"""
A collection of utility functions and classes. Originally, many
(but not all) were from the Python Cookbook -- hence the name cbook.
This module is safe to import from anywhere within Matplotlib;
it imports Matplotlib only at runtime.
"""
import collections
import collections.abc
import contextlib
import functools
import gzip
import itertools
import operator
import os
from pathlib import Path
import re
import shlex
import subprocess
import sys
import time
import traceback
import types
import warnings
import weakref
import numpy as np
import matplotlib
from .deprecation import (
deprecated, warn_deprecated,
_rename_parameter, _delete_parameter, _make_keyword_only,
_deprecate_method_override, _deprecate_privatize_attribute,
_suppress_matplotlib_deprecation_warning,
MatplotlibDeprecationWarning, mplDeprecation)
def _get_running_interactive_framework():
"""
Return the interactive framework whose event loop is currently running, if
any, or "headless" if no event loop can be started, or None.
Returns
-------
Optional[str]
One of the following values: "qt5", "qt4", "gtk3", "wx", "tk",
"macosx", "headless", ``None``.
"""
QtWidgets = (sys.modules.get("PyQt5.QtWidgets")
or sys.modules.get("PySide2.QtWidgets"))
if QtWidgets and QtWidgets.QApplication.instance():
return "qt5"
QtGui = (sys.modules.get("PyQt4.QtGui")
or sys.modules.get("PySide.QtGui"))
if QtGui and QtGui.QApplication.instance():
return "qt4"
Gtk = sys.modules.get("gi.repository.Gtk")
if Gtk and Gtk.main_level():
return "gtk3"
wx = sys.modules.get("wx")
if wx and wx.GetApp():
return "wx"
tkinter = sys.modules.get("tkinter")
if tkinter:
for frame in sys._current_frames().values():
while frame:
if frame.f_code == tkinter.mainloop.__code__:
return "tk"
frame = frame.f_back
if 'matplotlib.backends._macosx' in sys.modules:
if sys.modules["matplotlib.backends._macosx"].event_loop_is_running():
return "macosx"
if sys.platform.startswith("linux") and not os.environ.get("DISPLAY"):
return "headless"
return None
def _exception_printer(exc):
if _get_running_interactive_framework() in ["headless", None]:
raise exc
else:
traceback.print_exc()
class _StrongRef:
"""
Wrapper similar to a weakref, but keeping a strong reference to the object.
"""
def __init__(self, obj):
self._obj = obj
def __call__(self):
return self._obj
def __eq__(self, other):
return isinstance(other, _StrongRef) and self._obj == other._obj
def __hash__(self):
return hash(self._obj)
[docs]class CallbackRegistry:
"""
Handle registering and disconnecting for a set of signals and callbacks:
>>> def oneat(x):
... print('eat', x)
>>> def ondrink(x):
... print('drink', x)
>>> from matplotlib.cbook import CallbackRegistry
>>> callbacks = CallbackRegistry()
>>> id_eat = callbacks.connect('eat', oneat)
>>> id_drink = callbacks.connect('drink', ondrink)
>>> callbacks.process('drink', 123)
drink 123
>>> callbacks.process('eat', 456)
eat 456
>>> callbacks.process('be merry', 456) # nothing will be called
>>> callbacks.disconnect(id_eat)
>>> callbacks.process('eat', 456) # nothing will be called
In practice, one should always disconnect all callbacks when they are
no longer needed to avoid dangling references (and thus memory leaks).
However, real code in Matplotlib rarely does so, and due to its design,
it is rather difficult to place this kind of code. To get around this,
and prevent this class of memory leaks, we instead store weak references
to bound methods only, so when the destination object needs to die, the
CallbackRegistry won't keep it alive.
Parameters
----------
exception_handler : callable, optional
If provided must have signature ::
def handler(exc: Exception) -> None:
If not None this function will be called with any `Exception`
subclass raised by the callbacks in `CallbackRegistry.process`.
The handler may either consume the exception or re-raise.
The callable must be pickle-able.
The default handler is ::
def h(exc):
traceback.print_exc()
"""
# We maintain two mappings:
# callbacks: signal -> {cid -> weakref-to-callback}
# _func_cid_map: signal -> {weakref-to-callback -> cid}
def __init__(self, exception_handler=_exception_printer):
self.exception_handler = exception_handler
self.callbacks = {}
self._cid_gen = itertools.count()
self._func_cid_map = {}
def __getstate__(self):
# In general, callbacks may not be pickled, so we just drop them.
return {**vars(self), "callbacks": {}, "_func_cid_map": {}}
[docs] def connect(self, s, func):
"""Register *func* to be called when signal *s* is generated."""
self._func_cid_map.setdefault(s, {})
try:
proxy = weakref.WeakMethod(func, self._remove_proxy)
except TypeError:
proxy = _StrongRef(func)
if proxy in self._func_cid_map[s]:
return self._func_cid_map[s][proxy]
cid = next(self._cid_gen)
self._func_cid_map[s][proxy] = cid
self.callbacks.setdefault(s, {})
self.callbacks[s][cid] = proxy
return cid
# Keep a reference to sys.is_finalizing, as sys may have been cleared out
# at that point.
def _remove_proxy(self, proxy, *, _is_finalizing=sys.is_finalizing):
if _is_finalizing():
# Weakrefs can't be properly torn down at that point anymore.
return
for signal, proxies in list(self._func_cid_map.items()):
try:
del self.callbacks[signal][proxies[proxy]]
except KeyError:
pass
if len(self.callbacks[signal]) == 0:
del self.callbacks[signal]
del self._func_cid_map[signal]
[docs] def disconnect(self, cid):
"""Disconnect the callback registered with callback id *cid*."""
for eventname, callbackd in list(self.callbacks.items()):
try:
del callbackd[cid]
except KeyError:
continue
else:
for signal, functions in list(self._func_cid_map.items()):
for function, value in list(functions.items()):
if value == cid:
del functions[function]
return
[docs] def process(self, s, *args, **kwargs):
"""
Process signal *s*.
All of the functions registered to receive callbacks on *s* will be
called with ``*args`` and ``**kwargs``.
"""
for cid, ref in list(self.callbacks.get(s, {}).items()):
func = ref()
if func is not None:
try:
func(*args, **kwargs)
# this does not capture KeyboardInterrupt, SystemExit,
# and GeneratorExit
except Exception as exc:
if self.exception_handler is not None:
self.exception_handler(exc)
else:
raise
[docs]class silent_list(list):
"""
A list with a short ``repr()``.
This is meant to be used for a homogeneous list of artists, so that they
don't cause long, meaningless output.
Instead of ::
[<matplotlib.lines.Line2D object at 0x7f5749fed3c8>,
<matplotlib.lines.Line2D object at 0x7f5749fed4e0>,
<matplotlib.lines.Line2D object at 0x7f5758016550>]
one will get ::
<a list of 3 Line2D objects>
"""
def __init__(self, type, seq=None):
self.type = type
if seq is not None:
self.extend(seq)
def __repr__(self):
return '<a list of %d %s objects>' % (len(self), self.type)
[docs]@deprecated("3.3")
class IgnoredKeywordWarning(UserWarning):
"""
A class for issuing warnings about keyword arguments that will be ignored
by Matplotlib.
"""
pass
[docs]@deprecated("3.3", alternative="normalize_kwargs")
def local_over_kwdict(local_var, kwargs, *keys):
"""
Enforces the priority of a local variable over potentially conflicting
argument(s) from a kwargs dict. The following possible output values are
considered in order of priority::
local_var > kwargs[keys[0]] > ... > kwargs[keys[-1]]
The first of these whose value is not None will be returned. If all are
None then None will be returned. Each key in keys will be removed from the
kwargs dict in place.
Parameters
----------
local_var : any object
The local variable (highest priority).
kwargs : dict
Dictionary of keyword arguments; modified in place.
keys : str(s)
Name(s) of keyword arguments to process, in descending order of
priority.
Returns
-------
any object
Either local_var or one of kwargs[key] for key in keys.
Raises
------
IgnoredKeywordWarning
For each key in keys that is removed from kwargs but not used as
the output value.
