ToC = {
'1. Collections': [List, Dictionary, Set, Tuple, Range, Enumerate, Iterator, Generator],
'2. Types': [Type, String, Regular_Exp, Format, Numbers, Combinatorics, Datetime],
'3. Syntax': [Args, Inline, Import, Decorator, Class, Duck_Types, Enum, Exception],
'4. System': [Exit, Print, Input, Command_Line_Arguments, Open, Path, OS_Commands],
'5. Data': [JSON, Pickle, CSV, SQLite, Bytes, Struct, Array, Memory_View, Deque],
'6. Advanced': [Operator, Match_Stmt, Logging, Introspection, Threading, Coroutines],
'7. Libraries': [Progress_Bar, Plot, Table, Console_App, GUI, Scraping, Web, Profile],
'8. Multimedia': [NumPy, Image, Animation, Audio, Synthesizer, Pygame, Pandas, Plotly]
}
if __name__ == '__main__': # Skips next line if file was imported.
main() # Runs `def main(): ...` function.
<list> = [<el_1>, <el_2>, ...] # Creates new list. Also list(<collection>).
<el> = <list>[index] # First index is 0. Last -1. Allows assignments.
<list> = <list>[<slice>] # Also <list>[from_inclusive : to_exclusive : ±step].
<list>.append(<el>) # Appends element to the end. Also <list> += [<el>].
<list>.extend(<collection>) # Appends elements to the end. Also <list> += <coll>.
<list>.sort() # Sorts elements in ascending order.
<list>.reverse() # Reverses the list in-place.
<list> = sorted(<collection>) # Returns new list with sorted elements.
<iter> = reversed(<list>) # Returns reversed iterator of elements.
<el> = max(<collection>) # Returns largest element. Also min(<el_1>, ...).
<num> = sum(<collection>) # Returns sum of elements. Also math.prod(<coll>).
elementwise_sum = [sum(pair) for pair in zip(list_a, list_b)]
sorted_by_second = sorted(<collection>, key=lambda el: el[1])
sorted_by_both = sorted(<collection>, key=lambda el: (el[1], el[0]))
flatter_list = list(itertools.chain.from_iterable(<list>))
<int> = len(<list>) # Returns number of items. Also works on dict, set and string.
<int> = <list>.count(<el>) # Returns number of occurrences. Also `if <el> in <coll>: ...`.
<int> = <list>.index(<el>) # Returns index of the first occurrence or raises ValueError.
<el> = <list>.pop() # Removes and returns item from the end or at index if passed.
<list>.insert(<int>, <el>) # Inserts item at index and moves the rest to the right.
<list>.remove(<el>) # Removes first occurrence of the item or raises ValueError.
<list>.clear() # Removes all items. Also works on dictionary and set.
<dict> = {key_1: val_1, key_2: val_2, ...} # Use `<dict>[key]` to get or set the value.
<view> = <dict>.keys() # Collection of keys that reflects changes.
<view> = <dict>.values() # Collection of values that reflects changes.
<view> = <dict>.items() # Coll. of key-value tuples that reflects chgs.
value = <dict>.get(key, default=None) # Returns default if key is missing.
value = <dict>.setdefault(key, default=None) # Returns and writes default if key is missing.
<dict> = collections.defaultdict(<type>) # Returns a dict with default value `<type>()`.
<dict> = collections.defaultdict(lambda: 1) # Returns a dict with default value 1.
<dict> = dict(<collection>) # Creates a dict from coll. of key-value pairs.
<dict> = dict(zip(keys, values)) # Creates a dict from two collections.
<dict> = dict.fromkeys(keys [, value]) # Creates a dict from collection of keys.
<dict>.update(<dict>) # Adds items. Replaces ones with matching keys.
value = <dict>.pop(key) # Removes item or raises KeyError if missing.
{k for k, v in <dict>.items() if v == value} # Returns set of keys that point to the value.
{k: v for k, v in <dict>.items() if k in keys} # Filters the dictionary by keys.
>>> from collections import Counter
>>> counter = Counter(['blue', 'blue', 'blue', 'red', 'red'])
>>> counter['yellow'] += 1
>>> print(counter.most_common())
[('blue', 3), ('red', 2), ('yellow', 1)]
<set> = {<el_1>, <el_2>, ...} # Use `set()` for empty set.
<set>.add(<el>) # Or: <set> |= {<el>}
<set>.update(<collection> [, ...]) # Or: <set> |= <set>
<set> = <set>.union(<coll.>) # Or: <set> | <set>
<set> = <set>.intersection(<coll.>) # Or: <set> & <set>
<set> = <set>.difference(<coll.>) # Or: <set> - <set>
<set> = <set>.symmetric_difference(<coll.>) # Or: <set> ^ <set>
<bool> = <set>.issubset(<coll.>) # Or: <set> <= <set>
<bool> = <set>.issuperset(<coll.>) # Or: <set> >= <set>
<el> = <set>.pop() # Raises KeyError if empty.
<set>.remove(<el>) # Raises KeyError if missing.
<set>.discard(<el>) # Doesn't raise an error.
<frozenset> = frozenset(<collection>)
Tuple is an immutable and hashable list.
<tuple> = () # Empty tuple.
<tuple> = (<el>,) # Or: <el>,
<tuple> = (<el_1>, <el_2> [, ...]) # Or: <el_1>, <el_2> [, ...]
Tuple's subclass with named elements.
>>> from collections import namedtuple
>>> Point = namedtuple('Point', 'x y')
>>> p = Point(1, y=2); p
Point(x=1, y=2)
>>> p[0]
1
>>> p.x
1
>>> getattr(p, 'y')
2
Immutable and hashable sequence of integers.
<range> = range(stop) # range(to_exclusive)
<range> = range(start, stop) # range(from_inclusive, to_exclusive)
<range> = range(start, stop, ±step) # range(from_inclusive, to_exclusive, ±step_size)
>>> [i for i in range(3)]
[0, 1, 2]
for i, el in enumerate(<coll>, start=0): # Returns next element and its index on each pass.
...
<iter> = iter(<collection>) # `iter(<iter>)` returns unmodified iterator.
<iter> = iter(<function>, to_exclusive) # A sequence of return values until 'to_exclusive'.
<el> = next(<iter> [, default]) # Raises StopIteration or returns 'default' on end.
<list> = list(<iter>) # Returns a list of iterator's remaining elements.
import itertools as it
<iter> = it.count(start=0, step=1) # Returns updated value endlessly. Accepts floats.
<iter> = it.repeat(<el> [, times]) # Returns element endlessly or 'times' times.
<iter> = it.cycle(<collection>) # Repeats the sequence endlessly.
<iter> = it.chain(<coll>, <coll> [, ...]) # Empties collections in order (figuratively).
<iter> = it.chain.from_iterable(<coll>) # Empties collections inside a collection in order.
<iter> = it.islice(<coll>, to_exclusive) # Only returns first 'to_exclusive' elements.
<iter> = it.islice(<coll>, from_inc, …) # `to_exclusive, +step_size`. Indices can be None.
def count(start, step):
while True:
yield start
start += step
>>> counter = count(10, 2)
>>> next(counter), next(counter), next(counter)
(10, 12, 14)
<type> = type(<el>) # Or: <el>.__class__
<bool> = isinstance(<el>, <type>) # Or: issubclass(type(<el>), <type>)
>>> type('a'), 'a'.__class__, str
(<class 'str'>, <class 'str'>, <class 'str'>)
from types import FunctionType, MethodType, LambdaType, GeneratorType, ModuleType
Each abstract base class specifies a set of virtual subclasses. These classes are then recognized by isinstance() and issubclass() as subclasses of the ABC, although they are really not. ABC can also manually decide whether or not a specific class is its virtual subclass, usually based on which methods the class has implemented. For instance, Iterable ABC looks for method iter(), while Collection ABC looks for iter(), contains() and len().
>>> from collections.abc import Iterable, Collection, Sequence
>>> isinstance([1, 2, 3], Iterable)
True
┏━━━━━━━━━━━━━━━━━━┯━━━━━━━━━━━━┯━━━━━━━━━━━━┯━━━━━━━━━━━━┓
┃ │ Iterable │ Collection │ Sequence ┃
┠──────────────────┼────────────┼────────────┼────────────┨
┃ list, range, str │ ✓ │ ✓ │ ✓ ┃
┃ dict, set │ ✓ │ ✓ │ ┃
┃ iter │ ✓ │ │ ┃
┗━━━━━━━━━━━━━━━━━━┷━━━━━━━━━━━━┷━━━━━━━━━━━━┷━━━━━━━━━━━━┛
>>> from numbers import Number, Complex, Real, Rational, Integral
>>> isinstance(123, Number)
True
┏━━━━━━━━━━━━━━━━━━━━┯━━━━━━━━━━┯━━━━━━━━━━┯━━━━━━━━━━┯━━━━━━━━━━┯━━━━━━━━━━┓
┃ │ Number │ Complex │ Real │ Rational │ Integral ┃
┠────────────────────┼──────────┼──────────┼──────────┼──────────┼──────────┨
┃ int │ ✓ │ ✓ │ ✓ │ ✓ │ ✓ ┃
┃ fractions.Fraction │ ✓ │ ✓ │ ✓ │ ✓ │ ┃
┃ float │ ✓ │ ✓ │ ✓ │ │ ┃
┃ complex │ ✓ │ ✓ │ │ │ ┃
┃ decimal.Decimal │ ✓ │ │ │ │ ┃
┗━━━━━━━━━━━━━━━━━━━━┷━━━━━━━━━━┷━━━━━━━━━━┷━━━━━━━━━━┷━━━━━━━━━━┷━━━━━━━━━━┛
Immutable sequence of characters.
<str> = <str>.strip() # Strips all whitespace characters from both ends.
<str> = <str>.strip('<chars>') # Strips passed characters. Also lstrip/rstrip().
<list> = <str>.split() # Splits on one or more whitespace characters.
<list> = <str>.split(sep=None, maxsplit=-1) # Splits on 'sep' str at most 'maxsplit' times.
<list> = <str>.splitlines(keepends=False) # On [\n\r\f\v\x1c-\x1e\x85\u2028\u2029] and \r\n.
<str> = <str>.join(<coll_of_strings>) # Joins elements using string as a separator.
<bool> = <sub_str> in <str> # Checks if string contains the substring.
<bool> = <str>.startswith(<sub_str>) # Pass tuple of strings for multiple options.
<int> = <str>.find(<sub_str>) # Returns start index of the first match or -1.
<int> = <str>.index(<sub_str>) # Same, but raises ValueError if there's no match.
<str> = <str>.lower() # Changes the case. Also upper/capitalize/title().
<str> = <str>.replace(old, new [, count]) # Replaces 'old' with 'new' at most 'count' times.
<str> = <str>.translate(<table>) # Use `str.maketrans(<dict>)` to generate table.
<str> = chr(<int>) # Converts int to Unicode character.
<int> = ord(<str>) # Converts Unicode character to int.
'unicodedata.normalize("NFC", <str>)'
on strings like 'Motörhead'
before comparing them to other strings, because 'ö'
can be stored as one or two characters.'NFC'
converts such characters to a single character, while 'NFD'
converts them to two.<bool> = <str>.isdecimal() # Checks for [0-9]. Also [०-९] and [٠-٩].
<bool> = <str>.isdigit() # Checks for [²³¹…] and isdecimal().
<bool> = <str>.isnumeric() # Checks for [¼½¾…], [零〇一…] and isdigit().
<bool> = <str>.isalnum() # Checks for [a-zA-Z…] and isnumeric().
<bool> = <str>.isprintable() # Checks for [ !#$%…] and isalnum().
<bool> = <str>.isspace() # Checks for [ \t\n\r\f\v\x1c-\x1f\x85\xa0…].
Functions for regular expression matching.
import re
<str> = re.sub(r'<regex>', new, text, count=0) # Substitutes all occurrences with 'new'.
<list> = re.findall(r'<regex>', text) # Returns all occurrences as strings.
