spaceweather.omni.omnie_mask_missing() - Code Metrics - st-bender/pyspaceweather - Measure and Improve Code Quality continuously with Scrutinizer

spaceweather.omni.omnie_mask_missing() A
last analyzed 2024-04-10 07:57 UTC

↳ Parent: spaceweather.omni

Complexity

Conditions

Size

Total Lines	30
Code Lines	9

Duplication

Lines	0
Ratio	0 %

Importance

Changes

Metric	Value
cc	3
eloc	9
nop	1
dl	0
loc	30
rs	9.95
c	0
b	0
f	0

# -*- coding: utf-8 -*-
# Copyright (c) 2022 Stefan Bender
#
# This module is part of pyspaceweather.
# pyspaceweather is free software: you can redistribute it or modify
# it under the terms of the GNU General Public License as published
# by the Free Software Foundation, version 2.
# See accompanying COPYING.GPLv2 file or http://www.gnu.org/licenses/gpl-2.0.html.
"""Python interface for OMNI space weather data

Omni2 [#]_ space weather data interface for python.

.. [#] https://omniweb.gsfc.nasa.gov/ow.html
"""
import os
from pkg_resources import resource_filename
import logging
from warnings import warn

from posixpath import join as urljoin

import numpy as np
import pandas as pd

from .core import _assert_file_exists, _dl_file

__all__ = [
	"cache_omnie",
	"omnie_hourly",
	"omnie_mask_missing",
	"read_omnie",
]

OMNI_URL_BASE = "https://spdf.gsfc.nasa.gov/pub/data/omni/low_res_omni/extended"
OMNI_PREFIX, OMNI_EXT = "omni2", "dat"
OMNI_SUBDIR = "omni_extended"
LOCAL_PATH = resource_filename(__name__, os.path.join("data", OMNI_SUBDIR))

_OMNI_MISSING = {
	"year": None,
	"doy": None,
	"hour": None,
	"bsrn": 9999,
	"id_imf": 99,
	"id_sw": 99,
	"n_imf": 999,
	"n_plasma": 999,
	"B_mag_avg": 999.9,
	"B_mag": 999.9,
	"theta_B": 999.9,
	"phi_B": 999.9,
	"B_x": 999.9,
	"B_y_GSE": 999.9,
	"B_z_GSE": 999.9,
	"B_y_GSM": 999.9,
	"B_z_GSM": 999.9,
	"sigma_B_mag_avg": 999.9,
	"sigma_B_mag": 999.9,
	"sigma_B_x_GSE": 999.9,
	"sigma_B_y_GSE": 999.9,
	"sigma_B_z_GSE": 999.9,
	"T_p": 9999999.0,
	"n_p": 999.9,
	"v_plasma": 9999.0,
	"phi_v": 999.9,
	"theta_v": 999.9,
	"n_alpha_n_p": 9.999,
	"p_flow": 99.99,
	"sigma_T": 9999999.0,
	"sigma_n": 999.9,
	"sigma_v": 9999.0,
	"sigma_phi_v": 999.9,
	"sigma_theta_v": 999.9,
	"sigma_na_np": 9.999,
	"E": 999.99,
	"beta_plasma": 999.99,
	"mach": 999.9,
	"Kp": 9.9,
	"R": 999,
	"Dst": 99999,
	"AE": 9999,
	"p_01MeV": 999999.99,
	"p_02MeV": 99999.99,
	"p_04MeV": 99999.99,
	"p_10MeV": 99999.99,
	"p_30MeV": 99999.99,
	"p_60MeV": 99999.99,
	"flag": 0,
	"Ap": 999,
	"f107_adj": 999.9,
	"PC": 999.9,
	"AL": 99999,
	"AU": 99999,
	"mach_mag": 99.9,
	"Lya": 0.999999,
	"QI_p": 9.9999
}


def cache_omnie(
	year,
	prefix=None,
	ext=None,
	local_path=None,
	url_base=None,
):
	"""Download OMNI2 data to local cache

	Downloads the OMNI2 (extended) data file from [#]_ to the local location.

