spaceweather.omni.omnie_hourly() - Code Metrics - Inspection of "docs: Include OMNI API" - st-bender/pyspaceweather - Measure and Improve Code Quality continuously with Scrutinizer

Passed

Push — master ( a30c46...d0e17e )

by Stefan

created 2022-02-04 20:06 UTC

spaceweather.omni.omnie_hourly() A

↳ Parent: spaceweather.omni

Complexity

Conditions

Size

Total Lines	63
Code Lines	21

Duplication

Lines	63
Ratio	100 %

Importance

Changes

Metric	Value
cc	3
eloc	21
nop	6
dl	63
loc	63
rs	9.376
c	0
b	0
f	0

How to fix Long Method

# 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

import numpy as np
import pandas as pd

from .core import _assert_file_exists, _dl_file

__all__ = [
	"cache_omnie",
	"omnie_hourly",
	"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))


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


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:
			warn("Trying to cache to `{0}'".format(omnie_file))
			_dl_file(omnie_file, os.path.join(url_base, basename))
		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		# Copyright (c) 2022 Stefan Bender
2		#
3		# This module is part of pyspaceweather.
4		# pyspaceweather is free software: you can redistribute it or modify
5		# it under the terms of the GNU General Public License as published
6		# by the Free Software Foundation, version 2.
7		# See accompanying COPYING.GPLv2 file or http://www.gnu.org/licenses/gpl-2.0.html.
8		"""Python interface for OMNI space weather data
9
10		Omni2 [#]_ space weather data interface for python.
11
12		.. [#] https://omniweb.gsfc.nasa.gov/ow.html
13		"""
14		import os
15		from pkg_resources import resource_filename
16		import logging
17		from warnings import warn
18
19		import numpy as np
20		import pandas as pd
21
22		from .core import _assert_file_exists, _dl_file
23
24		__all__ = [
25		"cache_omnie",
26		"omnie_hourly",
27		"read_omnie",
28		]
29
30		OMNI_URL_BASE = "https://spdf.gsfc.nasa.gov/pub/data/omni/low_res_omni/extended"
31		OMNI_PREFIX, OMNI_EXT = "omni2", "dat"
32		OMNI_SUBDIR = "omni_extended"
33		LOCAL_PATH = resource_filename(__name__, os.path.join("data", OMNI_SUBDIR))
34
35
36	View Code Duplication	def cache_omnie(
		0 ignored issues – show Duplication introduced 2022-02-04 20:07 UTC by Report Bug Copy Issue Report This code seems to be duplicated in your project. Loading history...
37		year,
38		prefix=None,
39		ext=None,
40		local_path=None,
41		url_base=None,
42		):
43		"""Download OMNI2 data to local cache
44
45		Downloads the OMNI2 (extended) data file to the local location.
46
47		.. [#] https://spdf.gsfc.nasa.gov/pub/data/omni/low_res_omni/extended/
48
49		Parameters
50		----------
51		year: int
52		Year of the data.
53		prefix: str, optional
54		File prefix for constructing the file name as <prefix>_year.<ext>.
55		Defaults to 'omni2'.
56		ext: str, optional
57		File extension for constructing the file name as <prefix>_year.<ext>.
58		Defaults to 'dat'.
59		local_path: str, optional
60		Path to the locally stored data yearly files, defaults to the
61		data location within the package.
62		url_base: str, optional
63		URL for the directory that contains the yearly files.
64
65		Returns
66		-------
67		Nothing.
68		"""
69		prefix = prefix or OMNI_PREFIX
70		ext = ext or OMNI_EXT
71		local_path = local_path or LOCAL_PATH
72		url_base = url_base or OMNI_URL_BASE
73
74		basename = "{0}_{1:04d}.{2}".format(prefix, year, ext)
75
76		if not os.path.exists(local_path):
77		os.makedirs(local_path)
78
79		omnie_file = os.path.join(local_path, basename)
80		if not os.path.exists(omnie_file):
81		url = os.path.join(url_base, basename)
82		logging.info("%s not found, downloading from %s.", omnie_file, url)
83		_dl_file(omnie_file, url)
84
85
86		def read_omnie(omnie_file):
