NG4R3P

Linux 4gvps.4gvps.com 3.10.0-1127.18.2.vz7.163.46 #1 SMP Fri Nov 20 21:47:55 MSK 2020 x86_64
SOFT : Apache PHP : 7.4.33
/proc/self/root/opt/alt/python38/lib64/python3.8/

38.135.39.45

[ NAME ]	[ SIZE ]	[ PERM ]	[ DATE ]	[ ACT ]
+FILE +DIR
__pycache__	dir	drwxr-xr-x	2022-06-03 01:15	R D
asyncio	dir	drwxr-xr-x	2022-06-03 01:15	R D
collections	dir	drwxr-xr-x	2022-06-03 01:15	R D
concurrent	dir	drwxr-xr-x	2022-06-03 01:15	R D
config-3.8-x86_64-linux-gnu	dir	drwxr-xr-x	2022-06-03 01:15	R D
ctypes	dir	drwxr-xr-x	2022-06-03 01:15	R D
curses	dir	drwxr-xr-x	2022-06-03 01:15	R D
dbm	dir	drwxr-xr-x	2022-06-03 01:15	R D
distutils	dir	drwxr-xr-x	2022-06-03 01:15	R D
email	dir	drwxr-xr-x	2022-06-03 01:15	R D
encodings	dir	drwxr-xr-x	2022-06-03 01:15	R D
ensurepip	dir	drwxr-xr-x	2022-06-03 01:15	R D
html	dir	drwxr-xr-x	2022-06-03 01:15	R D
http	dir	drwxr-xr-x	2022-06-03 01:15	R D
importlib	dir	drwxr-xr-x	2022-06-03 01:15	R D
json	dir	drwxr-xr-x	2022-06-03 01:15	R D
lib-dynload	dir	drwxr-xr-x	2022-06-03 01:15	R D
lib2to3	dir	drwxr-xr-x	2022-08-08 06:03	R D
logging	dir	drwxr-xr-x	2022-06-03 01:15	R D
multiprocessing	dir	drwxr-xr-x	2022-06-03 01:15	R D
pydoc_data	dir	drwxr-xr-x	2022-06-03 01:15	R D
site-packages	dir	drwxr-xr-x	2022-08-08 06:03	R D
sqlite3	dir	drwxr-xr-x	2022-08-08 06:03	R D
unittest	dir	drwxr-xr-x	2022-06-03 01:15	R D
urllib	dir	drwxr-xr-x	2022-06-03 01:15	R D
venv	dir	drwxr-xr-x	2022-06-03 01:15	R D
wsgiref	dir	drwxr-xr-x	2022-06-03 01:15	R D
xml	dir	drwxr-xr-x	2022-06-03 01:15	R D
xmlrpc	dir	drwxr-xr-x	2025-06-26 06:15	R D
LICENSE.txt	13.599 KB	-rw-r--r--	2021-08-30 14:26	R E G D
__future__.py	5.026 KB	-rw-r--r--	2021-08-30 14:26	R E G D
__phello__.foo.py	0.063 KB	-rw-r--r--	2021-08-30 14:26	R E G D
_bootlocale.py	1.759 KB	-rw-r--r--	2021-08-30 14:26	R E G D
_collections_abc.py	25.488 KB	-rw-r--r--	2021-08-30 14:26	R E G D
_compat_pickle.py	8.544 KB	-rw-r--r--	2021-08-30 14:26	R E G D
_compression.py	5.215 KB	-rw-r--r--	2021-08-30 14:26	R E G D
_dummy_thread.py	5.886 KB	-rw-r--r--	2021-08-30 14:26	R E G D
_markupbase.py	14.256 KB	-rw-r--r--	2021-08-30 14:26	R E G D
_osx_support.py	21.264 KB	-rw-r--r--	2021-08-30 14:26	R E G D
_py_abc.py	6.044 KB	-rw-r--r--	2021-08-30 14:26	R E G D
_pydecimal.py	223.307 KB	-rw-r--r--	2021-08-30 14:26	R E G D
_pyio.py	90.993 KB	-rw-r--r--	2021-08-30 14:26	R E G D
_sitebuiltins.py	3.042 KB	-rw-r--r--	2021-08-30 14:26	R E G D
_strptime.py	24.676 KB	-rw-r--r--	2021-08-30 14:26	R E G D
_sysconfigdata__linux_x86_64-linux-gnu.py	37.549 KB	-rw-r--r--	2022-04-22 10:23	R E G D
_sysconfigdata_d_linux_x86_64-linux-gnu.py	37.289 KB	-rw-r--r--	2022-04-22 10:13	R E G D
_threading_local.py	7.051 KB	-rw-r--r--	2021-08-30 14:26	R E G D
_weakrefset.py	5.601 KB	-rw-r--r--	2021-08-30 14:26	R E G D
abc.py	4.384 KB	-rw-r--r--	2021-08-30 14:26	R E G D
aifc.py	32.045 KB	-rw-r--r--	2021-08-30 14:26	R E G D
antigravity.py	0.466 KB	-rw-r--r--	2021-08-30 14:26	R E G D
argparse.py	93.765 KB	-rw-r--r--	2021-08-30 14:26	R E G D
ast.py	18.783 KB	-rw-r--r--	2021-08-30 14:26	R E G D
asynchat.py	11.063 KB	-rw-r--r--	2021-08-30 14:26	R E G D
asyncore.py	19.623 KB	-rw-r--r--	2021-08-30 14:26	R E G D
base64.py	19.917 KB	-rwxr-xr-x	2021-08-30 14:26	R E G D
bdb.py	31.305 KB	-rw-r--r--	2021-08-30 14:26	R E G D
binhex.py	13.627 KB	-rw-r--r--	2021-08-30 14:26	R E G D
bisect.py	2.162 KB	-rw-r--r--	2021-08-30 14:26	R E G D
bz2.py	12.264 KB	-rw-r--r--	2021-08-30 14:26	R E G D
cProfile.py	6.847 KB	-rwxr-xr-x	2021-08-30 14:26	R E G D
calendar.py	24.25 KB	-rw-r--r--	2021-08-30 14:26	R E G D
cgi.py	33.149 KB	-rwxr-xr-x	2021-08-30 14:26	R E G D
cgitb.py	11.813 KB	-rw-r--r--	2021-08-30 14:26	R E G D
chunk.py	5.308 KB	-rw-r--r--	2021-08-30 14:26	R E G D
cmd.py	14.512 KB	-rw-r--r--	2021-08-30 14:26	R E G D
code.py	10.373 KB	-rw-r--r--	2021-08-30 14:26	R E G D
codecs.py	35.808 KB	-rw-r--r--	2021-08-30 14:26	R E G D
codeop.py	6.182 KB	-rw-r--r--	2021-08-30 14:26	R E G D
colorsys.py	3.969 KB	-rw-r--r--	2021-08-30 14:26	R E G D
compileall.py	13.357 KB	-rw-r--r--	2021-08-30 14:26	R E G D
configparser.py	53.1 KB	-rw-r--r--	2021-08-30 14:26	R E G D
contextlib.py	24.409 KB	-rw-r--r--	2021-08-30 14:26	R E G D
contextvars.py	0.126 KB	-rw-r--r--	2021-08-30 14:26	R E G D
copy.py	8.458 KB	-rw-r--r--	2021-08-30 14:26	R E G D
copyreg.py	6.968 KB	-rw-r--r--	2021-08-30 14:26	R E G D
crypt.py	3.525 KB	-rw-r--r--	2021-08-30 14:26	R E G D
csv.py	15.766 KB	-rw-r--r--	2021-08-30 14:26	R E G D
dataclasses.py	48.802 KB	-rw-r--r--	2021-08-30 14:26	R E G D
datetime.py	86.218 KB	-rw-r--r--	2021-08-30 14:26	R E G D
decimal.py	0.313 KB	-rw-r--r--	2021-08-30 14:26	R E G D
difflib.py	82.088 KB	-rw-r--r--	2021-08-30 14:26	R E G D
dis.py	20.088 KB	-rw-r--r--	2021-08-30 14:26	R E G D
doctest.py	102.093 KB	-rw-r--r--	2021-08-30 14:26	R E G D
dummy_threading.py	2.749 KB	-rw-r--r--	2021-08-30 14:26	R E G D
enum.py	37.242 KB	-rw-r--r--	2021-08-30 14:26	R E G D
filecmp.py	9.6 KB	-rw-r--r--	2021-08-30 14:26	R E G D
fileinput.py	14.364 KB	-rw-r--r--	2021-08-30 14:26	R E G D
fnmatch.py	3.983 KB	-rw-r--r--	2021-08-30 14:26	R E G D
formatter.py	14.788 KB	-rw-r--r--	2021-08-30 14:26	R E G D
fractions.py	23.759 KB	-rw-r--r--	2021-08-30 14:26	R E G D
ftplib.py	34.306 KB	-rw-r--r--	2021-08-30 14:26	R E G D
functools.py	36.529 KB	-rw-r--r--	2021-08-30 14:26	R E G D
genericpath.py	4.858 KB	-rw-r--r--	2021-08-30 14:26	R E G D
getopt.py	7.313 KB	-rw-r--r--	2021-08-30 14:26	R E G D
getpass.py	5.854 KB	-rw-r--r--	2021-08-30 14:26	R E G D
gettext.py	26.502 KB	-rw-r--r--	2021-08-30 14:26	R E G D
glob.py	5.563 KB	-rw-r--r--	2021-08-30 14:26	R E G D
gzip.py	20.911 KB	-rw-r--r--	2021-08-30 14:26	R E G D