	.. [#] https://spdf.gsfc.nasa.gov/pub/data/omni/low_res_omni/extended/

	Parameters
	----------
	year: int
		Year of the data.
	prefix: str, optional
		File prefix for constructing the file name as <prefix>_year.<ext>.
		Defaults to 'omni2'.
	ext: str, optional
		File extension for constructing the file name as <prefix>_year.<ext>.
		Defaults to 'dat'.
	local_path: str, optional
		Path to the locally stored data yearly files, defaults to the
		data location within the package.
	url_base: str, optional
		URL for the directory that contains the yearly files.

	Returns
	-------
	Nothing.
	"""
	prefix = prefix or OMNI_PREFIX
	ext = ext or OMNI_EXT
	local_path = local_path or LOCAL_PATH
	url_base = url_base or OMNI_URL_BASE

	basename = "{0}_{1:04d}.{2}".format(prefix, year, ext)

	if not os.path.exists(local_path):
		os.makedirs(local_path)

	omnie_file = os.path.join(local_path, basename)
	if not os.path.exists(omnie_file):
		url = urljoin(url_base, basename)
		logging.info("%s not found, downloading from %s.", omnie_file, url)
		_dl_file(omnie_file, url)


def omnie_mask_missing(df):
	"""Mask missing values with NaN

	Marks missing values in the OMNI2 data set by NaN.
	The missing value indicating numbers are taken from the file format description
	https://spdf.gsfc.nasa.gov/pub/data/omni/low_res_omni/extended/aareadme_extended

	Parameters
	----------
	df: pandas.DataFrame
		The OMNI2 data set, e.g. from :func:`omnie_hourly()` or :func:`read_omnie()`.

	Returns
	-------
	df: pandas.DataFrame
		The same dataframe with the missing values masked with ``numpy.nan``.

	Notes
	-----
	This function returns a copy of the dataframe, and all the integer columns
	will be converted to float to support NaN.
	"""
	res = df.copy()
	for _c in df.columns:
		_m = _OMNI_MISSING.get(_c, None)
		if _m is None:
			continue
		_mask = df[_c] != _m
		res[_c] = df[_c].where(_mask)
	return res


def read_omnie(omnie_file):
	"""Read and parse OMNI2 extended files [#]_

	Parses the Omni2 extended data files,  available at [#]_,
	into a :class:`pandas.DataFrame`.

	.. [#] https://omniweb.gsfc.nasa.gov/ow.html
	.. [#] https://spdf.gsfc.nasa.gov/pub/data/omni/low_res_omni/extended/

	Parameters
	----------
	omnie_file: str
		File to parse, absolute path or relative to the current dir.

	Returns
	-------
	sw_df: pandas.DataFrame
		The parsed OMNI2 space weather data (hourly values).
		Details in
		https://spdf.gsfc.nasa.gov/pub/data/omni/low_res_omni/extended/aareadme_extended

		Raises an ``IOError`` if the file is not found.

		The dataframe contains the following columns:

