinometer_coef import rot_matrix_x, rot_matrix_y #rotate_x, rotate_y
# R*[xyz]. As we next will need apply coefs Ag = Rz*Ry*Rx we can incorporate this
# operation by precalculate it adding known angles on each axes to Rz,Ry,Rx.
# If rotation is 180 deg, then we can add it only to Rx. Modified coef: Ag_new = Rz*Ry*R(x+180)
# R(x+180) = Rx*Rx180 equivalent to rotate Ag.T in opposite direction:
# Ag_new = rotate_x()
# inclinometer changed so that applying coefs returns rotated data fiels vectors:
# Out_rotated = Ag * In
# We rotate it back:
# Out = rotate(Out_rotated) =
# after angle after calibration to some angle P so determine angle relative to vertical
# by rotate data vector in opposite dir: Out = Ag * R_back * In. This equivalent to have new coef by apply rotation to Ag:
# Ag_new = Ag * R_back = (R_back.T * Ag.T).T = rotate_forward(Ag.T).T =
# Applying calibration coef will get data in inverted basis so we need rotate it after:
#
# coefs['Ag'] = rotate_x(coefs['Ag'], angle_degrees=180)
# coefs['Ah'] = rotate_x(coefs['Ah'], angle_degrees=180)
# dfLogOld, cfg_out['db'], cfg_out['b_skip_if_up_to_date'] = h5temp_open(**cfg_out)
for i1, (tbl, coefs) in enumerate(h5_names_gen(cfg_in), start=1):
# using property of rotation around same axis: R(x, θ1)@R(x, θ2) = R(x, θ1 + θ2)
coefs['Ag'] = coefs['Ag'] @ rot_matrix_x(np.cos(np.pi), np.sin(np.pi))
coefs['Ah'] = coefs['Ah'] @ rot_matrix_x(np.cos(np.pi), np.sin(np.pi))
coefs['azimuth_shift_deg'] = 180
h5copy_coef(None,
cfg['out']['db_path'],
tbl,
dict_matrices=dict_matrices_for_h5(coefs,
tbl,
to_nested_keys=True))
# Calculate velocity and average
if st(2):
# if aggregate_period_s is None then not average and write to *_proc_noAvg.h5 else loading from that h5 and writing to _proc.h5
if not cfg['out']['aggregate_period_s']:
cfg['out']['aggregate_period_s'] = [
None, 2, 600,
3600 if 'w' in cfg['in']['probes_prefix'] else 7200
]
if cfg['in']['azimuth_add']:
if 'Lat' in cfg['in']['azimuth_add']:
from datetime import datetime
# add magnetic declination,° for used coordinates
# todo: get time
azimuth_add = mag_dec(cfg['in']['azimuth_add']['Lat'],
cfg['in']['azimuth_add']['Lon'],
datetime(2020, 9, 10),
depth=-1)
else:
azimuth_add = 0
if 'constant' in cfg['in']['azimuth_add']:
# and add constant. For example, subtruct declination at the calibration place if it was applied
azimuth_add += cfg['in']['azimuth_add'][
'constant'] # add -6.65644183° to account for calibration in Kaliningrad
for aggregate_period_s in cfg['out']['aggregate_period_s']:
if aggregate_period_s is None:
db_path_in = db_path
db_path_out = db_path.with_name(
f'{db_path.stem}_proc_noAvg.h5')
else:
db_path_in = db_path.with_name(f'{db_path.stem}_proc_noAvg.h5')
db_path_out = f'{db_path.stem}_proc.h5' # or separately: '_proc{aggregate_period_s}.h5'
args = [
Path(incl_h5clc.__file__).with_name(
f'incl_h5clc_{db_path.stem}.yaml'),
# if no such file all settings are here
'--db_path',
str(db_path_in),
# ! 'incl.*|w\d*' inclinometers or wavegauges w\d\d # 'incl09':
'--tables_list',
'incl.*' if not cfg['in']['probes'] else
f"incl.*(?:{'|'.join('{:0>2}'.format(p) for p in cfg['in']['probes'])})",
'--aggregate_period',
f'{aggregate_period_s}S' if aggregate_period_s else '',
'--out.db_path',
str(db_path_out),
'--table',
f'V_incl_bin{aggregate_period_s}'
if aggregate_period_s else 'V_incl',
'--verbose',
'INFO', #'DEBUG' get many numba messages
'--b_del_temp_db',
'1',
# '--calc_version', 'polynom(force)', # depreshiated
# '--chunksize', '20000',
# '--not_joined_h5_path', f'{db_path.stem}_proc.h5',
]
# if aggregate_period_s <= 5: # [s], do not need split csv for big average interval
# args += (['--split_period', '1D'])
if aggregate_period_s is None: # proc. parameters (if we have saved proc. data then when aggregating we are not processing)
args += ([
'--max_dict',
'M[xyz]:4096',
# Note: for Baranov's prog 4096 is not suited
# '--time_range_zeroing_dict', "incl19: '2019-11-10T13:00:00', '2019-11-10T14:00:00'\n," # not works - use kwarg
# '--time_range_zeroing_list', '2019-08-26T04:00:00, 2019-08-26T05:00:00'
'--split_period',
'1D'
] if subs_made else [
'--bad_p_at_bursts_starts_peroiod',
'1H',
])
# csv splitted by 1day (default for no avg) and monolith csv if aggregate_period_s==600
if aggregate_period_s not in cfg['out'][
'aggregate_period_s_not_to_text']: # , 300, 600]:
args += ['--text_path', str(db_path.parent / 'text_output')]
kwarg = {
'in': {
'min_date': cfg['filter']['min_date'][0],
'max_date': cfg['filter']['max_date'][0],
'time_range_zeroing': cfg['in']['time_range_zeroing'],
'azimuth_add': azimuth_add
}
}
# If need all data to be combined one after one:
# set_field_if_no(kwarg, 'in', {})
# kwarg['in'].update({
#
# 'tables': [f'incl{i:0>2}' for i in min_date.keys() if i!=0],
# 'dates_min': min_date.values(), # in table list order
# 'dates_max': max_date.values(), #
# })
# set_field_if_no(kwarg, 'out', {})
# kwarg['out'].update({'b_all_to_one_col': 'True'})
incl_h5clc.main(args, **kwarg)
