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

spaceweather.celestrak.update_data() A
last analyzed 2025-08-15 09:40 UTC

↳ Parent: spaceweather.celestrak

Complexity

Conditions

Size

Total Lines	63
Code Lines	20

Duplication

Lines	0
Ratio	0 %

Importance

Changes

Metric	Value
cc	3
eloc	20
nop	5
dl	0
loc	63
rs	9.4
c	0
b	0
f	0

How to fix Long Method

# Copyright (c) 2020--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 space weather indices

Celestrak space weather indices file parser for python [#]_.

.. [#] https://celestrak.com/SpaceData/
"""
import os
import logging
from warnings import warn

import numpy as np
import pandas as pd

from .core import _assert_file_exists, _dl_file, _resource_filepath

__all__ = [
	"sw_daily", "ap_kp_3h", "read_sw",
	"get_file_age", "update_data",
	"SW_PATH_ALL", "SW_PATH_5Y",
]

DL_URL_ALL = "https://celestrak.com/SpaceData/SW-All.txt"
DL_URL_5Y = "https://celestrak.com/SpaceData/SW-Last5Years.txt"
SW_FILE_ALL = os.path.basename(DL_URL_ALL)
SW_FILE_5Y = os.path.basename(DL_URL_5Y)
SW_PATH_ALL = _resource_filepath(SW_FILE_ALL)
SW_PATH_5Y = _resource_filepath(SW_FILE_5Y)


def get_file_age(swpath, relative=True):
	"""Age of the downloaded data file

	Retrieves the last update time of the given file or full path.

	Parameters
	----------
	swpath: str
		Filename to check, absolute path or relative to the current dir.
	relative: bool, optional, default True
		Return the file's age (True) or the last update time (False).

	Returns
	-------
	upd: pandas.Timestamp or pandas.Timedelta
		The last updated time or the file age, depending on the setting
		of `relative` above.
		Raises ``IOError`` if the file is not found.
	"""
	_assert_file_exists(swpath)
	with open(swpath) as fp:
		for line in fp:
			if line.startswith("UPDATED"):
				# closes the file automatically
				break
	upd = pd.to_datetime(line.lstrip("UPDATED"), utc=True)

	if relative:
		return pd.Timestamp.utcnow() - upd
	return upd


def update_data(
	min_age="3h",
	swpath_all=None, swpath_5y=None,
	url_all=None, url_5y=None,
):
	"""Update the local space weather index data

	Updates the local space weather index data from the website [#]_,
	given that the 5-year file is older
	than `min_age`, or the combined (large) file is older than four years.
	If the data is missing for some reason, a download will be attempted nonetheless.

	All arguments are optional and changing them from the defaults should not
	be required neither should it be necessary nor is it recommended.

	.. [#] https://celestrak.com/SpaceData/

	Parameters
	----------
	min_age: str, optional, default "3h"
		The time after which a new download will be attempted.
		The online data is updated every 3 hours, thus setting this value to
		a shorter time is not needed and not recommended.
	swpath_all: `None` or str, optional, default `None`
		Filename for the large combined index file including the
		historic data, absolute path or relative to the current dir.
		`None` uses the package's default file location.
	swpath_5y: `None` or str, optional, default `None`
		Filename for the 5-year index file, absolute path or relative to the current dir.
		`None` uses the package's default file location.
	url_all: `None` or str, optional, default `None`
		The url of the "historic" data file.
		`None` uses the default url.
	url_5y: `None` or str, optional, default `None`
		The url of the data file of containing the indices of the last 5 years.
		`None` uses the default url.