		year:
			The observation year
		doy:
			Day of the year
		hour:
			Hour of the day
		bsrn:
			Bartels Solar Rotation Number.
		id_imf:
			ID for IMF spacecraft
		id_sw:
			ID for SW plasma spacecraft
		n_imf:
			Number of points in IMF averages
		n_plasma:
			Numberof points in plasma averages
		B_mag_avg:
			Magnetic field magnitude average B
		B_mag:
			Magnetic field vector magnitude
		theta_B:
			Latitude angle of the magnetic field vector
		phi_B:
			Longitude angle of the magnetic field vector
		B_x:
			B_x GSE, GSM
		B_y_GSE:
			B_y GSE
		B_z_GSE:
			B_z GSE
		B_y_GSM:
			B_y GSM
		B_z_GSM:
			B_z GSM
		sigma_B_mag_avg:
			RMS standard deviation of B_mag_avg
		sigma_B_mag:
			RMS standard deviation of B_mag
		sigma_B_x_GSE:
			RMS standard deviation of B_x_GSE
		sigma_B_y_GSE:
			RMS standard deviation of B_y_GSE
		sigma_B_z_GSE:
			RMS standard deviation of B_z_GSE
		T_p:
			Proton temperature
		n_p:
			Proton density
		v_plasma:
			Plasma flow speed
		phi_v:
			Plasma flow longitude angle
		theta_v:
			Plasma flow latitude angle
		n_alpha_n_p:
			Alpha/Proton ratio
		p_flow:
			Flow pressure
		sigma_T:
			Standard deviation of T_p
		sigma_n:
			Standard deviation of n_p
		sigma_v:
			Standard deviation of v_plasma
		sigma_phi_v:
			Standard deviation of phi_v
		sigma_theta_v:
			Standard deviation of theta_v
		sigma_na_np:
			Standard deviation of n_alpha_n_p
		E:
			Electric field magnitude
		beta_plasma:
			Plasma beta
		mach:
			Alfvén Mach number
		Kp:
			Kp index value
		R:
			Sunspot number
		Dst:
			Dst index value
		AE:
			AE index value
		p_01MeV, p_02MeV, p_04MeV, p_10MeV, p_30MeV, p_60MeV:
			Proton fluxes >1 MeV, >2 MeV, >4 MeV, >10 MeV, >30 MeV, > 60 MeV
		flag:
			Flag (-1, ..., 6)
		Ap:
			Ap index value
		f107_adj:
			F10.7 radio flux at 1 AU
		PC:
			PC index value
		AL, AU:
			AL and AU index values
		mach_mag:
			Magnetosonic Mach number

		The extended dataset contains the addional columns:

		Lya:
			Solar Lyman-alpha irradiance
		QI_p:
			Proton QI
	"""
	_assert_file_exists(omnie_file)
	# FORMAT(
	#     2I4,I3,I5,2I3,2I4,14F6.1,F9.0,F6.1,F6.0,2F6.1,F6.3,F6.2,
	#     F9.0,F6.1,F6.0,2F6.1,F6.3,2F7.2,F6.1,I3,I4,I6,I5,F10.2,
	#     5F9.2,I3,I4,2F6.1,2I6,F5.1,F9.6,F7.4
	# )
	sw = np.genfromtxt(
		omnie_file,
		skip_header=0,
		delimiter=[
		#   1  2  3  4  5  6  7  8  9 10 11 12 13 14 15 16 17 18 19 20
		#  yy dd hr br i1 i2 n1 n2  B B' tB fB Bx By Bz By Bz sB sB sB
			4, 4, 3, 5, 3, 3, 4, 4, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,
		#  21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40
		#  sB sB Tp np  v fv tv nr  p sT sn sv sf st sr  E bp  M Kp  R
			6, 6, 9, 6, 6, 6, 6, 6, 6, 9, 6, 6, 6, 6, 6, 7, 7, 6, 3, 4,
		#  41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57
		#  Ds AE p1 p2 p4p10p30p60 fl Apf10 PC AL AU Mm La QI
			6, 5,10, 9, 9, 9, 9, 9, 3, 4, 6, 6, 6, 6, 5, 9, 7,
		],
		dtype=(
			"i4,i4,i4,i4,i4,i4,i4,i4,f8,f8,f8,f8,f8,f8,f8,f8,f8,f8,f8,f8,"
			"f8,f8,f8,f8,f8,f8,f8,f8,f8,f8,f8,f8,f8,f8,f8,f8,f8,f8,i4,i4,"
			"i4,i4,f8,f8,f8,f8,f8,f8,i4,i4,f8,f8,i4,i4,f8,f8,f8"
		),
		names=[
			"year", "doy", "hour", "bsrn", "id_imf", "id_sw", "n_imf", "n_plasma",
			"B_mag_avg", "B_mag", "theta_B", "phi_B",
			"B_x", "B_y_GSE", "B_z_GSE", "B_y_GSM", "B_z_GSM",
			"sigma_B_mag_avg", "sigma_B_mag",
			"sigma_B_x_GSE", "sigma_B_y_GSE", "sigma_B_z_GSE",
			"T_p", "n_p", "v_plasma", "phi_v", "theta_v", "n_alpha_n_p", "p_flow",
			"sigma_T", "sigma_n", "sigma_v",
			"sigma_phi_v", "sigma_theta_v", "sigma_na_np",
			"E", "beta_plasma", "mach", "Kp", "R", "Dst", "AE",
			"p_01MeV", "p_02MeV", "p_04MeV", "p_10MeV", "p_30MeV", "p_60MeV",
			"flag", "Ap", "f107_adj", "PC", "AL", "AU", "mach_mag", "Lya", "QI_p",
		]
	)
	sw = sw[sw["year"] != -1]
	ts = pd.to_datetime(
		[
			"{0:04d}.{1:03d} {2:02d}".format(yy, dd, hh)
			for yy, dd, hh in sw[["year", "doy", "hour"]]
		],
		format="%Y.%j %H",
	)
	sw_df = pd.DataFrame(sw, index=ts)
	# Adjust Kp to 0...9
	sw_df["Kp"] = 0.1 * sw_df["Kp"]
	return sw_df