"""
return _local_over_kwdict(local_var, kwargs, *keys, IgnoredKeywordWarning)
def _local_over_kwdict(
local_var, kwargs, *keys, warning_cls=MatplotlibDeprecationWarning):
out = local_var
for key in keys:
kwarg_val = kwargs.pop(key, None)
if kwarg_val is not None:
if out is None:
out = kwarg_val
else:
_warn_external('"%s" keyword argument will be ignored' % key,
warning_cls)
return out
[docs]def strip_math(s):
"""
Remove latex formatting from mathtext.
Only handles fully math and fully non-math strings.
"""
if len(s) >= 2 and s[0] == s[-1] == "$":
s = s[1:-1]
for tex, plain in [
(r"\times", "x"), # Specifically for Formatter support.
(r"\mathdefault", ""),
(r"\rm", ""),
(r"\cal", ""),
(r"\tt", ""),
(r"\it", ""),
("\\", ""),
("{", ""),
("}", ""),
]:
s = s.replace(tex, plain)
return s
[docs]def is_writable_file_like(obj):
"""Return whether *obj* looks like a file object with a *write* method."""
return callable(getattr(obj, 'write', None))
[docs]def file_requires_unicode(x):
"""
Return whether the given writable file-like object requires Unicode to be
written to it.
"""
try:
x.write(b'')
except TypeError:
return True
else:
return False
[docs]def to_filehandle(fname, flag='r', return_opened=False, encoding=None):
"""
Convert a path to an open file handle or pass-through a file-like object.
Consider using `open_file_cm` instead, as it allows one to properly close
newly created file objects more easily.
Parameters
----------
fname : str or path-like or file-like
If `str` or `os.PathLike`, the file is opened using the flags specified
by *flag* and *encoding*. If a file-like object, it is passed through.
flag : str, default 'r'
Passed as the *mode* argument to `open` when *fname* is `str` or
`os.PathLike`; ignored if *fname* is file-like.
return_opened : bool, default False
If True, return both the file object and a boolean indicating whether
this was a new file (that the caller needs to close). If False, return
only the new file.
encoding : str or None, default None
Passed as the *mode* argument to `open` when *fname* is `str` or
`os.PathLike`; ignored if *fname* is file-like.
Returns
-------
fh : file-like
opened : bool
*opened* is only returned if *return_opened* is True.
"""
if isinstance(fname, os.PathLike):
fname = os.fspath(fname)
if "U" in flag:
warn_deprecated("3.3", message="Passing a flag containing 'U' to "
"to_filehandle() is deprecated since %(since)s and "
"will be removed %(removal)s.")
flag = flag.replace("U", "")
if isinstance(fname, str):
if fname.endswith('.gz'):
fh = gzip.open(fname, flag)
elif fname.endswith('.bz2'):
# python may not be complied with bz2 support,
# bury import until we need it
import bz2
fh = bz2.BZ2File(fname, flag)
else:
fh = open(fname, flag, encoding=encoding)
opened = True
elif hasattr(fname, 'seek'):
fh = fname
opened = False
else:
raise ValueError('fname must be a PathLike or file handle')
if return_opened:
return fh, opened
return fh
[docs]@contextlib.contextmanager
def open_file_cm(path_or_file, mode="r", encoding=None):
r"""Pass through file objects and context-manage path-likes."""
fh, opened = to_filehandle(path_or_file, mode, True, encoding)
if opened:
with fh:
yield fh
else:
yield fh
[docs]def is_scalar_or_string(val):
"""Return whether the given object is a scalar or string like."""
return isinstance(val, str) or not np.iterable(val)
[docs]def get_sample_data(fname, asfileobj=True, *, np_load=False):
"""
Return a sample data file. *fname* is a path relative to the
:file:`mpl-data/sample_data` directory. If *asfileobj* is `True`
return a file object, otherwise just a file path.
Sample data files are stored in the 'mpl-data/sample_data' directory within
the Matplotlib package.
If the filename ends in .gz, the file is implicitly ungzipped. If the
filename ends with .npy or .npz, *asfileobj* is True, and *np_load* is
True, the file is loaded with `numpy.load`. *np_load* currently defaults
to False but will default to True in a future release.
"""
path = _get_data_path('sample_data', fname)
if asfileobj:
suffix = path.suffix.lower()
if suffix == '.gz':
return gzip.open(path)
elif suffix in ['.npy', '.npz']:
if np_load:
return np.load(path)
else:
warn_deprecated(
"3.3", message="In a future release, get_sample_data "
"will automatically load numpy arrays. Set np_load to "
"True to get the array and suppress this warning. Set "
"asfileobj to False to get the path to the data file and "
"suppress this warning.")
return path.open('rb')
elif suffix in ['.csv', '.xrc', '.txt']:
return path.open('r')
else:
return path.open('rb')
else:
return str(path)
def _get_data_path(*args):
"""
Return the `Path` to a resource file provided by Matplotlib.
``*args`` specify a path relative to the base data path.
"""
return Path(matplotlib.get_data_path(), *args)
[docs]def flatten(seq, scalarp=is_scalar_or_string):
"""
Return a generator of flattened nested containers.
For example:
>>> from matplotlib.cbook import flatten
>>> l = (('John', ['Hunter']), (1, 23), [[([42, (5, 23)], )]])
>>> print(list(flatten(l)))
['John', 'Hunter', 1, 23, 42, 5, 23]
By: Composite of Holger Krekel and Luther Blissett
From: https://code.activestate.com/recipes/121294/
and Recipe 1.12 in cookbook
"""
for item in seq:
if scalarp(item) or item is None:
yield item
else:
yield from flatten(item, scalarp)
[docs]@deprecated("3.3", alternative="os.path.realpath and os.stat")
@functools.lru_cache()
def get_realpath_and_stat(path):
realpath = os.path.realpath(path)
stat = os.stat(realpath)
stat_key = (stat.st_ino, stat.st_dev)
return realpath, stat_key
# A regular expression used to determine the amount of space to
# remove. It looks for the first sequence of spaces immediately
# following the first newline, or at the beginning of the string.
_find_dedent_regex = re.compile(r"(?:(?:\n\r?)|^)( *)\S")
# A cache to hold the regexs that actually remove the indent.
_dedent_regex = {}
[docs]class maxdict(dict):
"""
A dictionary with a maximum size.
Notes
-----
This doesn't override all the relevant methods to constrain the size,
just ``__setitem__``, so use with caution.
"""
def __init__(self, maxsize):
dict.__init__(self)
self.maxsize = maxsize
self._killkeys = []
def __setitem__(self, k, v):
if k not in self:
if len(self) >= self.maxsize:
del self[self._killkeys[0]]
del self._killkeys[0]
self._killkeys.append(k)
dict.__setitem__(self, k, v)
[docs]class Stack:
"""
Stack of elements with a movable cursor.
Mimics home/back/forward in a web browser.
"""
def __init__(self, default=None):
self.clear()
self._default = default
def __call__(self):
"""Return the current element, or None."""
if not self._elements:
return self._default
else:
return self._elements[self._pos]
def __len__(self):
return len(self._elements)
def __getitem__(self, ind):
return self._elements[ind]
[docs] def forward(self):
"""Move the position forward and return the current element."""
self._pos = min(self._pos + 1, len(self._elements) - 1)
return self()
[docs] def back(self):
"""Move the position back and return the current element."""
if self._pos > 0:
self._pos -= 1
return self()
[docs] def push(self, o):
"""
Push *o* to the stack at current position. Discard all later elements.
*o* is returned.
"""
self._elements = self._elements[:self._pos + 1] + [o]
self._pos = len(self._elements) - 1
return self()
[docs] def home(self):
"""
Push the first element onto the top of the stack.
The first element is returned.
"""
if not self._elements:
return
self.push(self._elements[0])
return self()
[docs] def empty(self):
"""Return whether the stack is empty."""
return len(self._elements) == 0
[docs] def clear(self):
"""Empty the stack."""
self._pos = -1
self._elements = []
[docs] def bubble(self, o):
"""
Raise all references of *o* to the top of the stack, and return it.
Raises
------
ValueError
If *o* is not in the stack.
"""
if o not in self._elements:
raise ValueError('Given element not contained in the stack')
old_elements = self._elements.copy()
self.clear()
top_elements = []
for elem in old_elements:
if elem == o:
top_elements.append(elem)
else:
self.push(elem)
for _ in top_elements:
self.push(o)
return o
[docs] def remove(self, o):
"""
Remove *o* from the stack.
Raises
------
ValueError
If *o* is not in the stack.