87		"""Read and parse OMNI2 extended files [#]_
88
89		Parses the Omni2 extended data files, available at [#]_,
90		into a :class:`pandas.DataFrame`.
91
92		.. [#] https://omniweb.gsfc.nasa.gov/ow.html
93		.. [#] https://spdf.gsfc.nasa.gov/pub/data/omni/low_res_omni/extended/
94
95		Parameters
96		----------
97		omnie_file: str
98		File to parse, absolute path or relative to the current dir.
99
100		Returns
101		-------
102		sw_df: pandas.DataFrame
103		The parsed OMNI2 space weather data (hourly values).
104		Details in
105		https://spdf.gsfc.nasa.gov/pub/data/omni/low_res_omni/extended/aareadme_extended
106
107		Raises an ``IOError`` if the file is not found.
108
109		The dataframe contains the following columns:
110
111		year:
112		The observation year
113		doy:
114		Day of the year
115		hour:
116		Hour of the day
117		bsrn:
118		Bartels Solar Rotation Number.
119		id_imf:
120		ID for IMF spacecraft
121		id_sw:
122		ID for SW plasma spacecraft
123		n_imf:
124		Number of points in IMF averages
125		n_plasma:
126		Numberof points in plasma averages
127		B_mag_avg:
128		Magnetic field magnitude average B
129		B_mag:
130		Magnetic field vector magnitude
131		theta_B:
132		Latitude angle of the magnetic field vector
133		phi_B:
134		Longitude angle of the magnetic field vector
135		B_x:
136		B_x GSE, GSM
137		B_y_GSE:
138		B_y GSE
139		B_z_GSE:
140		B_z GSE
141		B_y_GSM:
142		B_y GSM
143		B_z_GSM:
144		B_z GSM
145		sigma_B_mag_avg:
146		RMS standard deviation of B_mag_avg
147		sigma_B_mag:
148		RMS standard deviation of B_mag
149		sigma_B_x_GSE:
150		RMS standard deviation of B_x_GSE
151		sigma_B_y_GSE:
152		RMS standard deviation of B_y_GSE
153		sigma_B_z_GSE:
154		RMS standard deviation of B_z_GSE
155		T_p:
156		Proton temperature
157		n_p:
158		Proton density
159		v_plasma:
160		Plasma flow speed
161		phi_v:
162		Plasma flow longitude angle
163		theta_v:
164		Plasma flow latitude angle
165		n_alpha_n_p:
166		Alpha/Proton ratio
167		p_flow:
168		Flow pressure
169		sigma_T:
170		Standard deviation of T_p
171		sigma_n:
172		Standard deviation of n_p
173		sigma_v:
174		Standard deviation of v_plasma
175		sigma_phi_v:
176		Standard deviation of phi_v
177		sigma_theta_v:
178		Standard deviation of theta_v
179		sigma_na_np:
180		Standard deviation of n_alpha_n_p
181		E:
182		Electric field magnitude
183		beta_plasma:
184		Plasma beta
185		mach:
186		Alfvén Mach number
187		Kp:
188		Kp index value
189		R:
190		Sunspot number
191		Dst:
192		Dst index value
193		AE:
194		AE index value
195		p_01MeV, p_02MeV, p_04MeV, p_10MeV, p_30MeV, p_60MeV:
196		Proton fluxes >1 MeV, >2 MeV, >4 MeV, >10 MeV, >30 MeV, > 60 MeV
197		flag:
198		Flag (-1, ..., 6)
199		Ap:
200		Ap index value
201		f107_adj:
202		F10.7 radio flux at 1 AU
203		PC:
204		PC index value
205		AL, AU:
206		AL and AU index values
207		mach_mag:
208		Magnetosonic Mach number
209
210		The extended dataset contains the addional columns:
211
212		Lya:
213		Solar Lyman-alpha irradiance
214		QI_p:
215		Proton QI
216		"""
217		_assert_file_exists(omnie_file)
218		# FORMAT(
219		# 2I4,I3,I5,2I3,2I4,14F6.1,F9.0,F6.1,F6.0,2F6.1,F6.3,F6.2,
220		# F9.0,F6.1,F6.0,2F6.1,F6.3,2F7.2,F6.1,I3,I4,I6,I5,F10.2,
221		# 5F9.2,I3,I4,2F6.1,2I6,F5.1,F9.6,F7.4
222		# )
223		sw = np.genfromtxt(
224		omnie_file,
225		skip_header=0,
226		delimiter=[
227		# 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20
228		# yy dd hr br i1 i2 n1 n2 B B' tB fB Bx By Bz By Bz sB sB sB
229		4, 4, 3, 5, 3, 3, 4, 4, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,
230		# 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40
231		# sB sB Tp np v fv tv nr p sT sn sv sf st sr E bp M Kp R
232		6, 6, 9, 6, 6, 6, 6, 6, 6, 9, 6, 6, 6, 6, 6, 7, 7, 6, 3, 4,