def omnie_hourly(
	year,
	prefix=None,
	ext=None,
	local_path=None,
	url_base=None,
	cache=False,
):
	"""OMNI hourly data for year `year`

	Loads the OMNI hourly data for the given year,
	from the locally cached data.
	Use `local_path` to set a custom location if you
	have the omni data already available.

	Parameters
	----------
	year: int
		Year of the data.
	prefix: str, optional, default 'omni2'
		File prefix for constructing the file name as <prefix>_year.<ext>.
	ext: str, optional, default 'dat'
		File extension for constructing the file name as <prefix>_year.<ext>.
	local_path: str, optional
		Path to the locally stored data yearly files, defaults to the
		data location within the package.
	url_base: str, optional
		URL for the directory that contains the yearly files.
	cache: boolean, optional, default False
		Download files locally if they are not already available.

	Returns
	-------
	sw_df: pandas.DataFrame
		The parsed space weather data (hourly values).

		Raises an ``IOError`` if the file is not available.

	See Also
	--------
	read_omnie
	"""
	prefix = prefix or OMNI_PREFIX
	ext = ext or OMNI_EXT
	local_path = local_path or LOCAL_PATH
	url_base = url_base or OMNI_URL_BASE

	basename = "{0}_{1:04d}.{2}".format(prefix, year, ext)
	omnie_file = os.path.join(local_path, basename)

	# ensure that the file exists
	if not os.path.exists(omnie_file):
		warn("Could not find OMNI2 data {0}.".format(omnie_file))
		if cache:
			cache_omnie(
				year,
				prefix=prefix, ext=ext,
				local_path=local_path, url_base=url_base,
			)
		else:
			warn(
				"Local data files not found, pass `cache=True` "
				"or run `sw.cache_omnie()` to download the file."
			)

	return read_omnie(omnie_file)


