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

spaceweather.omni.cache_omnie() A
last analyzed 2025-08-15 09:40 UTC

↳ Parent: spaceweather.omni

Complexity

Conditions

Size

Total Lines	51
Code Lines	19

Duplication

Lines	0
Ratio	0 %

Importance

Changes

Metric	Value
cc	3
eloc	19
nop	5
dl	0
loc	51
rs	9.45
c	0
b	0
f	0

How to fix Long Method

# -*- 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
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, _resource_filepath

__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_filepath(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 _doc_param(**sub):
	def dec(obj):
		obj.__doc__ = obj.__doc__.format(**sub)
		return obj
	return dec


@_doc_param(prefix=OMNI_PREFIX, ext=OMNI_EXT)
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: `None` or str, optional, default `None`
		File prefix for constructing the file name as <prefix>_year.<ext>.
		`None` defaults to '{prefix}'.
	ext: `None` or str, optional, default `None`
		File extension for constructing the file name as <prefix>_year.<ext>.
		`None` defaults to '{ext}'.
	local_path: `None` or str, optional, default `None`
		Path to the locally stored data yearly files, defaults to the
		data location within the package.
		`None` uses the package's default file location.
	url_base: `None` or str, optional, default `None`
		URL for the directory that contains the yearly files.
		`None` uses the default base url.

	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 index is returned timezone-naive but contains UTC timestamps.
		To convert to a timezone-aware index, use
		:meth:`pandas.DataFrame.tz_localize()`: ``sw_df.tz_localize("utc")``.

		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


@_doc_param(prefix=OMNI_PREFIX, ext=OMNI_EXT)
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: `None` or str, optional, default `None`
		File prefix for constructing the file name as <prefix>_year.<ext>.
		`None` defaults to '{prefix}'.
	ext: `None` or str, optional, default `None`
		File extension for constructing the file name as <prefix>_year.<ext>.
		`None` defaults to '{ext}'.
	local_path: `None` or str, optional, default `None`
		Path to the locally stored data yearly files, defaults to the
		data location within the package.
		`None` uses the package's default file location.
	url_base: `None` or str, optional, default `None`
		URL for the directory that contains the yearly files.
		`None` uses the default base url.
	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.
		The index is returned timezone-naive but contains UTC timestamps.
		To convert to a timezone-aware index, use
		:meth:`pandas.DataFrame.tz_localize()`: ``sw_df.tz_localize("utc")``.