# Calculate spectrograms.
if st(3): # Can be done at any time after step 1
def raise_ni():
raise NotImplementedError(
'Can not proc probes having different fs in one run: you need to do it separately'
)
args = [
Path(incl_h5clc.__file__).with_name(
f'incl_h5spectrum{db_path.stem}.yaml'),
# if no such file all settings are here
'--db_path',
str(db_path.with_name(f'{db_path.stem}_proc_noAvg.h5')),
'--tables_list',
f"{cfg['in']['probes_prefix']}.*", # inclinometers or wavegauges w\d\d ## 'w02', 'incl.*',
# '--aggregate_period', f'{aggregate_period_s}S' if aggregate_period_s else '',
'--min_date',
datetime64_str(cfg['filter']['min_date'][0]),
'--max_date',
datetime64_str(cfg['filter']['max_date']
[0]), # '2019-09-09T16:31:00', #17:00:00
# '--max_dict', 'M[xyz]:4096', # use if db_path is not ends with _proc_noAvg.h5 i.e. need calc velocity
'--out.db_path',
f"{db_path.stem.replace('incl', cfg['in']['probes_prefix'])}_proc_psd.h5",
# '--table', f'psd{aggregate_period_s}' if aggregate_period_s else 'psd',
'--fs_float',
f"{fs(probes[0], cfg['in']['probes_prefix'])}",
# (lambda x: x == x[0])(np.vectorize(fs)(probes, prefix))).all() else raise_ni()
#
# '--time_range_zeroing_list', '2019-08-26T04:00:00, 2019-08-26T05:00:00'
# '--verbose', 'DEBUG',
# '--chunksize', '20000',
'--b_interact',
'0',
]
if 'w' in cfg['in']['probes_prefix']:
args += [
'--split_period',
'1H',
'--dt_interval_minutes',
'10', # burst mode
'--fmin',
'0.0001',
'--fmax',
'4'
]
else:
args += [
'--split_period',
'2H',
'--fmin',
'0.0004', #0.0004
'--fmax',
'1.05'
]
incl_h5spectrum.main(args)
# Draw in Veusz
if st(4):
b_images_only = True # False
pattern_path = db_path.parent / r'vsz_5min\191119_0000_5m_incl19.vsz' # r'vsz_5min\191126_0000_5m_w02.vsz'
if not b_images_only:
pattern_bytes_slice_old = re.escape(b'((5828756, 5830223, None),)')
# Length of not adjacent intervals, s (set None to not allow)
period = '1D'
length = '5m' # period # '1D'
dt_custom_s = pd_period_to_timedelta(
length) if length != period else None # None # 60 * 5
if True:
# Load starts and assign ends
t_intervals_start = pd.read_csv(
cfg['in']['path_cruise'] /
r'vsz+h5_proc\intervals_selected.txt',
converters={
'time_start': lambda x: np.datetime64(x, 'ns')
},
index_col=0).index
edges = (pd.DatetimeIndex(t_intervals_start),
pd.DatetimeIndex(t_intervals_start + dt_custom_s)
) # np.zeros_like()
else:
# Generate periodic intervals
t_interval_start, t_intervals_end = intervals_from_period(
datetime_range=np.array(
[
cfg['filter']['min_date']['0'],
cfg['filter']['max_date']['0']
],
# ['2018-08-11T18:00:00', '2018-09-06T00:00:00'],
# ['2019-02-11T13:05:00', '2019-03-07T11:30:00'],
# ['2018-11-16T15:19', '2018-12-14T14:35'],
# ['2018-10-22T12:30', '2018-10-27T06:30:00'],
'datetime64[s]'),
period=period)
edges = (pd.DatetimeIndex([t_interval_start
]).append(t_intervals_end[:-1]),
pd.DatetimeIndex(t_intervals_end))
for i, probe in enumerate(probes):
probe_name = f"{cfg['in']['probes_prefix']}{probe:02}" # table name in db
l.info('Draw %s in Veusz: %d intervals...', probe_name,
edges[0].size)
# for i_interval, (t_interval_start, t_interval_end) in enumerate(zip(pd.DatetimeIndex([t_interval_start]).append(t_intervals_end[:-1]), t_intervals_end), start=1):
cfg_vp = {'veusze': None}
for i_interval, (t_interval_start,
t_interval_end) in enumerate(zip(*edges),
start=1):
# if i_interval < 23: #<= 0: # TEMPORARY Skip this number of intervals
# continue
if period != length:
t_interval_start = t_interval_end - pd.Timedelta(
dt_custom_s, 's')
try: # skipping absent probes
start_end = h5q_interval2coord(
db_path=str(db_path),
table=f'/{probe_name}',
t_interval=(t_interval_start, t_interval_end))
if not len(start_end):
break # no data
except KeyError:
break # device name not in specified range, go to next name
pattern_path_new = pattern_path.with_name(
f"{t_interval_start:%y%m%d_%H%M}_{length}_{probe_name}.vsz"
)
# Modify pattern file
if not b_images_only:
probe_name_old = re.match('.*((?:incl|w)\d*).*',
pattern_path.name).groups()[0]
bytes_slice = bytes(
'(({:d}, {:d}, None),)'.format(*(start_end +
np.int32([-1, 1]))),
'ascii')
def f_replace(line):
"""
Replace in file
1. probe name
2. slice
"""
# if i_interval == 1:
line, ok = re.subn(bytes(probe_name_old, 'ascii'),
bytes(probe_name, 'ascii'), line)
if ok: # can be only in same line
line = re.sub(pattern_bytes_slice_old, bytes_slice,
line)
return line
if not rep_in_file(pattern_path,
pattern_path_new,
f_replace=f_replace):
l.warning('Veusz pattern not changed!')