"""
if o not in self._elements:
raise ValueError('Given element not contained in the stack')
old_elements = self._elements.copy()
self.clear()
for elem in old_elements:
if elem != o:
self.push(elem)
[docs]def report_memory(i=0): # argument may go away
"""Return the memory consumed by the process."""
def call(command, os_name):
try:
return subprocess.check_output(command)
except subprocess.CalledProcessError as err:
raise NotImplementedError(
"report_memory works on %s only if "
"the '%s' program is found" % (os_name, command[0])
) from err
pid = os.getpid()
if sys.platform == 'sunos5':
lines = call(['ps', '-p', '%d' % pid, '-o', 'osz'], 'Sun OS')
mem = int(lines[-1].strip())
elif sys.platform == 'linux':
lines = call(['ps', '-p', '%d' % pid, '-o', 'rss,sz'], 'Linux')
mem = int(lines[1].split()[1])
elif sys.platform == 'darwin':
lines = call(['ps', '-p', '%d' % pid, '-o', 'rss,vsz'], 'Mac OS')
mem = int(lines[1].split()[0])
elif sys.platform == 'win32':
lines = call(["tasklist", "/nh", "/fi", "pid eq %d" % pid], 'Windows')
mem = int(lines.strip().split()[-2].replace(',', ''))
else:
raise NotImplementedError(
"We don't have a memory monitor for %s" % sys.platform)
return mem
[docs]def safe_masked_invalid(x, copy=False):
x = np.array(x, subok=True, copy=copy)
if not x.dtype.isnative:
# If we have already made a copy, do the byteswap in place, else make a
# copy with the byte order swapped.
x = x.byteswap(inplace=copy).newbyteorder('N') # Swap to native order.
try:
xm = np.ma.masked_invalid(x, copy=False)
xm.shrink_mask()
except TypeError:
return x
return xm
[docs]def print_cycles(objects, outstream=sys.stdout, show_progress=False):
"""
Print loops of cyclic references in the given *objects*.
It is often useful to pass in ``gc.garbage`` to find the cycles that are
preventing some objects from being garbage collected.
Parameters
----------
objects
A list of objects to find cycles in.
outstream
The stream for output.
show_progress : bool
If True, print the number of objects reached as they are found.
"""
import gc
def print_path(path):
for i, step in enumerate(path):
# next "wraps around"
next = path[(i + 1) % len(path)]
outstream.write(" %s -- " % type(step))
if isinstance(step, dict):
for key, val in step.items():
if val is next:
outstream.write("[{!r}]".format(key))
break
if key is next:
outstream.write("[key] = {!r}".format(val))
break
elif isinstance(step, list):
outstream.write("[%d]" % step.index(next))
elif isinstance(step, tuple):
outstream.write("( tuple )")
else:
outstream.write(repr(step))
outstream.write(" ->\n")
outstream.write("\n")
def recurse(obj, start, all, current_path):
if show_progress:
outstream.write("%d\r" % len(all))
all[id(obj)] = None
referents = gc.get_referents(obj)
for referent in referents:
# If we've found our way back to the start, this is
# a cycle, so print it out
if referent is start:
print_path(current_path)
# Don't go back through the original list of objects, or
# through temporary references to the object, since those
# are just an artifact of the cycle detector itself.
elif referent is objects or isinstance(referent, types.FrameType):
continue
# We haven't seen this object before, so recurse
elif id(referent) not in all:
recurse(referent, start, all, current_path + [obj])
for obj in objects:
outstream.write(f"Examining: {obj!r}\n")
recurse(obj, obj, {}, [])
[docs]class Grouper:
"""
A disjoint-set data structure.
Objects can be joined using :meth:`join`, tested for connectedness
using :meth:`joined`, and all disjoint sets can be retrieved by
using the object as an iterator.
The objects being joined must be hashable and weak-referenceable.
Examples
--------
>>> from matplotlib.cbook import Grouper
>>> class Foo:
... def __init__(self, s):
... self.s = s
... def __repr__(self):
... return self.s
...
>>> a, b, c, d, e, f = [Foo(x) for x in 'abcdef']
>>> grp = Grouper()
>>> grp.join(a, b)
>>> grp.join(b, c)
>>> grp.join(d, e)
>>> sorted(map(tuple, grp))
[(a, b, c), (d, e)]
>>> grp.joined(a, b)
True
>>> grp.joined(a, c)
True
>>> grp.joined(a, d)
False
"""
def __init__(self, init=()):
self._mapping = {weakref.ref(x): [weakref.ref(x)] for x in init}
def __contains__(self, item):
return weakref.ref(item) in self._mapping
[docs] def clean(self):
"""Clean dead weak references from the dictionary."""
mapping = self._mapping
to_drop = [key for key in mapping if key() is None]
for key in to_drop:
val = mapping.pop(key)
val.remove(key)
[docs] def join(self, a, *args):
"""
Join given arguments into the same set. Accepts one or more arguments.
"""
mapping = self._mapping
set_a = mapping.setdefault(weakref.ref(a), [weakref.ref(a)])
for arg in args:
set_b = mapping.get(weakref.ref(arg), [weakref.ref(arg)])
if set_b is not set_a:
if len(set_b) > len(set_a):
set_a, set_b = set_b, set_a
set_a.extend(set_b)
for elem in set_b:
mapping[elem] = set_a
self.clean()
[docs] def joined(self, a, b):
"""Return whether *a* and *b* are members of the same set."""
self.clean()
return (self._mapping.get(weakref.ref(a), object())
is self._mapping.get(weakref.ref(b)))
[docs] def remove(self, a):
self.clean()
set_a = self._mapping.pop(weakref.ref(a), None)
if set_a:
set_a.remove(weakref.ref(a))
def __iter__(self):
"""
Iterate over each of the disjoint sets as a list.
The iterator is invalid if interleaved with calls to join().
"""
self.clean()
unique_groups = {id(group): group for group in self._mapping.values()}
for group in unique_groups.values():
yield [x() for x in group]
[docs] def get_siblings(self, a):
"""Return all of the items joined with *a*, including itself."""
self.clean()
siblings = self._mapping.get(weakref.ref(a), [weakref.ref(a)])
return [x() for x in siblings]
[docs]def simple_linear_interpolation(a, steps):
"""
Resample an array with ``steps - 1`` points between original point pairs.
Along each column of *a*, ``(steps - 1)`` points are introduced between
each original values; the values are linearly interpolated.
Parameters
----------
a : array, shape (n, ...)
steps : int
Returns
-------
array
shape ``((n - 1) * steps + 1, ...)``
"""
fps = a.reshape((len(a), -1))
xp = np.arange(len(a)) * steps
x = np.arange((len(a) - 1) * steps + 1)
return (np.column_stack([np.interp(x, xp, fp) for fp in fps.T])
.reshape((len(x),) + a.shape[1:]))
[docs]def delete_masked_points(*args):
"""
Find all masked and/or non-finite points in a set of arguments,
and return the arguments with only the unmasked points remaining.
Arguments can be in any of 5 categories:
1) 1-D masked arrays
2) 1-D ndarrays
3) ndarrays with more than one dimension
4) other non-string iterables
5) anything else
The first argument must be in one of the first four categories;
any argument with a length differing from that of the first
argument (and hence anything in category 5) then will be
passed through unchanged.
Masks are obtained from all arguments of the correct length
in categories 1, 2, and 4; a point is bad if masked in a masked
array or if it is a nan or inf. No attempt is made to
extract a mask from categories 2, 3, and 4 if `numpy.isfinite`
does not yield a Boolean array.
All input arguments that are not passed unchanged are returned
as ndarrays after removing the points or rows corresponding to
masks in any of the arguments.
A vastly simpler version of this function was originally
written as a helper for Axes.scatter().