	Returns
	-------
	Nothing.
	"""
	def _update_file(swpath, url, min_age):
		if not os.path.exists(swpath):
			logging.info("{0} not found, downloading.".format(swpath))
			_dl_file(swpath, url)
			return
		if get_file_age(swpath) < pd.Timedelta(min_age):
			logging.info("not updating '{0}'.".format(swpath))
			return
		logging.info("updating '{0}'.".format(swpath))
		_dl_file(swpath, url)

	swpath_all = swpath_all or SW_PATH_ALL
	swpath_5y = swpath_5y or SW_PATH_5Y
	url_all = url_all or DL_URL_ALL
	url_5y = url_5y or DL_URL_5Y

	# Update the large file after four years
	# to have some overlap with the 5-year data
	# 1460 = 4 * 365
	_update_file(swpath_all, url_all, "1460days")
	# Don't re-download before `min_age` has passed (3h)
	_update_file(swpath_5y, url_5y, min_age)


def read_sw(swpath):
	"""Read and parse space weather index data file

	Reads the given file and parses it according to the space weather data format.

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

	Returns
	-------
	sw_df: pandas.DataFrame
		The parsed space weather data (daily values).
		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", "month", "day":
			The observation date
		"bsrn":
			Bartels Solar Rotation Number.
			A sequence of 27-day intervals counted continuously from 1832 Feb 8.
		"rotd":
			Number of Day within the Bartels 27-day cycle (01-27).
		"Kp0", "Kp3", "Kp6", "Kp9", "Kp12", "Kp15", "Kp18", "Kp21":
			Planetary 3-hour Range Index (Kp) for 0000-0300, 0300-0600,
			0600-0900, 0900-1200, 1200-1500, 1500-1800, 1800-2100, 2100-2400 UT
		"Kpsum": Sum of the 8 Kp indices for the day.
			Expressed to the nearest third of a unit.
		"Ap0", "Ap3", "Ap6", "Ap9", "Ap12", "Ap15", "Ap18", "Ap21":
			Planetary Equivalent Amplitude (Ap) for 0000-0300, 0300-0600,
			0600-0900, 0900-1200, 1200-1500, 1500-1800, 1800-2100, 2100-2400 UT
		"Apavg":
			Arithmetic average of the 8 Ap indices for the day.
		"Cp":
			Cp or Planetary Daily Character Figure. A qualitative estimate of
			overall level of magnetic activity for the day determined from the sum
			of the 8 Ap indices. Cp ranges, in steps of one-tenth, from 0 (quiet)
			to 2.5 (highly disturbed). "C9":
		"isn":
			International Sunspot Number.
			Records contain the Zurich number through 1980 Dec 31 and the
			International Brussels number thereafter.
		"f107_adj":
			10.7-cm Solar Radio Flux (F10.7) Adjusted to 1 AU.
			Measured at Ottawa at 1700 UT daily from 1947 Feb 14 until
			1991 May 31 and measured at Penticton at 2000 UT from 1991 Jun 01 on.
			Expressed in units of 10-22 W/m2/Hz.
		"Q":
			Flux Qualifier.
			0 indicates flux required no adjustment;
			1 indicates flux required adjustment for burst in progress at time of measurement;
			2 indicates a flux approximated by either interpolation or extrapolation;
			3 indicates no observation; and
			4 indicates CSSI interpolation of missing data.
		"f107_81ctr_adj":
			Centered 81-day arithmetic average of F10.7 (adjusted).
		"f107_81lst_adj":
			Last 81-day arithmetic average of F10.7 (adjusted).
		"f107_obs":
			Observed (unadjusted) value of F10.7.
		"f107_81ctr_obs":
			Centered 81-day arithmetic average of F10.7 (observed).
		"f107_81lst_obs":
			Last 81-day arithmetic average of F10.7 (observed).
	"""
	_assert_file_exists(swpath)
	sw = np.genfromtxt(
		swpath,
		skip_header=3,
		delimiter=[
		#  yy mm dd br rd kp kp kp kp kp kp kp kp Kp
			4, 3, 3, 5, 3, 3, 3, 3, 3, 3, 3, 3, 3, 4,
		#  ap ap ap ap ap ap ap ap Ap cp c9 is f1  q
			4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 2, 4, 6, 2,
		#  f2 f3 f4 f5 f6
			6, 6, 6, 6, 6],
		dtype=(
			"i4,i4,i4,i4,i4,i4,i4,i4,i4,i4,i4,i4,i4,i4,"
			"i4,i4,i4,i4,i4,i4,i4,i4,i4,f8,i4,i4,f8,i4,"
			"f8,f8,f8,f8,f8"
		),
		names=[
			"year", "month", "day", "bsrn", "rotd",
			"Kp0", "Kp3", "Kp6", "Kp9", "Kp12", "Kp15", "Kp18", "Kp21", "Kpsum",
			"Ap0", "Ap3", "Ap6", "Ap9", "Ap12", "Ap15", "Ap18", "Ap21", "Apavg",
			"Cp", "C9", "isn", "f107_adj", "Q", "f107_81ctr_adj", "f107_81lst_adj",
			"f107_obs", "f107_81ctr_obs", "f107_81lst_obs"
		]
	)[2:-1]
	sw = sw[sw["year"] != -1]
	ts = pd.to_datetime([
		"{0:04d}-{1:02d}-{2:02d}".format(yy, mm, dd)
		for yy, mm, dd in sw[["year", "month", "day"]]
	])
	sw_df = pd.DataFrame(sw, index=ts)
	# Adjust Kp to 0...9
	kpns = list(map("Kp{0}".format, range(0, 23, 3))) + ["Kpsum"]
	sw_df[kpns] = 0.1 * sw_df[kpns]
	return sw_df