<list> = re.split(r'<regex>', text, maxsplit=0) # Add brackets around regex to keep matches.
<Match> = re.search(r'<regex>', text) # First occurrence of the pattern or None.
<Match> = re.match(r'<regex>', text) # Searches only at the beginning of the text.
<iter> = re.finditer(r'<regex>', text) # Returns all occurrences as Match objects.
'flags=re.IGNORECASE'
can be used with all functions.'flags=re.MULTILINE'
makes '^'
and '$'
match the start/end of each line.'flags=re.DOTALL'
makes '.'
also accept the '\n'
.'re.compile(<regex>)'
returns a Pattern object with methods sub(), findall(), …<str> = <Match>.group() # Returns the whole match. Also group(0).
<str> = <Match>.group(1) # Returns part inside the first brackets.
<tuple> = <Match>.groups() # Returns all bracketed parts.
<int> = <Match>.start() # Returns start index of the match.
<int> = <Match>.end() # Returns exclusive end index of the match.
'\d' == '[0-9]' # Also [०-९…]. Matches a decimal character.
'\w' == '[a-zA-Z0-9_]' # Also [ª²³…]. Matches an alphanumeric or _.
'\s' == '[ \t\n\r\f\v]' # Also [\x1c-\x1f…]. Matches a whitespace.
'flags=re.ASCII'
is used. It restricts special sequence matches to the first 128 Unicode characters and also prevents '\s'
from accepting '\x1c'
, '\x1d'
, '\x1e'
and '\x1f'
(non-printable characters that divide text into files, tables, rows and fields, respectively).<str> = f'{<el_1>}, {<el_2>}' # Curly brackets can also contain expressions.
<str> = '{}, {}'.format(<el_1>, <el_2>) # Or: '{0}, {a}'.format(<el_1>, a=<el_2>)
<str> = '%s, %s' % (<el_1>, <el_2>) # Redundant and inferior C-style formatting.
>>> Person = collections.namedtuple('Person', 'name height')
>>> person = Person('Jean-Luc', 187)
>>> f'{person.name} is {person.height / 100} meters tall.'
'Jean-Luc is 1.87 meters tall.'
{<el>:<10} # '<el> '
{<el>:^10} # ' <el> '
{<el>:>10} # ' <el>'
{<el>:.<10} # '<el>......'
{<el>:0} # '<el>'
'format(<el>, "<options>")'
.f'{<el>:{<str/int>}[…]}'
.'='
to the expression prepends it to the output: f'{1+1=}'
returns '1+1=2'
.'!r'
to the expression converts object to string by calling its repr() method.{'abcde':10} # 'abcde '
{'abcde':10.3} # 'abc '
{'abcde':.3} # 'abc'
{'abcde'!r:10} # "'abcde' "
{123456:10} # ' 123456'
{123456:10,} # ' 123,456'
{123456:10_} # ' 123_456'
{123456:+10} # ' +123456'
{123456:=+10} # '+ 123456'
{123456: } # ' 123456'
{-123456: } # '-123456'
{1.23456:10.3} # ' 1.23'
{1.23456:10.3f} # ' 1.235'
{1.23456:10.3e} # ' 1.235e+00'
{1.23456:10.3%} # ' 123.456%'
┏━━━━━━━━━━━━━━┯━━━━━━━━━━━━━━━━┯━━━━━━━━━━━━━━━━┯━━━━━━━━━━━━━━━━┯━━━━━━━━━━━━━━━━┓
┃ │ {<float>} │ {<float>:f} │ {<float>:e} │ {<float>:%} ┃
┠──────────────┼────────────────┼────────────────┼────────────────┼────────────────┨
┃ 0.000056789 │ '5.6789e-05' │ '0.000057' │ '5.678900e-05' │ '0.005679%' ┃
┃ 0.00056789 │ '0.00056789' │ '0.000568' │ '5.678900e-04' │ '0.056789%' ┃
┃ 0.0056789 │ '0.0056789' │ '0.005679' │ '5.678900e-03' │ '0.567890%' ┃
┃ 0.056789 │ '0.056789' │ '0.056789' │ '5.678900e-02' │ '5.678900%' ┃
┃ 0.56789 │ '0.56789' │ '0.567890' │ '5.678900e-01' │ '56.789000%' ┃
┃ 5.6789 │ '5.6789' │ '5.678900' │ '5.678900e+00' │ '567.890000%' ┃
┃ 56.789 │ '56.789' │ '56.789000' │ '5.678900e+01' │ '5678.900000%' ┃
┗━━━━━━━━━━━━━━┷━━━━━━━━━━━━━━━━┷━━━━━━━━━━━━━━━━┷━━━━━━━━━━━━━━━━┷━━━━━━━━━━━━━━━━┛
┏━━━━━━━━━━━━━━┯━━━━━━━━━━━━━━━━┯━━━━━━━━━━━━━━━━┯━━━━━━━━━━━━━━━━┯━━━━━━━━━━━━━━━━┓
┃ │ {<float>:.2} │ {<float>:.2f} │ {<float>:.2e} │ {<float>:.2%} ┃
┠──────────────┼────────────────┼────────────────┼────────────────┼────────────────┨
┃ 0.000056789 │ '5.7e-05' │ '0.00' │ '5.68e-05' │ '0.01%' ┃
┃ 0.00056789 │ '0.00057' │ '0.00' │ '5.68e-04' │ '0.06%' ┃
┃ 0.0056789 │ '0.0057' │ '0.01' │ '5.68e-03' │ '0.57%' ┃
┃ 0.056789 │ '0.057' │ '0.06' │ '5.68e-02' │ '5.68%' ┃
┃ 0.56789 │ '0.57' │ '0.57' │ '5.68e-01' │ '56.79%' ┃
┃ 5.6789 │ '5.7' │ '5.68' │ '5.68e+00' │ '567.89%' ┃
┃ 56.789 │ '5.7e+01' │ '56.79' │ '5.68e+01' │ '5678.90%' ┃
┗━━━━━━━━━━━━━━┷━━━━━━━━━━━━━━━━┷━━━━━━━━━━━━━━━━┷━━━━━━━━━━━━━━━━┷━━━━━━━━━━━━━━━━┛
'{<float>:g}'
is '{<float>:.6}'
with stripped zeros, exponent starting at '1e+06'
.'{6.5:.0f}'
a '6'
and '{7.5:.0f}'
an '8'
..5
, .25
, …).{90:c} # 'Z'. Unicode character with value 90.
{90:b} # '1011010'. Number 90 in binary.
{90:X} # '5A'. Number 90 in uppercase hexadecimal.
<int> = int(<float/str/bool>) # Or: math.trunc(<float>)
<float> = float(<int/str/bool>) # Or: <int/float>e±<int>
<complex> = complex(real=0, imag=0) # Or: <int/float> ± <int/float>j
<Fraction> = fractions.Fraction(0, 1) # Or: Fraction(numerator=0, denominator=1)
<Decimal> = decimal.Decimal(<str/int>) # Or: Decimal((sign, digits, exponent))
'int(<str>)'
and 'float(<str>)'
raise ValueError on malformed strings.'1.1 + 2.2 != 3.3'
.'math.isclose(<float>, <float>)'
.'decimal.getcontext().prec = <int>'
.<num> = pow(<num>, <num>) # Or: <number> ** <number>
<num> = abs(<num>) # <float> = abs(<complex>)
<num> = round(<num> [, ±ndigits]) # `round(126, -1) == 130`
from math import e, pi, inf, nan, isinf, isnan # `<el> == nan` is always False.
from math import sin, cos, tan, asin, acos, atan # Also: degrees, radians.
from math import log, log10, log2 # Log can accept base as second arg.
from statistics import mean, median, variance # Also: stdev, quantiles, groupby.
from random import random, randint, choice # Also: shuffle, gauss, triangular, seed.
<float> = random() # A float inside [0, 1).
<int> = randint(from_inc, to_inc) # An int inside [from_inc, to_inc].
<el> = choice(<sequence>) # Keeps the sequence intact.
<int> = ±0b<bin> # Or: ±0x<hex>
<int> = int('±<bin>', 2) # Or: int('±<hex>', 16)
<int> = int('±0b<bin>', 0) # Or: int('±0x<hex>', 0)
<str> = bin(<int>) # Returns '[-]0b<bin>'. Also hex().
<int> = <int> & <int> # And (0b1100 & 0b1010 == 0b1000).
<int> = <int> | <int> # Or (0b1100 | 0b1010 == 0b1110).
<int> = <int> ^ <int> # Xor (0b1100 ^ 0b1010 == 0b0110).
<int> = <int> << n_bits # Left shift. Use >> for right.
<int> = ~<int> # Not. Also -<int> - 1.
import itertools as it
>>> list(it.product([0, 1], repeat=3))
[(0, 0, 0), (0, 0, 1), (0, 1, 0), (0, 1, 1),
(1, 0, 0), (1, 0, 1), (1, 1, 0), (1, 1, 1)]
>>> list(it.product('abc', 'abc')) # a b c
[('a', 'a'), ('a', 'b'), ('a', 'c'), # a x x x
('b', 'a'), ('b', 'b'), ('b', 'c'), # b x x x
('c', 'a'), ('c', 'b'), ('c', 'c')] # c x x x
>>> list(it.combinations('abc', 2)) # a b c
[('a', 'b'), ('a', 'c'), # a . x x
('b', 'c')] # b . . x
>>> list(it.combinations_with_replacement('abc', 2)) # a b c
[('a', 'a'), ('a', 'b'), ('a', 'c'), # a x x x
('b', 'b'), ('b', 'c'), # b . x x
('c', 'c')] # c . . x
>>> list(it.permutations('abc', 2)) # a b c
[('a', 'b'), ('a', 'c'), # a . x x
('b', 'a'), ('b', 'c'), # b x . x
('c', 'a'), ('c', 'b')] # c x x .
Provides 'date', 'time', 'datetime' and 'timedelta' classes. All are immutable and hashable.
# $ pip3 install python-dateutil
from datetime import date, time, datetime, timedelta, timezone
import zoneinfo, dateutil.tz
<D> = date(year, month, day) # Only accepts valid dates from 1 to 9999 AD.
<T> = time(hour=0, minute=0, second=0) # Also: `microsecond=0, tzinfo=None, fold=0`.
<DT> = datetime(year, month, day, hour=0) # Also: `minute=0, second=0, microsecond=0, …`.
<TD> = timedelta(weeks=0, days=0, hours=0) # Also: `minutes=0, seconds=0, microseconds=0`.
'fold=1'
means the second pass in case of time jumping back for one hour.'[±D, ]H:MM:SS[.…]'
and total_seconds() a float of all seconds.'<D/DT>.weekday()'
to get the day of the week as an int, with Monday being 0.<D/DTn> = D/DT.today() # Current local date or naive DT. Also DT.now().
<DTa> = DT.now(<tzinfo>) # Aware DT from current time in passed timezone.
'<DTn>.time()'
, '<DTa>.time()'
or '<DTa>.timetz()'
.<tzinfo> = timezone.utc # London without daylight saving time (DST).
<tzinfo> = timezone(<timedelta>) # Timezone with fixed offset from UTC.
<tzinfo> = dateutil.tz.tzlocal() # Local timezone with dynamic offset from UTC.
<tzinfo> = zoneinfo.ZoneInfo('<iana_key>') # 'Continent/City_Name' zone with dynamic offset.
<DTa> = <DT>.astimezone([<tzinfo>]) # Converts DT to the passed or local fixed zone.
<Ta/DTa> = <T/DT>.replace(tzinfo=<tzinfo>) # Changes object's timezone without conversion.
'> pip3 install tzdata'
.<D/T/DT> = D/T/DT.fromisoformat(<str>) # Object from ISO string. Raises ValueError.
<DT> = DT.strptime(<str>, '<format>') # Datetime from str, according to format.
<D/DTn> = D/DT.fromordinal(<int>) # D/DT from days since the Gregorian NYE 1.
<DTn> = DT.fromtimestamp(<float>) # Local naive DT from seconds since the Epoch.