	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			import logging
17			from warnings import warn
18
19			from posixpath import join as urljoin
20
21			import numpy as np
22			import pandas as pd
23
24			from .core import _assert_file_exists, _dl_file, _resource_filepath
25
26			__all__ = [
27			"cache_omnie",
28			"omnie_hourly",
29			"omnie_mask_missing",
30			"read_omnie",
31			]
32
33			OMNI_URL_BASE = "https://spdf.gsfc.nasa.gov/pub/data/omni/low_res_omni/extended"
34			OMNI_PREFIX, OMNI_EXT = "omni2", "dat"
35			OMNI_SUBDIR = "omni_extended"
36			LOCAL_PATH = _resource_filepath(OMNI_SUBDIR)
37
38			_OMNI_MISSING = {
39			"year": None,
40			"doy": None,
41			"hour": None,
42			"bsrn": 9999,
43			"id_imf": 99,
44			"id_sw": 99,
45			"n_imf": 999,
46			"n_plasma": 999,
47			"B_mag_avg": 999.9,
48			"B_mag": 999.9,
49			"theta_B": 999.9,
50			"phi_B": 999.9,
51			"B_x": 999.9,
52			"B_y_GSE": 999.9,
53			"B_z_GSE": 999.9,
54			"B_y_GSM": 999.9,
55			"B_z_GSM": 999.9,
56			"sigma_B_mag_avg": 999.9,
57			"sigma_B_mag": 999.9,
58			"sigma_B_x_GSE": 999.9,
59			"sigma_B_y_GSE": 999.9,
60			"sigma_B_z_GSE": 999.9,
61			"T_p": 9999999.0,
62			"n_p": 999.9,
63			"v_plasma": 9999.0,
64			"phi_v": 999.9,
65			"theta_v": 999.9,
66			"n_alpha_n_p": 9.999,
67			"p_flow": 99.99,
68			"sigma_T": 9999999.0,
69			"sigma_n": 999.9,
70			"sigma_v": 9999.0,
71			"sigma_phi_v": 999.9,
72			"sigma_theta_v": 999.9,
73			"sigma_na_np": 9.999,
74			"E": 999.99,
75			"beta_plasma": 999.99,
76			"mach": 999.9,
77			"Kp": 9.9,
78			"R": 999,
79			"Dst": 99999,
80			"AE": 9999,
81			"p_01MeV": 999999.99,
82			"p_02MeV": 99999.99,
83			"p_04MeV": 99999.99,
84			"p_10MeV": 99999.99,
85			"p_30MeV": 99999.99,
86			"p_60MeV": 99999.99,
87			"flag": 0,
88			"Ap": 999,
89			"f107_adj": 999.9,
90			"PC": 999.9,
91			"AL": 99999,
92			"AU": 99999,
93			"mach_mag": 99.9,
94			"Lya": 0.999999,
95			"QI_p": 9.9999
96			}
97
98
99			def _doc_param(**sub):
100			def dec(obj):
101			obj.__doc__ = obj.__doc__.format(**sub)
102			return obj
103			return dec
104
105
106			@_doc_param(prefix=OMNI_PREFIX, ext=OMNI_EXT)
107			def cache_omnie(
108			year,
109			prefix=None,
110			ext=None,
111			local_path=None,
112			url_base=None,
113			):
114			"""Download OMNI2 data to local cache
115
116			Downloads the OMNI2 (extended) data file from [#]_ to the local location.
117
118			.. [#] https://spdf.gsfc.nasa.gov/pub/data/omni/low_res_omni/extended/
119
120			Parameters
121			----------
122			year: int
123			Year of the data.
124			prefix: `None` or str, optional, default `None`
125			File prefix for constructing the file name as <prefix>_year.<ext>.
126			`None` defaults to '{prefix}'.
127			ext: `None` or str, optional, default `None`
128			File extension for constructing the file name as <prefix>_year.<ext>.
129			`None` defaults to '{ext}'.
130			local_path: `None` or str, optional, default `None`
131			Path to the locally stored data yearly files, defaults to the
132			data location within the package.
133			`None` uses the package's default file location.
134			url_base: `None` or str, optional, default `None`
135			URL for the directory that contains the yearly files.
136			`None` uses the default base url.
137
138			Returns
139			-------
140			Nothing.
141			"""
142			prefix = prefix or OMNI_PREFIX
143			ext = ext or OMNI_EXT
144			local_path = local_path or LOCAL_PATH
145			url_base = url_base or OMNI_URL_BASE
146
147			basename = "{0}_{1:04d}.{2}".format(prefix, year, ext)
148
149			if not os.path.exists(local_path):
150			os.makedirs(local_path)
151
152			omnie_file = os.path.join(local_path, basename)
153			if not os.path.exists(omnie_file):
154			url = urljoin(url_base, basename)
155			logging.info("%s not found, downloading from %s.", omnie_file, url)
156			_dl_file(omnie_file, url)
157
158
159			def omnie_mask_missing(df):
160			"""Mask missing values with NaN
161
162			Marks missing values in the OMNI2 data set by NaN.
163			The missing value indicating numbers are taken from the file format description
164			https://spdf.gsfc.nasa.gov/pub/data/omni/low_res_omni/extended/aareadme_extended
165
166			Parameters
167			----------
168			df: pandas.DataFrame
169			The OMNI2 data set, e.g. from :func:`omnie_hourly()` or :func:`read_omnie()`.
170
171			Returns
172			-------
173			df: pandas.DataFrame