# Common arguments for the public daily and 3h interfaces
_SW_COMMON_PARAMS = """
Parameters
----------
swpath_all: `None` or str, optional, default `None`
	Filename for the large combined index file including the
	historic data, absolute path or relative to the current dir.
	`None` uses the package's default file location.
swpath_5y: `None` or str, optional, default `None`
	Filename for the 5-year index file, absolute path or relative to the current dir.
	`None` uses the package's default file location.
update: bool, optional, default False
	Attempt to update the local data if it is older than `update_interval`.
update_interval: str, optional, default "30days"
	The time after which the data are considered "old".
	By default, no automatic re-download is initiated, set `update` to true.
	The online data is updated every 3 hours, thus setting this value to
	a shorter time is not needed and not recommended.
"""


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


@_doc_param(params=_SW_COMMON_PARAMS)
def sw_daily(swpath_all=None, swpath_5y=None, update=False, update_interval="30days"):
	"""Combined daily Ap, Kp, and f10.7 index values

	Combines the "historic" and last-5-year data into one dataframe.

	All arguments are optional and changing them from the defaults should not
	be required neither should it be necessary nor is it recommended.
	{params}
	Returns
	-------
	sw_df: pandas.DataFrame
		The combined parsed space weather data (daily values).
		Raises ``IOError`` if the data files cannot be 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")``.

	See Also
	--------
	ap_kp_3h, read_sw
	"""
	swpath_all = swpath_all or SW_PATH_ALL
	swpath_5y = swpath_5y or SW_PATH_5Y

	# ensure that the file exists and is up to date
	if (
		not os.path.exists(swpath_all)
		or not os.path.exists(swpath_5y)
	):
		warn("Could not find space weather data, trying to download.")
		update_data(swpath_all=swpath_all, swpath_5y=swpath_5y)

	if (
		# 1460 = 4 * 365
		get_file_age(swpath_all) > pd.Timedelta("1460days")
		or get_file_age(swpath_5y) > pd.Timedelta(update_interval)
	):
		if update:
			update_data(swpath_all=swpath_all, swpath_5y=swpath_5y)
		else:
			warn(
				"Local data files are older than {0}, pass `update=True` or "
				"run `sw.update_data()` manually if you need newer data.".format(
					update_interval
				)
			)

	df_all = read_sw(swpath_all)
	df_5y = read_sw(swpath_5y)
	return pd.concat([df_all[:df_5y.index[0]], df_5y[1:]])


@_doc_param(params=_SW_COMMON_PARAMS)
def ap_kp_3h(*args, **kwargs):
	"""3h values of Ap and Kp

	Provides the 3-hourly Ap and Kp indices from the full daily data set.

	Accepts the same arguments as `sw_daily()`.
	All arguments are optional and changing them from the defaults should not
	be required neither should it be necessary nor is it recommended.
	{params}
	Returns
	-------
	sw_df: pandas.DataFrame
		The combined Ap and Kp index data (3h values).
		The index values are centred at the 3h interval, i.e. at 01:30:00,
		04:30:00, 07:30:00, ... and so on.
		Raises ``IOError`` if the data files cannot be 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")``.