<DTa> = DT.fromtimestamp(<float>, <tz>) # Aware datetime from seconds since the Epoch.
'YYYY-MM-DD'
, 'HH:MM:SS.mmmuuu[±HH:MM]'
, or both separated by an arbitrary character. All parts following the hours are optional.'1970-01-01 00:00 UTC'
, '1970-01-01 01:00 CET'
, …<str> = <D/T/DT>.isoformat(sep='T') # Also `timespec='auto/hours/minutes/seconds/…'`.
<str> = <D/T/DT>.strftime('<format>') # Custom string representation of the object.
<int> = <D/DT>.toordinal() # Days since Gregorian NYE 1, ignoring time and tz.
<float> = <DTn>.timestamp() # Seconds since the Epoch, from local naive DT.
<float> = <DTa>.timestamp() # Seconds since the Epoch, from aware datetime.
>>> dt = datetime.strptime('2025-08-14 23:39:00.00 +0200', '%Y-%m-%d %H:%M:%S.%f %z')
>>> dt.strftime("%dth of %B '%y (%a), %I:%M %p %Z")
"14th of August '25 (Thu), 11:39 PM UTC+02:00"
'%z'
accepts '±HH[:]MM'
and returns '±HHMM'
or empty string if datetime is naive.'%Z'
accepts 'UTC/GMT'
and local timezone's code and returns timezone's name, 'UTC[±HH:MM]'
if timezone is nameless, or an empty string if datetime is naive.<bool> = <D/T/DTn> > <D/T/DTn> # Ignores time jumps (fold attribute). Also ==.
<bool> = <DTa> > <DTa> # Ignores jumps if they share tz object. Broken ==.
<TD> = <D/DTn> - <D/DTn> # Ignores jumps. Convert to UTC for actual delta.
<TD> = <DTa> - <DTa> # Ignores jumps if they share tzinfo object.
<D/DT> = <D/DT> ± <TD> # Returned datetime can fall into missing hour.
<TD> = <TD> * <float> # Also: <TD> = abs(<TD>) and <TD> = <TD> ±% <TD>.
<float> = <TD> / <TD> # E.g. how many hours are in TD. Also //, divmod().
func(<positional_args>) # func(0, 0)
func(<keyword_args>) # func(x=0, y=0)
func(<positional_args>, <keyword_args>) # func(0, y=0)
def func(<nondefault_args>): ... # def func(x, y): ...
def func(<default_args>): ... # def func(x=0, y=0): ...
def func(<nondefault_args>, <default_args>): ... # def func(x, y=0): ...
Splat expands a collection into positional arguments, while splatty-splat expands a dictionary into keyword arguments.
args = (1, 2)
kwargs = {'x': 3, 'y': 4, 'z': 5}
func(*args, **kwargs)
func(1, 2, x=3, y=4, z=5)
Splat combines zero or more positional arguments into a tuple, while splatty-splat combines zero or more keyword arguments into a dictionary.
def add(*a):
return sum(a)
>>> add(1, 2, 3)
6
def f(*args): ... # f(1, 2, 3)
def f(x, *args): ... # f(1, 2, 3)
def f(*args, z): ... # f(1, 2, z=3)
def f(**kwargs): ... # f(x=1, y=2, z=3)
def f(x, **kwargs): ... # f(x=1, y=2, z=3) | f(1, y=2, z=3)
def f(*args, **kwargs): ... # f(x=1, y=2, z=3) | f(1, y=2, z=3) | f(1, 2, z=3) | f(1, 2, 3)
def f(x, *args, **kwargs): ... # f(x=1, y=2, z=3) | f(1, y=2, z=3) | f(1, 2, z=3) | f(1, 2, 3)
def f(*args, y, **kwargs): ... # f(x=1, y=2, z=3) | f(1, y=2, z=3)
def f(*, x, y, z): ... # f(x=1, y=2, z=3)
def f(x, *, y, z): ... # f(x=1, y=2, z=3) | f(1, y=2, z=3)
def f(x, y, *, z): ... # f(x=1, y=2, z=3) | f(1, y=2, z=3) | f(1, 2, z=3)
<list> = [*<coll.> [, ...]] # Or: list(<collection>) [+ ...]
<tuple> = (*<coll.>, [...]) # Or: tuple(<collection>) [+ ...]
<set> = {*<coll.> [, ...]} # Or: set(<collection>) [| ...]
<dict> = {**<dict> [, ...]} # Or: <dict> | ...
head, *body, tail = <coll.> # Head or tail can be omitted.
<func> = lambda: <return_value> # A single statement function.
<func> = lambda <arg_1>, <arg_2>: <return_value> # Also allows default arguments.
<list> = [i+1 for i in range(10)] # Or: [1, 2, ..., 10]
<iter> = (i for i in range(10) if i > 5) # Or: iter([6, 7, 8, 9])
<set> = {i+5 for i in range(10)} # Or: {5, 6, ..., 14}
<dict> = {i: i*2 for i in range(10)} # Or: {0: 0, 1: 2, ..., 9: 18}
>>> [l+r for l in 'abc' for r in 'abc'] # Inner loop is on the right side.
['aa', 'ab', 'ac', ..., 'cc']
from functools import reduce
<iter> = map(lambda x: x + 1, range(10)) # Or: iter([1, 2, ..., 10])
<iter> = filter(lambda x: x > 5, range(10)) # Or: iter([6, 7, 8, 9])
<obj> = reduce(lambda out, x: out + x, range(10)) # Or: 45
<bool> = any(<collection>) # Is `bool(<el>)` True for any el?
<bool> = all(<collection>) # True for all? Also True if empty.
<obj> = <exp> if <condition> else <exp> # Only one expression is evaluated.
>>> [a if a else 'zero' for a in (0, 1, 2, 3)] # `any([0, '', [], None]) == False`
['zero', 1, 2, 3]
from collections import namedtuple
Point = namedtuple('Point', 'x y') # Creates a tuple's subclass.
point = Point(0, 0) # Returns its instance.
from enum import Enum
Direction = Enum('Direction', 'N E S W') # Creates an enum.
direction = Direction.N # Returns its member.
from dataclasses import make_dataclass
Player = make_dataclass('Player', ['loc', 'dir']) # Creates a class.
player = Player(point, direction) # Returns its instance.
Mechanism that makes code in one file available to another file.
import <module> # Imports a built-in or '<module>.py'.
import <package> # Imports a built-in or '<package>/__init__.py'.
import <package>.<module> # Imports a built-in or '<package>/<module>.py'.
'import <package>'
does not automatically provide access to the package's modules unless they are explicitly imported in its init script.'from .[…][<pkg/module>[.…]] import <obj>'
.We have/get a closure in Python when a nested function references a value of its enclosing function and then the enclosing function returns the nested function.
def get_multiplier(a):
def out(b):
return a * b
return out
>>> multiply_by_3 = get_multiplier(3)
>>> multiply_by_3(10)
30
from functools import partial
<function> = partial(<function> [, <arg_1> [, ...]])
>>> def multiply(a, b):
... return a * b
>>> multiply_by_3 = partial(multiply, 3)
>>> multiply_by_3(10)
30
'defaultdict(<func>)'
, 'iter(<func>, to_exc)'
and dataclass's 'field(default_factory=<func>)'
.If variable is being assigned to anywhere in the scope, it is regarded as a local variable, unless it is declared as a 'global' or a 'nonlocal'.
def get_counter():
i = 0
def out():
nonlocal i
i += 1
return i
return out
>>> counter = get_counter()
>>> counter(), counter(), counter()
(1, 2, 3)
@decorator_name
def function_that_gets_passed_to_decorator():
...
Decorator that prints function's name every time the function is called.
from functools import wraps
def debug(func):
@wraps(func)
def out(*args, **kwargs):
print(func.__name__)
return func(*args, **kwargs)
return out
@debug
def add(x, y):
return x + y
'add.__name__'
would return 'out'
.Decorator that caches function's return values. All function's arguments must be hashable.
from functools import cache
@cache
def fib(n):
return n if n < 2 else fib(n-2) + fib(n-1)
'fib.cache_clear()'
, or use '@lru_cache(maxsize=<int>)'
decorator instead.'sys.setrecursionlimit(<int>)'
.A decorator that accepts arguments and returns a normal decorator that accepts a function.
from functools import wraps
def debug(print_result=False):
def decorator(func):
@wraps(func)
def out(*args, **kwargs):
result = func(*args, **kwargs)
print(func.__name__, result if print_result else '')
return result
return out
return decorator
@debug(print_result=True)
def add(x, y):
return x + y
'@debug'
to decorate the add() function would not work here, because debug would then receive the add() function as a 'print_result' argument. Decorators can however manually check if the argument they received is a function and act accordingly.A template for creating user-defined objects.
class MyClass:
def __init__(self, a):
self.a = a
def __str__(self):
return str(self.a)
def __repr__(self):
class_name = self.__class__.__name__
return f'{class_name}({self.a!r})'
@classmethod
def get_class_name(cls):
return cls.__name__
>>> obj = MyClass(1)
>>> obj.a, str(obj), repr(obj)
(1, '1', 'MyClass(1)')
'@staticmethod'
do not receive 'self' nor 'cls' as their first argument.print(<obj>)
f'{<obj>}'
logging.warning(<obj>)
csv.writer(<file>).writerow([<obj>])
raise Exception(<obj>)
print/str/repr([<obj>])
print/str/repr({<obj>: <obj>})
f'{<obj>!r}'
Z = dataclasses.make_dataclass('Z', ['a']); print/str/repr(Z(<obj>))
>>> <obj>
class Person:
def __init__(self, name):
self.name = name
class Employee(Person):
def __init__(self, name, staff_num):
super().__init__(name)
self.staff_num = staff_num
class A: pass
class B: pass
class C(A, B): pass
MRO determines the order in which parent classes are traversed when searching for a method or an attribute:
>>> C.mro()
[<class 'C'>, <class 'A'>, <class 'B'>, <class 'object'>]
'def f() -> <type>:'
).from collections import abc
<name>: <type> [| ...] [= <obj>] # `|` since 3.10.
<name>: list/set/abc.Iterable/abc.Sequence[<type>] [= <obj>] # Since 3.9.
<name>: dict/tuple[<type>, ...] [= <obj>] # Since 3.9.
Decorator that uses class variables to generate init(), repr() and eq() special methods.
from dataclasses import dataclass, field, make_dataclass
@dataclass(order=False, frozen=False)
class <class_name>:
<attr_name>: <type>
<attr_name>: <type> = <default_value>
<attr_name>: list/dict/set = field(default_factory=list/dict/set)
'order=True'
and immutable with 'frozen=True'
.'<attr_name>: list = []'
would make a list that is shared among all instances. Its 'default_factory' argument can be any callable.'typing.Any'
.Point = make_dataclass('Point', ['x', 'y'])
Point = make_dataclass('Point', [('x', float), ('y', float)])
Point = make_dataclass('Point', [('x', float, 0), ('y', float, 0)])
Pythonic way of implementing getters and setters.
class Person:
@property
def name(self):
return ' '.join(self._name)
@name.setter
def name(self, value):
self._name = value.split()
>>> person = Person()
>>> person.name = '\t Guido van Rossum \n'
>>> person.name
'Guido van Rossum'
Mechanism that restricts objects to attributes listed in 'slots', reduces their memory footprint.
class MyClassWithSlots:
__slots__ = ['a']
def __init__(self):
self.a = 1
from copy import copy, deepcopy
<object> = copy/deepcopy(<object>)
A duck type is an implicit type that prescribes a set of special methods. Any object that has those methods defined is considered a member of that duck type.