1			# -- coding: utf-8 --
2			# Copyright (c) 2022 Stefan Bender
3			#
4			# This module is part of pyspaceweather.
5			# pyspaceweather is free software: you can redistribute it or modify
6			# it under the terms of the GNU General Public License as published
7			# by the Free Software Foundation, version 2.
8			# See accompanying COPYING.GPLv2 file or http://www.gnu.org/licenses/gpl-2.0.html.
9			"""Python interface for OMNI space weather data
10
11			Omni2 [#]_ space weather data interface for python.
12
13			.. [#] https://omniweb.gsfc.nasa.gov/ow.html
14			"""
15			import os
16			from pkg_resources import resource_filename
17			import logging
18			from warnings import warn
19
20			from posixpath import join as urljoin
21
22			import numpy as np
23			import pandas as pd
24
25			from .core import _assert_file_exists, _dl_file
26
27			__all__ = [
28			"cache_omnie",
29			"omnie_hourly",
30			"omnie_mask_missing",
31			"read_omnie",
32			]
33
34			OMNI_URL_BASE = "https://spdf.gsfc.nasa.gov/pub/data/omni/low_res_omni/extended"
35			OMNI_PREFIX, OMNI_EXT = "omni2", "dat"
36			OMNI_SUBDIR = "omni_extended"
37			LOCAL_PATH = resource_filename(__name__, os.path.join("data", OMNI_SUBDIR))
38
39			_OMNI_MISSING = {
40			"year": None,
41			"doy": None,
42			"hour": None,
43			"bsrn": 9999,
44			"id_imf": 99,
45			"id_sw": 99,
46			"n_imf": 999,
47			"n_plasma": 999,
48			"B_mag_avg": 999.9,
49			"B_mag": 999.9,
50			"theta_B": 999.9,
51			"phi_B": 999.9,
52			"B_x": 999.9,
53			"B_y_GSE": 999.9,
54			"B_z_GSE": 999.9,
55			"B_y_GSM": 999.9,
56			"B_z_GSM": 999.9,
57			"sigma_B_mag_avg": 999.9,
58			"sigma_B_mag": 999.9,
59			"sigma_B_x_GSE": 999.9,
60			"sigma_B_y_GSE": 999.9,
61			"sigma_B_z_GSE": 999.9,
62			"T_p": 9999999.0,
63			"n_p": 999.9,
64			"v_plasma": 9999.0,
65			"phi_v": 999.9,
66			"theta_v": 999.9,
67			"n_alpha_n_p": 9.999,
68			"p_flow": 99.99,
69			"sigma_T": 9999999.0,
70			"sigma_n": 999.9,
71			"sigma_v": 9999.0,
72			"sigma_phi_v": 999.9,
73			"sigma_theta_v": 999.9,
74			"sigma_na_np": 9.999,
75			"E": 999.99,
76			"beta_plasma": 999.99,
77			"mach": 999.9,
78			"Kp": 9.9,
79			"R": 999,
80			"Dst": 99999,
81			"AE": 9999,
82			"p_01MeV": 999999.99,
83			"p_02MeV": 99999.99,
84			"p_04MeV": 99999.99,
85			"p_10MeV": 99999.99,
86			"p_30MeV": 99999.99,
87			"p_60MeV": 99999.99,
88			"flag": 0,
89			"Ap": 999,
90			"f107_adj": 999.9,
91			"PC": 999.9,
92			"AL": 99999,
93			"AU": 99999,
94			"mach_mag": 99.9,
95			"Lya": 0.999999,
96			"QI_p": 9.9999
97			}
98
99
100			def cache_omnie(
101			year,
102			prefix=None,
103			ext=None,
104			local_path=None,
105			url_base=None,
106			):
107			"""Download OMNI2 data to local cache
108
109			Downloads the OMNI2 (extended) data file from [#]_ to the local location.
110
111			.. [#] https://spdf.gsfc.nasa.gov/pub/data/omni/low_res_omni/extended/
112
113			Parameters
114			----------
115			year: int
116			Year of the data.
117			prefix: str, optional
118			File prefix for constructing the file name as <prefix>_year.<ext>.
119			Defaults to 'omni2'.
120			ext: str, optional
121			File extension for constructing the file name as <prefix>_year.<ext>.