"""
if not len(args):
return ()
if is_scalar_or_string(args[0]):
raise ValueError("First argument must be a sequence")
nrecs = len(args[0])
margs = []
seqlist = [False] * len(args)
for i, x in enumerate(args):
if not isinstance(x, str) and np.iterable(x) and len(x) == nrecs:
seqlist[i] = True
if isinstance(x, np.ma.MaskedArray):
if x.ndim > 1:
raise ValueError("Masked arrays must be 1-D")
else:
x = np.asarray(x)
margs.append(x)
masks = [] # list of masks that are True where good
for i, x in enumerate(margs):
if seqlist[i]:
if x.ndim > 1:
continue # Don't try to get nan locations unless 1-D.
if isinstance(x, np.ma.MaskedArray):
masks.append(~np.ma.getmaskarray(x)) # invert the mask
xd = x.data
else:
xd = x
try:
mask = np.isfinite(xd)
if isinstance(mask, np.ndarray):
masks.append(mask)
except Exception: # Fixme: put in tuple of possible exceptions?
pass
if len(masks):
mask = np.logical_and.reduce(masks)
igood = mask.nonzero()[0]
if len(igood) < nrecs:
for i, x in enumerate(margs):
if seqlist[i]:
margs[i] = x[igood]
for i, x in enumerate(margs):
if seqlist[i] and isinstance(x, np.ma.MaskedArray):
margs[i] = x.filled()
return margs
def _combine_masks(*args):
"""
Find all masked and/or non-finite points in a set of arguments,
and return the arguments as masked arrays with a common mask.
Arguments can be in any of 5 categories:
1) 1-D masked arrays
2) 1-D ndarrays
3) ndarrays with more than one dimension
4) other non-string iterables
5) anything else
The first argument must be in one of the first four categories;
any argument with a length differing from that of the first
argument (and hence anything in category 5) then will be
passed through unchanged.
Masks are obtained from all arguments of the correct length
in categories 1, 2, and 4; a point is bad if masked in a masked
array or if it is a nan or inf. No attempt is made to
extract a mask from categories 2 and 4 if :meth:`np.isfinite`
does not yield a Boolean array. Category 3 is included to
support RGB or RGBA ndarrays, which are assumed to have only
valid values and which are passed through unchanged.
All input arguments that are not passed unchanged are returned
as masked arrays if any masked points are found, otherwise as
ndarrays.
"""
if not len(args):
return ()
if is_scalar_or_string(args[0]):
raise ValueError("First argument must be a sequence")
nrecs = len(args[0])
margs = [] # Output args; some may be modified.
seqlist = [False] * len(args) # Flags: True if output will be masked.
masks = [] # List of masks.
for i, x in enumerate(args):
if is_scalar_or_string(x) or len(x) != nrecs:
margs.append(x) # Leave it unmodified.
else:
if isinstance(x, np.ma.MaskedArray) and x.ndim > 1:
raise ValueError("Masked arrays must be 1-D")
try:
x = np.asanyarray(x)
except (np.VisibleDeprecationWarning, ValueError):
# NumPy 1.19 raises a warning about ragged arrays, but we want
# to accept basically anything here.
x = np.asanyarray(x, dtype=object)
if x.ndim == 1:
x = safe_masked_invalid(x)
seqlist[i] = True
if np.ma.is_masked(x):
masks.append(np.ma.getmaskarray(x))
margs.append(x) # Possibly modified.
if len(masks):
mask = np.logical_or.reduce(masks)
for i, x in enumerate(margs):
if seqlist[i]:
margs[i] = np.ma.array(x, mask=mask)
return margs
[docs]def boxplot_stats(X, whis=1.5, bootstrap=None, labels=None,
autorange=False):
r"""
Return a list of dictionaries of statistics used to draw a series of box
and whisker plots using `~.Axes.bxp`.
Parameters
----------
X : array-like
Data that will be represented in the boxplots. Should have 2 or
fewer dimensions.
whis : float or (float, float), default: 1.5
The position of the whiskers.
If a float, the lower whisker is at the lowest datum above
``Q1 - whis*(Q3-Q1)``, and the upper whisker at the highest datum below
``Q3 + whis*(Q3-Q1)``, where Q1 and Q3 are the first and third
quartiles. The default value of ``whis = 1.5`` corresponds to Tukey's
original definition of boxplots.
If a pair of floats, they indicate the percentiles at which to draw the
whiskers (e.g., (5, 95)). In particular, setting this to (0, 100)
results in whiskers covering the whole range of the data. "range" is
a deprecated synonym for (0, 100).
In the edge case where ``Q1 == Q3``, *whis* is automatically set to
(0, 100) (cover the whole range of the data) if *autorange* is True.
Beyond the whiskers, data are considered outliers and are plotted as
individual points.
bootstrap : int, optional
Number of times the confidence intervals around the median
should be bootstrapped (percentile method).
labels : array-like, optional
Labels for each dataset. Length must be compatible with
dimensions of *X*.
autorange : bool, optional (False)
When `True` and the data are distributed such that the 25th and 75th
percentiles are equal, ``whis`` is set to (0, 100) such that the
whisker ends are at the minimum and maximum of the data.
Returns
-------
list of dict
A list of dictionaries containing the results for each column
of data. Keys of each dictionary are the following:
======== ===================================
Key Value Description
======== ===================================
label tick label for the boxplot
mean arithmetic mean value
med 50th percentile
q1 first quartile (25th percentile)
q3 third quartile (75th percentile)
cilo lower notch around the median
cihi upper notch around the median
whislo end of the lower whisker
whishi end of the upper whisker
fliers outliers
======== ===================================
Notes
-----
Non-bootstrapping approach to confidence interval uses Gaussian-based
asymptotic approximation:
.. math::
\mathrm{med} \pm 1.57 \times \frac{\mathrm{iqr}}{\sqrt{N}}
General approach from:
McGill, R., Tukey, J.W., and Larsen, W.A. (1978) "Variations of
Boxplots", The American Statistician, 32:12-16.
"""
def _bootstrap_median(data, N=5000):
# determine 95% confidence intervals of the median
M = len(data)
percentiles = [2.5, 97.5]
bs_index = np.random.randint(M, size=(N, M))
bsData = data[bs_index]
estimate = np.median(bsData, axis=1, overwrite_input=True)
CI = np.percentile(estimate, percentiles)
return CI
def _compute_conf_interval(data, med, iqr, bootstrap):
if bootstrap is not None:
# Do a bootstrap estimate of notch locations.
# get conf. intervals around median
CI = _bootstrap_median(data, N=bootstrap)
notch_min = CI[0]
notch_max = CI[1]
else:
N = len(data)
notch_min = med - 1.57 * iqr / np.sqrt(N)
notch_max = med + 1.57 * iqr / np.sqrt(N)
return notch_min, notch_max
# output is a list of dicts
bxpstats = []
# convert X to a list of lists
X = _reshape_2D(X, "X")
ncols = len(X)
if labels is None:
labels = itertools.repeat(None)
elif len(labels) != ncols:
raise ValueError("Dimensions of labels and X must be compatible")
input_whis = whis
for ii, (x, label) in enumerate(zip(X, labels)):
# empty dict
stats = {}
if label is not None:
stats['label'] = label
# restore whis to the input values in case it got changed in the loop
whis = input_whis
# note tricksiness, append up here and then mutate below
bxpstats.append(stats)
# if empty, bail
if len(x) == 0:
stats['fliers'] = np.array([])
stats['mean'] = np.nan
stats['med'] = np.nan
stats['q1'] = np.nan
stats['q3'] = np.nan
stats['cilo'] = np.nan
stats['cihi'] = np.nan
stats['whislo'] = np.nan
stats['whishi'] = np.nan
stats['med'] = np.nan
continue
# up-convert to an array, just to be safe
x = np.asarray(x)
# arithmetic mean
stats['mean'] = np.mean(x)
# medians and quartiles
q1, med, q3 = np.percentile(x, [25, 50, 75])
# interquartile range
stats['iqr'] = q3 - q1
if stats['iqr'] == 0 and autorange:
whis = (0, 100)
# conf. interval around median
stats['cilo'], stats['cihi'] = _compute_conf_interval(
x, med, stats['iqr'], bootstrap
)
# lowest/highest non-outliers
if np.isscalar(whis):
if np.isreal(whis):
loval = q1 - whis * stats['iqr']
hival = q3 + whis * stats['iqr']
elif whis in ['range', 'limit', 'limits', 'min/max']:
warn_deprecated(
"3.2", message=f"Setting whis to {whis!r} is deprecated "
"since %(since)s and support for it will be removed "
"%(removal)s; set it to [0, 100] to achieve the same "
"effect.")
loval = np.min(x)
hival = np.max(x)
else:
raise ValueError('whis must be a float or list of percentiles')
else:
loval, hival = np.percentile(x, whis)
# get high extreme
wiskhi = x[x <= hival]
if len(wiskhi) == 0 or np.max(wiskhi) < q3:
stats['whishi'] = q3
else:
stats['whishi'] = np.max(wiskhi)
# get low extreme
wisklo = x[x >= loval]
if len(wisklo) == 0 or np.min(wisklo) > q1:
stats['whislo'] = q1
else:
stats['whislo'] = np.min(wisklo)
# compute a single array of outliers
stats['fliers'] = np.hstack([
x[x < stats['whislo']],
x[x > stats['whishi']],
])
# add in the remaining stats
stats['q1'], stats['med'], stats['q3'] = q1, med, q3
return bxpstats
# The ls_mapper maps short codes for line style to their full name used by
# backends; the reverse mapper is for mapping full names to short ones.
ls_mapper = {'-': 'solid', '--': 'dashed', '-.': 'dashdot', ':': 'dotted'}
ls_mapper_r = {v: k for k, v in ls_mapper.items()}
[docs]def contiguous_regions(mask):
"""
Return a list of (ind0, ind1) such that ``mask[ind0:ind1].all()`` is
True and we cover all such regions.