hashlib.py	9.502 KB	-rw-r--r--	2021-08-30 14:26	R E G D
heapq.py	22.341 KB	-rw-r--r--	2021-08-30 14:26	R E G D
hmac.py	6.474 KB	-rw-r--r--	2021-08-30 14:26	R E G D
imaplib.py	52.35 KB	-rw-r--r--	2021-08-30 14:26	R E G D
imghdr.py	3.719 KB	-rw-r--r--	2021-08-30 14:26	R E G D
imp.py	10.289 KB	-rw-r--r--	2021-08-30 14:26	R E G D
inspect.py	115.771 KB	-rw-r--r--	2021-08-30 14:26	R E G D
io.py	3.458 KB	-rw-r--r--	2021-08-30 14:26	R E G D
ipaddress.py	69.965 KB	-rw-r--r--	2021-08-30 14:26	R E G D
keyword.py	0.923 KB	-rw-r--r--	2021-08-30 14:26	R E G D
linecache.py	5.205 KB	-rw-r--r--	2021-08-30 14:26	R E G D
locale.py	76.358 KB	-rw-r--r--	2021-08-30 14:26	R E G D
lzma.py	12.679 KB	-rw-r--r--	2021-08-30 14:26	R E G D
mailbox.py	76.817 KB	-rw-r--r--	2021-08-30 14:26	R E G D
mailcap.py	7.914 KB	-rw-r--r--	2021-08-30 14:26	R E G D
mimetypes.py	21.156 KB	-rw-r--r--	2021-08-30 14:26	R E G D
modulefinder.py	23.857 KB	-rw-r--r--	2021-08-30 14:26	R E G D
netrc.py	5.436 KB	-rw-r--r--	2021-08-30 14:26	R E G D
nntplib.py	42.247 KB	-rw-r--r--	2021-08-30 14:26	R E G D
ntpath.py	27.084 KB	-rw-r--r--	2021-08-30 14:26	R E G D
nturl2path.py	2.819 KB	-rw-r--r--	2021-08-30 14:26	R E G D
numbers.py	10.004 KB	-rw-r--r--	2021-08-30 14:26	R E G D
opcode.py	5.672 KB	-rw-r--r--	2021-08-30 14:26	R E G D
operator.py	10.46 KB	-rw-r--r--	2021-08-30 14:26	R E G D
optparse.py	58.954 KB	-rw-r--r--	2021-08-30 14:26	R E G D
os.py	38.081 KB	-rw-r--r--	2021-08-30 14:26	R E G D
pathlib.py	51.377 KB	-rw-r--r--	2021-08-30 14:26	R E G D
pdb.py	61.28 KB	-rwxr-xr-x	2021-08-30 14:26	R E G D
pickle.py	62.956 KB	-rw-r--r--	2021-08-30 14:26	R E G D
pickletools.py	91.295 KB	-rw-r--r--	2021-08-30 14:26	R E G D
pipes.py	8.707 KB	-rw-r--r--	2021-08-30 14:26	R E G D
pkgutil.py	20.996 KB	-rw-r--r--	2021-08-30 14:26	R E G D
platform.py	39.49 KB	-rwxr-xr-x	2021-08-30 14:26	R E G D
plistlib.py	31.465 KB	-rw-r--r--	2021-08-30 14:26	R E G D
poplib.py	14.724 KB	-rw-r--r--	2021-08-30 14:26	R E G D
posixpath.py	15.261 KB	-rw-r--r--	2021-08-30 14:26	R E G D
pprint.py	20.98 KB	-rw-r--r--	2021-08-30 14:26	R E G D
profile.py	22.995 KB	-rwxr-xr-x	2021-08-30 14:26	R E G D
pstats.py	26.704 KB	-rw-r--r--	2021-08-30 14:26	R E G D
pty.py	4.694 KB	-rw-r--r--	2021-08-30 14:26	R E G D
py_compile.py	8.011 KB	-rw-r--r--	2022-04-22 10:10	R E G D
pyclbr.py	14.897 KB	-rw-r--r--	2021-08-30 14:26	R E G D
pydoc.py	104.199 KB	-rw-r--r--	2022-04-22 10:25	R E G D
queue.py	11.09 KB	-rw-r--r--	2021-08-30 14:26	R E G D
quopri.py	7.095 KB	-rwxr-xr-x	2021-08-30 14:26	R E G D
random.py	28.127 KB	-rw-r--r--	2021-08-30 14:26	R E G D
re.py	15.489 KB	-rw-r--r--	2021-08-30 14:26	R E G D
reprlib.py	5.144 KB	-rw-r--r--	2021-08-30 14:26	R E G D
rlcompleter.py	6.931 KB	-rw-r--r--	2021-08-30 14:26	R E G D
runpy.py	11.77 KB	-rw-r--r--	2021-08-30 14:26	R E G D
sched.py	6.291 KB	-rw-r--r--	2021-08-30 14:26	R E G D
secrets.py	1.99 KB	-rw-r--r--	2021-08-30 14:26	R E G D
selectors.py	18.126 KB	-rw-r--r--	2021-08-30 14:26	R E G D
shelve.py	8.327 KB	-rw-r--r--	2021-08-30 14:26	R E G D
shlex.py	13.013 KB	-rw-r--r--	2021-08-30 14:26	R E G D
shutil.py	50.268 KB	-rw-r--r--	2021-08-30 14:26	R E G D
signal.py	2.22 KB	-rw-r--r--	2021-08-30 14:26	R E G D
site.py	21.091 KB	-rw-r--r--	2022-04-22 10:10	R E G D
smtpd.py	33.908 KB	-rwxr-xr-x	2021-08-30 14:26	R E G D
smtplib.py	43.959 KB	-rwxr-xr-x	2021-08-30 14:26	R E G D
sndhdr.py	6.933 KB	-rw-r--r--	2021-08-30 14:26	R E G D
socket.py	34.417 KB	-rw-r--r--	2021-08-30 14:26	R E G D
socketserver.py	26.656 KB	-rw-r--r--	2021-08-30 14:26	R E G D
sre_compile.py	26.069 KB	-rw-r--r--	2021-08-30 14:26	R E G D
sre_constants.py	6.986 KB	-rw-r--r--	2021-08-30 14:26	R E G D
sre_parse.py	39.287 KB	-rw-r--r--	2021-08-30 14:26	R E G D
ssl.py	49.57 KB	-rw-r--r--	2021-08-30 14:26	R E G D
stat.py	5.356 KB	-rw-r--r--	2021-08-30 14:26	R E G D
statistics.py	38.76 KB	-rw-r--r--	2021-08-30 14:26	R E G D
string.py	10.288 KB	-rw-r--r--	2021-08-30 14:26	R E G D
stringprep.py	12.614 KB	-rw-r--r--	2021-08-30 14:26	R E G D
struct.py	0.251 KB	-rw-r--r--	2021-08-30 14:26	R E G D
subprocess.py	75.518 KB	-rw-r--r--	2021-08-30 14:26	R E G D
sunau.py	17.944 KB	-rw-r--r--	2021-08-30 14:26	R E G D
symbol.py	2.06 KB	-rw-r--r--	2022-04-22 10:13	R E G D
symtable.py	7.833 KB	-rw-r--r--	2021-08-30 14:26	R E G D
sysconfig.py	24.313 KB	-rw-r--r--	2022-04-22 10:24	R E G D
tabnanny.py	11.151 KB	-rwxr-xr-x	2021-08-30 14:26	R E G D
tarfile.py	91.739 KB	-rwxr-xr-x	2021-08-30 14:26	R E G D
telnetlib.py	22.709 KB	-rw-r--r--	2021-08-30 14:26	R E G D
tempfile.py	26.892 KB	-rw-r--r--	2021-08-30 14:26	R E G D
textwrap.py	18.952 KB	-rw-r--r--	2021-08-30 14:26	R E G D
this.py	0.979 KB	-rw-r--r--	2021-08-30 14:26	R E G D
threading.py	49.629 KB	-rw-r--r--	2021-08-30 14:26	R E G D
timeit.py	13.177 KB	-rwxr-xr-x	2021-08-30 14:26	R E G D
token.py	2.313 KB	-rw-r--r--	2021-08-30 14:26	R E G D
tokenize.py	25.235 KB	-rw-r--r--	2021-08-30 14:26	R E G D
trace.py	29.171 KB	-rwxr-xr-x	2021-08-30 14:26	R E G D
traceback.py	23.058 KB	-rw-r--r--	2021-08-30 14:26	R E G D
tracemalloc.py	16.676 KB	-rw-r--r--	2021-08-30 14:26	R E G D
tty.py	0.858 KB	-rw-r--r--	2021-08-30 14:26	R E G D
types.py	9.485 KB	-rw-r--r--	2021-08-30 14:26	R E G D
typing.py	67.346 KB	-rw-r--r--	2021-08-30 14:26	R E G D
uu.py	6.807 KB	-rwxr-xr-x	2021-08-30 14:26	R E G D
uuid.py	29.752 KB	-rw-r--r--	2021-08-30 14:26	R E G D
warnings.py	19.227 KB	-rw-r--r--	2021-08-30 14:26	R E G D
wave.py	17.803 KB	-rw-r--r--	2021-08-30 14:26	R E G D
weakref.py	20.886 KB	-rw-r--r--	2021-08-30 14:26	R E G D
webbrowser.py	23.531 KB	-rwxr-xr-x	2021-08-30 14:26	R E G D
xdrlib.py	5.774 KB	-rw-r--r--	2021-08-30 14:26	R E G D