122			Defaults to 'dat'.
123			local_path: str, optional
124			Path to the locally stored data yearly files, defaults to the
125			data location within the package.
126			url_base: str, optional
127			URL for the directory that contains the yearly files.
128
129			Returns
130			-------
131			Nothing.
132			"""
133			prefix = prefix or OMNI_PREFIX
134			ext = ext or OMNI_EXT
135			local_path = local_path or LOCAL_PATH
136			url_base = url_base or OMNI_URL_BASE
137
138			basename = "{0}_{1:04d}.{2}".format(prefix, year, ext)
139
140			if not os.path.exists(local_path):
141			os.makedirs(local_path)
142
143			omnie_file = os.path.join(local_path, basename)
144			if not os.path.exists(omnie_file):
145			url = urljoin(url_base, basename)
146			logging.info("%s not found, downloading from %s.", omnie_file, url)
147			_dl_file(omnie_file, url)
148
149
150			def omnie_mask_missing(df):
151			"""Mask missing values with NaN
152
153			Marks missing values in the OMNI2 data set by NaN.
154			The missing value indicating numbers are taken from the file format description
155			https://spdf.gsfc.nasa.gov/pub/data/omni/low_res_omni/extended/aareadme_extended
156
157			Parameters
158			----------
159			df: pandas.DataFrame
160			The OMNI2 data set, e.g. from :func:`omnie_hourly()` or :func:`read_omnie()`.
161
162			Returns
163			-------
164			df: pandas.DataFrame
165			The same dataframe with the missing values masked with ``numpy.nan``.
166
167			Notes
168			-----
169			This function returns a copy of the dataframe, and all the integer columns
170			will be converted to float to support NaN.
171			"""
172			res = df.copy()
173			for _c in df.columns:
174			_m = _OMNI_MISSING.get(_c, None)
175			if _m is None:
176			continue
177			_mask = df[_c] != _m
178			res[_c] = df[_c].where(_mask)
179			return res
180
181
182			def read_omnie(omnie_file):
183			"""Read and parse OMNI2 extended files [#]_
184
185			Parses the Omni2 extended data files, available at [#]_,
186			into a :class:`pandas.DataFrame`.
187
188			.. [#] https://omniweb.gsfc.nasa.gov/ow.html
189			.. [#] https://spdf.gsfc.nasa.gov/pub/data/omni/low_res_omni/extended/
190
191			Parameters
192			----------
193			omnie_file: str
194			File to parse, absolute path or relative to the current dir.
195
196			Returns
197			-------
198			sw_df: pandas.DataFrame
199			The parsed OMNI2 space weather data (hourly values).
200			Details in
201			https://spdf.gsfc.nasa.gov/pub/data/omni/low_res_omni/extended/aareadme_extended
202
203			Raises an ``IOError`` if the file is not found.
204
205			The dataframe contains the following columns:
206
207			year:
208			The observation year
209			doy:
210			Day of the year
211			hour:
212			Hour of the day
213			bsrn:
214			Bartels Solar Rotation Number.
215			id_imf:
216			ID for IMF spacecraft
217			id_sw:
218			ID for SW plasma spacecraft
219			n_imf:
220			Number of points in IMF averages
221			n_plasma:
222			Numberof points in plasma averages
223			B_mag_avg:
224			Magnetic field magnitude average B
225			B_mag:
226			Magnetic field vector magnitude
227			theta_B:
228			Latitude angle of the magnetic field vector