174			The same dataframe with the missing values masked with ``numpy.nan``.
175
176			Notes
177			-----
178			This function returns a copy of the dataframe, and all the integer columns
179			will be converted to float to support NaN.
180			"""
181			res = df.copy()
182			for _c in df.columns:
183			_m = _OMNI_MISSING.get(_c, None)
184			if _m is None:
185			continue
186			_mask = df[_c] != _m
187			res[_c] = df[_c].where(_mask)
188			return res
189
190
191			def read_omnie(omnie_file):
192			"""Read and parse OMNI2 extended files [#]_
193
194			Parses the Omni2 extended data files, available at [#]_,
195			into a :class:`pandas.DataFrame`.
196
197			.. [#] https://omniweb.gsfc.nasa.gov/ow.html
198			.. [#] https://spdf.gsfc.nasa.gov/pub/data/omni/low_res_omni/extended/
199
200			Parameters
201			----------
202			omnie_file: str
203			File to parse, absolute path or relative to the current dir.
204
205			Returns
206			-------
207			sw_df: pandas.DataFrame
208			The parsed OMNI2 space weather data (hourly values).
209			Details in
210			https://spdf.gsfc.nasa.gov/pub/data/omni/low_res_omni/extended/aareadme_extended
211
212			Raises an ``IOError`` if the file is not found.
213			The index is returned timezone-naive but contains UTC timestamps.
214			To convert to a timezone-aware index, use
215			:meth:`pandas.DataFrame.tz_localize()`: ``sw_df.tz_localize("utc")``.
216
217			The dataframe contains the following columns:
218
219			year:
220			The observation year
221			doy:
222			Day of the year
223			hour:
224			Hour of the day
225			bsrn:
226			Bartels Solar Rotation Number.
227			id_imf:
228			ID for IMF spacecraft
229			id_sw:
230			ID for SW plasma spacecraft
231			n_imf:
232			Number of points in IMF averages
233			n_plasma:
234			Numberof points in plasma averages
235			B_mag_avg:
236			Magnetic field magnitude average B
237			B_mag:
238			Magnetic field vector magnitude
239			theta_B:
240			Latitude angle of the magnetic field vector
241			phi_B:
242			Longitude angle of the magnetic field vector
243			B_x:
244			B_x GSE, GSM
245			B_y_GSE:
246			B_y GSE
247			B_z_GSE:
248			B_z GSE
249			B_y_GSM:
250			B_y GSM
251			B_z_GSM:
252			B_z GSM
253			sigma_B_mag_avg:
254			RMS standard deviation of B_mag_avg
255			sigma_B_mag:
256			RMS standard deviation of B_mag
257			sigma_B_x_GSE:
258			RMS standard deviation of B_x_GSE
259			sigma_B_y_GSE:
260			RMS standard deviation of B_y_GSE
261			sigma_B_z_GSE:
262			RMS standard deviation of B_z_GSE
263			T_p:
264			Proton temperature
265			n_p:
266			Proton density
267			v_plasma:
268			Plasma flow speed
269			phi_v:
270			Plasma flow longitude angle
271			theta_v:
272			Plasma flow latitude angle
273			n_alpha_n_p:
274			Alpha/Proton ratio
275			p_flow:
276			Flow pressure
277			sigma_T:
278			Standard deviation of T_p
279			sigma_n:
280			Standard deviation of n_p
281			sigma_v:
282			Standard deviation of v_plasma
283			sigma_phi_v:
284			Standard deviation of phi_v
285			sigma_theta_v:
286			Standard deviation of theta_v
287			sigma_na_np:
288			Standard deviation of n_alpha_n_p
289			E:
290			Electric field magnitude
291			beta_plasma:
292			Plasma beta
293			mach:
294			Alfvén Mach number
295			Kp:
296			Kp index value
297			R:
298			Sunspot number
299			Dst:
300			Dst index value
301			AE:
302			AE index value
303			p_01MeV, p_02MeV, p_04MeV, p_10MeV, p_30MeV, p_60MeV:
304			Proton fluxes >1 MeV, >2 MeV, >4 MeV, >10 MeV, >30 MeV, > 60 MeV
305			flag:
306			Flag (-1, ..., 6)
307			Ap:
308			Ap index value
309			f107_adj:
310			F10.7 radio flux at 1 AU
311			PC:
312			PC index value
313			AL, AU:
314			AL and AU index values
315			mach_mag:
316			Magnetosonic Mach number
317
318			The extended dataset contains the addional columns:
319
320			Lya:
321			Solar Lyman-alpha irradiance
322			QI_p:
323			Proton QI
324			"""
325			_assert_file_exists(omnie_file)
326			# FORMAT(
327			# 2I4,I3,I5,2I3,2I4,14F6.1,F9.0,F6.1,F6.0,2F6.1,F6.3,F6.2,
328			# F9.0,F6.1,F6.0,2F6.1,F6.3,2F7.2,F6.1,I3,I4,I6,I5,F10.2,
329			# 5F9.2,I3,I4,2F6.1,2I6,F5.1,F9.6,F7.4
330			# )
331			sw = np.genfromtxt(
332			omnie_file,
333			skip_header=0,
334			delimiter=[
335			# 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20
336			# yy dd hr br i1 i2 n1 n2 B B' tB fB Bx By Bz By Bz sB sB sB
337			4, 4, 3, 5, 3, 3, 4, 4, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,
338			# 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40