zipapp.py	7.358 KB	-rw-r--r--	2021-08-30 14:26	R E G D
zipfile.py	85.672 KB	-rw-r--r--	2021-08-30 14:26	R E G D
zipimport.py	30.044 KB	-rw-r--r--	2021-08-30 14:26	R E G D
REQUEST EXIT

""" Basic statistics module. This module provides functions for calculating statistics of data, including averages, variance, and standard deviation. Calculating averages -------------------- ================== ================================================== Function Description ================== ================================================== mean Arithmetic mean (average) of data. fmean Fast, floating point arithmetic mean. geometric_mean Geometric mean of data. harmonic_mean Harmonic mean of data. median Median (middle value) of data. median_low Low median of data. median_high High median of data. median_grouped Median, or 50th percentile, of grouped data. mode Mode (most common value) of data. multimode List of modes (most common values of data). quantiles Divide data into intervals with equal probability. ================== ================================================== Calculate the arithmetic mean ("the average") of data: >>> mean([-1.0, 2.5, 3.25, 5.75]) 2.625 Calculate the standard median of discrete data: >>> median([2, 3, 4, 5]) 3.5 Calculate the median, or 50th percentile, of data grouped into class intervals centred on the data values provided. E.g. if your data points are rounded to the nearest whole number: >>> median_grouped([2, 2, 3, 3, 3, 4]) #doctest: +ELLIPSIS 2.8333333333... This should be interpreted in this way: you have two data points in the class interval 1.5-2.5, three data points in the class interval 2.5-3.5, and one in the class interval 3.5-4.5. The median of these data points is 2.8333... Calculating variability or spread --------------------------------- ================== ============================================= Function Description ================== ============================================= pvariance Population variance of data. variance Sample variance of data. pstdev Population standard deviation of data. stdev Sample standard deviation of data. ================== ============================================= Calculate the standard deviation of sample data: >>> stdev([2.5, 3.25, 5.5, 11.25, 11.75]) #doctest: +ELLIPSIS 4.38961843444... If you have previously calculated the mean, you can pass it as the optional second argument to the four "spread" functions to avoid recalculating it: >>> data = [1, 2, 2, 4, 4, 4, 5, 6] >>> mu = mean(data) >>> pvariance(data, mu) 2.5 Exceptions ---------- A single exception is defined: StatisticsError is a subclass of ValueError. """ __all__ = [ 'NormalDist', 'StatisticsError', 'fmean', 'geometric_mean', 'harmonic_mean', 'mean', 'median', 'median_grouped', 'median_high', 'median_low', 'mode', 'multimode', 'pstdev', 'pvariance', 'quantiles', 'stdev', 'variance', ] import math import numbers import random from fractions import Fraction from decimal import Decimal from itertools import groupby from bisect import bisect_left, bisect_right from math import hypot, sqrt, fabs, exp, erf, tau, log, fsum from operator import itemgetter from collections import Counter # === Exceptions === class StatisticsError(ValueError): pass # === Private utilities === def _sum(data, start=0): """_sum(data [, start]) -> (type, sum, count) Return a high-precision sum of the given numeric data as a fraction, together with the type to be converted to and the count of items. If optional argument ``start`` is given, it is added to the total. If ``data`` is empty, ``start`` (defaulting to 0) is returned. Examples -------- >>> _sum([3, 2.25, 4.5, -0.5, 1.0], 0.75) (, Fraction(11, 1), 5) Some sources of round-off error will be avoided: # Built-in sum returns zero. >>> _sum([1e50, 1, -1e50] * 1000) (, Fraction(1000, 1), 3000) Fractions and Decimals are also supported: >>> from fractions import Fraction as F >>> _sum([F(2, 3), F(7, 5), F(1, 4), F(5, 6)]) (, Fraction(63, 20), 4) >>> from decimal import Decimal as D >>> data = [D("0.1375"), D("0.2108"), D("0.3061"), D("0.0419")] >>> _sum(data) (, Fraction(6963, 10000), 4) Mixed types are currently treated as an error, except that int is allowed. """ count = 0 n, d = _exact_ratio(start) partials = {d: n} partials_get = partials.get T = _coerce(int, type(start)) for typ, values in groupby(data, type): T = _coerce(T, typ) # or raise TypeError for n,d in map(_exact_ratio, values): count += 1 partials[d] = partials_get(d, 0) + n if None in partials: # The sum will be a NAN or INF. We can ignore all the finite # partials, and just look at this special one. total = partials[None] assert not _isfinite(total) else: # Sum all the partial sums using builtin sum. # FIXME is this faster if we sum them in order of the denominator? total = sum(Fraction(n, d) for d, n in sorted(partials.items())) return (T, total, count) def _isfinite(x): try: return x.is_finite() # Likely a Decimal. except AttributeError: return math.isfinite(x) # Coerces to float first. def _coerce(T, S): """Coerce types T and S to a common type, or raise TypeError. Coercion rules are currently an implementation detail. See the CoerceTest test class in test_statistics for details. """ # See http://bugs.python.org/issue24068. assert T is not bool, "initial type T is bool" # If the types are the same, no need to coerce anything. Put this # first, so that the usual case (no coercion needed) happens as soon # as possible. if T is S: return T # Mixed int & other coerce to the other type. if S is int or S is bool: return T if T is int: return S # If one is a (strict) subclass of the other, coerce to the subclass. if issubclass(S, T): return S if issubclass(T, S): return T # Ints coerce to the other type. if issubclass(T, int): return S if issubclass(S, int): return T # Mixed fraction & float coerces to float (or float subclass). if issubclass(T, Fraction) and issubclass(S, float): return S if issubclass(T, float) and issubclass(S, Fraction): return T # Any other combination is disallowed. msg = "don't know how to coerce %s and %s" raise TypeError(msg % (T.