'id(self) == id(other)'
, which is the same as 'self is other'
.class MyComparable:
def __init__(self, a):
self.a = a
def __eq__(self, other):
if isinstance(other, type(self)):
return self.a == other.a
return NotImplemented
'id(self)'
will not do.class MyHashable:
def __init__(self, a):
self._a = a
@property
def a(self):
return self._a
def __eq__(self, other):
if isinstance(other, type(self)):
return self.a == other.a
return NotImplemented
def __hash__(self):
return hash(self.a)
'key=locale.strxfrm'
to sorted() after running 'locale.setlocale(locale.LC_COLLATE, "en_US.UTF-8")'
.from functools import total_ordering
@total_ordering
class MySortable:
def __init__(self, a):
self.a = a
def __eq__(self, other):
if isinstance(other, type(self)):
return self.a == other.a
return NotImplemented
def __lt__(self, other):
if isinstance(other, type(self)):
return self.a < other.a
return NotImplemented
class Counter:
def __init__(self):
self.i = 0
def __next__(self):
self.i += 1
return self.i
def __iter__(self):
return self
>>> counter = Counter()
>>> next(counter), next(counter), next(counter)
(1, 2, 3)
'callable(<obj>)'
or 'isinstance(<obj>, collections.abc.Callable)'
to check if object is callable.'<function>'
as an argument, it means '<callable>'
.class Counter:
def __init__(self):
self.i = 0
def __call__(self):
self.i += 1
return self.i
>>> counter = Counter()
>>> counter(), counter(), counter()
(1, 2, 3)
class MyOpen:
def __init__(self, filename):
self.filename = filename
def __enter__(self):
self.file = open(self.filename)
return self.file
def __exit__(self, exc_type, exception, traceback):
self.file.close()
>>> with open('test.txt', 'w') as file:
... file.write('Hello World!')
>>> with MyOpen('test.txt') as file:
... print(file.read())
Hello World!
class MyIterable:
def __init__(self, a):
self.a = a
def __iter__(self):
return iter(self.a)
def __contains__(self, el):
return el in self.a
>>> obj = MyIterable([1, 2, 3])
>>> [el for el in obj]
[1, 2, 3]
>>> 1 in obj
True
'<iterable>'
when it uses '<collection>'
.class MyCollection:
def __init__(self, a):
self.a = a
def __iter__(self):
return iter(self.a)
def __contains__(self, el):
return el in self.a
def __len__(self):
return len(self.a)
class MySequence:
def __init__(self, a):
self.a = a
def __iter__(self):
return iter(self.a)
def __contains__(self, el):
return el in self.a
def __len__(self):
return len(self.a)
def __getitem__(self, i):
return self.a[i]
def __reversed__(self):
return reversed(self.a)
'abc.Iterable'
and 'abc.Collection'
, it is not a duck type. That is why 'issubclass(MySequence, abc.Sequence)'
would return False even if MySequence had all the methods defined. It however recognizes list, tuple, range, str, bytes, bytearray, array, memoryview and deque, since they are registered as Sequence's virtual subclasses.from collections import abc
class MyAbcSequence(abc.Sequence):
def __init__(self, a):
self.a = a
def __len__(self):
return len(self.a)
def __getitem__(self, i):
return self.a[i]
┏━━━━━━━━━━━━┯━━━━━━━━━━━━┯━━━━━━━━━━━━┯━━━━━━━━━━━━┯━━━━━━━━━━━━━━┓
┃ │ Iterable │ Collection │ Sequence │ abc.Sequence ┃
┠────────────┼────────────┼────────────┼────────────┼──────────────┨
┃ iter() │ ! │ ! │ ✓ │ ✓ ┃
┃ contains() │ ✓ │ ✓ │ ✓ │ ✓ ┃
┃ len() │ │ ! │ ! │ ! ┃
┃ getitem() │ │ │ ! │ ! ┃
┃ reversed() │ │ │ ✓ │ ✓ ┃
┃ index() │ │ │ │ ✓ ┃
┃ count() │ │ │ │ ✓ ┃
┗━━━━━━━━━━━━┷━━━━━━━━━━━━┷━━━━━━━━━━━━┷━━━━━━━━━━━━┷━━━━━━━━━━━━━━┛
'isinstance(<obj>, abc.Iterable)'
to return True, however any object with getitem() will work with any code expecting an iterable.'<abc>.__abstractmethods__'
to get names of required methods.class <enum_name>(Enum):
<member_name> = auto() # Increment of the last numeric value or 1.
<member_name> = <value> # Values don't have to be hashable.
<member_name> = <el_1>, <el_2> # Values can be collections (this is a tuple).
<member> = <enum>.<member_name> # Returns a member. Raises AttributeError.
<member> = <enum>['<member_name>'] # Returns a member. Raises KeyError.
<member> = <enum>(<value>) # Returns a member. Raises ValueError.
<str> = <member>.name # Returns member's name.
<obj> = <member>.value # Returns member's value.
<list> = list(<enum>) # Returns enum's members.
<list> = [a.name for a in <enum>] # Returns enum's member names.
<list> = [a.value for a in <enum>] # Returns enum's member values.
<enum> = type(<member>) # Returns member's enum.
<iter> = itertools.cycle(<enum>) # Returns endless iterator of members.
<member> = random.choice(list(<enum>)) # Returns a random member.
Cutlery = Enum('Cutlery', 'FORK KNIFE SPOON')
Cutlery = Enum('Cutlery', ['FORK', 'KNIFE', 'SPOON'])
Cutlery = Enum('Cutlery', {'FORK': 1, 'KNIFE': 2, 'SPOON': 3})
from functools import partial
LogicOp = Enum('LogicOp', {'AND': partial(lambda l, r: l and r),
'OR': partial(lambda l, r: l or r)})
try:
<code>
except <exception>:
<code>
try:
<code_1>
except <exception_a>:
<code_2_a>
except <exception_b>:
<code_2_b>
else:
<code_2_c>
finally:
<code_3>
'else'
block will only be executed if 'try'
block had no exceptions.'finally'
block will always be executed (unless a signal is received).'signal.signal(signal_number, <func>)'
.except <exception>: ...
except <exception> as <name>: ...
except (<exception>, [...]): ...
except (<exception>, [...]) as <name>: ...
'traceback.print_exc()'
to print the full error message to stderr.'print(<name>)'
to print just the cause of the exception (its arguments).'logging.exception(<str>)'
to log the passed message, followed by the full error message of the caught exception. For details see logging.'sys.exc_info()'
to get exception type, object, and traceback of caught exception.raise <exception>
raise <exception>()
raise <exception>(<obj> [, ...])
except <exception> [as <name>]:
...
raise
arguments = <name>.args
exc_type = <name>.__class__
filename = <name>.__traceback__.tb_frame.f_code.co_filename
func_name = <name>.__traceback__.tb_frame.f_code.co_name
line = linecache.getline(filename, <name>.__traceback__.tb_lineno)
trace_str = ''.join(traceback.format_tb(<name>.__traceback__))
error_msg = ''.join(traceback.format_exception(type(<name>), <name>, <name>.__traceback__))
BaseException
├── SystemExit # Raised by the sys.exit() function.
├── KeyboardInterrupt # Raised when the user hits the interrupt key (ctrl-c).
└── Exception # User-defined exceptions should be derived from this class.
├── ArithmeticError # Base class for arithmetic errors such as ZeroDivisionError.
├── AssertionError # Raised by `assert <exp>` if expression returns false value.
├── AttributeError # Raised when object doesn't have requested attribute/method.
├── EOFError # Raised by input() when it hits an end-of-file condition.
├── LookupError # Base class for errors when a collection can't find an item.
│ ├── IndexError # Raised when a sequence index is out of range.
│ └── KeyError # Raised when a dictionary key or set element is missing.
├── MemoryError # Out of memory. May be too late to start deleting variables.
├── NameError # Raised when nonexistent name (variable/func/class) is used.
│ └── UnboundLocalError # Raised when local name is used before it's being defined.
├── OSError # Errors such as FileExistsError/TimeoutError (see #Open).
│ └── ConnectionError # Errors such as BrokenPipeError/ConnectionAbortedError.
├── RuntimeError # Raised by errors that don't fall into other categories.
│ ├── NotImplementedEr… # Can be raised by abstract methods or by unfinished code.
│ └── RecursionError # Raised when the maximum recursion depth is exceeded.
├── StopIteration # Raised when an empty iterator is passed to next().
├── TypeError # When an argument of the wrong type is passed to function.
└── ValueError # When argument has the right type but inappropriate value.
┏━━━━━━━━━━━┯━━━━━━━━━━━━┯━━━━━━━━━━━━┯━━━━━━━━━━━━┓
┃ │ List │ Set │ Dict ┃
┠───────────┼────────────┼────────────┼────────────┨
┃ getitem() │ IndexError │ │ KeyError ┃
┃ pop() │ IndexError │ KeyError │ KeyError ┃
┃ remove() │ ValueError │ KeyError │ ┃
┃ index() │ ValueError │ │ ┃
┗━━━━━━━━━━━┷━━━━━━━━━━━━┷━━━━━━━━━━━━┷━━━━━━━━━━━━┛
raise TypeError('Argument is of the wrong type!')
raise ValueError('Argument has the right type but an inappropriate value!')
raise RuntimeError('I am too lazy to define my own exception!')
class MyError(Exception): pass
class MyInputError(MyError): pass
Exits the interpreter by raising SystemExit exception.
import sys
sys.exit() # Exits with exit code 0 (success).
sys.exit(<int>) # Exits with the passed exit code.
sys.exit(<obj>) # Prints to stderr and exits with 1.
print(<el_1>, ..., sep=' ', end='\n', file=sys.stdout, flush=False)
'file=sys.stderr'
for messages about errors.'flush=True'
is used, or program exits.from pprint import pprint
pprint(<collection>, width=80, depth=None, compact=False, sort_dicts=True)
<str> = input(prompt=None)
import sys
scripts_path = sys.argv[0]
arguments = sys.argv[1:]
from argparse import ArgumentParser, FileType
p = ArgumentParser(description=<str>) # Returns a parser.
p.add_argument('-<short_name>', '--<name>', action='store_true') # Flag (defaults to False).
p.add_argument('-<short_name>', '--<name>', type=<type>) # Option (defaults to None).
p.add_argument('<name>', type=<type>, nargs=1) # Mandatory first argument.
p.add_argument('<name>', type=<type>, nargs='+') # Mandatory remaining args.
p.add_argument('<name>', type=<type>, nargs='?/*') # Optional argument/s.
args = p.parse_args() # Exits on parsing error.
<obj> = args.<name> # Returns `<type>(<arg>)`.
'help=<str>'
to set argument description that will be displayed in help message.'default=<obj>'
to set option's or optional argument's default value.'type=FileType(<mode>)'
for files. Accepts 'encoding', but 'newline' is None.Opens the file and returns a corresponding file object.
<file> = open(<path>, mode='r', encoding=None, newline=None)
'encoding=None'
means that the default encoding is used, which is platform dependent. Best practice is to use 'encoding="utf-8"'
whenever possible.'newline=None'
means all different end of line combinations are converted to '\n' on read, while on write all '\n' characters are converted to system's default line separator.'newline=""'
means no conversions take place, but input is still broken into chunks by readline() and readlines() on every '\n', '\r' and '\r\n'.'r'
- Read. Used by default.'w'
- Write. Deletes existing contents.'x'
- Write or fail if the file already exists.'a'
- Append. Creates new file if it doesn't exist.'w+'
- Read and write. Deletes existing contents.'r+'
- Read and write from the start.'a+'
- Read and write from the end.'b'
- Binary mode ('rb'
, 'wb'
, 'xb'
, …).'FileNotFoundError'
can be raised when reading with 'r'
or 'r+'
.'FileExistsError'
can be raised when writing with 'x'
.'IsADirectoryError'
and 'PermissionError'
can be raised by any.'OSError'
is the parent class of all listed exceptions.<file>.seek(0) # Moves to the start of the file.
<file>.seek(offset) # Moves 'offset' chars/bytes from the start.
<file>.seek(0, 2) # Moves to the end of the file.
<bin_file>.seek(±offset, origin) # Origin: 0 start, 1 current position, 2 end.
<str/bytes> = <file>.read(size=-1) # Reads 'size' chars/bytes or until EOF.