	See Also
	--------
	sw_daily
	"""
	daily_df = sw_daily(*args, **kwargs)
	ret = daily_df.copy()
	apns = list(map("Ap{0}".format, range(0, 23, 3)))
	kpns = list(map("Kp{0}".format, range(0, 23, 3)))
	for i, (ap, kp) in enumerate(zip(apns, kpns)):
		ret[ap].index = daily_df[ap].index + pd.Timedelta((i * 3 + 1.5), unit="h")
		ret[kp].index = daily_df[kp].index + pd.Timedelta((i * 3 + 1.5), unit="h")
	sw_ap = pd.concat(map(ret.__getitem__, apns))
	sw_kp = pd.concat(map(ret.__getitem__, kpns))
	df = pd.DataFrame({"Ap": sw_ap, "Kp": sw_kp})
	return df.reindex(df.index.sort_values())


1			# Copyright (c) 2020--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 space weather indices
9
10			Celestrak space weather indices file parser for python [#]_.
11
12			.. [#] https://celestrak.com/SpaceData/
13			"""
14			import os
15			import logging
16			from warnings import warn
17
18			import numpy as np
19			import pandas as pd
20
21			from .core import _assert_file_exists, _dl_file, _resource_filepath
22
23			__all__ = [
24			"sw_daily", "ap_kp_3h", "read_sw",
25			"get_file_age", "update_data",
26			"SW_PATH_ALL", "SW_PATH_5Y",
27			]
28
29			DL_URL_ALL = "https://celestrak.com/SpaceData/SW-All.txt"
30			DL_URL_5Y = "https://celestrak.com/SpaceData/SW-Last5Years.txt"
31			SW_FILE_ALL = os.path.basename(DL_URL_ALL)
32			SW_FILE_5Y = os.path.basename(DL_URL_5Y)
33			SW_PATH_ALL = _resource_filepath(SW_FILE_ALL)
34			SW_PATH_5Y = _resource_filepath(SW_FILE_5Y)
35
36
37			def get_file_age(swpath, relative=True):
38			"""Age of the downloaded data file
39
40			Retrieves the last update time of the given file or full path.
41
42			Parameters
43			----------
44			swpath: str
45			Filename to check, absolute path or relative to the current dir.
46			relative: bool, optional, default True
47			Return the file's age (True) or the last update time (False).
48
49			Returns
50			-------
51			upd: pandas.Timestamp or pandas.Timedelta
52			The last updated time or the file age, depending on the setting
53			of `relative` above.
54			Raises ``IOError`` if the file is not found.
55			"""
56			_assert_file_exists(swpath)
57			with open(swpath) as fp:
58			for line in fp:
59			if line.startswith("UPDATED"):
60			# closes the file automatically
61			break
62			upd = pd.to_datetime(line.lstrip("UPDATED"), utc=True)
			0 ignored issues – show introduced 2020-06-07 18:52 UTC by Report Bug Copy Issue Report The variable `line` does not seem to be defined in case the `for` loop on line `58` is not entered. Are you sure this can never be the case? Loading history...
63			if relative:
64			return pd.Timestamp.utcnow() - upd
65			return upd
66
67
68			def update_data(
69			min_age="3h",
70			swpath_all=None, swpath_5y=None,
71			url_all=None, url_5y=None,
72			):
73			"""Update the local space weather index data
74
75			Updates the local space weather index data from the website [#]_,
76			given that the 5-year file is older
77			than `min_age`, or the combined (large) file is older than four years.
78			If the data is missing for some reason, a download will be attempted nonetheless.
79
80			All arguments are optional and changing them from the defaults should not
81			be required neither should it be necessary nor is it recommended.
82
83			.. [#] https://celestrak.com/SpaceData/
84
85			Parameters
86			----------
87			min_age: str, optional, default "3h"
88			The time after which a new download will be attempted.
89			The online data is updated every 3 hours, thus setting this value to
90			a shorter time is not needed and not recommended.