__name__, S.__name__)) def _exact_ratio(x): """Return Real number x to exact (numerator, denominator) pair. >>> _exact_ratio(0.25) (1, 4) x is expected to be an int, Fraction, Decimal or float. """ try: # Optimise the common case of floats. We expect that the most often # used numeric type will be builtin floats, so try to make this as # fast as possible. if type(x) is float or type(x) is Decimal: return x.as_integer_ratio() try: # x may be an int, Fraction, or Integral ABC. return (x.numerator, x.denominator) except AttributeError: try: # x may be a float or Decimal subclass. return x.as_integer_ratio() except AttributeError: # Just give up? pass except (OverflowError, ValueError): # float NAN or INF. assert not _isfinite(x) return (x, None) msg = "can't convert type '{}' to numerator/denominator" raise TypeError(msg.format(type(x).__name__)) def _convert(value, T): """Convert value to given numeric type T.""" if type(value) is T: # This covers the cases where T is Fraction, or where value is # a NAN or INF (Decimal or float). return value if issubclass(T, int) and value.denominator != 1: T = float try: # FIXME: what do we do if this overflows? return T(value) except TypeError: if issubclass(T, Decimal): return T(value.numerator)/T(value.denominator) else: raise def _find_lteq(a, x): 'Locate the leftmost value exactly equal to x' i = bisect_left(a, x) if i != len(a) and a[i] == x: return i raise ValueError def _find_rteq(a, l, x): 'Locate the rightmost value exactly equal to x' i = bisect_right(a, x, lo=l) if i != (len(a)+1) and a[i-1] == x: return i-1 raise ValueError def _fail_neg(values, errmsg='negative value'): """Iterate over values, failing if any are less than zero.""" for x in values: if x < 0: raise StatisticsError(errmsg) yield x # === Measures of central tendency (averages) === def mean(data): """Return the sample arithmetic mean of data. >>> mean([1, 2, 3, 4, 4]) 2.8 >>> from fractions import Fraction as F >>> mean([F(3, 7), F(1, 21), F(5, 3), F(1, 3)]) Fraction(13, 21) >>> from decimal import Decimal as D >>> mean([D("0.5"), D("0.75"), D("0.625"), D("0.375")]) Decimal('0.5625') If ``data`` is empty, StatisticsError will be raised. """ if iter(data) is data: data = list(data) n = len(data) if n < 1: raise StatisticsError('mean requires at least one data point') T, total, count = _sum(data) assert count == n return _convert(total/n, T) def fmean(data): """Convert data to floats and compute the arithmetic mean. This runs faster than the mean() function and it always returns a float. If the input dataset is empty, it raises a StatisticsError. >>> fmean([3.5, 4.0, 5.25]) 4.25 """ try: n = len(data) except TypeError: # Handle iterators that do not define __len__(). n = 0 def count(iterable): nonlocal n for n, x in enumerate(iterable, start=1): yield x total = fsum(count(data)) else: total = fsum(data) try: return total / n except ZeroDivisionError: raise StatisticsError('fmean requires at least one data point') from None def geometric_mean(data): """Convert data to floats and compute the geometric mean. Raises a StatisticsError if the input dataset is empty, if it contains a zero, or if it contains a negative value. No special efforts are made to achieve exact results. (However, this may change in the future.) >>> round(geometric_mean([54, 24, 36]), 9) 36.0 """ try: return exp(fmean(map(log, data))) except ValueError: raise StatisticsError('geometric mean requires a non-empty dataset ' ' containing positive numbers') from None def harmonic_mean(data): """Return the harmonic mean of data. The harmonic mean, sometimes called the subcontrary mean, is the reciprocal of the arithmetic mean of the reciprocals of the data, and is often appropriate when averaging quantities which are rates or ratios, for example speeds. Example: Suppose an investor purchases an equal value of shares in each of three companies, with P/E (price/earning) ratios of 2.5, 3 and 10. What is the average P/E ratio for the investor's portfolio? >>> harmonic_mean([2.5, 3, 10]) # For an equal investment portfolio. 3.6 Using the arithmetic mean would give an average of about 5.167, which is too high. If ``data`` is empty, or any element is less than zero, ``harmonic_mean`` will raise ``StatisticsError``. """ # For a justification for using harmonic mean for P/E ratios, see # http://fixthepitch.pellucid.com/comps-analysis-the-missing-harmony-of-summary-statistics/ # http://papers.ssrn.com/sol3/papers.cfm?abstract_id=2621087 if iter(data) is data: data = list(data) errmsg = 'harmonic mean does not support negative values' n = len(data) if n < 1: raise StatisticsError('harmonic_mean requires at least one data point') elif n == 1: x = data[0] if isinstance(x, (numbers.Real, Decimal)): if x < 0: raise StatisticsError(errmsg) return x else: raise TypeError('unsupported type') try: T, total, count = _sum(1/x for x in _fail_neg(data, errmsg)) except ZeroDivisionError: return 0 assert count == n return _convert(n/total, T) # FIXME: investigate ways to calculate medians without sorting? Quickselect? def median(data): """Return the median (middle value) of numeric data. When the number of data points is odd, return the middle data point. When the number of