<str/bytes> = <file>.readline() # Returns a line or empty string/bytes on EOF.
<list> = <file>.readlines() # Returns a list of remaining lines.
<str/bytes> = next(<file>) # Returns a line using buffer. Do not mix.
<file>.write(<str/bytes>) # Writes a string or bytes object.
<file>.writelines(<collection>) # Writes a coll. of strings or bytes objects.
<file>.flush() # Flushes write buffer. Runs every 4096/8192 B.
<file>.close() # Closes the file after flushing write buffer.
def read_file(filename):
with open(filename, encoding='utf-8') as file:
return file.readlines()
def write_to_file(filename, text):
with open(filename, 'w', encoding='utf-8') as file:
file.write(text)
import os, glob
from pathlib import Path
<str> = os.getcwd() # Returns working dir. Starts as shell's $PWD.
<str> = os.path.join(<path>, ...) # Joins two or more pathname components.
<str> = os.path.realpath(<path>) # Resolves symlinks and calls path.abspath().
<str> = os.path.basename(<path>) # Returns final component of the path.
<str> = os.path.dirname(<path>) # Returns path without the final component.
<tup.> = os.path.splitext(<path>) # Splits on last period of the final component.
<list> = os.listdir(path='.') # Returns filenames located at the path.
<list> = glob.glob('<pattern>') # Returns paths matching the wildcard pattern.
<bool> = os.path.exists(<path>) # Or: <Path>.exists()
<bool> = os.path.isfile(<path>) # Or: <DirEntry/Path>.is_file()
<bool> = os.path.isdir(<path>) # Or: <DirEntry/Path>.is_dir()
<stat> = os.stat(<path>) # Or: <DirEntry/Path>.stat()
<num> = <stat>.st_mtime/st_size/… # Modification time, size in bytes, etc.
Unlike listdir(), scandir() returns DirEntry objects that cache isfile, isdir, and on Windows also stat information, thus significantly increasing the performance of code that requires it.
<iter> = os.scandir(path='.') # Returns DirEntry objects located at the path.
<str> = <DirEntry>.path # Returns the whole path as a string.
<str> = <DirEntry>.name # Returns final component as a string.
<file> = open(<DirEntry>) # Opens the file and returns a file object.
<Path> = Path(<path> [, ...]) # Accepts strings, Paths, and DirEntry objects.
<Path> = <path> / <path> [/ ...] # First or second path must be a Path object.
<Path> = <Path>.resolve() # Returns absolute path with resolved symlinks.
<Path> = Path() # Returns relative CWD. Also Path('.').
<Path> = Path.cwd() # Returns absolute CWD. Also Path().resolve().
<Path> = Path.home() # Returns user's home directory (absolute).
<Path> = Path(__file__).resolve() # Returns script's path if CWD wasn't changed.
<Path> = <Path>.parent # Returns Path without the final component.
<str> = <Path>.name # Returns final component as a string.
<str> = <Path>.stem # Returns final component without extension.
<str> = <Path>.suffix # Returns final component's extension.
<tup.> = <Path>.parts # Returns all components as strings.
<iter> = <Path>.iterdir() # Returns directory contents as Path objects.
<iter> = <Path>.glob('<pattern>') # Returns Paths matching the wildcard pattern.
<str> = str(<Path>) # Returns path as a string.
<file> = open(<Path>) # Also <Path>.read/write_text/bytes(<args>).
import os, shutil, subprocess
os.chdir(<path>) # Changes the current working directory.
os.mkdir(<path>, mode=0o777) # Creates a directory. Permissions are in octal.
os.makedirs(<path>, mode=0o777) # Creates all path's dirs. Also `exist_ok=False`.
shutil.copy(from, to) # Copies the file. 'to' can exist or be a dir.
shutil.copy2(from, to) # Also copies creation and modification time.
shutil.copytree(from, to) # Copies the directory. 'to' must not exist.
os.rename(from, to) # Renames/moves the file or directory.
os.replace(from, to) # Same, but overwrites file 'to' even on Windows.
shutil.move(from, to) # Rename() that moves into 'to' if it's a dir.
os.remove(<path>) # Deletes the file.
os.rmdir(<path>) # Deletes the empty directory.
shutil.rmtree(<path>) # Deletes the directory.
<pipe> = os.popen('<commands>') # Executes commands in sh/cmd. Returns combined stdout.
<str> = <pipe>.read(size=-1) # Reads 'size' chars or until EOF. Also readline/s().
<int> = <pipe>.close() # Returns None if last command exited with returncode 0.
>>> subprocess.run('bc', input='1 + 1\n', capture_output=True, text=True)
CompletedProcess(args='bc', returncode=0, stdout='2\n', stderr='')
>>> from shlex import split
>>> os.popen('echo 1 + 1 > test.in')
>>> subprocess.run(split('bc -s'), stdin=open('test.in'), stdout=open('test.out', 'w'))
CompletedProcess(args=['bc', '-s'], returncode=0)
>>> open('test.out').read()
'2\n'
Text file format for storing collections of strings and numbers.
import json
<str> = json.dumps(<list/dict>) # Converts collection to JSON string.
<coll> = json.loads(<str>) # Converts JSON string to collection.
def read_json_file(filename):
with open(filename, encoding='utf-8') as file:
return json.load(file)
def write_to_json_file(filename, list_or_dict):
with open(filename, 'w', encoding='utf-8') as file:
json.dump(list_or_dict, file, ensure_ascii=False, indent=2)
Binary file format for storing Python objects.
import pickle
<bytes> = pickle.dumps(<object>) # Converts object to bytes object.
<object> = pickle.loads(<bytes>) # Converts bytes object to object.
def read_pickle_file(filename):
with open(filename, 'rb') as file:
return pickle.load(file)
def write_to_pickle_file(filename, an_object):
with open(filename, 'wb') as file:
pickle.dump(an_object, file)
<reader> = csv.reader(<file>) # Also: `dialect='excel', delimiter=','`.
<list> = next(<reader>) # Returns next row as a list of strings.
<list> = list(<reader>) # Returns a list of remaining rows.
'newline=""'
argument, or newlines embedded inside quoted fields will not be interpreted correctly!<writer> = csv.writer(<file>) # Also: `dialect='excel', delimiter=','`.
<writer>.writerow(<collection>) # Encodes objects using `str(<el>)`.
<writer>.writerows(<coll_of_coll>) # Appends multiple rows.
'newline=""'
argument, or '\r' will be added in front of every '\n' on platforms that use '\r\n' line endings!'mode="a"'
to append to it or 'mode="w"'
to overwrite it.'dialect'
- Master parameter that sets the default values. String or a 'csv.Dialect' object.'delimiter'
- A one-character string used to separate fields.'lineterminator'
- How writer terminates rows. Reader is hardcoded to '\n', '\r', '\r\n'.'quotechar'
- Character for quoting fields that contain special characters.'escapechar'
- Character for escaping quotechars.'doublequote'
- Whether quotechars inside fields are/get doubled or escaped.'quoting'
- 0: As necessary, 1: All, 2: All but numbers which are read as floats, 3: None.'skipinitialspace'
- Is space character at the start of the field stripped by the reader.┏━━━━━━━━━━━━━━━━━━┯━━━━━━━━━━━━━━┯━━━━━━━━━━━━━━┯━━━━━━━━━━━━━━┓
┃ │ excel │ excel-tab │ unix ┃
┠──────────────────┼──────────────┼──────────────┼──────────────┨
┃ delimiter │ ',' │ '\t' │ ',' ┃
┃ lineterminator │ '\r\n' │ '\r\n' │ '\n' ┃
┃ quotechar │ '"' │ '"' │ '"' ┃
┃ escapechar │ None │ None │ None ┃
┃ doublequote │ True │ True │ True ┃
┃ quoting │ 0 │ 0 │ 1 ┃
┃ skipinitialspace │ False │ False │ False ┃
┗━━━━━━━━━━━━━━━━━━┷━━━━━━━━━━━━━━┷━━━━━━━━━━━━━━┷━━━━━━━━━━━━━━┛
def read_csv_file(filename, **csv_params):
with open(filename, encoding='utf-8', newline='') as file:
return list(csv.reader(file, **csv_params))
def write_to_csv_file(filename, rows, mode='w', **csv_params):
with open(filename, mode, encoding='utf-8', newline='') as file:
writer = csv.writer(file, **csv_params)
writer.writerows(rows)
A server-less database engine that stores each database into its own file.
import sqlite3
<conn> = sqlite3.connect(<path>) # Opens existing or new file. Also ':memory:'.
<conn>.close() # Closes connection. Discards uncommitted data.
<cursor> = <conn>.execute('<query>') # Can raise a subclass of sqlite3.Error.
<tuple> = <cursor>.fetchone() # Returns next row. Also next(<cursor>).
<list> = <cursor>.fetchall() # Returns remaining rows. Also list(<cursor>).
<conn>.execute('<query>') # Can raise a subclass of sqlite3.Error.
<conn>.commit() # Saves all changes since the last commit.
<conn>.rollback() # Discards all changes since the last commit.
with <conn>: # Exits the block with commit() or rollback(),
<conn>.execute('<query>') # depending on whether any exception occurred.
<conn>.execute('<query>', <list/tuple>) # Replaces '?'s in query with values.
<conn>.execute('<query>', <dict/namedtuple>) # Replaces ':<key>'s with values.
<conn>.executemany('<query>', <coll_of_coll>) # Runs execute() multiple times.
Values are not actually saved in this example because 'conn.commit()'
is omitted!
>>> conn = sqlite3.connect('test.db')
>>> conn.execute('CREATE TABLE person (person_id INTEGER PRIMARY KEY, name, height)')
>>> conn.execute('INSERT INTO person VALUES (NULL, ?, ?)', ('Jean-Luc', 187)).lastrowid
1
>>> conn.execute('SELECT * FROM person').fetchall()
[(1, 'Jean-Luc', 187)]
Library for interacting with various DB systems via SQL, method chaining, or ORM.
# $ pip3 install sqlalchemy
from sqlalchemy import create_engine, text
<engine> = create_engine('<url>') # Url: 'dialect://user:password@host/dbname'.
<conn> = <engine>.connect() # Creates a connection. Also <conn>.close().
<cursor> = <conn>.execute(text('<query>'), …) # `<dict>`. Replaces ':<key>'s with values.
with <conn>.begin(): ... # Exits the block with commit or rollback.
┏━━━━━━━━━━━━━━━━━┯━━━━━━━━━━━━━━┯━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┓
┃ Dialect │ pip3 install │ Dependencies ┃
┠─────────────────┼──────────────┼──────────────────────────────────┨
┃ mysql │ mysqlclient │ www.pypi.org/project/mysqlclient ┃
┃ postgresql │ psycopg2 │ www.pypi.org/project/psycopg2 ┃
┃ mssql │ pyodbc │ www.pypi.org/project/pyodbc ┃
┃ oracle+oracledb │ oracledb │ www.pypi.org/project/oracledb ┃
┗━━━━━━━━━━━━━━━━━┷━━━━━━━━━━━━━━┷━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┛
A bytes object is an immutable sequence of single bytes. Mutable version is called bytearray.
<bytes> = b'<str>' # Only accepts ASCII characters and \x00-\xff.
<int> = <bytes>[index] # Returns an int in range from 0 to 255.
<bytes> = <bytes>[<slice>] # Returns bytes even if it has only one element.
<bytes> = <bytes>.join(<coll_of_bytes>) # Joins elements using bytes as a separator.
<bytes> = bytes(<coll_of_ints>) # Ints must be in range from 0 to 255.
<bytes> = bytes(<str>, 'utf-8') # Encodes the string. Also <str>.encode().
<bytes> = bytes.fromhex('<hex>') # Hex pairs can be separated by whitespaces.
<bytes> = <int>.to_bytes(n_bytes, …) # `byteorder='big/little', signed=False`.
<list> = list(<bytes>) # Returns ints in range from 0 to 255.
<str> = str(<bytes>, 'utf-8') # Returns a string. Also <bytes>.decode().