91			swpath_all: `None` or str, optional, default `None`
92			Filename for the large combined index file including the
93			historic data, absolute path or relative to the current dir.
94			`None` uses the package's default file location.
95			swpath_5y: `None` or str, optional, default `None`
96			Filename for the 5-year index file, absolute path or relative to the current dir.
97			`None` uses the package's default file location.
98			url_all: `None` or str, optional, default `None`
99			The url of the "historic" data file.
100			`None` uses the default url.
101			url_5y: `None` or str, optional, default `None`
102			The url of the data file of containing the indices of the last 5 years.
103			`None` uses the default url.
104
105			Returns
106			-------
107			Nothing.
108			"""
109			def _update_file(swpath, url, min_age):
110			if not os.path.exists(swpath):
111			logging.info("{0} not found, downloading.".format(swpath))
112			_dl_file(swpath, url)
113			return
114			if get_file_age(swpath) < pd.Timedelta(min_age):
115			logging.info("not updating '{0}'.".format(swpath))
116			return
117			logging.info("updating '{0}'.".format(swpath))
118			_dl_file(swpath, url)
119
120			swpath_all = swpath_all or SW_PATH_ALL
121			swpath_5y = swpath_5y or SW_PATH_5Y
122			url_all = url_all or DL_URL_ALL
123			url_5y = url_5y or DL_URL_5Y
124
125			# Update the large file after four years
126			# to have some overlap with the 5-year data
127			# 1460 = 4 * 365
128			_update_file(swpath_all, url_all, "1460days")
129			# Don't re-download before `min_age` has passed (3h)
130			_update_file(swpath_5y, url_5y, min_age)
131
132
133			def read_sw(swpath):
134			"""Read and parse space weather index data file
135
136			Reads the given file and parses it according to the space weather data format.
137
138			Parameters
139			----------
140			swpath: str
141			File to parse, absolute path or relative to the current dir.
142
143			Returns
144			-------
145			sw_df: pandas.DataFrame
146			The parsed space weather data (daily values).
147			Raises an ``IOError`` if the file is not found.
148			The index is returned timezone-naive but contains UTC timestamps.
149			To convert to a timezone-aware index, use
150			:meth:`pandas.DataFrame.tz_localize()`: ``sw_df.tz_localize("utc")``.
151
152			The dataframe contains the following columns:
153
154			"year", "month", "day":
155			The observation date
156			"bsrn":
157			Bartels Solar Rotation Number.
158			A sequence of 27-day intervals counted continuously from 1832 Feb 8.
159			"rotd":
160			Number of Day within the Bartels 27-day cycle (01-27).
161			"Kp0", "Kp3", "Kp6", "Kp9", "Kp12", "Kp15", "Kp18", "Kp21":
162			Planetary 3-hour Range Index (Kp) for 0000-0300, 0300-0600,
163			0600-0900, 0900-1200, 1200-1500, 1500-1800, 1800-2100, 2100-2400 UT
164			"Kpsum": Sum of the 8 Kp indices for the day.
165			Expressed to the nearest third of a unit.
166			"Ap0", "Ap3", "Ap6", "Ap9", "Ap12", "Ap15", "Ap18", "Ap21":
167			Planetary Equivalent Amplitude (Ap) for 0000-0300, 0300-0600,
168			0600-0900, 0900-1200, 1200-1500, 1500-1800, 1800-2100, 2100-2400 UT
169			"Apavg":
170			Arithmetic average of the 8 Ap indices for the day.
171			"Cp":
172			Cp or Planetary Daily Character Figure. A qualitative estimate of
173			overall level of magnetic activity for the day determined from the sum
174			of the 8 Ap indices. Cp ranges, in steps of one-tenth, from 0 (quiet)
175			to 2.5 (highly disturbed). "C9":
176			"isn":
177			International Sunspot Number.