data points is even, the median is interpolated by taking the average of the two middle values: >>> median([1, 3, 5]) 3 >>> median([1, 3, 5, 7]) 4.0 """ data = sorted(data) n = len(data) if n == 0: raise StatisticsError("no median for empty data") if n%2 == 1: return data[n//2] else: i = n//2 return (data[i - 1] + data[i])/2 def median_low(data): """Return the low median of numeric data. When the number of data points is odd, the middle value is returned. When it is even, the smaller of the two middle values is returned. >>> median_low([1, 3, 5]) 3 >>> median_low([1, 3, 5, 7]) 3 """ data = sorted(data) n = len(data) if n == 0: raise StatisticsError("no median for empty data") if n%2 == 1: return data[n//2] else: return data[n//2 - 1] def median_high(data): """Return the high median of data. When the number of data points is odd, the middle value is returned. When it is even, the larger of the two middle values is returned. >>> median_high([1, 3, 5]) 3 >>> median_high([1, 3, 5, 7]) 5 """ data = sorted(data) n = len(data) if n == 0: raise StatisticsError("no median for empty data") return data[n//2] def median_grouped(data, interval=1): """Return the 50th percentile (median) of grouped continuous data. >>> median_grouped([1, 2, 2, 3, 4, 4, 4, 4, 4, 5]) 3.7 >>> median_grouped([52, 52, 53, 54]) 52.5 This calculates the median as the 50th percentile, and should be used when your data is continuous and grouped. In the above example, the values 1, 2, 3, etc. actually represent the midpoint of classes 0.5-1.5, 1.5-2.5, 2.5-3.5, etc. The middle value falls somewhere in class 3.5-4.5, and interpolation is used to estimate it. Optional argument ``interval`` represents the class interval, and defaults to 1. Changing the class interval naturally will change the interpolated 50th percentile value: >>> median_grouped([1, 3, 3, 5, 7], interval=1) 3.25 >>> median_grouped([1, 3, 3, 5, 7], interval=2) 3.5 This function does not check whether the data points are at least ``interval`` apart. """ data = sorted(data) n = len(data) if n == 0: raise StatisticsError("no median for empty data") elif n == 1: return data[0] # Find the value at the midpoint. Remember this corresponds to the # centre of the class interval. x = data[n//2] for obj in (x, interval): if isinstance(obj, (str, bytes)): raise TypeError('expected number but got %r' % obj) try: L = x - interval/2 # The lower limit of the median interval. except TypeError: # Mixed type. For now we just coerce to float. L = float(x) - float(interval)/2 # Uses bisection search to search for x in data with log(n) time complexity # Find the position of leftmost occurrence of x in data l1 = _find_lteq(data, x) # Find the position of rightmost occurrence of x in data[l1...len(data)] # Assuming always l1 <= l2 l2 = _find_rteq(data, l1, x) cf = l1 f = l2 - l1 + 1 return L + interval*(n/2 - cf)/f def mode(data): """Return the most common data point from discrete or nominal data. ``mode`` assumes discrete data, and returns a single value. This is the standard treatment of the mode as commonly taught in schools: >>> mode([1, 1, 2, 3, 3, 3, 3, 4]) 3 This also works with nominal (non-numeric) data: >>> mode(["red", "blue", "blue", "red", "green", "red", "red"]) 'red' If there are multiple modes with same frequency, return the first one encountered: >>> mode(['red', 'red', 'green', 'blue', 'blue']) 'red' If *data* is empty, ``mode``, raises StatisticsError. """ data = iter(data) pairs = Counter(data).most_common(1) try: return pairs[0][0] except IndexError: raise StatisticsError('no mode for empty data') from None def multimode(data): """Return a list of the most frequently occurring values. Will return more than one result if there are multiple modes or an empty list if *data* is empty. >>> multimode('aabbbbbbbbcc') ['b'] >>> multimode('aabbbbccddddeeffffgg') ['b', 'd', 'f'] >>> multimode('') [] """ counts = Counter(iter(data)).most_common() maxcount, mode_items = next(groupby(counts, key=itemgetter(1)), (0, [])) return list(map(itemgetter(0), mode_items)) # Notes on methods for computing quantiles # ---------------------------------------- # # There is no one perfect way to compute quantiles. Here we offer # two methods that serve common needs. Most other packages # surveyed offered at least one or both of these two, making them # "standard" in the sense of "widely-adopted and reproducible". # They are also easy to explain, easy to compute manually, and have # straight-forward interpretations that aren't surprising. # The default method is known as "R6", "PERCENTILE.EXC", or "expected # value of rank order statistics". The alternative method is known as # "R7", "PERCENTILE.INC", or "mode of rank order statistics". # For sample data where there is a positive probability for values # beyond the range of the data, the R6 exclusive method is a # reasonable choice. Consider a random sample of nine values from a # population with a uniform distribution from 0.0 to 100.0. The # distribution of the third ranked sample point is described by # betavariate(alpha=3, beta=7) which has mode=0.250, median=0.286, and # mean=0.300. Only the latter (which corresponds with R6) gives the # desired cut point with 30% of the population falling below that # value, making it comparable to a result from an inv_cdf() function. # The R6 exclusive method is also idempotent. # For describing population data where the end points are known to # be included in the data, the R7 inclusive method is a reasonable # choice. Instead of the mean, it uses the mode of the beta # distribution for the interior points. Per Hyndman & Fan, "One nice # property is that the