<str> = <bytes>.hex() # Returns hex pairs. Accepts `sep=<str>`.
<int> = int.from_bytes(<bytes>, …) # `byteorder='big/little', signed=False`.
def read_bytes(filename):
with open(filename, 'rb') as file:
return file.read()
def write_bytes(filename, bytes_obj):
with open(filename, 'wb') as file:
file.write(bytes_obj)
from struct import pack, unpack
<bytes> = pack('<format>', <el_1> [, ...]) # Packs objects according to format string.
<tuple> = unpack('<format>', <bytes>) # Use iter_unpack() to get iterator of tuples.
>>> pack('>hhl', 1, 2, 3)
b'\x00\x01\x00\x02\x00\x00\x00\x03'
>>> unpack('>hhl', b'\x00\x01\x00\x02\x00\x00\x00\x03')
(1, 2, 3)
'='
- System's byte order (usually little-endian).'<'
- Little-endian (i.e. least significant byte first).'>'
- Big-endian (also '!'
).'c'
- A bytes object with a single element. For pad byte use 'x'
.'<n>s'
- A bytes object with n elements (not effected by byte order).'b'
- char (1/1)'h'
- short (2/2)'i'
- int (2/4)'l'
- long (4/4)'q'
- long long (8/8)'f'
- float (4/4)'d'
- double (8/8)List that can only hold numbers of a predefined type. Available types and their minimum sizes in bytes are listed above. Type sizes and byte order are always determined by the system, however bytes of each element can be reversed with byteswap() method.
from array import array
<array> = array('<typecode>', <coll_of_nums>) # Creates array from collection of numbers.
<array> = array('<typecode>', <bytes>) # Writes passed bytes to array's memory.
<array> = array('<typecode>', <array>) # Treats passed array as a sequence of numbers.
<array>.fromfile(<file>, n_items) # Appends file's contents to array's memory.
<bytes> = bytes(<array>) # Returns a copy of array's memory.
<file>.write(<array>) # Writes array's memory to the binary file.
A sequence object that points to the memory of another bytes-like object. Each element can reference a single or multiple consecutive bytes, depending on format. Order and number of elements can be changed with slicing.
<mview> = memoryview(<bytes/bytearray/array>) # Immutable if bytes is passed, else mutable.
<obj> = <mview>[index] # Returns int or float. Bytes if format is 'c'.
<mview> = <mview>[<slice>] # Returns memoryview with rearranged elements.
<mview> = <mview>.cast('<typecode>') # Only works between B/b/c and other types.
<mview>.release() # Releases memory buffer of the base object.
<bytes> = bytes(<mview>) # Returns a new bytes object. Also bytearray().
<bytes> = <bytes>.join(<coll_of_mviews>) # Joins memoryviews using bytes as a separator.
<array> = array('<typecode>', <mview>) # Treats memoryview as a sequence of numbers.
<file>.write(<mview>) # Writes `bytes(<mview>)` to the binary file.
<list> = list(<mview>) # Returns a list of ints, floats, or bytes.
<str> = str(<mview>, 'utf-8') # Treats memoryview as a bytes object.
<str> = <mview>.hex() # Returns hex pairs. Accepts `sep=<str>`.
List with efficient appends and pops from either side. Pronounced "deck".
from collections import deque
<deque> = deque(<collection>) # Use `maxlen=<int>` to set size limit.
<deque>.appendleft(<el>) # Opposite element is dropped if full.
<deque>.extendleft(<collection>) # Passed collection gets reversed.
<deque>.rotate(n=1) # Last element becomes first.
<el> = <deque>.popleft() # Raises IndexError if deque is empty.
Module of functions that provide the functionality of operators. Functions are ordered and grouped by operator precedence, from least to most binding. Logical and arithmetic operators in rows 1, 3 and 5 are ordered by precedence also within a group.
import operator as op
<bool> = op.not_(<obj>) # or, and, not (or/and missing)
<bool> = op.eq/ne/lt/ge/is_/is_not/contains(<obj>, <obj>) # ==, !=, <, >=, is, is not, in
<obj> = op.or_/xor/and_(<int/set>, <int/set>) # |, ^, &
<int> = op.lshift/rshift(<int>, <int>) # <<, >>
<obj> = op.add/sub/mul/truediv/floordiv/mod(<obj>, <obj>) # +, -, *, /, //, %
<num> = op.neg/invert(<num>) # -, ~
<num> = op.pow(<num>, <num>) # **
<func> = op.itemgetter/attrgetter/methodcaller(<obj> [, ...]) # [index/key], .name, .name([…])
elementwise_sum = map(op.add, list_a, list_b)
sorted_by_second = sorted(<coll>, key=op.itemgetter(1))
sorted_by_both = sorted(<coll>, key=op.itemgetter(1, 0))
first_element = op.methodcaller('pop', 0)(<list>)
'x < y < z'
gets converted to '(x < y) and (y < z)
'.Executes the first block with matching pattern. Added in Python 3.10.
match <object/expression>:
case <pattern> [if <condition>]:
<code>
...
<value_pattern> = 1/'abc'/True/None/math.pi # Matches the literal or a dotted name.
<class_pattern> = <type>() # Matches any object of that type (or ABC).
<wildcard_patt> = _ # Matches any object. Useful in last case.
<capture_patt> = <name> # Matches any object and binds it to name.
<as_pattern> = <pattern> as <name> # Binds match to name. Also <type>(<name>).
<or_pattern> = <pattern> | <pattern> [| ...] # Matches any of the patterns.
<sequence_patt> = [<pattern>, ...] # Matches sequence with matching items.
<mapping_patt> = {<value_pattern>: <patt>, ...} # Matches dictionary with matching items.
<class_pattern> = <type>(<attr_name>=<patt>, ...) # Matches object with matching attributes.
'*<name>'
and '**<name>'
in sequence/mapping patterns to bind remaining items.'|'
> 'as'
> ','
).>>> from pathlib import Path
>>> match Path('/home/gto/python-cheatsheet/README.md'):
... case Path(
... parts=['/', 'home', user, *_]
... ) as p if p.name.lower().startswith('readme') and p.is_file():
... print(f'{p.name} is a readme file that belongs to user {user}.')
'README.md is a readme file that belongs to user gto.'
import logging as log
log.basicConfig(filename=<path>, level='DEBUG') # Configures the root logger (see Setup).
log.debug/info/warning/error/critical(<str>) # Sends message to the root logger.
<Logger> = log.getLogger(__name__) # Returns logger named after the module.
<Logger>.<level>(<str>) # Sends message to the logger.
<Logger>.exception(<str>) # Error() that appends caught exception.
log.basicConfig(
filename=None, # Logs to stderr or appends to file.
format='%(levelname)s:%(name)s:%(message)s', # Add '%(asctime)s' for local datetime.
level=log.WARNING, # Drops messages with lower priority.
handlers=[log.StreamHandler(sys.stderr)] # Uses FileHandler if filename is set.
)
<Formatter> = log.Formatter('<format>') # Creates a Formatter.
<Handler> = log.FileHandler(<path>, mode='a') # Creates a Handler. Also `encoding=None`.
<Handler>.setFormatter(<Formatter>) # Adds Formatter to the Handler.
<Handler>.setLevel(<int/str>) # Processes all messages by default.
<Logger>.addHandler(<Handler>) # Adds Handler to the Logger.
<Logger>.setLevel(<int/str>) # What is sent to its/ancestors' handlers.
<Logger>.propagate = <bool> # Cuts off ancestors' handlers if False.
'<parent>.<name>'
.'filter(<LogRecord>)'
method (or the method itself) can be added to loggers and handlers via addFilter(). Message is dropped if filter() returns a false value.>>> logger = log.getLogger('my_module')
>>> handler = log.FileHandler('test.log', encoding='utf-8')
>>> handler.setFormatter(log.Formatter('%(asctime)s %(levelname)s:%(name)s:%(message)s'))
>>> logger.addHandler(handler)
>>> logger.setLevel('DEBUG')
>>> log.basicConfig()
>>> log.root.handlers[0].setLevel('WARNING')
>>> logger.critical('Running out of disk space.')
CRITICAL:my_module:Running out of disk space.
>>> print(open('test.log').read())
2023-02-07 23:21:01,430 CRITICAL:my_module:Running out of disk space.
<list> = dir() # List of local names (variables, funcs, classes, modules).
<dict> = vars() # Dict of local names and their objects. Also locals().
<dict> = globals() # Dict of global names and their objects, e.g. __builtin__.
<list> = dir(<obj>) # Returns names of object's attributes (including methods).
<dict> = vars(<obj>) # Returns dict of writable attributes. Also <obj>.__dict__.
<bool> = hasattr(<obj>, '<name>') # Checks if object possesses attribute with passed name.
value = getattr(<obj>, '<name>') # Returns object's attribute or raises AttributeError.
setattr(<obj>, '<name>', value) # Sets attribute. Only works on objects with __dict__ attr.
delattr(<obj>, '<name>') # Deletes attribute from __dict__. Also `del <obj>.<name>`.
<Sig> = inspect.signature(<func>) # Returns a Signature object of the passed function.
<dict> = <Sig>.parameters # Returns dict of Parameters. Also <Sig>.return_annotation.
<memb> = <Param>.kind # Returns ParameterKind member (Parameter.KEYWORD_ONLY, …).
<type> = <Param>.annotation # Returns Parameter.empty if missing. Also <Param>.default.
CPython interpreter can only run a single thread at a time. Using multiple threads won't result in a faster execution, unless at least one of the threads contains an I/O operation.
from threading import Thread, Lock, RLock, Semaphore, Event, Barrier
from concurrent.futures import ThreadPoolExecutor, as_completed
<Thread> = Thread(target=<function>) # Use `args=<collection>` to set the arguments.
<Thread>.start() # Starts the thread. Also <Thread>.is_alive().
<Thread>.join() # Waits for the thread to finish.
'kwargs=<dict>'
to pass keyword arguments to the function.'daemon=True'
, or the program will not be able to exit while the thread is alive.<lock> = Lock/RLock() # RLock can only be released by acquirer.
<lock>.acquire() # Waits for the lock to be available.
<lock>.release() # Makes the lock available again.
with <lock>: # Enters the block by calling acquire() and
... # exits it with release(), even on error.
<Semaphore> = Semaphore(value=1) # Lock that can be acquired by 'value' threads.
<Event> = Event() # Method wait() blocks until set() is called.
<Barrier> = Barrier(n_times) # Wait() blocks until it's called n times.
<Queue> = queue.Queue(maxsize=0) # A thread-safe first-in-first-out queue.
<Queue>.put(<el>) # Blocks until queue stops being full.
<Queue>.put_nowait(<el>) # Raises queue.Full exception if full.
<el> = <Queue>.get() # Blocks until queue stops being empty.
<el> = <Queue>.get_nowait() # Raises queue.Empty exception if empty.
<Exec> = ThreadPoolExecutor(max_workers=None) # Or: `with ThreadPoolExecutor() as <name>: ...`
<iter> = <Exec>.map(<func>, <args_1>, ...) # Multithreaded and non-lazy map(). Keeps order.
<Futr> = <Exec>.submit(<func>, <arg_1>, ...) # Creates a thread and returns its Future obj.
<Exec>.shutdown() # Blocks until all threads finish executing.
<bool> = <Future>.done() # Checks if the thread has finished executing.
<obj> = <Future>.result(timeout=None) # Waits for thread to finish and returns result.
<bool> = <Future>.cancel() # Cancels or returns False if running/finished.
<iter> = as_completed(<coll_of_Futures>) # `next(<iter>)` returns next completed Future.
'if __name__ == "__main__": ...'
.'async'
and its call with 'await'
.'asyncio.run(<coroutine>)'
to start the first/main coroutine.import asyncio as aio
<coro> = <async_function>(<args>) # Creates a coroutine by calling async def function.
<obj> = await <coroutine> # Starts the coroutine and returns its result.
<task> = aio.create_task(<coroutine>) # Schedules the coroutine for execution.