# break
elif cfg_vp['veusze']:
cfg_vp['veusze'].Load(str(pattern_path_new))
elif cfg_vp['veusze']:
cfg_vp['veusze'].Load(str(pattern_path_new))
txt_time_range = \
"""
"[['{:%Y-%m-%dT%H:%M}', '{:%Y-%m-%dT%H:%M}']]" \
""".format(t_interval_start, t_interval_end)
print(f'{i_interval}. {txt_time_range}', end=' ')
cfg_vp = veuszPropagate.main(
[
Path(veuszPropagate.__file__).parent.with_name(
'veuszPropagate.ini'),
# '--data_yield_prefix', '-',
'--path',
str(
db_path
), # use for custom loading from db and some source is required
'--tables_list',
f'/{probe_name}', # 181022inclinometers/ \d*
'--pattern_path',
str(pattern_path_new),
# fr'd:\workData\BalticSea\190801inclinometer_Schuka\{probe_name}_190807_1D.vsz',
# str(db_path.parent / dir_incl / f'{probe_name}_190211.vsz'), #warning: create file with small name
# '--before_next', 'restore_config',
# '--add_to_filename', f"_{t_interval_start:%y%m%d_%H%M}_{length}",
'--filename_fun',
f'lambda tbl: "{pattern_path_new.name}"',
'--add_custom_list',
'USEtime', # nAveragePrefer',
'--add_custom_expressions_list',
txt_time_range,
# + """
# ", 5"
# """,
'--b_update_existed',
'True',
'--export_pages_int_list',
'1, 2', # 0 for all '6, 7, 8', #'1, 2, 3'
# '--export_dpi_int', '200',
'--export_format',
'emf',
'--b_interact',
'0',
'--b_images_only',
f'{b_images_only}',
'--return',
'<embedded_object>', # reuse to not bloat memory
],
veusze=cfg_vp['veusze'])
prefix = 'incl' # 'incl' or 'w' # table name prefix in db and in raw files (to find raw fales name case will be UPPER anyway): 'incl' - inclinometer, 'w' - wavegauge
# dir_incl = '' if 'inclinometer' in str(path_cruise) else 'inclinometer'
# if not db_name: # then name by cruise dir:
# db_name = re.match('(^[\d_]*).*', (path_cruise.parent if dir_incl else path_cruise).name
# ).group(1).strip('_') + 'incl.h5'
db_path_out = paths_db_in[0].with_name('many2one_out.h5')
# Run steps (inclusive):
st.start = 2 # 1
st.end = 2
m_TimeStart_csv = pd.Timestamp('2019-07-08T00:00:00Z')
# Calculate velocity and average
if st(2):
# if aggregate_period_s is None then not average and write to *_proc_noAvg.h5 else loading from that h5 and writing to _proc.h5
for aggregate_period_s in [
720
]: # [None, 2, 300, 600, 3600 if 'w' in prefix else 7200]
args = [
Path(incl_h5clc.__file__).with_name(f'incl_h5clc_many2one.yaml'),
# if no such file all settings are here
'--db_path',
'|'.join(str(p) for p in paths_db_in),
'--tables_list',
','.join(
f'incl{i:0>2}' for i in probes
), #incl.*| ! 'incl.*|w\d*' inclinometers or wavegauges w\d\d # 'incl09',
'--aggregate_period',
def main(new_arg=None, **kwargs):
"""
:param new_arg: list of strings, command line arguments
:kwargs: dicts of dictcts (for each ini section): specified values overwrites ini values
"""
# global l
cfg = cfg_from_args(my_argparser(), new_arg, **kwargs)
if not cfg['program']:
return # usually error of unrecognized arguments displayed
cfg['in']['db_coefs'] = Path(cfg['in']['db_coefs'])
for path_field in ['db_coefs', 'path_cruise']:
if not cfg['in'][path_field].is_absolute():
cfg['in'][path_field] = (
cfg['in']['cfgFile'].parent / cfg['in'][path_field]
).resolve().absolute() # cfg['in']['cfgFile'].parent /
def constant_factory(val):
def default_val():
return val
return default_val
for lim in ('min_date', 'max_date'):
# convert keys to int because they must be comparable to probes_int_list (for command line arguments keys are allways strings, in yaml you can set string or int)
_ = {int(k): v for k, v in cfg['filter'][lim].items()}
cfg['filter'][lim] = defaultdict(constant_factory(_.get(0)), _)
l = init_logging(logging, None, None, 'INFO')
#l = init_logging(logging, None, cfg['program']['log'], cfg['program']['verbose'])
if True: # False. Experimental speedup but takes memory
from dask.cache import Cache
cache = Cache(2e9) # Leverage two gigabytes of memory
cache.register() # Turn cache on globally
#if __debug__:
# # because there was errors on debug when default scheduler used
# cfg['program']['dask_scheduler'] = 'synchronous'
if cfg['program']['dask_scheduler']:
if cfg['program']['dask_scheduler'] == 'distributed':
from dask.distributed import Client
# cluster = dask.distributed.LocalCluster(n_workers=2, threads_per_worker=1, memory_limit="5.5Gb")
client = Client(processes=False)
# navigate to http://localhost:8787/status to see the diagnostic dashboard if you have Bokeh installed
# processes=False: avoide inter-worker communication for computations releases the GIL (numpy, da.array) # without is error
else:
if cfg['program']['dask_scheduler'] == 'synchronous':
l.warning('using "synchronous" scheduler for debugging')