"""
mask = np.asarray(mask, dtype=bool)
if not mask.size:
return []
# Find the indices of region changes, and correct offset
idx, = np.nonzero(mask[:-1] != mask[1:])
idx += 1
# List operations are faster for moderately sized arrays
idx = idx.tolist()
# Add first and/or last index if needed
if mask[0]:
idx = [0] + idx
if mask[-1]:
idx.append(len(mask))
return list(zip(idx[::2], idx[1::2]))
[docs]def is_math_text(s):
"""
Return whether the string *s* contains math expressions.
This is done by checking whether *s* contains an even number of
non-escaped dollar signs.
"""
s = str(s)
dollar_count = s.count(r'$') - s.count(r'\$')
even_dollars = (dollar_count > 0 and dollar_count % 2 == 0)
return even_dollars
def _to_unmasked_float_array(x):
"""
Convert a sequence to a float array; if input was a masked array, masked
values are converted to nans.
"""
if hasattr(x, 'mask'):
return np.ma.asarray(x, float).filled(np.nan)
else:
return np.asarray(x, float)
def _check_1d(x):
"""Convert scalars to 1d arrays; pass-through arrays as is."""
if not hasattr(x, 'shape') or len(x.shape) < 1:
return np.atleast_1d(x)
else:
try:
# work around
# https://github.com/pandas-dev/pandas/issues/27775 which
# means the shape of multi-dimensional slicing is not as
# expected. That this ever worked was an unintentional
# quirk of pandas and will raise an exception in the
# future. This slicing warns in pandas >= 1.0rc0 via
# https://github.com/pandas-dev/pandas/pull/30588
#
# < 1.0rc0 : x[:, None].ndim == 1, no warning, custom type
# >= 1.0rc1 : x[:, None].ndim == 2, warns, numpy array
# future : x[:, None] -> raises
#
# This code should correctly identify and coerce to a
# numpy array all pandas versions.
with warnings.catch_warnings(record=True) as w:
warnings.filterwarnings(
"always",
category=Warning,
message='Support for multi-dimensional indexing')
ndim = x[:, None].ndim
# we have definitely hit a pandas index or series object
# cast to a numpy array.
if len(w) > 0:
return np.asanyarray(x)
# We have likely hit a pandas object, or at least
# something where 2D slicing does not result in a 2D
# object.
if ndim < 2:
return np.atleast_1d(x)
return x
# In pandas 1.1.0, multidimensional indexing leads to an
# AssertionError for some Series objects, but should be
# IndexError as described in
# https://github.com/pandas-dev/pandas/issues/35527
except (AssertionError, IndexError, TypeError):
return np.atleast_1d(x)
def _reshape_2D(X, name):
"""
Use Fortran ordering to convert ndarrays and lists of iterables to lists of
1D arrays.
Lists of iterables are converted by applying `np.asanyarray` to each of
their elements. 1D ndarrays are returned in a singleton list containing
them. 2D ndarrays are converted to the list of their *columns*.
*name* is used to generate the error message for invalid inputs.
"""
# unpack if we have a values or to_numpy method.
try:
X = X.to_numpy()
except AttributeError:
try:
if isinstance(X.values, np.ndarray):
X = X.values
except AttributeError:
pass
# Iterate over columns for ndarrays.
if isinstance(X, np.ndarray):
X = X.T
if len(X) == 0:
return [[]]
elif X.ndim == 1 and np.ndim(X[0]) == 0:
# 1D array of scalars: directly return it.
return [X]
elif X.ndim in [1, 2]:
# 2D array, or 1D array of iterables: flatten them first.
return [np.reshape(x, -1) for x in X]
else:
raise ValueError(f'{name} must have 2 or fewer dimensions')
# Iterate over list of iterables.
if len(X) == 0:
return [[]]
result = []
is_1d = True
for xi in X:
# check if this is iterable, except for strings which we
# treat as singletons.
if (isinstance(xi, collections.abc.Iterable) and
not isinstance(xi, str)):
is_1d = False
xi = np.asanyarray(xi)
nd = np.ndim(xi)
if nd > 1:
raise ValueError(f'{name} must have 2 or fewer dimensions')
result.append(xi.reshape(-1))
if is_1d:
# 1D array of scalars: directly return it.
return [np.reshape(result, -1)]
else:
# 2D array, or 1D array of iterables: use flattened version.
return result
[docs]def violin_stats(X, method, points=100, quantiles=None):
"""
Return a list of dictionaries of data which can be used to draw a series
of violin plots.
See the ``Returns`` section below to view the required keys of the
dictionary.
Users can skip this function and pass a user-defined set of dictionaries
with the same keys to `~.axes.Axes.violinplot` instead of using Matplotlib
to do the calculations. See the *Returns* section below for the keys
that must be present in the dictionaries.
Parameters
----------
X : array-like
Sample data that will be used to produce the gaussian kernel density
estimates. Must have 2 or fewer dimensions.
method : callable
The method used to calculate the kernel density estimate for each
column of data. When called via ``method(v, coords)``, it should
return a vector of the values of the KDE evaluated at the values
specified in coords.
points : int, default: 100
Defines the number of points to evaluate each of the gaussian kernel
density estimates at.
quantiles : array-like, default: None
Defines (if not None) a list of floats in interval [0, 1] for each
column of data, which represents the quantiles that will be rendered
for that column of data. Must have 2 or fewer dimensions. 1D array will
be treated as a singleton list containing them.
Returns
-------
list of dict
A list of dictionaries containing the results for each column of data.
The dictionaries contain at least the following:
- coords: A list of scalars containing the coordinates this particular
kernel density estimate was evaluated at.
- vals: A list of scalars containing the values of the kernel density
estimate at each of the coordinates given in *coords*.
- mean: The mean value for this column of data.
- median: The median value for this column of data.
- min: The minimum value for this column of data.
- max: The maximum value for this column of data.
- quantiles: The quantile values for this column of data.
"""
# List of dictionaries describing each of the violins.
vpstats = []
# Want X to be a list of data sequences
X = _reshape_2D(X, "X")
# Want quantiles to be as the same shape as data sequences
if quantiles is not None and len(quantiles) != 0:
quantiles = _reshape_2D(quantiles, "quantiles")
# Else, mock quantiles if is none or empty
else:
quantiles = [[]] * len(X)
# quantiles should has the same size as dataset
if len(X) != len(quantiles):
raise ValueError("List of violinplot statistics and quantiles values"
" must have the same length")
# Zip x and quantiles
for (x, q) in zip(X, quantiles):
# Dictionary of results for this distribution
stats = {}
# Calculate basic stats for the distribution
min_val = np.min(x)
max_val = np.max(x)
quantile_val = np.percentile(x, 100 * q)
# Evaluate the kernel density estimate
coords = np.linspace(min_val, max_val, points)
stats['vals'] = method(x, coords)
stats['coords'] = coords
# Store additional statistics for this distribution
stats['mean'] = np.mean(x)
stats['median'] = np.median(x)
stats['min'] = min_val
stats['max'] = max_val
stats['quantiles'] = np.atleast_1d(quantile_val)
# Append to output
vpstats.append(stats)
return vpstats
[docs]def pts_to_prestep(x, *args):
"""
Convert continuous line to pre-steps.
Given a set of ``N`` points, convert to ``2N - 1`` points, which when
connected linearly give a step function which changes values at the
beginning of the intervals.