<obj> = await <task> # Returns coroutine's result. Also <task>.cancel().
<coro> = aio.gather(<coro/task>, ...) # Schedules coros. Returns list of results on await.
<coro> = aio.wait(<tasks>, …) # `aio.ALL/FIRST_COMPLETED`. Returns (done, pending).
<iter> = aio.as_completed(<coros/tasks>) # Iterator of coros. All return next result on await.
import asyncio, collections, curses, curses.textpad, enum, random
P = collections.namedtuple('P', 'x y') # Position
D = enum.Enum('D', 'n e s w') # Direction
W, H = 15, 7 # Width, Height
def main(screen):
curses.curs_set(0) # Makes cursor invisible.
screen.nodelay(True) # Makes getch() non-blocking.
asyncio.run(main_coroutine(screen)) # Starts running asyncio code.
async def main_coroutine(screen):
moves = asyncio.Queue()
state = {'*': P(0, 0)} | {id_: P(W//2, H//2) for id_ in range(10)}
ai = [random_controller(id_, moves) for id_ in range(10)]
mvc = [human_controller(screen, moves), model(moves, state), view(state, screen)]
tasks = [asyncio.create_task(coro) for coro in ai + mvc]
await asyncio.wait(tasks, return_when=asyncio.FIRST_COMPLETED)
async def random_controller(id_, moves):
while True:
d = random.choice(list(D))
moves.put_nowait((id_, d))
await asyncio.sleep(random.triangular(0.01, 0.65))
async def human_controller(screen, moves):
while True:
key_mappings = {258: D.s, 259: D.n, 260: D.w, 261: D.e}
if d := key_mappings.get(screen.getch()):
moves.put_nowait(('*', d))
await asyncio.sleep(0.005)
async def model(moves, state):
while state['*'] not in (state[id_] for id_ in range(10)):
id_, d = await moves.get()
deltas = {D.n: P(0, -1), D.e: P(1, 0), D.s: P(0, 1), D.w: P(-1, 0)}
state[id_] = P((state[id_].x + deltas[d].x) % W, (state[id_].y + deltas[d].y) % H)
async def view(state, screen):
offset = P(curses.COLS//2 - W//2, curses.LINES//2 - H//2)
while True:
screen.erase()
curses.textpad.rectangle(screen, offset.y-1, offset.x-1, offset.y+H, offset.x+W)
for id_, p in state.items():
screen.addstr(offset.y + (p.y - state['*'].y + H//2) % H,
offset.x + (p.x - state['*'].x + W//2) % W, str(id_))
screen.refresh()
await asyncio.sleep(0.005)
if __name__ == '__main__':
curses.wrapper(main)
# $ pip3 install tqdm
>>> import tqdm, time
>>> for el in tqdm.tqdm([1, 2, 3], desc='Processing'):
... time.sleep(1)
Processing: 100%|████████████████████| 3/3 [00:03<00:00, 1.00s/it]
# $ pip3 install matplotlib
import matplotlib.pyplot as plt
plt.plot/bar/scatter(x_data, y_data [, label=<str>]) # Also plt.plot(y_data).
plt.legend() # Adds a legend.
plt.title/xlabel/ylabel(<str>) # Adds a title or label.
plt.savefig(<path>) # Saves the plot.
plt.show() # Displays the plot.
plt.clf() # Clears the plot.
# $ pip3 install tabulate
import csv, tabulate
with open('test.csv', encoding='utf-8', newline='') as file:
rows = list(csv.reader(file))
print(tabulate.tabulate(rows, headers='firstrow'))
# $ pip3 install windows-curses
import curses, os
from curses import A_REVERSE, KEY_DOWN, KEY_UP, KEY_LEFT, KEY_RIGHT, KEY_ENTER
def main(screen):
ch, first, selected, paths = 0, 0, 0, os.listdir()
while ch != ord('q'):
height, width = screen.getmaxyx()
screen.erase()
for y, filename in enumerate(paths[first : first+height]):
color = A_REVERSE if filename == paths[selected] else 0
screen.addnstr(y, 0, filename, width-1, color)
ch = screen.getch()
selected += (ch == KEY_DOWN) - (ch == KEY_UP)
selected = max(0, min(len(paths)-1, selected))
first += (selected >= first + height) - (selected < first)
if ch in [KEY_LEFT, KEY_RIGHT, KEY_ENTER, ord('\n'), ord('\r')]:
new_dir = '..' if ch == KEY_LEFT else paths[selected]
if os.path.isdir(new_dir):
os.chdir(new_dir)
first, selected, paths = 0, 0, os.listdir()
if __name__ == '__main__':
curses.wrapper(main)
# $ pip3 install PySimpleGUI
import PySimpleGUI as sg
text_box = sg.Input(default_text='100', enable_events=True, key='-QUANTITY-')
dropdown = sg.InputCombo(['g', 'kg', 't'], 'kg', readonly=True, enable_events=True, k='-UNIT-')
label = sg.Text('100 kg is 220.462 lbs.', key='-OUTPUT-')
button = sg.Button('Close')
window = sg.Window('Weight Converter', [[text_box, dropdown], [label], [button]])
while True:
event, values = window.read()
if event in [sg.WIN_CLOSED, 'Close']:
break
try:
quantity = float(values['-QUANTITY-'])
except ValueError:
continue
unit = values['-UNIT-']
factors = {'g': 0.001, 'kg': 1, 't': 1000}
lbs = quantity * factors[unit] / 0.45359237
window['-OUTPUT-'].update(value=f'{quantity} {unit} is {lbs:g} lbs.')
window.close()
# $ pip3 install requests beautifulsoup4
import requests, bs4, os
response = requests.get('https://en.wikipedia.org/wiki/Python_(programming_language)')
document = bs4.BeautifulSoup(response.text, 'html.parser')
table = document.find('table', class_='infobox vevent')
python_url = table.find('th', text='Website').next_sibling.a['href']
logo_url = table.find('img')['src']
logo = requests.get(f'https:{logo_url}').content
filename = os.path.basename(logo_url)
with open(filename, 'wb') as file:
file.write(logo)
print(f'{python_url}, file://{os.path.abspath(filename)}')
Library for scraping websites with dynamic content.
# $ pip3 install selenium
from selenium import webdriver
<WebDrv> = webdriver.Chrome/Firefox/Safari/Edge() # Opens a browser. Also <WebDrv>.quit().
<WebDrv>.get('<url>') # Also <WebDrv>.implicitly_wait(seconds).
<El> = <WebDrv/El>.find_element('css selector', …) # '<tag>#<id>.<class>[<attr>="<val>"]…'.
<list> = <WebDrv/El>.find_elements('xpath', …) # '//<tag>[@<attr>="<val>"]…'. See XPath.
<str> = <El>.get_attribute(<str>) # Property if exists. Also <El>.text.
<El>.click/clear() # Also <El>.send_keys(<str>).
'$x("<xpath>")'
:<xpath> = //<element>[/ or // <element>] # /<child>, //<descendant>, /../<sibling>
<xpath> = //<element>/following::<element> # Next element. Also preceding/parent/…
<element> = <tag><conditions><index> # `<tag> = */a/…`, `<index> = [1/2/…]`.
<condition> = [<sub_cond> [and/or <sub_cond>]] # For negation use `not(<sub_cond>)`.
<sub_cond> = @<attr>[="<val>"] # `text()=`, `.=` match (complete) text.
<sub_cond> = contains(@<attr>, "<val>") # Is <val> a substring of attr's value?
<sub_cond> = [//]<element> # Has matching child? Descendant if //.
Flask is a micro web framework/server. If you just want to open a html file in a web browser use 'webbrowser.open(<path>)'
instead.
# $ pip3 install flask
import flask as fl
app = fl.Flask(__name__) # Returns the app object. Put at the top.
app.run(host=None, port=None, debug=None) # Or: $ flask --app FILE run [--ARG[=VAL]]…
'http://localhost:5000'
. Use 'host="0.0.0.0"'
to run externally.@app.route('/img/<path:filename>')
def serve_file(filename):
return fl.send_from_directory('dirname/', filename)
@app.route('/<sport>')
def serve_html(sport):
return fl.render_template_string('<h1>{{title}}</h1>', title=sport)
'fl.render_template(filename, <kwargs>)'
renders a file located in 'templates' dir.'fl.abort(<int>)'
returns error code and 'return fl.redirect(<url>)'
redirects.'fl.request.args[<str>]'
returns parameter from the query string (URL right of '?').'fl.session[<str>] = <obj>'
stores session data. It requires secret key to be set at the startup with 'app.secret_key = <str>'
.@app.post('/<sport>/odds')
def serve_json(sport):
team = fl.request.form['team']
return {'team': team, 'odds': [2.09, 3.74, 3.68]}
# $ pip3 install requests
>>> import threading, requests
>>> threading.Thread(target=app.run, daemon=True).start()
>>> url = 'http://localhost:5000/football/odds'
>>> response = requests.post(url, data={'team': 'arsenal f.c.'})
>>> response.json()
{'team': 'arsenal f.c.', 'odds': [2.09, 3.74, 3.68]}
from time import perf_counter
start_time = perf_counter()
...
duration_in_seconds = perf_counter() - start_time
>>> from timeit import timeit
>>> timeit('list(range(10000))', number=1000, globals=globals(), setup='pass')
0.19373
$ pip3 install line_profiler
$ echo '@profile
def main():
a = list(range(10000))
b = set(range(10000))
main()' > test.py
$ kernprof -lv test.py
Line # Hits Time Per Hit % Time Line Contents
==============================================================
1 @profile
2 def main():
3 1 253.4 253.4 32.2 a = list(range(10000))
4 1 534.1 534.1 67.8 b = set(range(10000))
$ apt/brew install graphviz && pip3 install gprof2dot snakeviz # Or download installer.
$ tail --lines=+2 test.py > test.py # Removes first line.
$ python3 -m cProfile -o test.prof test.py # Runs built-in profiler.
$ gprof2dot --format=pstats test.prof | dot -T png -o test.png # Generates call graph.
$ xdg-open/open test.png # Displays call graph.
$ snakeviz test.prof # Displays flame graph.
┏━━━━━━━━━━━━━━┯━━━━━━━━━━━━┯━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┯━━━━━━━┯━━━━━━┓
┃ pip3 install │ Target │ How to run │ Lines │ Live ┃
┠──────────────┼────────────┼───────────────────────────────┼───────┼──────┨
┃ pyinstrument │ CPU │ pyinstrument test.py │ × │ × ┃
┃ py-spy │ CPU │ py-spy top -- python3 test.py │ × │ ✓ ┃
┃ scalene │ CPU+Memory │ scalene test.py │ ✓ │ × ┃
┃ memray │ Memory │ memray run --live test.py │ ✓ │ ✓ ┃
┗━━━━━━━━━━━━━━┷━━━━━━━━━━━━┷━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┷━━━━━━━┷━━━━━━┛
Array manipulation mini-language. It can run up to one hundred times faster than the equivalent Python code. An even faster alternative that runs on a GPU is called CuPy.
# $ pip3 install numpy
import numpy as np
<array> = np.array(<list/list_of_lists/…>) # Returns a 1d/2d/… NumPy array.
<array> = np.zeros/ones/empty(<shape>) # Also np.full(<shape>, <el>).
<array> = np.arange(from_inc, to_exc, ±step) # Also np.linspace(start, stop, len).
<array> = np.random.randint(from_inc, to_exc, <shape>) # Also np.random.random(<shape>).
<view> = <array>.reshape(<shape>) # Also `<array>.shape = <shape>`.
<array> = <array>.flatten() # Also `<view> = <array>.ravel()`.
<view> = <array>.transpose() # Or: <array>.T
<array> = np.copy/abs/sqrt/log/int64(<array>) # Returns new array of the same shape.
<array> = <array>.sum/max/mean/argmax/all(axis) # Aggregates specified dimension.
<array> = np.apply_along_axis(<func>, axis, <array>) # Func can return a scalar or array.