import dask
dask.config.set(scheduler=cfg['program']['dask_scheduler'])
# Run steps :
st.start = cfg['program']['step_start']
st.end = cfg['program']['step_end']
st.go = True
if not cfg['out'][
'db_name']: # set name by 'path_cruise' name or parent if it has digits at start. priority for name is "*inclinometer*"
for p in (lambda p: [p, p.parent])(cfg['in']['path_cruise']):
m = re.match('(^[\d_]*).*', p.name)
if m:
break
cfg['out']['db_name'] = f"{m.group(1).strip('_')}incl.h5"
dir_incl = next((d for d in cfg['in']['path_cruise'].glob('*inclinometer*')
if d.is_dir()), cfg['in']['path_cruise'])
db_path = dir_incl / '_raw' / cfg['out']['db_name']
# ---------------------------------------------------------------------------------------------
# def fs(probe, name):
# if 'w' in name.lower(): # Baranov's wavegauge electronic
# return 10 # 5
# return 5
# if probe < 20 or probe in [23, 29, 30, 32, 33]: # 30 [4, 11, 5, 12] + [1, 7, 13, 30]
# return 5
# if probe in [21, 25, 26] + list(range(28, 35)):
# return 8.2
# return 4.8
def datetime64_str(time_str: Optional[str] = None) -> np.ndarray:
"""
Reformat time_str to ISO 8601 or to 'NaT'. Used here for input in funcs that converts str to numpy.datetime64
:param time_str: May be 'NaT'
:return: ndarray of strings (tested for 1 element only) formatted by numpy.
"""
return np.datetime_as_string(np.datetime64(time_str, 's'))
probes = cfg['in']['probes'] or range(
1, 41) # sets default range, specify your values before line ---
raw_root, probe_is_incl = re.subn('INCL_?', 'INKL_',
cfg['in']['probes_prefix'].upper())
# some parameters that depends of probe type (indicated by probes_prefix)
p_type = defaultdict(
# baranov's format
constant_factory({
'correct_fun':
partial(correct_txt,
mod_file_name=mod_incl_name,
sub_str_list=[
b'^\r?(?P<use>20\d{2}(\t\d{1,2}){5}(\t\d{5}){8}).*',
b'^.+'
]),
'fs':
10,
'format':
'Baranov',
}),
{
(lambda x: x if x.startswith('incl') else 'incl')(cfg['in']['probes_prefix']):
{
'correct_fun':
partial(
correct_txt,
mod_file_name=mod_incl_name,
sub_str_list=[
b'^(?P<use>20\d{2}(,\d{1,2}){5}(,\-?\d{1,6}){6}(,\d{1,2}\.\d{2})(,\-?\d{1,3}\.\d{2})).*',
b'^.+'
]),
'fs':
5,
'format':
'Kondrashov',
},
'voln': {
'correct_fun':
partial(
correct_txt,
mod_file_name=mod_incl_name,
sub_str_list=[
b'^(?P<use>20\d{2}(,\d{1,2}){5}(,\-?\d{1,8})(,\-?\d{1,2}\.\d{2}){2}).*',
b'^.+'
]),
'fs':
5,
#'tbl_prefix': 'w',
'format':
'Kondrashov',
}
})
if st(1, 'Save inclinometer or wavegage data from ASCII to HDF5'):
# Note: Can not find additional not corrected files for same probe if already have any corrected in search path (move them out if need)
i_proc_probe = 0 # counter of processed probes
i_proc_file = 0 # counter of processed files
# patten to identify only _probe_'s raw data files that need to correct '*INKL*{:0>2}*.[tT][xX][tT]':
raw_parent = dir_incl / '_raw' # raw_parent /=
if cfg['in']['raw_subdir'] is None:
cfg['in']['raw_subdir'] = ''
dir_out = raw_parent / re.sub(r'[.\\/ *?]', '_',
cfg['in']['raw_subdir'])
# sub replaces multilevel subdirs to 1 level that correct_fun() can only make
def dt_from_utc_2000(probe):
""" Correct time of probes started without time setting. Raw date must start from 2000-01-01T00:00"""
return (
datetime(year=2000, month=1, day=1) -
cfg['in']['time_start_utc'][probe]
) if cfg['in']['time_start_utc'].get(probe) else timedelta(0)
# convert cfg['in']['dt_from_utc'] keys to int
cfg['in']['dt_from_utc'] = {
int(p): v
for p, v in cfg['in']['dt_from_utc'].items()
}
# convert cfg['in']['t_start_utc'] to cfg['in']['dt_from_utc'] and keys to int
cfg['in']['dt_from_utc'].update( # overwriting the 'time_start_utc' where already exist
{int(p): dt_from_utc_2000(p) for p, v in cfg['in']['time_start_utc'].items()}
)
# make cfg['in']['dt_from_utc'][0] be default value
cfg['in']['dt_from_utc'] = defaultdict(
constant_factory(cfg['in']['dt_from_utc'].pop(0, timedelta(0))),
cfg['in']['dt_from_utc'])
for probe in probes:
raw_found = []
raw_pattern_file = str(
Path(glob.escape(cfg['in']['raw_subdir'])) /
cfg['in']['raw_pattern'].format(prefix=raw_root, number=probe))
correct_fun = p_type[cfg['in']['probes_prefix']]['correct_fun']
# if not archive:
if (not re.match(r'.*(\.zip|\.rar)$', cfg['in']['raw_subdir'],
re.IGNORECASE)) and raw_parent.is_dir():
raw_found = list(raw_parent.glob(raw_pattern_file))
if not raw_found:
# Check if already have corrected files for probe generated by correct_txt(). If so then just use them
raw_found = list(
dir_out.glob(
f"{cfg['in']['probes_prefix']}{probe:0>2}.txt"))
if raw_found:
print('corrected csv file', [r.name for r in raw_found],