233		# 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57
234		# Ds AE p1 p2 p4p10p30p60 fl Apf10 PC AL AU Mm La QI
235		6, 5,10, 9, 9, 9, 9, 9, 3, 4, 6, 6, 6, 6, 5, 9, 7,
236		],
237		dtype=(
238		"i4,i4,i4,i4,i4,i4,i4,i4,f8,f8,f8,f8,f8,f8,f8,f8,f8,f8,f8,f8,"
239		"f8,f8,f8,f8,f8,f8,f8,f8,f8,f8,f8,f8,f8,f8,f8,f8,f8,f8,i4,i4,"
240		"i4,i4,f8,f8,f8,f8,f8,f8,i4,i4,f8,f8,i4,i4,f8,f8,f8"
241		),
242		names=[
243		"year", "doy", "hour", "bsrn", "id_imf", "id_sw", "n_imf", "n_plasma",
244		"B_mag_avg", "B_mag", "theta_B", "phi_B",
245		"B_x", "B_y_GSE", "B_z_GSE", "B_y_GSM", "B_z_GSM",
246		"sigma_B_mag_avg", "sigma_B_mag",
247		"sigma_B_x_GSE", "sigma_B_y_GSE", "sigma_B_z_GSE",
248		"T_p", "n_p", "v_plasma", "phi_v", "theta_v", "n_alpha_n_p", "p_flow",
249		"sigma_T", "sigma_n", "sigma_v",
250		"sigma_phi_v", "sigma_theta_v", "sigma_na_np",
251		"E", "beta_plasma", "mach", "Kp", "R", "Dst", "AE",
252		"p_01MeV", "p_02MeV", "p_04MeV", "p_10MeV", "p_30MeV", "p_60MeV",
253		"flag", "Ap", "f107_adj", "PC", "AL", "AU", "mach_mag", "Lya", "QI_p",
254		]
255		)
256		sw = sw[sw["year"] != -1]
257		ts = pd.to_datetime(
258		[
259		"{0:04d}.{1:03d} {2:02d}".format(yy, dd, hh)
260		for yy, dd, hh in sw[["year", "doy", "hour"]]
261		],
262		format="%Y.%j %H",
263		)
264		sw_df = pd.DataFrame(sw, index=ts)
265		# Adjust Kp to 0...9
266		sw_df["Kp"] = 0.1 * sw_df["Kp"]
267		return sw_df
268
269
270	View Code Duplication	def omnie_hourly(
		0 ignored issues – show Duplication introduced 2022-02-04 20:07 UTC by Report Bug Copy Issue Report This code seems to be duplicated in your project. Loading history...
271		year,
272		prefix=None,
273		ext=None,
274		local_path=None,
275		url_base=None,
276		cache=False,
277		):
278		"""OMNI hourly data for year `year`
279
280		Loads the OMNI hourly data for the given year,
281		from the locally cached data.
282		Use `local_path` to set a custom location if you
283		have the omni data already available.
284
285		Parameters:
286		-----------
287		year: int
288		Year of the data.
289		prefix: str, optional, default 'omni2'
290		File prefix for constructing the file name as <prefix>_year.<ext>.
291		ext: str, optional, default 'dat'
292		File extension for constructing the file name as <prefix>_year.<ext>.
293		local_path: str, optional
294		Path to the locally stored data yearly files, defaults to the
295		data location within the package.
296		url_base: str, optional
297		URL for the directory that contains the yearly files.
298		cache: boolean, optional, default False
299		Download files locally if they are not already available.
300
301		Returns
302		-------
303		sw_df: pandas.DataFrame
304		The parsed space weather data (hourly values).
305
306		Raises an ``IOError`` if the file is not available.
307
308		See Also
309		--------
310		read_omnie
311		"""
312		prefix = prefix or OMNI_PREFIX
313		ext = ext or OMNI_EXT
314		local_path = local_path or LOCAL_PATH
315		url_base = url_base or OMNI_URL_BASE
316
317		basename = "{0}_{1:04d}.{2}".format(prefix, year, ext)
318		omnie_file = os.path.join(local_path, basename)
319
320		# ensure that the file exists
321		if not os.path.exists(omnie_file):
322		warn("Could not find OMNI2 data {0}.".format(omnie_file))
323		if cache:
324		warn("Trying to cache to `{0}'".format(omnie_file))
325		_dl_file(omnie_file, os.path.join(url_base, basename))
326		else:
327		warn(
328		"Local data files not found, pass `cache=True` "
329		"or run `sw.cache_omnie()` to download the file."
330		)
331
332		return read_omnie(omnie_file)
333

st-bender / pyspaceweather

Push — master ( a30c46...d0e17e )

spaceweather.omni.omnie_hourly() A

Complexity

Size

Duplication

Importance

How to fix Long Method

Long Method

Duplication Side-by-Side

Filter issues like