178			Records contain the Zurich number through 1980 Dec 31 and the
179			International Brussels number thereafter.
180			"f107_adj":
181			10.7-cm Solar Radio Flux (F10.7) Adjusted to 1 AU.
182			Measured at Ottawa at 1700 UT daily from 1947 Feb 14 until
183			1991 May 31 and measured at Penticton at 2000 UT from 1991 Jun 01 on.
184			Expressed in units of 10-22 W/m2/Hz.
185			"Q":
186			Flux Qualifier.
187			0 indicates flux required no adjustment;
188			1 indicates flux required adjustment for burst in progress at time of measurement;
189			2 indicates a flux approximated by either interpolation or extrapolation;
190			3 indicates no observation; and
191			4 indicates CSSI interpolation of missing data.
192			"f107_81ctr_adj":
193			Centered 81-day arithmetic average of F10.7 (adjusted).
194			"f107_81lst_adj":
195			Last 81-day arithmetic average of F10.7 (adjusted).
196			"f107_obs":
197			Observed (unadjusted) value of F10.7.
198			"f107_81ctr_obs":
199			Centered 81-day arithmetic average of F10.7 (observed).
200			"f107_81lst_obs":
201			Last 81-day arithmetic average of F10.7 (observed).
202			"""
203			_assert_file_exists(swpath)
204			sw = np.genfromtxt(
205			swpath,
206			skip_header=3,
207			delimiter=[
208			# yy mm dd br rd kp kp kp kp kp kp kp kp Kp
209			4, 3, 3, 5, 3, 3, 3, 3, 3, 3, 3, 3, 3, 4,
210			# ap ap ap ap ap ap ap ap Ap cp c9 is f1 q
211			4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 2, 4, 6, 2,
212			# f2 f3 f4 f5 f6
213			6, 6, 6, 6, 6],
214			dtype=(
215			"i4,i4,i4,i4,i4,i4,i4,i4,i4,i4,i4,i4,i4,i4,"
216			"i4,i4,i4,i4,i4,i4,i4,i4,i4,f8,i4,i4,f8,i4,"
217			"f8,f8,f8,f8,f8"
218			),
219			names=[
220			"year", "month", "day", "bsrn", "rotd",
221			"Kp0", "Kp3", "Kp6", "Kp9", "Kp12", "Kp15", "Kp18", "Kp21", "Kpsum",
222			"Ap0", "Ap3", "Ap6", "Ap9", "Ap12", "Ap15", "Ap18", "Ap21", "Apavg",
223			"Cp", "C9", "isn", "f107_adj", "Q", "f107_81ctr_adj", "f107_81lst_adj",
224			"f107_obs", "f107_81ctr_obs", "f107_81lst_obs"
225			]
226			)[2:-1]
227			sw = sw[sw["year"] != -1]
228			ts = pd.to_datetime([
229			"{0:04d}-{1:02d}-{2:02d}".format(yy, mm, dd)
230			for yy, mm, dd in sw[["year", "month", "day"]]
231			])
232			sw_df = pd.DataFrame(sw, index=ts)
233			# Adjust Kp to 0...9
234			kpns = list(map("Kp{0}".format, range(0, 23, 3))) + ["Kpsum"]
235			sw_df[kpns] = 0.1 * sw_df[kpns]
236			return sw_df
237
238
239			# Common arguments for the public daily and 3h interfaces
240			_SW_COMMON_PARAMS = """
241			Parameters
242			----------
243			swpath_all: `None` or str, optional, default `None`
244			Filename for the large combined index file including the
245			historic data, absolute path or relative to the current dir.
246			`None` uses the package's default file location.
247			swpath_5y: `None` or str, optional, default `None`
248			Filename for the 5-year index file, absolute path or relative to the current dir.
249			`None` uses the package's default file location.
250			update: bool, optional, default False
251			Attempt to update the local data if it is older than `update_interval`.
252			update_interval: str, optional, default "30days"
253			The time after which the data are considered "old".
254			By default, no automatic re-download is initiated, set `update` to true.
255			The online data is updated every 3 hours, thus setting this value to
256			a shorter time is not needed and not recommended.
257			"""
258
259
260			def _doc_param(**sub):
261			def dec(obj):
262			obj.__doc__ = obj.__doc__.format(**sub)
263			return obj
264			return dec
265
266