'found')
correct_fun = lambda x, dir_out: x
elif not cfg['in']['raw_subdir']:
continue
for file_in in (raw_found or open_csv_or_archive_of_them(
raw_parent, binary_mode=False, pattern=raw_pattern_file)):
file_in = correct_fun(file_in, dir_out=dir_out)
if not file_in:
continue
tbl = file_in.stem # f"{cfg['in']['probes_prefix']}{probe:0>2}"
# tbl = re.sub('^((?P<i>inkl)|w)_0', lambda m: 'incl' if m.group('i') else 'w', # correct name
# re.sub('^[\d_]*|\*', '', file_in.stem).lower()), # remove date-prefix if in name
csv2h5(
[
str(
Path(__file__).parent / 'ini' /
f"csv_{'inclin' if probe_is_incl else 'wavegage'}_{p_type[cfg['in']['probes_prefix']]['format']}.ini"
),
'--path',
str(file_in),
'--blocksize_int',
'50_000_000', # 50Mbt
'--table',
tbl,
'--db_path',
str(db_path),
# '--log', str(scripts_path / 'log/csv2h5_inclin_Kondrashov.log'),
# '--b_raise_on_err', '0', # ?
'--b_interact',
'0',
'--fs_float',
str(p_type[cfg['in']['probes_prefix']]
['fs']), #f'{fs(probe, file_in.stem)}',
'--dt_from_utc_seconds',
str(cfg['in']['dt_from_utc'][probe].total_seconds()),
'--b_del_temp_db',
'1',
] +
(['--csv_specific_param_dict', 'invert_magnitometr: True']
if probe_is_incl else []),
**{
'filter': {
'min_date':
cfg['filter']['min_date'].get(
probe, np.datetime64(0, 'ns')),
'max_date':
cfg['filter']['max_date'].get(
probe, np.datetime64('now', 'ns')
), # simple 'now' works in sinchronious mode
}
})
# Get coefs:
l.info(
f"Adding coefficients to {db_path}/{tbl} from {cfg['in']['db_coefs']}"
)
try:
h5copy_coef(cfg['in']['db_coefs'], db_path, tbl)
except KeyError as e: # Unable to open object (component not found)
l.warning(
'No coefs to copy?'
) # write some dummy coefficients to can load Veusz patterns:
h5copy_coef(None,
db_path,
tbl,
dict_matrices=dict_matrices_for_h5(tbl=tbl))
except OSError as e:
l.warning(
'Not found DB with coefs?'
) # write some dummy coefficients to can load Veusz patterns:
h5copy_coef(None,
db_path,
tbl,
dict_matrices=dict_matrices_for_h5(tbl=tbl))
i_proc_file += 1
else:
print('no', raw_pattern_file, end=', ')
i_proc_probe += 1
print('Ok:', i_proc_probe, 'probes,', i_proc_file, 'files processed.')
if st(2, 'Calculate physical parameters and average'):
kwarg = {
'in': {
'min_date': cfg['filter']['min_date'][0],
'max_date': cfg['filter']['max_date'][0],
'time_range_zeroing': cfg['in']['time_range_zeroing']
},
'proc': {}
}
# if aggregate_period_s is None then not average and write to *_proc_noAvg.h5 else loading from that h5 and writing to _proc.h5
if not cfg['out']['aggregate_period_s']:
cfg['out']['aggregate_period_s'] = [
None, 2, 600, 7200 if probe_is_incl else 3600
]
if cfg['in']['azimuth_add']:
if 'Lat' in cfg['in']['azimuth_add']:
# add magnetic declination,° for used coordinates
# todo: get time
kwarg['proc']['azimuth_add'] = mag_dec(
cfg['in']['azimuth_add']['Lat'],
cfg['in']['azimuth_add']['Lon'],
datetime(2020, 9, 10),
depth=-1)
else:
kwarg['proc']['azimuth_add'] = 0
if 'constant' in cfg['in']['azimuth_add']:
# and add constant. For example, subtruct declination at the calibration place if it was applied
kwarg['proc']['azimuth_add'] += cfg['in']['azimuth_add'][
'constant'] # add -6.656 to account for calibration in Kaliningrad (mag deg = 6.656°)
for aggregate_period_s in cfg['out']['aggregate_period_s']:
if aggregate_period_s is None:
db_path_in = db_path
db_path_out = dir_incl / f'{db_path.stem}_proc_noAvg.h5'
else:
db_path_in = dir_incl / f'{db_path.stem}_proc_noAvg.h5'
db_path_out = dir_incl / f'{db_path.stem}_proc.h5' # or separately: '_proc{aggregate_period_s}.h5'
# 'incl.*|w\d*' inclinometers or wavegauges w\d\d # 'incl09':
tables_list_regex = f"{cfg['in']['probes_prefix'].replace('voln', 'w')}.*"
if cfg['in']['probes']:
tables_list_regex += "(?:{})".format('|'.join(
'{:0>2}'.format(p) for p in cfg['in']['probes']))
args = [
'../../empty.yml', # all settings are here, so to not print 'using default configuration' we use some existed empty file
'--db_path',
str(db_path_in),
'--tables_list',
tables_list_regex,
'--aggregate_period',
f'{aggregate_period_s}S' if aggregate_period_s else '',
'--out.db_path',
str(db_path_out),
'--table',
f'V_incl_bin{aggregate_period_s}'
if aggregate_period_s else 'V_incl',
'--verbose',
'INFO', #'DEBUG' get many numba messages
'--b_del_temp_db',
'1',
# '--calc_version', 'polynom(force)', # depreshiated
# '--chunksize', '20000',
# '--not_joined_h5_path', f'{db_path.stem}_proc.h5',
]
if aggregate_period_s is None: # proc. parameters (if we have saved proc. data then when aggregating we are not processing)
# Note: for Baranov's prog 4096 is not suited:
args += ([
'--max_dict',
'M[xyz]:4096',