Parameters
----------
x : array
The x location of the steps. May be empty.
y1, ..., yp : array
y arrays to be turned into steps; all must be the same length as ``x``.
Returns
-------
array
The x and y values converted to steps in the same order as the input;
can be unpacked as ``x_out, y1_out, ..., yp_out``. If the input is
length ``N``, each of these arrays will be length ``2N + 1``. For
``N=0``, the length will be 0.
Examples
--------
>>> x_s, y1_s, y2_s = pts_to_prestep(x, y1, y2)
"""
steps = np.zeros((1 + len(args), max(2 * len(x) - 1, 0)))
# In all `pts_to_*step` functions, only assign once using *x* and *args*,
# as converting to an array may be expensive.
steps[0, 0::2] = x
steps[0, 1::2] = steps[0, 0:-2:2]
steps[1:, 0::2] = args
steps[1:, 1::2] = steps[1:, 2::2]
return steps
[docs]def pts_to_poststep(x, *args):
"""
Convert continuous line to post-steps.
Given a set of ``N`` points convert to ``2N + 1`` points, which when
connected linearly give a step function which changes values at the end of
the intervals.
Parameters
----------
x : array
The x location of the steps. May be empty.
y1, ..., yp : array
y arrays to be turned into steps; all must be the same length as ``x``.
Returns
-------
array
The x and y values converted to steps in the same order as the input;
can be unpacked as ``x_out, y1_out, ..., yp_out``. If the input is
length ``N``, each of these arrays will be length ``2N + 1``. For
``N=0``, the length will be 0.
Examples
--------
>>> x_s, y1_s, y2_s = pts_to_poststep(x, y1, y2)
"""
steps = np.zeros((1 + len(args), max(2 * len(x) - 1, 0)))
steps[0, 0::2] = x
steps[0, 1::2] = steps[0, 2::2]
steps[1:, 0::2] = args
steps[1:, 1::2] = steps[1:, 0:-2:2]
return steps
[docs]def pts_to_midstep(x, *args):
"""
Convert continuous line to mid-steps.
Given a set of ``N`` points convert to ``2N`` points which when connected
linearly give a step function which changes values at the middle of the
intervals.
Parameters
----------
x : array
The x location of the steps. May be empty.
y1, ..., yp : array
y arrays to be turned into steps; all must be the same length as
``x``.
Returns
-------
array
The x and y values converted to steps in the same order as the input;
can be unpacked as ``x_out, y1_out, ..., yp_out``. If the input is
length ``N``, each of these arrays will be length ``2N``.
Examples
--------
>>> x_s, y1_s, y2_s = pts_to_midstep(x, y1, y2)
"""
steps = np.zeros((1 + len(args), 2 * len(x)))
x = np.asanyarray(x)
steps[0, 1:-1:2] = steps[0, 2::2] = (x[:-1] + x[1:]) / 2
steps[0, :1] = x[:1] # Also works for zero-sized input.
steps[0, -1:] = x[-1:]
steps[1:, 0::2] = args
steps[1:, 1::2] = steps[1:, 0::2]
return steps
STEP_LOOKUP_MAP = {'default': lambda x, y: (x, y),
'steps': pts_to_prestep,
'steps-pre': pts_to_prestep,
'steps-post': pts_to_poststep,
'steps-mid': pts_to_midstep}
[docs]def index_of(y):
"""
A helper function to create reasonable x values for the given *y*.
This is used for plotting (x, y) if x values are not explicitly given.
First try ``y.index`` (assuming *y* is a `pandas.Series`), if that
fails, use ``range(len(y))``.
This will be extended in the future to deal with more types of
labeled data.
Parameters
----------
y : float or array-like
Returns
-------
x, y : ndarray
The x and y values to plot.
"""
try:
return y.index.values, y.values
except AttributeError:
pass
try:
y = _check_1d(y)
except (np.VisibleDeprecationWarning, ValueError):
# NumPy 1.19 will warn on ragged input, and we can't actually use it.
pass
else:
return np.arange(y.shape[0], dtype=float), y
raise ValueError('Input could not be cast to an at-least-1D NumPy array')
[docs]def safe_first_element(obj):
"""
Return the first element in *obj*.
This is an type-independent way of obtaining the first element, supporting
both index access and the iterator protocol.
"""
if isinstance(obj, collections.abc.Iterator):
# needed to accept `array.flat` as input.
# np.flatiter reports as an instance of collections.Iterator
# but can still be indexed via [].
# This has the side effect of re-setting the iterator, but
# that is acceptable.
try:
return obj[0]
except TypeError:
pass
raise RuntimeError("matplotlib does not support generators "
"as input")
return next(iter(obj))
[docs]def sanitize_sequence(data):
"""
Convert dictview objects to list. Other inputs are returned unchanged.
"""
return (list(data) if isinstance(data, collections.abc.MappingView)
else data)
[docs]@_delete_parameter("3.3", "required")
@_delete_parameter("3.3", "forbidden")
@_delete_parameter("3.3", "allowed")
def normalize_kwargs(kw, alias_mapping=None, required=(), forbidden=(),
allowed=None):
"""
Helper function to normalize kwarg inputs.
The order they are resolved are:
1. aliasing
2. required
3. forbidden
4. allowed
This order means that only the canonical names need appear in
*allowed*, *forbidden*, *required*.
Parameters
----------
kw : dict
A dict of keyword arguments.
alias_mapping : dict or Artist subclass or Artist instance, optional
A mapping between a canonical name to a list of
aliases, in order of precedence from lowest to highest.
If the canonical value is not in the list it is assumed to have
the highest priority.
If an Artist subclass or instance is passed, use its properties alias
mapping.
required : list of str, optional
A list of keys that must be in *kws*. This parameter is deprecated.
forbidden : list of str, optional
A list of keys which may not be in *kw*. This parameter is deprecated.
allowed : list of str, optional
A list of allowed fields. If this not None, then raise if
*kw* contains any keys not in the union of *required*
and *allowed*. To allow only the required fields pass in
an empty tuple ``allowed=()``. This parameter is deprecated.
Raises
------
TypeError
To match what python raises if invalid args/kwargs are passed to
a callable.
"""
from matplotlib.artist import Artist
# deal with default value of alias_mapping
if alias_mapping is None:
alias_mapping = dict()
elif (isinstance(alias_mapping, type) and issubclass(alias_mapping, Artist)
or isinstance(alias_mapping, Artist)):
alias_mapping = getattr(alias_mapping, "_alias_map", {})
to_canonical = {alias: canonical
for canonical, alias_list in alias_mapping.items()
for alias in alias_list}
canonical_to_seen = {}
ret = {} # output dictionary
for k, v in kw.items():
canonical = to_canonical.get(k, k)
if canonical in canonical_to_seen:
raise TypeError(f"Got both {canonical_to_seen[canonical]!r} and "
f"{k!r}, which are aliases of one another")
canonical_to_seen[canonical] = k
ret[canonical] = v
fail_keys = [k for k in required if k not in ret]
if fail_keys:
raise TypeError("The required keys {keys!r} "
"are not in kwargs".format(keys=fail_keys))
fail_keys = [k for k in forbidden if k in ret]
if fail_keys:
raise TypeError("The forbidden keys {keys!r} "
"are in kwargs".format(keys=fail_keys))
if allowed is not None:
allowed_set = {*required, *allowed}
fail_keys = [k for k in ret if k not in allowed_set]
if fail_keys:
raise TypeError(
"kwargs contains {keys!r} which are not in the required "
"{req!r} or allowed {allow!r} keys".format(
keys=fail_keys, req=required, allow=allowed))
return ret
@contextlib.contextmanager
def _lock_path(path):
"""
Context manager for locking a path.
Usage::
with _lock_path(path):
...
Another thread or process that attempts to lock the same path will wait
until this context manager is exited.
The lock is implemented by creating a temporary file in the parent
directory, so that directory must exist and be writable.
"""
path = Path(path)
lock_path = path.with_name(path.name + ".matplotlib-lock")
retries = 50
sleeptime = 0.1
for _ in range(retries):
try:
with lock_path.open("xb"):
break
except FileExistsError:
time.sleep(sleeptime)
else:
raise TimeoutError("""\
Lock error: Matplotlib failed to acquire the following lock file:
{}
This maybe due to another process holding this lock file. If you are sure no
other Matplotlib process is running, remove this file and try again.""".format(
lock_path))
try:
yield
finally:
lock_path.unlink()
def _topmost_artist(
artists,
_cached_max=functools.partial(max, key=operator.attrgetter("zorder"))):
"""
Get the topmost artist of a list.