vertices of Q7(p) divide the range into n - 1 # intervals, and exactly 100p% of the intervals lie to the left of # Q7(p) and 100(1 - p)% of the intervals lie to the right of Q7(p)." # If needed, other methods could be added. However, for now, the # position is that fewer options make for easier choices and that # external packages can be used for anything more advanced. def quantiles(data, *, n=4, method='exclusive'): """Divide *data* into *n* continuous intervals with equal probability. Returns a list of (n - 1) cut points separating the intervals. Set *n* to 4 for quartiles (the default). Set *n* to 10 for deciles. Set *n* to 100 for percentiles which gives the 99 cuts points that separate *data* in to 100 equal sized groups. The *data* can be any iterable containing sample. The cut points are linearly interpolated between data points. If *method* is set to *inclusive*, *data* is treated as population data. The minimum value is treated as the 0th percentile and the maximum value is treated as the 100th percentile. """ if n < 1: raise StatisticsError('n must be at least 1') data = sorted(data) ld = len(data) if ld < 2: raise StatisticsError('must have at least two data points') if method == 'inclusive': m = ld - 1 result = [] for i in range(1, n): j = i * m // n delta = i*m - j*n interpolated = (data[j] * (n - delta) + data[j+1] * delta) / n result.append(interpolated) return result if method == 'exclusive': m = ld + 1 result = [] for i in range(1, n): j = i * m // n # rescale i to m/n j = 1 if j < 1 else ld-1 if j > ld-1 else j # clamp to 1 .. ld-1 delta = i*m - j*n # exact integer math interpolated = (data[j-1] * (n - delta) + data[j] * delta) / n result.append(interpolated) return result raise ValueError(f'Unknown method: {method!r}') # === Measures of spread === # See http://mathworld.wolfram.com/Variance.html # http://mathworld.wolfram.com/SampleVariance.html # http://en.wikipedia.org/wiki/Algorithms_for_calculating_variance # # Under no circumstances use the so-called "computational formula for # variance", as that is only suitable for hand calculations with a small # amount of low-precision data. It has terrible numeric properties. # # See a comparison of three computational methods here: # http://www.johndcook.com/blog/2008/09/26/comparing-three-methods-of-computing-standard-deviation/ def _ss(data, c=None): """Return sum of square deviations of sequence data. If ``c`` is None, the mean is calculated in one pass, and the deviations from the mean are calculated in a second pass. Otherwise, deviations are calculated from ``c`` as given. Use the second case with care, as it can lead to garbage results. """ if c is not None: T, total, count = _sum((x-c)**2 for x in data) return (T, total) c = mean(data) T, total, count = _sum((x-c)**2 for x in data) # The following sum should mathematically equal zero, but due to rounding # error may not. U, total2, count2 = _sum((x-c) for x in data) assert T == U and count == count2 total -= total2**2/len(data) assert not total < 0, 'negative sum of square deviations: %f' % total return (T, total) def variance(data, xbar=None): """Return the sample variance of data. data should be an iterable of Real-valued numbers, with at least two values. The optional argument xbar, if given, should be the mean of the data. If it is missing or None, the mean is automatically calculated. Use this function when your data is a sample from a population. To calculate the variance from the entire population, see ``pvariance``. Examples: >>> data = [2.75, 1.75, 1.25, 0.25, 0.5, 1.25, 3.5] >>> variance(data) 1.3720238095238095 If you have already calculated the mean of your data, you can pass it as the optional second argument ``xbar`` to avoid recalculating it: >>> m = mean(data) >>> variance(data, m) 1.3720238095238095 This function does not check that ``xbar`` is actually the mean of ``data``. Giving arbitrary values for ``xbar`` may lead to invalid or impossible results. Decimals and Fractions are supported: >>> from decimal import Decimal as D >>> variance([D("27.5"), D("30.25"), D("30.25"), D("34.5"), D("41.75")]) Decimal('31.01875') >>> from fractions import Fraction as F >>> variance([F(1, 6), F(1, 2), F(5, 3)]) Fraction(67, 108) """ if iter(data) is data: data = list(data) n = len(data) if n < 2: raise StatisticsError('variance requires at least two data points') T, ss = _ss(data, xbar) return _convert(ss/(n-1), T) def pvariance(data, mu=None): """Return the population variance of ``data``. data should be a sequence or iterable of Real-valued numbers, with at least one value. The optional argument mu, if given, should be the mean of the data. If it is missing or None, the mean is automatically calculated. Use this function to calculate the variance from the entire population. To estimate the variance from a sample, the ``variance`` function is usually a better choice. Examples: >>> data = [0.0, 0.25, 0.25, 1.25, 1.5, 1.75, 2.75, 3.25] >>> pvariance(data) 1.25 If you have already calculated the mean of the data, you can pass it as the optional second argument to avoid recalculating it: >>> mu = mean(data) >>> pvariance(data, mu) 1.25 Decimals and Fractions are supported: >>> from decimal import Decimal as D >>> pvariance([D("27.5"), D("30.25"), D("30.25"), D("34.5"), D("41.75")]) Decimal('24.815') >>> from fractions import Fraction as F >>> pvariance([F(1, 4), F(5, 4), F(1, 2)]) Fraction(13, 72) """ if iter(data) is data: data = list(data) n = len(data) if n < 1: raise StatisticsError('pvariance requires at least one data point') T, ss = _ss(data, mu) return _convert(ss/n, T) def stdev(data, xbar=None): """Return