# '--time_range_zeroing_dict', "incl19: '2019-11-10T13:00:00', '2019-11-10T14:00:00'\n," # not works - use kwarg
# '--time_range_zeroing_list', '2019-08-26T04:00:00, 2019-08-26T05:00:00'
'--split_period',
'1D'
] if probe_is_incl else [
'--bad_p_at_bursts_starts_peroiod',
'1H',
])
# csv splitted by 1day (default for no avg) else csv is monolith
if aggregate_period_s not in cfg['out'][
'aggregate_period_s_not_to_text']: # , 300, 600]:
args += ['--text_path', str(dir_incl / 'text_output')]
# If need all data to be combined one after one:
# set_field_if_no(kwarg, 'in', {})
# kwarg['in'].update({
#
# 'tables': [f'incl{i:0>2}' for i in min_date.keys() if i!=0],
# 'dates_min': min_date.values(), # in table list order
# 'dates_max': max_date.values(), #
# })
# set_field_if_no(kwarg, 'out', {})
# kwarg['out'].update({'b_all_to_one_col': 'True'})
incl_h5clc.main(args, **kwarg)
if st(3, 'Calculate spectrograms'): # Can be done at any time after step 1
min_Pressure = 7
# add dict dates_min like {probe: parameter} of incl_clc to can specify param to each probe
def raise_ni():
raise NotImplementedError(
'Can not proc probes having different fs in one run: you need to do it separately'
)
args = [
Path(incl_h5clc.__file__).with_name(
f'incl_h5spectrum{db_path.stem}.yaml'),
# if no such file all settings are here
'--db_path',
str(dir_incl / f'{db_path.stem}_proc_noAvg.h5'),
'--tables_list',
f"{cfg['in']['probes_prefix']}.*", # inclinometers or wavegauges w\d\d ## 'w02', 'incl.*',
# '--aggregate_period', f'{aggregate_period_s}S' if aggregate_period_s else '',
'--min_date',
datetime64_str(cfg['filter']['min_date'][0]),
'--max_date',
datetime64_str(cfg['filter']['max_date']
[0]), # '2019-09-09T16:31:00', #17:00:00
'--min_Pressure',
f'{min_Pressure}',
# '--max_dict', 'M[xyz]:4096', # use if db_path is not ends with _proc_noAvg.h5 i.e. need calc velocity
'--out.db_path',
f"{db_path.stem.replace('incl', cfg['in']['probes_prefix'])}_proc_psd.h5",
# '--table', f'psd{aggregate_period_s}' if aggregate_period_s else 'psd',
'--fs_float',
str(p_type[cfg['in']['probes_prefix']]
['fs']), # f"{fs(probes[0], cfg['in']['probes_prefix'])}",
# (lambda x: x == x[0])(np.vectorize(fs)(probes, prefix))).all() else raise_ni()
#
# '--time_range_zeroing_list', '2019-08-26T04:00:00, 2019-08-26T05:00:00'
# '--verbose', 'DEBUG',
# '--chunksize', '20000',
'--b_interact',
'0',
]
if probe_is_incl:
args += [
'--split_period',
'2H',
'--fmin',
'0.0004', #0.0004
'--fmax',
'1.05'
]
else:
args += [
'--split_period',
'1H',
'--dt_interval_minutes',
'15', # set this if burst mode to the burst interval
'--fmin',
'0.0001',
'--fmax',
'4',
#'--min_Pressure', '-1e15', # to not load NaNs
]
incl_h5spectrum.main(args)
if st(4, 'Draw in Veusz'):
pattern_path = dir_incl / r'processed_h5,vsz/201202-210326incl_proc#28.vsz'
# r'\201202_1445incl_proc#03_pattern.vsz' #'
# db_path.parent / r'vsz_5min\191119_0000_5m_incl19.vsz' # r'vsz_5min\191126_0000_5m_w02.vsz'
b_images_only = False
# importing in vsz index slices replacing:
pattern_str_slice_old = None
# Length of not adjacent intervals, s (set None to not allow)
# pandas interval in string or tuple representation '1D' of period between intervals and interval to draw
period_str = '0s' # '1D' # dt
dt_str = '0s' # '5m'
file_intervals = None
period = to_offset(period_str).delta
dt = to_offset(dt_str).delta # timedelta(0) # 60 * 5
if file_intervals and period and dt:
# Load starts and assign ends
t_intervals_start = pd.read_csv(
cfg['in']['path_cruise'] /
r'vsz+h5_proc\intervals_selected.txt',
converters={
'time_start': lambda x: np.datetime64(x, 'ns')
},
index_col=0).index
edges = (pd.DatetimeIndex(t_intervals_start),
pd.DatetimeIndex(t_intervals_start + dt_custom_s)
) # np.zeros_like()
elif period and dt:
# Generate periodic intervals
t_interval_start, t_intervals_end = intervals_from_period(
datetime_range=np.array(
[
cfg['filter']['min_date']['0'],
cfg['filter']['max_date']['0']
],
# ['2018-08-11T18:00:00', '2018-09-06T00:00:00'],
# ['2019-02-11T13:05:00', '2019-03-07T11:30:00'],
# ['2018-11-16T15:19', '2018-12-14T14:35'],
# ['2018-10-22T12:30', '2018-10-27T06:30:00'],
'datetime64[s]'),
period=period)
edges = (pd.DatetimeIndex([t_interval_start
]).append(t_intervals_end[:-1]),
pd.DatetimeIndex(t_intervals_end))
else: # [min, max] edges for each probe
edges_dict = {
pr:
[cfg['filter']['min_date'][pr], cfg['filter']['max_date'][pr]]
for pr in probes
}
cfg_vp = {'veusze': None}
for i, probe in enumerate(probes):
# cfg_vp = {'veusze': None}
if edges_dict: # custom edges for each probe
edges = [pd.DatetimeIndex([t]) for t in edges_dict[probe]]