In case of a tie, return the *last* of the tied artists, as it will be
drawn on top of the others. `max` returns the first maximum in case of
ties, so we need to iterate over the list in reverse order.
"""
return _cached_max(reversed(artists))
def _str_equal(obj, s):
"""
Return whether *obj* is a string equal to string *s*.
This helper solely exists to handle the case where *obj* is a numpy array,
because in such cases, a naive ``obj == s`` would yield an array, which
cannot be used in a boolean context.
"""
return isinstance(obj, str) and obj == s
def _str_lower_equal(obj, s):
"""
Return whether *obj* is a string equal, when lowercased, to string *s*.
This helper solely exists to handle the case where *obj* is a numpy array,
because in such cases, a naive ``obj == s`` would yield an array, which
cannot be used in a boolean context.
"""
return isinstance(obj, str) and obj.lower() == s
def _define_aliases(alias_d, cls=None):
"""
Class decorator for defining property aliases.
Use as ::
@cbook._define_aliases({"property": ["alias", ...], ...})
class C: ...
For each property, if the corresponding ``get_property`` is defined in the
class so far, an alias named ``get_alias`` will be defined; the same will
be done for setters. If neither the getter nor the setter exists, an
exception will be raised.
The alias map is stored as the ``_alias_map`` attribute on the class and
can be used by `~.normalize_kwargs` (which assumes that higher priority
aliases come last).
"""
if cls is None: # Return the actual class decorator.
return functools.partial(_define_aliases, alias_d)
def make_alias(name): # Enforce a closure over *name*.
@functools.wraps(getattr(cls, name))
def method(self, *args, **kwargs):
return getattr(self, name)(*args, **kwargs)
return method
for prop, aliases in alias_d.items():
exists = False
for prefix in ["get_", "set_"]:
if prefix + prop in vars(cls):
exists = True
for alias in aliases:
method = make_alias(prefix + prop)
method.__name__ = prefix + alias
method.__doc__ = "Alias for `{}`.".format(prefix + prop)
setattr(cls, prefix + alias, method)
if not exists:
raise ValueError(
"Neither getter nor setter exists for {!r}".format(prop))
def get_aliased_and_aliases(d):
return {*d, *(alias for aliases in d.values() for alias in aliases)}
preexisting_aliases = getattr(cls, "_alias_map", {})
conflicting = (get_aliased_and_aliases(preexisting_aliases)
& get_aliased_and_aliases(alias_d))
if conflicting:
# Need to decide on conflict resolution policy.
raise NotImplementedError(
f"Parent class already defines conflicting aliases: {conflicting}")
cls._alias_map = {**preexisting_aliases, **alias_d}
return cls
def _array_perimeter(arr):
"""
Get the elements on the perimeter of *arr*.
Parameters
----------
arr : ndarray, shape (M, N)
The input array.
Returns
-------
ndarray, shape (2*(M - 1) + 2*(N - 1),)
The elements on the perimeter of the array::
[arr[0, 0], ..., arr[0, -1], ..., arr[-1, -1], ..., arr[-1, 0], ...]
Examples
--------
>>> i, j = np.ogrid[:3,:4]
>>> a = i*10 + j
>>> a
array([[ 0, 1, 2, 3],
[10, 11, 12, 13],
[20, 21, 22, 23]])
>>> _array_perimeter(a)
array([ 0, 1, 2, 3, 13, 23, 22, 21, 20, 10])
"""
# note we use Python's half-open ranges to avoid repeating
# the corners
forward = np.s_[0:-1] # [0 ... -1)
backward = np.s_[-1:0:-1] # [-1 ... 0)
return np.concatenate((
arr[0, forward],
arr[forward, -1],
arr[-1, backward],
arr[backward, 0],
))
def _unfold(arr, axis, size, step):
"""
Append an extra dimension containing sliding windows along *axis*.
All windows are of size *size* and begin with every *step* elements.
Parameters
----------
arr : ndarray, shape (N_1, ..., N_k)
The input array
axis : int
Axis along which the windows are extracted
size : int
Size of the windows
step : int
Stride between first elements of subsequent windows.
Returns
-------
ndarray, shape (N_1, ..., 1 + (N_axis-size)/step, ..., N_k, size)
Examples
--------
>>> i, j = np.ogrid[:3,:7]
>>> a = i*10 + j
>>> a
array([[ 0, 1, 2, 3, 4, 5, 6],
[10, 11, 12, 13, 14, 15, 16],
[20, 21, 22, 23, 24, 25, 26]])
>>> _unfold(a, axis=1, size=3, step=2)
array([[[ 0, 1, 2],
[ 2, 3, 4],
[ 4, 5, 6]],
[[10, 11, 12],
[12, 13, 14],
[14, 15, 16]],
[[20, 21, 22],
[22, 23, 24],
[24, 25, 26]]])
"""
new_shape = [*arr.shape, size]
new_strides = [*arr.strides, arr.strides[axis]]
new_shape[axis] = (new_shape[axis] - size) // step + 1
new_strides[axis] = new_strides[axis] * step
return np.lib.stride_tricks.as_strided(arr,
shape=new_shape,
strides=new_strides,
writeable=False)
def _array_patch_perimeters(x, rstride, cstride):
"""
Extract perimeters of patches from *arr*.
Extracted patches are of size (*rstride* + 1) x (*cstride* + 1) and
share perimeters with their neighbors. The ordering of the vertices matches
that returned by ``_array_perimeter``.
Parameters
----------
x : ndarray, shape (N, M)
Input array
rstride : int
Vertical (row) stride between corresponding elements of each patch
cstride : int
Horizontal (column) stride between corresponding elements of each patch
Returns
-------
ndarray, shape (N/rstride * M/cstride, 2 * (rstride + cstride))
"""
assert rstride > 0 and cstride > 0
assert (x.shape[0] - 1) % rstride == 0
assert (x.shape[1] - 1) % cstride == 0
# We build up each perimeter from four half-open intervals. Here is an
# illustrated explanation for rstride == cstride == 3
#
# T T T R
# L R
# L R
# L B B B
#
# where T means that this element will be in the top array, R for right,
# B for bottom and L for left. Each of the arrays below has a shape of:
#
# (number of perimeters that can be extracted vertically,
# number of perimeters that can be extracted horizontally,
# cstride for top and bottom and rstride for left and right)
#
# Note that _unfold doesn't incur any memory copies, so the only costly
# operation here is the np.concatenate.
top = _unfold(x[:-1:rstride, :-1], 1, cstride, cstride)
bottom = _unfold(x[rstride::rstride, 1:], 1, cstride, cstride)[..., ::-1]
right = _unfold(x[:-1, cstride::cstride], 0, rstride, rstride)
left = _unfold(x[1:, :-1:cstride], 0, rstride, rstride)[..., ::-1]
return (np.concatenate((top, right, bottom, left), axis=2)
.reshape(-1, 2 * (rstride + cstride)))
@contextlib.contextmanager
def _setattr_cm(obj, **kwargs):
"""
Temporarily set some attributes; restore original state at context exit.
"""
sentinel = object()
origs = {}
for attr in kwargs:
orig = getattr(obj, attr, sentinel)
if attr in obj.__dict__ or orig is sentinel:
# if we are pulling from the instance dict or the object
# does not have this attribute we can trust the above
origs[attr] = orig
else:
# if the attribute is not in the instance dict it must be
# from the class level
cls_orig = getattr(type(obj), attr)
# if we are dealing with a property (but not a general descriptor)
# we want to set the original value back.
if isinstance(cls_orig, property):
origs[attr] = orig
# otherwise this is _something_ we are going to shadow at
# the instance dict level from higher up in the MRO. We
# are going to assume we can delattr(obj, attr) to clean
# up after ourselves. It is possible that this code will
# fail if used with a non-property custom descriptor which
# implements __set__ (and __delete__ does not act like a
# stack). However, this is an internal tool and we do not
# currently have any custom descriptors.
else:
origs[attr] = sentinel
try:
for attr, val in kwargs.items():
setattr(obj, attr, val)
yield
finally:
for attr, orig in origs.items():
if orig is sentinel:
delattr(obj, attr)
else:
setattr(obj, attr, orig)
def _warn_external(message, category=None):
"""
`warnings.warn` wrapper that sets *stacklevel* to "outside Matplotlib".