339			# sB sB Tp np v fv tv nr p sT sn sv sf st sr E bp M Kp R
340			6, 6, 9, 6, 6, 6, 6, 6, 6, 9, 6, 6, 6, 6, 6, 7, 7, 6, 3, 4,
341			# 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57
342			# Ds AE p1 p2 p4p10p30p60 fl Apf10 PC AL AU Mm La QI
343			6, 5,10, 9, 9, 9, 9, 9, 3, 4, 6, 6, 6, 6, 5, 9, 7,
344			],
345			dtype=(
346			"i4,i4,i4,i4,i4,i4,i4,i4,f8,f8,f8,f8,f8,f8,f8,f8,f8,f8,f8,f8,"
347			"f8,f8,f8,f8,f8,f8,f8,f8,f8,f8,f8,f8,f8,f8,f8,f8,f8,f8,i4,i4,"
348			"i4,i4,f8,f8,f8,f8,f8,f8,i4,i4,f8,f8,i4,i4,f8,f8,f8"
349			),
350			names=[
351			"year", "doy", "hour", "bsrn", "id_imf", "id_sw", "n_imf", "n_plasma",
352			"B_mag_avg", "B_mag", "theta_B", "phi_B",
353			"B_x", "B_y_GSE", "B_z_GSE", "B_y_GSM", "B_z_GSM",
354			"sigma_B_mag_avg", "sigma_B_mag",
355			"sigma_B_x_GSE", "sigma_B_y_GSE", "sigma_B_z_GSE",
356			"T_p", "n_p", "v_plasma", "phi_v", "theta_v", "n_alpha_n_p", "p_flow",
357			"sigma_T", "sigma_n", "sigma_v",
358			"sigma_phi_v", "sigma_theta_v", "sigma_na_np",
359			"E", "beta_plasma", "mach", "Kp", "R", "Dst", "AE",
360			"p_01MeV", "p_02MeV", "p_04MeV", "p_10MeV", "p_30MeV", "p_60MeV",
361			"flag", "Ap", "f107_adj", "PC", "AL", "AU", "mach_mag", "Lya", "QI_p",
362			]
363			)
364			sw = sw[sw["year"] != -1]
365			ts = pd.to_datetime(
366			[
367			"{0:04d}.{1:03d} {2:02d}".format(yy, dd, hh)
368			for yy, dd, hh in sw[["year", "doy", "hour"]]
369			],
370			format="%Y.%j %H",
371			)
372			sw_df = pd.DataFrame(sw, index=ts)
373			# Adjust Kp to 0...9
374			sw_df["Kp"] = 0.1 * sw_df["Kp"]
375			return sw_df
376
377
378			@_doc_param(prefix=OMNI_PREFIX, ext=OMNI_EXT)
379			def omnie_hourly(
380			year,
381			prefix=None,
382			ext=None,
383			local_path=None,
384			url_base=None,
385			cache=False,
386			):
387			"""OMNI hourly data for year `year`
388
389			Loads the OMNI hourly data for the given year,
390			from the locally cached data.
391			Use `local_path` to set a custom location if you
392			have the omni data already available.
393
394			Parameters
395			----------
396			year: int
397			Year of the data.
398			prefix: `None` or str, optional, default `None`
399			File prefix for constructing the file name as <prefix>_year.<ext>.
400			`None` defaults to '{prefix}'.
401			ext: `None` or str, optional, default `None`
402			File extension for constructing the file name as <prefix>_year.<ext>.
403			`None` defaults to '{ext}'.
404			local_path: `None` or str, optional, default `None`
405			Path to the locally stored data yearly files, defaults to the
406			data location within the package.
407			`None` uses the package's default file location.
408			url_base: `None` or str, optional, default `None`
409			URL for the directory that contains the yearly files.
410			`None` uses the default base url.
411			cache: boolean, optional, default False
412			Download files locally if they are not already available.
413
414			Returns
415			-------
416			sw_df: pandas.DataFrame
417			The parsed space weather data (hourly values).
418
419			Raises an ``IOError`` if the file is not available.
420			The index is returned timezone-naive but contains UTC timestamps.
421			To convert to a timezone-aware index, use
422			:meth:`pandas.DataFrame.tz_localize()`: ``sw_df.tz_localize("utc")``.
423
424			See Also
425			--------
426			read_omnie
427			"""
428			prefix = prefix or OMNI_PREFIX
429			ext = ext or OMNI_EXT
430			local_path = local_path or LOCAL_PATH
431			url_base = url_base or OMNI_URL_BASE
432
433			basename = "{0}_{1:04d}.{2}".format(prefix, year, ext)
434			omnie_file = os.path.join(local_path, basename)
435
436			# ensure that the file exists
437			if not os.path.exists(omnie_file):
438			warn("Could not find OMNI2 data {0}.".format(omnie_file))
439			if cache:
440			cache_omnie(
441			year,
442			prefix=prefix, ext=ext,
443			local_path=local_path, url_base=url_base,
444			)
445			else:
446			warn(
447			"Local data files not found, pass `cache=True` "
448			"or run `sw.cache_omnie()` to download the file."
449			)
450
451			return read_omnie(omnie_file)
452

st-bender / pyspaceweather

spaceweather.omni.cache_omnie() A last analyzed 2025-08-15 09:40 UTC

Complexity

Size

Duplication

Importance

How to fix Long Method

Long Method

Duplication Side-by-Side

Filter issues like

spaceweather.omni.cache_omnie() A
last analyzed 2025-08-15 09:40 UTC