# substr in file to rerplace probe_name_in_pattern (see below).
probe_name = f"_{cfg['in']['probes_prefix'].replace('incl', 'i')}{probe:02}"
tbl = None # f"/{cfg['in']['probes_prefix']}{probe:02}" # to check probe data exist in db else will not check
l.info('Draw %s in Veusz: %d intervals...', probe_name,
edges[0].size)
# for i_interval, (t_interval_start, t_interval_end) in enumerate(zip(pd.DatetimeIndex([t_interval_start]).append(t_intervals_end[:-1]), t_intervals_end), start=1):
for i_interval, (t_interval_start,
t_interval_end) in enumerate(zip(*edges),
start=1):
# if i_interval < 23: #<= 0: # TEMPORARY Skip this number of intervals
# continue
if period and period != dt:
t_interval_start = t_interval_end - pd.Timedelta(
dt_custom_s, 's')
if tbl:
try: # skipping absent probes
start_end = h5q_interval2coord(
db_path=str(db_path),
table=tbl,
t_interval=(t_interval_start, t_interval_end))
if not len(start_end):
break # no data
except KeyError:
break # device name not in specified range, go to next name
pattern_path_new = pattern_path.with_name(''.join([
f'{t_interval_start:%y%m%d_%H%M}',
f'_{dt_str}' if dt else '', f'{probe_name}.vsz'
]))
# Modify pattern file
if not b_images_only:
pattern_type, pattern_number = re.match(
r'.*(incl|w)_proc?#?(\d*).*',
pattern_path.name).groups()
probe_name_in_pattern = f"_{pattern_type.replace('incl', 'i')}{pattern_number}"
def f_replace(line):
"""
Replace in file
1. probe name
2. slice
"""
# if i_interval == 1:
line, ok = re.subn(probe_name_in_pattern, probe_name,
line)
if ok and pattern_str_slice_old: # can be only in same line
str_slice = '(({:d}, {:d}, None),)'.format(
*(start_end +
np.int32([-1, 1]))) # bytes(, 'ascii')
line = re.sub(pattern_str_slice_old, str_slice,
line)
return line
if not rep_in_file(pattern_path,
pattern_path_new,
f_replace=f_replace,
binary_mode=False):
l.warning('Veusz pattern not changed!'
) # may be ok if we need draw pattern
# break
elif cfg_vp['veusze']:
cfg_vp['veusze'].Load(str(pattern_path_new))
elif cfg_vp['veusze']:
cfg_vp['veusze'].Load(str(pattern_path_new))
txt_time_range = \
"""
"[['{:%Y-%m-%dT%H:%M}', '{:%Y-%m-%dT%H:%M}']]" \
""".format(t_interval_start, t_interval_end)
print(f'{i_interval}. {txt_time_range}', end=' ')
cfg_vp = veuszPropagate.main(
[
Path(veuszPropagate.__file__).parent.with_name(
'veuszPropagate.ini'),
# '--data_yield_prefix', '-',
# '--path', str(db_path), # if custom loading from db and some source is required
'--tables_list',
'', # switches to search vsz-files only # f'/{probe_name}', # 181022inclinometers/ \d*
'--pattern_path',
str(pattern_path_new),
# fr'd:\workData\BalticSea\190801inclinometer_Schuka\{probe_name}_190807_1D.vsz',
# str(dir_incl / f'{probe_name}_190211.vsz'), #warning: create file with small name
# '--before_next', 'restore_config',
# '--add_to_filename', f"_{t_interval_start:%y%m%d_%H%M}_{dt}",
'--filename_fun',
f'lambda tbl: "{pattern_path_new.name}"',
'--add_custom_list',
f'USEtime__', # f'USEtime{probe_name}', nAveragePrefer',
'--add_custom_expressions_list',
txt_time_range,
# + """
# ", 5"
# """,
'--b_update_existed',
'True',
'--export_pages_int_list',
'0', # 0 for all '6, 7, 8', #'1, 2, 3'
# '--export_dpi_int', '200',
'--export_format',
'jpg', #'emf',
'--b_interact',
'0',
'--b_images_only',
f'{b_images_only}',
'--return',
'<embedded_object>', # reuse to not bloat memory
'--b_execute_vsz',
'True',
'--before_next',
'Close()' # Close() need if b_execute_vsz many files
],
veusze=cfg_vp['veusze'])
if st(40, f'Draw in Veusz by loader-drawer.vsz method'):
# save all vsz files that uses separate code
from os import chdir as os_chdir
dt_s = 300
cfg['in'][
'pattern_path'] = db_path.parent / f'vsz_{dt_s:d}s' / '~pattern~.vsz'
time_starts = pd.read_csv(
db_path.parent / r'processed_h5,vsz' / 'intervals_selected.txt',
index_col=0,
parse_dates=True,
date_parser=lambda x: pd.to_datetime(x, format='%Y-%m-%dT%H:%M:%S'
)).index
pattern_code = cfg['in']['pattern_path'].read_bytes(
) # encoding='utf-8'
path_vsz_all = []