229			phi_B:
230			Longitude angle of the magnetic field vector
231			B_x:
232			B_x GSE, GSM
233			B_y_GSE:
234			B_y GSE
235			B_z_GSE:
236			B_z GSE
237			B_y_GSM:
238			B_y GSM
239			B_z_GSM:
240			B_z GSM
241			sigma_B_mag_avg:
242			RMS standard deviation of B_mag_avg
243			sigma_B_mag:
244			RMS standard deviation of B_mag
245			sigma_B_x_GSE:
246			RMS standard deviation of B_x_GSE
247			sigma_B_y_GSE:
248			RMS standard deviation of B_y_GSE
249			sigma_B_z_GSE:
250			RMS standard deviation of B_z_GSE
251			T_p:
252			Proton temperature
253			n_p:
254			Proton density
255			v_plasma:
256			Plasma flow speed
257			phi_v:
258			Plasma flow longitude angle
259			theta_v:
260			Plasma flow latitude angle
261			n_alpha_n_p:
262			Alpha/Proton ratio
263			p_flow:
264			Flow pressure
265			sigma_T:
266			Standard deviation of T_p
267			sigma_n:
268			Standard deviation of n_p
269			sigma_v:
270			Standard deviation of v_plasma
271			sigma_phi_v:
272			Standard deviation of phi_v
273			sigma_theta_v:
274			Standard deviation of theta_v
275			sigma_na_np:
276			Standard deviation of n_alpha_n_p
277			E:
278			Electric field magnitude
279			beta_plasma:
280			Plasma beta
281			mach:
282			Alfvén Mach number
283			Kp:
284			Kp index value
285			R:
286			Sunspot number
287			Dst:
288			Dst index value
289			AE:
290			AE index value
291			p_01MeV, p_02MeV, p_04MeV, p_10MeV, p_30MeV, p_60MeV:
292			Proton fluxes >1 MeV, >2 MeV, >4 MeV, >10 MeV, >30 MeV, > 60 MeV
293			flag:
294			Flag (-1, ..., 6)
295			Ap:
296			Ap index value
297			f107_adj:
298			F10.7 radio flux at 1 AU
299			PC:
300			PC index value
301			AL, AU:
302			AL and AU index values
303			mach_mag:
304			Magnetosonic Mach number
305
306			The extended dataset contains the addional columns:
307
308			Lya:
309			Solar Lyman-alpha irradiance
310			QI_p:
311			Proton QI
312			"""
313			_assert_file_exists(omnie_file)
314			# FORMAT(
315			# 2I4,I3,I5,2I3,2I4,14F6.1,F9.0,F6.1,F6.0,2F6.1,F6.3,F6.2,
316			# F9.0,F6.1,F6.0,2F6.1,F6.3,2F7.2,F6.1,I3,I4,I6,I5,F10.2,
317			# 5F9.2,I3,I4,2F6.1,2I6,F5.1,F9.6,F7.4
318			# )
319			sw = np.genfromtxt(
320			omnie_file,
321			skip_header=0,
322			delimiter=[
323			# 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20
324			# yy dd hr br i1 i2 n1 n2 B B' tB fB Bx By Bz By Bz sB sB sB
325			4, 4, 3, 5, 3, 3, 4, 4, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,
326			# 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40
327			# sB sB Tp np v fv tv nr p sT sn sv sf st sr E bp M Kp R
328			6, 6, 9, 6, 6, 6, 6, 6, 6, 9, 6, 6, 6, 6, 6, 7, 7, 6, 3, 4,
329			# 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57
330			# Ds AE p1 p2 p4p10p30p60 fl Apf10 PC AL AU Mm La QI
331			6, 5,10, 9, 9, 9, 9, 9, 3, 4, 6, 6, 6, 6, 5, 9, 7,
332			],
333			dtype=(
334			"i4,i4,i4,i4,i4,i4,i4,i4,f8,f8,f8,f8,f8,f8,f8,f8,f8,f8,f8,f8,"
335			"f8,f8,f8,f8,f8,f8,f8,f8,f8,f8,f8,f8,f8,f8,f8,f8,f8,f8,i4,i4,"
336			"i4,i4,f8,f8,f8,f8,f8,f8,i4,i4,f8,f8,i4,i4,f8,f8,f8"
337			),
338			names=[
339			"year", "doy", "hour", "bsrn", "id_imf", "id_sw", "n_imf", "n_plasma",
340			"B_mag_avg", "B_mag", "theta_B", "phi_B",