the square root of the sample variance. See ``variance`` for arguments and other details. >>> stdev([1.5, 2.5, 2.5, 2.75, 3.25, 4.75]) 1.0810874155219827 """ var = variance(data, xbar) try: return var.sqrt() except AttributeError: return math.sqrt(var) def pstdev(data, mu=None): """Return the square root of the population variance. See ``pvariance`` for arguments and other details. >>> pstdev([1.5, 2.5, 2.5, 2.75, 3.25, 4.75]) 0.986893273527251 """ var = pvariance(data, mu) try: return var.sqrt() except AttributeError: return math.sqrt(var) ## Normal Distribution ##################################################### def _normal_dist_inv_cdf(p, mu, sigma): # There is no closed-form solution to the inverse CDF for the normal # distribution, so we use a rational approximation instead: # Wichura, M.J. (1988). "Algorithm AS241: The Percentage Points of the # Normal Distribution". Applied Statistics. Blackwell Publishing. 37 # (3): 477–484. doi:10.2307/2347330. JSTOR 2347330. q = p - 0.5 if fabs(q) <= 0.425: r = 0.180625 - q * q # Hash sum: 55.88319_28806_14901_4439 num = (((((((2.50908_09287_30122_6727e+3 * r + 3.34305_75583_58812_8105e+4) * r + 6.72657_70927_00870_0853e+4) * r + 4.59219_53931_54987_1457e+4) * r + 1.37316_93765_50946_1125e+4) * r + 1.97159_09503_06551_4427e+3) * r + 1.33141_66789_17843_7745e+2) * r + 3.38713_28727_96366_6080e+0) * q den = (((((((5.22649_52788_52854_5610e+3 * r + 2.87290_85735_72194_2674e+4) * r + 3.93078_95800_09271_0610e+4) * r + 2.12137_94301_58659_5867e+4) * r + 5.39419_60214_24751_1077e+3) * r + 6.87187_00749_20579_0830e+2) * r + 4.23133_30701_60091_1252e+1) * r + 1.0) x = num / den return mu + (x * sigma) r = p if q <= 0.0 else 1.0 - p r = sqrt(-log(r)) if r <= 5.0: r = r - 1.6 # Hash sum: 49.33206_50330_16102_89036 num = (((((((7.74545_01427_83414_07640e-4 * r + 2.27238_44989_26918_45833e-2) * r + 2.41780_72517_74506_11770e-1) * r + 1.27045_82524_52368_38258e+0) * r + 3.64784_83247_63204_60504e+0) * r + 5.76949_72214_60691_40550e+0) * r + 4.63033_78461_56545_29590e+0) * r + 1.42343_71107_49683_57734e+0) den = (((((((1.05075_00716_44416_84324e-9 * r + 5.47593_80849_95344_94600e-4) * r + 1.51986_66563_61645_71966e-2) * r + 1.48103_97642_74800_74590e-1) * r + 6.89767_33498_51000_04550e-1) * r + 1.67638_48301_83803_84940e+0) * r + 2.05319_16266_37758_82187e+0) * r + 1.0) else: r = r - 5.0 # Hash sum: 47.52583_31754_92896_71629 num = (((((((2.01033_43992_92288_13265e-7 * r + 2.71155_55687_43487_57815e-5) * r + 1.24266_09473_88078_43860e-3) * r + 2.65321_89526_57612_30930e-2) * r + 2.96560_57182_85048_91230e-1) * r + 1.78482_65399_17291_33580e+0) * r + 5.46378_49111_64114_36990e+0) * r + 6.65790_46435_01103_77720e+0) den = (((((((2.04426_31033_89939_78564e-15 * r + 1.42151_17583_16445_88870e-7) * r + 1.84631_83175_10054_68180e-5) * r + 7.86869_13114_56132_59100e-4) * r + 1.48753_61290_85061_48525e-2) * r + 1.36929_88092_27358_05310e-1) * r + 5.99832_20655_58879_37690e-1) * r + 1.0) x = num / den if q < 0.0: x = -x return mu + (x * sigma) class NormalDist: "Normal distribution of a random variable" # https://en.wikipedia.org/wiki/Normal_distribution # https://en.wikipedia.org/wiki/Variance#Properties __slots__ = { '_mu': 'Arithmetic mean of a normal distribution', '_sigma': 'Standard deviation of a normal distribution', } def __init__(self, mu=0.0, sigma=1.0): "NormalDist where mu is the mean and sigma is the standard deviation." if sigma < 0.0: raise StatisticsError('sigma must be non-negative') self._mu = float(mu) self._sigma = float(sigma) @classmethod def from_samples(cls, data): "Make a normal distribution instance from sample data." if not isinstance(data, (list, tuple)): data = list(data) xbar = fmean(data) return cls(xbar, stdev(data, xbar)) def samples(self, n, *, seed=None): "Generate *n* samples for a given mean and standard deviation." gauss = random.gauss if seed is None else random.Random(seed).gauss mu, sigma = self._mu, self._sigma return [gauss(mu, sigma) for i in range(n)] def pdf(self, x): "Probability density function. P(x <= X < x+dx) / dx" variance = self._sigma ** 2.0 if not variance: raise StatisticsError('pdf() not defined when sigma is zero') return exp((x - self._mu)**2.0 / (-2.0*variance)) / sqrt(tau*variance) def cdf(self, x): "Cumulative distribution function. P(X <= x)" if not self._sigma: raise StatisticsError('cdf() not defined when sigma is zero') return 0.5 * (1.0 + erf((x - self._mu) / (self._sigma * sqrt(2.0)))) def inv_cdf(self, p): """Inverse cumulative distribution function. x : P(X <= x) = p Finds the value of the random variable such that the probability of the variable being less than or equal to that value equals the given probability. This function is also called the percent point function or quantile function. """ if p <= 0.0 or p >= 1.0: raise StatisticsError('p must be in the range 0.0 < p < 1.0') if self._sigma <= 0.0: raise StatisticsError('cdf() not defined when sigma at or below zero') return _normal_dist_inv_cdf(p, self._mu, self._sigma) def quantiles(self, n=4): """Divide into *n* continuous intervals with equal probability. Returns a list of (n - 1) cut points separating the intervals. Set *n* to 4 for quartiles (the default). Set *n* to 10 for deciles. Set *n* to 100 for percentiles which gives the 99 cuts points that separate the normal distribution in to 100 equal sized groups. """ return [self.inv_cdf(i / n) for i in range(1, n)] def overlap(self, other): """Compute the overlapping coefficient (OVL) between two normal distributions. Measures the agreement between two normal probability distributions. Returns a value between 0.0 and 1.0 giving the overlapping