spaceweather.omni.omnie_mask_missing() - Code Metrics - Inspection of "tests: Add OMNI2 missing value test" - st-bender/pyspaceweather - Measure and Improve Code Quality continuously with Scrutinizer

Passed

Push — master ( 190a35...75a1c3 )

by Stefan

created 2022-02-16 15:12 UTC

spaceweather.omni.omnie_mask_missing() A

↳ 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

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 = os.path.join(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 ``omnie_hourly()`` or ``read_omnie()``.

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

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

st-bender / pyspaceweather

Push — master ( 190a35...75a1c3 )

spaceweather.omni.omnie_mask_missing() A

Complexity

Size

Duplication

Importance

Duplication Side-by-Side

Filter issues like