341			"B_x", "B_y_GSE", "B_z_GSE", "B_y_GSM", "B_z_GSM",
342			"sigma_B_mag_avg", "sigma_B_mag",
343			"sigma_B_x_GSE", "sigma_B_y_GSE", "sigma_B_z_GSE",
344			"T_p", "n_p", "v_plasma", "phi_v", "theta_v", "n_alpha_n_p", "p_flow",
345			"sigma_T", "sigma_n", "sigma_v",
346			"sigma_phi_v", "sigma_theta_v", "sigma_na_np",
347			"E", "beta_plasma", "mach", "Kp", "R", "Dst", "AE",
348			"p_01MeV", "p_02MeV", "p_04MeV", "p_10MeV", "p_30MeV", "p_60MeV",
349			"flag", "Ap", "f107_adj", "PC", "AL", "AU", "mach_mag", "Lya", "QI_p",
350			]
351			)
352			sw = sw[sw["year"] != -1]
353			ts = pd.to_datetime(
354			[
355			"{0:04d}.{1:03d} {2:02d}".format(yy, dd, hh)
356			for yy, dd, hh in sw[["year", "doy", "hour"]]
357			],
358			format="%Y.%j %H",
359			)
360			sw_df = pd.DataFrame(sw, index=ts)
361			# Adjust Kp to 0...9
362			sw_df["Kp"] = 0.1 * sw_df["Kp"]
363			return sw_df
364
365
366			def omnie_hourly(
367			year,
368			prefix=None,
369			ext=None,
370			local_path=None,
371			url_base=None,
372			cache=False,
373			):
374			"""OMNI hourly data for year `year`
375
376			Loads the OMNI hourly data for the given year,
377			from the locally cached data.
378			Use `local_path` to set a custom location if you
379			have the omni data already available.
380
381			Parameters
382			----------
383			year: int
384			Year of the data.
385			prefix: str, optional, default 'omni2'
386			File prefix for constructing the file name as <prefix>_year.<ext>.
387			ext: str, optional, default 'dat'
388			File extension for constructing the file name as <prefix>_year.<ext>.
389			local_path: str, optional
390			Path to the locally stored data yearly files, defaults to the
391			data location within the package.
392			url_base: str, optional
393			URL for the directory that contains the yearly files.
394			cache: boolean, optional, default False
395			Download files locally if they are not already available.
396
397			Returns
398			-------
399			sw_df: pandas.DataFrame
400			The parsed space weather data (hourly values).
401
402			Raises an ``IOError`` if the file is not available.
403
404			See Also
405			--------
406			read_omnie
407			"""
408			prefix = prefix or OMNI_PREFIX
409			ext = ext or OMNI_EXT
410			local_path = local_path or LOCAL_PATH
411			url_base = url_base or OMNI_URL_BASE
412
413			basename = "{0}_{1:04d}.{2}".format(prefix, year, ext)
414			omnie_file = os.path.join(local_path, basename)
415
416			# ensure that the file exists
417			if not os.path.exists(omnie_file):
418			warn("Could not find OMNI2 data {0}.".format(omnie_file))
419			if cache:
420			cache_omnie(
421			year,
422			prefix=prefix, ext=ext,
423			local_path=local_path, url_base=url_base,
424			)
425			else:
426			warn(
427			"Local data files not found, pass `cache=True` "
428			"or run `sw.cache_omnie()` to download the file."
429			)
430
431			return read_omnie(omnie_file)
432

st-bender / pyspaceweather

spaceweather.omni.omnie_mask_missing() A last analyzed 2024-04-10 07:57 UTC

Complexity

Size

Duplication

Importance

Duplication Side-by-Side

Filter issues like

spaceweather.omni.omnie_mask_missing() A
last analyzed 2024-04-10 07:57 UTC