area in the two underlying probability density functions. >>> N1 = NormalDist(2.4, 1.6) >>> N2 = NormalDist(3.2, 2.0) >>> N1.overlap(N2) 0.8035050657330205 """ # See: "The overlapping coefficient as a measure of agreement between # probability distributions and point estimation of the overlap of two # normal densities" -- Henry F. Inman and Edwin L. Bradley Jr # http://dx.doi.org/10.1080/03610928908830127 if not isinstance(other, NormalDist): raise TypeError('Expected another NormalDist instance') X, Y = self, other if (Y._sigma, Y._mu) < (X._sigma, X._mu): # sort to assure commutativity X, Y = Y, X X_var, Y_var = X.variance, Y.variance if not X_var or not Y_var: raise StatisticsError('overlap() not defined when sigma is zero') dv = Y_var - X_var dm = fabs(Y._mu - X._mu) if not dv: return 1.0 - erf(dm / (2.0 * X._sigma * sqrt(2.0))) a = X._mu * Y_var - Y._mu * X_var b = X._sigma * Y._sigma * sqrt(dm**2.0 + dv * log(Y_var / X_var)) x1 = (a + b) / dv x2 = (a - b) / dv return 1.0 - (fabs(Y.cdf(x1) - X.cdf(x1)) + fabs(Y.cdf(x2) - X.cdf(x2))) @property def mean(self): "Arithmetic mean of the normal distribution." return self._mu @property def median(self): "Return the median of the normal distribution" return self._mu @property def mode(self): """Return the mode of the normal distribution The mode is the value x where which the probability density function (pdf) takes its maximum value. """ return self._mu @property def stdev(self): "Standard deviation of the normal distribution." return self._sigma @property def variance(self): "Square of the standard deviation." return self._sigma ** 2.0 def __add__(x1, x2): """Add a constant or another NormalDist instance. If *other* is a constant, translate mu by the constant, leaving sigma unchanged. If *other* is a NormalDist, add both the means and the variances. Mathematically, this works only if the two distributions are independent or if they are jointly normally distributed. """ if isinstance(x2, NormalDist): return NormalDist(x1._mu + x2._mu, hypot(x1._sigma, x2._sigma)) return NormalDist(x1._mu + x2, x1._sigma) def __sub__(x1, x2): """Subtract a constant or another NormalDist instance. If *other* is a constant, translate by the constant mu, leaving sigma unchanged. If *other* is a NormalDist, subtract the means and add the variances. Mathematically, this works only if the two distributions are independent or if they are jointly normally distributed. """ if isinstance(x2, NormalDist): return NormalDist(x1._mu - x2._mu, hypot(x1._sigma, x2._sigma)) return NormalDist(x1._mu - x2, x1._sigma) def __mul__(x1, x2): """Multiply both mu and sigma by a constant. Used for rescaling, perhaps to change measurement units. Sigma is scaled with the absolute value of the constant. """ return NormalDist(x1._mu * x2, x1._sigma * fabs(x2)) def __truediv__(x1, x2): """Divide both mu and sigma by a constant. Used for rescaling, perhaps to change measurement units. Sigma is scaled with the absolute value of the constant. """ return NormalDist(x1._mu / x2, x1._sigma / fabs(x2)) def __pos__(x1): "Return a copy of the instance." return NormalDist(x1._mu, x1._sigma) def __neg__(x1): "Negates mu while keeping sigma the same." return NormalDist(-x1._mu, x1._sigma) __radd__ = __add__ def __rsub__(x1, x2): "Subtract a NormalDist from a constant or another NormalDist." return -(x1 - x2) __rmul__ = __mul__ def __eq__(x1, x2): "Two NormalDist objects are equal if their mu and sigma are both equal." if not isinstance(x2, NormalDist): return NotImplemented return x1._mu == x2._mu and x1._sigma == x2._sigma def __hash__(self): "NormalDist objects hash equal if their mu and sigma are both equal." return hash((self._mu, self._sigma)) def __repr__(self): return f'{type(self).__name__}(mu={self._mu!r}, sigma={self._sigma!r})' # If available, use C implementation try: from _statistics import _normal_dist_inv_cdf except ImportError: pass if __name__ == '__main__': # Show math operations computed analytically in comparsion # to a monte carlo simulation of the same operations from math import isclose from operator import add, sub, mul, truediv from itertools import repeat import doctest g1 = NormalDist(10, 20) g2 = NormalDist(-5, 25) # Test scaling by a constant assert (g1 * 5 / 5).mean == g1.mean assert (g1 * 5 / 5).stdev == g1.stdev n = 100_000 G1 = g1.samples(n) G2 = g2.samples(n) for func in (add, sub): print(f'\nTest {func.__name__} with another NormalDist:') print(func(g1, g2)) print(NormalDist.from_samples(map(func, G1, G2))) const = 11 for func in (add, sub, mul, truediv): print(f'\nTest {func.__name__} with a constant:') print(func(g1, const)) print(NormalDist.from_samples(map(func, G1, repeat(const)))) const = 19 for func in (add, sub, mul): print(f'\nTest constant with {func.__name__}:') print(func(const, g1)) print(NormalDist.from_samples(map(func, repeat(const), G1))) def assert_close(G1, G2): assert isclose(G1.mean, G1.mean, rel_tol=0.01), (G1, G2) assert isclose(G1.stdev, G2.stdev, rel_tol=0.01), (G1, G2) X = NormalDist(-105, 73) Y = NormalDist(31, 47) s = 32.75 n = 100_000 S = NormalDist.from_samples([x + s for x in X.samples(n)]) assert_close(X + s, S) S = NormalDist.from_samples([x - s for x in X.samples(n)]) assert_close(X - s, S) S = NormalDist.from_samples([x * s for x in X.samples(n)]) assert_close(X * s, S) S = NormalDist.from_samples([x / s for x in X.samples(n)]) assert_close(X / s, S) S = NormalDist.from_samples([x + y for x, y in zip(X.samples(n), Y.samples(n))]) assert_close(X + Y, S) S = NormalDist.from_samples([x - y for x, y in zip(X.samples(n), Y.samples(n))]) assert_close(X - Y, S) print(doctest.testmod())