for i, probe in enumerate(probes):
probe_name = f"{cfg['in']['probes_prefix']}{probe:02}" # table name in db
l.info('Draw %s in Veusz: %d intervals...', probe_name,
time_starts.size)
for i_interval, time_start in enumerate(time_starts, start=1):
path_vsz = cfg['in']['pattern_path'].with_name(
f"{time_start:%y%m%d_%H%M}_{probe_name.replace('incl','i')}.vsz"
)
# copy file to path_vsz
path_vsz.write_bytes(pattern_code) # replaces 1st row
path_vsz_all.append(path_vsz)
os_chdir(cfg['in']['pattern_path'].parent)
veuszPropagate.main(
[
'ini/veuszPropagate.ini',
'--path',
str(cfg['in']['pattern_path'].with_name(
'??????_????_*.vsz')), # db_path),
'--pattern_path',
f"{cfg['in']['pattern_path']}_",
# here used to auto get export dir only. may not be _not existed file path_ if ['out']['paths'] is provided
# '--table_log', f'/{device}/logRuns',
# '--add_custom_list', f'{device_veusz_prefix}USE_time_search_runs', # 'i3_USE_timeRange',
# '--add_custom_expressions',
# """'[["{log_row[Index]:%Y-%m-%dT%H:%M:%S}", "{log_row[DateEnd]:%Y-%m-%dT%H:%M:%S}"]]'""",
# '--export_pages_int_list', '1', #'--b_images_only', 'True'
'--b_interact',
'0',
'--b_update_existed',
'True', # todo: delete_overlapped
'--b_images_only',
'True',
'--load_timeout_s_float',
str(cfg['program']['load_timeout_s'])
# '--min_time', '2020-07-08T03:35:00',
],
**{'out': {
'paths': path_vsz_all
}})
if st(50, 'Export from existed Veusz files in dir'):
pattern_parent = db_path.parent # r'vsz_5min\191126_0000_5m_w02.vsz''
pattern_path = str(pattern_parent / r'processed_h5,vsz' /
'??????incl_proc#[1-9][0-9].vsz') # [0-2,6-9]
veuszPropagate.main([
'ini/veuszPropagate.ini',
'--path',
pattern_path,
'--pattern_path',
pattern_path,
# '--export_pages_int_list', '1', #'--b_images_only', 'True'
'--b_interact',
'0',
'--b_update_existed',
'True', # todo: delete_overlapped
'--b_images_only',
'True',
'--load_timeout_s_float',
str(cfg['program']['load_timeout_s']),
'--b_execute_vsz',
'True',
'--before_next',
'Close()' # Close() need if b_execute_vsz many files
])
from to_pandas_hdf5.gpx2h5 import main as gpx2h5
from to_pandas_hdf5.CTD_calc import main as CTD_calc
from h5toGpx import main as h5toGpx
from grid2d_vsz import main as grid2d_vsz
path_cruise = Path(r'd:\workData\BalticSea\200819_AI56')
path_db = path_cruise / path_cruise.with_suffix('.h5').name # same name as dir
st.go = True # False #
st.start = 70 # default: 1, used: 5 30 70 80
st.end = 110 # 60 80 120
# Stop before steps that need manual preparings (70) i.e. set end < 70 at first
# Gridding (last step) needs debugging if interactive filtering is needed
# ---------------------------------------------------------------------------------------------
if st(1, 'Save gpx navigation to DB'):
gpx2h5([
'',
'--db_path',
str(path_db),
'--path',
str(path_cruise / r'navigation\_raw\*.gpx'),
'--tables_list',
',navigation,', # skip waypoints
'--table_prefix',
r'',
# '--min_date', '2019-07-17T14:00:00',
'--b_skip_if_up_to_date',
'0',
'--b_interact',
'0',
from to_vaex_hdf5.nmea2h5 import main as nmea2h5
st.go = True # False #
st.start = 110 # 5 30 70 80
st.end = 230 # 60 80 120
path_cruise = Path(r'd:\WorkData\BlackSea\200909_Ashamba')
path_db = path_cruise / path_cruise.with_suffix('.h5').name # same name as dir
# Stop before steps that need manual preparings (70) i.e. set end < 70 at first
# Gridding (last step) needs debugging if interactive filtering is needed
# ---------------------------------------------------------------------------------------------
min_coord = 'Lat:10, Lon:10'
max_coord = 'Lat:50, Lon:50'
if st(1, 'Save gpx navigation to DB'):
# Save navigation to DB
for folder in ('OpenCPN_my', 'MapSource_Baranov'):
gpx2h5([
'',
'--db_path',
str(path_db),
'--path',
str(path_cruise / 'navigation' / folder / '*.gpx'),
'--tables_list',
',navigation,', # skip waypoints
'--table_prefix',
r'',
#'--b_search_in_subdirs', if set True to get rid of this loop then will be problems with overlapped data files
# '--min_date', '2019-07-17T14:00:00',
'--b_interact',