The original emitter of the warning can be obtained by patching this
function back to `warnings.warn`, i.e. ``cbook._warn_external =
warnings.warn`` (or ``functools.partial(warnings.warn, stacklevel=2)``,
etc.).
"""
frame = sys._getframe()
for stacklevel in itertools.count(1): # lgtm[py/unused-loop-variable]
if frame is None:
# when called in embedded context may hit frame is None
break
if not re.match(r"\A(matplotlib|mpl_toolkits)(\Z|\.(?!tests\.))",
# Work around sphinx-gallery not setting __name__.
frame.f_globals.get("__name__", "")):
break
frame = frame.f_back
warnings.warn(message, category, stacklevel)
class _OrderedSet(collections.abc.MutableSet):
def __init__(self):
self._od = collections.OrderedDict()
def __contains__(self, key):
return key in self._od
def __iter__(self):
return iter(self._od)
def __len__(self):
return len(self._od)
def add(self, key):
self._od.pop(key, None)
self._od[key] = None
def discard(self, key):
self._od.pop(key, None)
# Agg's buffers are unmultiplied RGBA8888, which neither PyQt4 nor cairo
# support; however, both do support premultiplied ARGB32.
def _premultiplied_argb32_to_unmultiplied_rgba8888(buf):
"""
Convert a premultiplied ARGB32 buffer to an unmultiplied RGBA8888 buffer.
"""
rgba = np.take( # .take() ensures C-contiguity of the result.
buf,
[2, 1, 0, 3] if sys.byteorder == "little" else [1, 2, 3, 0], axis=2)
rgb = rgba[..., :-1]
alpha = rgba[..., -1]
# Un-premultiply alpha. The formula is the same as in cairo-png.c.
mask = alpha != 0
for channel in np.rollaxis(rgb, -1):
channel[mask] = (
(channel[mask].astype(int) * 255 + alpha[mask] // 2)
// alpha[mask])
return rgba
def _unmultiplied_rgba8888_to_premultiplied_argb32(rgba8888):
"""
Convert an unmultiplied RGBA8888 buffer to a premultiplied ARGB32 buffer.
"""
if sys.byteorder == "little":
argb32 = np.take(rgba8888, [2, 1, 0, 3], axis=2)
rgb24 = argb32[..., :-1]
alpha8 = argb32[..., -1:]
else:
argb32 = np.take(rgba8888, [3, 0, 1, 2], axis=2)
alpha8 = argb32[..., :1]
rgb24 = argb32[..., 1:]
# Only bother premultiplying when the alpha channel is not fully opaque,
# as the cost is not negligible. The unsafe cast is needed to do the
# multiplication in-place in an integer buffer.
if alpha8.min() != 0xff:
np.multiply(rgb24, alpha8 / 0xff, out=rgb24, casting="unsafe")
return argb32
def _pformat_subprocess(command):
"""Pretty-format a subprocess command for printing/logging purposes."""
return (command if isinstance(command, str)
else " ".join(shlex.quote(os.fspath(arg)) for arg in command))
def _check_and_log_subprocess(command, logger, **kwargs):
"""
Run *command*, returning its stdout output if it succeeds.
If it fails (exits with nonzero return code), raise an exception whose text
includes the failed command and captured stdout and stderr output.
Regardless of the return code, the command is logged at DEBUG level on
*logger*. In case of success, the output is likewise logged.
"""
logger.debug('%s', _pformat_subprocess(command))
proc = subprocess.run(
command, stdout=subprocess.PIPE, stderr=subprocess.PIPE, **kwargs)
if proc.returncode:
stdout = proc.stdout
if isinstance(stdout, bytes):
stdout = stdout.decode()
stderr = proc.stderr
if isinstance(stderr, bytes):
stderr = stderr.decode()
raise RuntimeError(
f"The command\n"
f" {_pformat_subprocess(command)}\n"
f"failed and generated the following output:\n"
f"{stdout}\n"
f"and the following error:\n"
f"{stderr}")
if proc.stdout:
logger.debug("stdout:\n%s", proc.stdout)
if proc.stderr:
logger.debug("stderr:\n%s", proc.stderr)
return proc.stdout
# In the following _check_foo functions, the first parameter starts with an
# underscore because it is intended to be positional-only (e.g., so that
# `_check_isinstance([...], types=foo)` doesn't fail.
def _check_isinstance(_types, **kwargs):
"""
For each *key, value* pair in *kwargs*, check that *value* is an instance
of one of *_types*; if not, raise an appropriate TypeError.
As a special case, a ``None`` entry in *_types* is treated as NoneType.
Examples
--------
>>> cbook._check_isinstance((SomeClass, None), arg=arg)
"""
types = _types
if isinstance(types, type) or types is None:
types = (types,)
none_allowed = None in types
types = tuple(tp for tp in types if tp is not None)
def type_name(tp):
return (tp.__qualname__ if tp.__module__ == "builtins"
else f"{tp.__module__}.{tp.__qualname__}")
names = [*map(type_name, types)]
if none_allowed:
types = (*types, type(None))
names.append("None")
for k, v in kwargs.items():
if not isinstance(v, types):
raise TypeError(
"{!r} must be an instance of {}, not a {}".format(
k,
", ".join(names[:-1]) + " or " + names[-1]
if len(names) > 1 else names[0],
type_name(type(v))))
def _check_in_list(_values, **kwargs):
"""
For each *key, value* pair in *kwargs*, check that *value* is in *_values*;
if not, raise an appropriate ValueError.
Examples
--------
>>> cbook._check_in_list(["foo", "bar"], arg=arg, other_arg=other_arg)
"""
values = _values
for k, v in kwargs.items():
if v not in values:
raise ValueError(
"{!r} is not a valid value for {}; supported values are {}"
.format(v, k, ', '.join(map(repr, values))))
def _check_shape(_shape, **kwargs):
"""
For each *key, value* pair in *kwargs*, check that *value* has the shape
*_shape*, if not, raise an appropriate ValueError.
*None* in the shape is treated as a "free" size that can have any length.
e.g. (None, 2) -> (N, 2)
The values checked must be numpy arrays.
Examples
--------
To check for (N, 2) shaped arrays
>>> cbook._check_in_list((None, 2), arg=arg, other_arg=other_arg)
"""
target_shape = _shape
for k, v in kwargs.items():
data_shape = v.shape
if len(target_shape) != len(data_shape) or any(
t not in [s, None]
for t, s in zip(target_shape, data_shape)
):
dim_labels = iter(itertools.chain(
'MNLIJKLH',
(f"D{i}" for i in itertools.count())))
text_shape = ", ".join((str(n)
if n is not None
else next(dim_labels)
for n in target_shape))
raise ValueError(
f"{k!r} must be {len(target_shape)}D "
f"with shape ({text_shape}). "
f"Your input has shape {v.shape}."
)
def _check_getitem(_mapping, **kwargs):
"""
*kwargs* must consist of a single *key, value* pair. If *key* is in
*_mapping*, return ``_mapping[value]``; else, raise an appropriate
ValueError.
Examples
--------
>>> cbook._check_getitem({"foo": "bar"}, arg=arg)
"""
mapping = _mapping
if len(kwargs) != 1:
raise ValueError("_check_getitem takes a single keyword argument")
(k, v), = kwargs.items()
try:
return mapping[v]
except KeyError:
raise ValueError(
"{!r} is not a valid value for {}; supported values are {}"
.format(v, k, ', '.join(map(repr, mapping)))) from None
class _classproperty:
"""
Like `property`, but also triggers on access via the class, and it is the
*class* that's passed as argument.
Examples
--------
::
class C:
@classproperty
def foo(cls):
return cls.__name__
assert C.foo == "C"
"""
def __init__(self, fget):
self._fget = fget
def __get__(self, instance, owner):
return self._fget(owner)
def _backend_module_name(name):
"""
Convert a backend name (either a standard backend -- "Agg", "TkAgg", ... --
or a custom backend -- "module://...") to the corresponding module name).
"""
return (name[9:] if name.startswith("module://")
else "matplotlib.backends.backend_{}".format(name.lower()))