267			@_doc_param(params=_SW_COMMON_PARAMS)
268			def sw_daily(swpath_all=None, swpath_5y=None, update=False, update_interval="30days"):
269			"""Combined daily Ap, Kp, and f10.7 index values
270
271			Combines the "historic" and last-5-year data into one dataframe.
272
273			All arguments are optional and changing them from the defaults should not
274			be required neither should it be necessary nor is it recommended.
275			{params}
276			Returns
277			-------
278			sw_df: pandas.DataFrame
279			The combined parsed space weather data (daily values).
280			Raises ``IOError`` if the data files cannot be found.
281			The index is returned timezone-naive but contains UTC timestamps.
282			To convert to a timezone-aware index, use
283			:meth:`pandas.DataFrame.tz_localize()`: ``sw_df.tz_localize("utc")``.
284
285			See Also
286			--------
287			ap_kp_3h, read_sw
288			"""
289			swpath_all = swpath_all or SW_PATH_ALL
290			swpath_5y = swpath_5y or SW_PATH_5Y
291
292			# ensure that the file exists and is up to date
293			if (
294			not os.path.exists(swpath_all)
295			or not os.path.exists(swpath_5y)
296			):
297			warn("Could not find space weather data, trying to download.")
298			update_data(swpath_all=swpath_all, swpath_5y=swpath_5y)
299
300			if (
301			# 1460 = 4 * 365
302			get_file_age(swpath_all) > pd.Timedelta("1460days")
303			or get_file_age(swpath_5y) > pd.Timedelta(update_interval)
304			):
305			if update:
306			update_data(swpath_all=swpath_all, swpath_5y=swpath_5y)
307			else:
308			warn(
309			"Local data files are older than {0}, pass `update=True` or "
310			"run `sw.update_data()` manually if you need newer data.".format(
311			update_interval
312			)
313			)
314
315			df_all = read_sw(swpath_all)
316			df_5y = read_sw(swpath_5y)
317			return pd.concat([df_all[:df_5y.index[0]], df_5y[1:]])
318
319
320			@_doc_param(params=_SW_COMMON_PARAMS)
321			def ap_kp_3h(args, *kwargs):
322			"""3h values of Ap and Kp
323
324			Provides the 3-hourly Ap and Kp indices from the full daily data set.
325
326			Accepts the same arguments as `sw_daily()`.
327			All arguments are optional and changing them from the defaults should not
328			be required neither should it be necessary nor is it recommended.
329			{params}
330			Returns
331			-------
332			sw_df: pandas.DataFrame
333			The combined Ap and Kp index data (3h values).
334			The index values are centred at the 3h interval, i.e. at 01:30:00,
335			04:30:00, 07:30:00, ... and so on.
336			Raises ``IOError`` if the data files cannot be found.
337			The index is returned timezone-naive but contains UTC timestamps.
338			To convert to a timezone-aware index, use
339			:meth:`pandas.DataFrame.tz_localize()`: ``sw_df.tz_localize("utc")``.
340
341			See Also
342			--------
343			sw_daily
344			"""
345			daily_df = sw_daily(args, *kwargs)
346			ret = daily_df.copy()
347			apns = list(map("Ap{0}".format, range(0, 23, 3)))
348			kpns = list(map("Kp{0}".format, range(0, 23, 3)))
349			for i, (ap, kp) in enumerate(zip(apns, kpns)):
350			ret[ap].index = daily_df[ap].index + pd.Timedelta((i * 3 + 1.5), unit="h")
351			ret[kp].index = daily_df[kp].index + pd.Timedelta((i * 3 + 1.5), unit="h")
352			sw_ap = pd.concat(map(ret.__getitem__, apns))
353			sw_kp = pd.concat(map(ret.__getitem__, kpns))
354			df = pd.DataFrame({"Ap": sw_ap, "Kp": sw_kp})
355			return df.reindex(df.index.sort_values())
356

st-bender / pyspaceweather

spaceweather.celestrak.update_data() 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.celestrak.update_data() A
last analyzed 2025-08-15 09:40 UTC