<array> = np.concatenate(<list_of_arrays>, axis=0) # Links arrays along first axis (rows).
<array> = np.vstack/column_stack(<list_of_arrays>) # Treats 1d arrays as rows or columns.
<array> = np.tile/repeat(<array>, <int/list> [, axis]) # Tiles array or repeats its elements.
<el> = <2d>[row_index, col_index] # Or: <3d>[<int>, <int>, <int>]
<1d_view> = <2d>[row_index] # Or: <3d>[<int>, <int>, <slice>]
<1d_view> = <2d>[:, col_index] # Or: <3d>[<int>, <slice>, <int>]
<2d_view> = <2d>[from:to_row_i, from:to_col_i] # Or: <3d>[<int>, <slice>, <slice>]
<1d_array> = <2d>[row_indices, col_indices] # Or: <3d>[<int/1d>, <1d>, <1d>]
<2d_array> = <2d>[row_indices] # Or: <3d>[<int/1d>, <1d>, <slice>]
<2d_array> = <2d>[:, col_indices] # Or: <3d>[<int/1d>, <slice>, <1d>]
<2d_array> = <2d>[np.ix_(row_indices, col_indices)] # Or: <3d>[<int/1d/2d>, <2d>, <2d>]
<2d_bools> = <2d> > <el/1d/2d> # 1d object must have size of a row.
<1/2d_arr> = <2d>[<2d/1d_bools>] # 1d_bools must have size of a column.
':'
returns a slice of all dimension's indices. Omitted dimensions default to ':'
.'obj[i, j]'
to 'obj[(i, j)]'
!'ix_([1, 2], [3, 4])'
returns '[[1], [2]]'
and '[[3, 4]]'
. Due to broadcasting rules, this is the same as using '[[1, 1], [2, 2]]'
and '[[3, 4], [3, 4]]'
.A set of rules by which NumPy functions operate on arrays of different shapes.
left = [ 0.1 , 0.6 , 0.8 ] # Shape: (3,)
right = [[0.1], [0.6], [0.8]] # Shape: (3, 1)
left = [[0.1 , 0.6 , 0.8]] # Shape: (1, 3) <- !
right = [[0.1], [0.6], [0.8]] # Shape: (3, 1)
left = [[0.1, 0.6, 0.8], # Shape: (3, 3) <- !
[0.1, 0.6, 0.8],
[0.1, 0.6, 0.8]]
right = [[0.1, 0.1, 0.1], # Shape: (3, 3) <- !
[0.6, 0.6, 0.6],
[0.8, 0.8, 0.8]]
[0.1, 0.6, 0.8] => [1, 2, 1]
):>>> points = np.array([0.1, 0.6, 0.8])
[ 0.1, 0.6, 0.8 ]
>>> wrapped_points = points.reshape(3, 1)
[[0.1], [0.6], [0.8]]
>>> distances = points - wrapped_points
[[ 0. , 0.5, 0.7],
[-0.5, 0. , 0.2],
[-0.7, -0.2, 0. ]]
>>> distances = np.abs(distances)
[[ 0. , 0.5, 0.7],
[ 0.5, 0. , 0.2],
[ 0.7, 0.2, 0. ]]
>>> distances[range(3), range(3)] = np.inf
[[ inf, 0.5, 0.7],
[ 0.5, inf, 0.2],
[ 0.7, 0.2, inf]]
>>> distances.argmin(1)
[1, 2, 1]
# $ pip3 install pillow
from PIL import Image
<Image> = Image.new('<mode>', (width, height)) # Creates new image. Also `color=<int/tuple>`.
<Image> = Image.open(<path>) # Identifies format based on file's contents.
<Image> = <Image>.convert('<mode>') # Converts image to the new mode (see Modes).
<Image>.save(<path>) # Selects format based on extension (PNG/JPG…).
<Image>.show() # Displays image in default preview app.
<int/tup> = <Image>.getpixel((x, y)) # Returns pixel's value (its color).
<ImgCore> = <Image>.getdata() # Returns a flattened view of pixel values.
<Image>.putpixel((x, y), <int/tuple>) # Updates pixel's value. Clips passed int/s.
<Image>.putdata(<list/ImgCore>) # Updates pixels with a copy of the sequence.
<Image>.paste(<Image>, (x, y)) # Draws passed image at the specified location.
<Image> = <Image>.filter(<Filter>) # Use ImageFilter.<name>(<args>) for Filter.
<Image> = <Enhance>.enhance(<float>) # Use ImageEnhance.<name>(<Image>) for Enhance.
<array> = np.array(<Image>) # Creates a 2d/3d NumPy array from the image.
<Image> = Image.fromarray(np.uint8(<array>)) # Use <array>.clip(0, 255) to clip the values.
'L'
- Lightness (greyscale image). Each pixel is an int between 0 and 255.'RGB'
- Red, green, blue (true color image). Each pixel is a tuple of three ints.'RGBA'
- RGB with alpha. Low alpha (i.e. forth int) makes pixels more transparent.'HSV'
- Hue, saturation, value. Three ints representing color in HSV color space.WIDTH, HEIGHT = 100, 100
n_pixels = WIDTH * HEIGHT
hues = (255 * i/n_pixels for i in range(n_pixels))
img = Image.new('HSV', (WIDTH, HEIGHT))
img.putdata([(int(h), 255, 255) for h in hues])
img.convert('RGB').save('test.png')
from random import randint
add_noise = lambda value: max(0, min(255, value + randint(-20, 20)))
img = Image.open('test.png').convert('HSV')
img.putdata([(add_noise(h), s, v) for h, s, v in img.getdata()])
img.show()
from PIL import ImageDraw
<Draw> = ImageDraw.Draw(<Image>) # Object for adding 2D graphics to the image.
<Draw>.point((x, y)) # Draws a point. Truncates floats into ints.
<Draw>.line((x1, y1, x2, y2 [, ...])) # To get anti-aliasing use Image's resize().
<Draw>.arc((x1, y1, x2, y2), deg1, deg2) # Draws in clockwise dir. Also pieslice().
<Draw>.rectangle((x1, y1, x2, y2)) # Also rounded_rectangle(), regular_polygon().
<Draw>.polygon((x1, y1, x2, y2, ...)) # Last point gets connected to the first.
<Draw>.ellipse((x1, y1, x2, y2)) # To rotate use Image's rotate() and paste().
<Draw>.text((x, y), <str>, font=<Font>) # `<Font> = ImageFont.truetype(<path>, size)`.
'fill=<color>'
to set the primary color.'width=<int>'
to set the width of lines or contours.'outline=<color>'
to set the color of the contours.'#rrggbb[aa]'
string or a color name.# $ pip3 install imageio
from PIL import Image, ImageDraw
import imageio
WIDTH, HEIGHT, R = 126, 126, 10
frames = []
for velocity in range(1, 16):
y = sum(range(velocity))
frame = Image.new('L', (WIDTH, HEIGHT))
draw = ImageDraw.Draw(frame)
draw.ellipse((WIDTH/2-R, y, WIDTH/2+R, y+R*2), fill='white')
frames.append(frame)
frames += reversed(frames[1:-1])
imageio.mimsave('test.gif', frames, duration=0.03)
import wave
<Wave> = wave.open('<path>') # Opens the WAV file for reading.
<int> = <Wave>.getframerate() # Returns number of frames per second.
<int> = <Wave>.getnchannels() # Returns number of samples per frame.
<int> = <Wave>.getsampwidth() # Returns number of bytes per sample.
<tuple> = <Wave>.getparams() # Returns namedtuple of all parameters.
<bytes> = <Wave>.readframes(nframes) # Returns next n frames (-1 returns all).
<Wave> = wave.open('<path>', 'wb') # Creates/truncates a file for writing.
<Wave>.setframerate(<int>) # Pass 44100 for CD, 48000 for video.
<Wave>.setnchannels(<int>) # Pass 1 for mono, 2 for stereo.
<Wave>.setsampwidth(<int>) # Pass 2 for CD, 3 for hi-res sound.
<Wave>.setparams(<tuple>) # Tuple must contain all parameters.
<Wave>.writeframes(<bytes>) # Appends frames to the file.
┏━━━━━━━━━━━┯━━━━━━━━━━━┯━━━━━━┯━━━━━━━━━━━┓
┃ sampwidth │ min │ zero │ max ┃
┠───────────┼───────────┼──────┼───────────┨
┃ 1 │ 0 │ 128 │ 255 ┃
┃ 2 │ -32768 │ 0 │ 32767 ┃
┃ 3 │ -8388608 │ 0 │ 8388607 ┃
┗━━━━━━━━━━━┷━━━━━━━━━━━┷━━━━━━┷━━━━━━━━━━━┛
def read_wav_file(filename):
def get_int(bytes_obj):
an_int = int.from_bytes(bytes_obj, 'little', signed=(p.sampwidth != 1))
return an_int - 128 * (p.sampwidth == 1)
with wave.open(filename) as file:
p = file.getparams()
frames = file.readframes(-1)
bytes_samples = (frames[i : i + p.sampwidth] for i in range(0, len(frames), p.sampwidth))
return [get_int(b) / pow(2, (p.sampwidth * 8) - 1) for b in bytes_samples], p
def write_to_wav_file(filename, samples_f, p=None, nchannels=1, sampwidth=2, framerate=44100):
def get_bytes(a_float):
a_float = max(-1, min(1 - 2e-16, a_float))
a_float += p.sampwidth == 1
a_float *= pow(2, (p.sampwidth * 8) - 1)
return int(a_float).to_bytes(p.sampwidth, 'little', signed=(p.sampwidth != 1))
if p is None:
p = wave._wave_params(nchannels, sampwidth, framerate, 0, 'NONE', 'not compressed')
with wave.open(filename, 'wb') as file:
file.setparams(p)
file.writeframes(b''.join(get_bytes(f) for f in samples_f))
from math import pi, sin
samples_f = (sin(i * 2 * pi * 440 / 44100) for i in range(100_000))
write_to_wav_file('test.wav', samples_f)
from random import uniform
samples_f, params = read_wav_file('test.wav')
samples_f = (f + uniform(-0.05, 0.05) for f in samples_f)
write_to_wav_file('test.wav', samples_f, params)
# $ pip3 install simpleaudio
from simpleaudio import play_buffer
with wave.open('test.wav') as file:
p = file.getparams()
frames = file.readframes(-1)
play_buffer(frames, p.nchannels, p.sampwidth, p.framerate).wait_done()
# $ pip3 install pyttsx3
import pyttsx3
engine = pyttsx3.init()
engine.say('Sally sells seashells by the seashore.')
engine.runAndWait()
# $ pip3 install simpleaudio
import array, itertools as it, math, simpleaudio
F = 44100
P1 = '71♩,69♪,,71♩,66♪,,62♩,66♪,,59♩,,,71♩,69♪,,71♩,66♪,,62♩,66♪,,59♩,,,'
P2 = '71♩,73♪,,74♩,73♪,,74♪,,71♪,,73♩,71♪,,73♪,,69♪,,71♩,69♪,,71♪,,67♪,,71♩,,,'
get_pause = lambda seconds: it.repeat(0, int(seconds * F))
sin_f = lambda i, hz: math.sin(i * 2 * math.pi * hz / F)
get_wave = lambda hz, seconds: (sin_f(i, hz) for i in range(int(seconds * F)))
get_hz = lambda note: 440 * 2 ** ((int(note[:2]) - 69) / 12)
get_sec = lambda note: 1/4 if '♩' in note else 1/8
get_samples = lambda note: get_wave(get_hz(note), get_sec(note)) if note else get_pause(1/8)
samples_f = it.chain.from_iterable(get_samples(n) for n in (P1+P2).split(','))
samples_i = array.array('h', (int(f * 30000) for f in samples_f))
simpleaudio.play_buffer(samples_i, 1, 2, F).wait_done()
# $ pip3 install pygame
import pygame as pg
pg.init()
screen = pg.display.set_mode((500, 500))
rect = pg.Rect(240, 240, 20, 20)
while not pg.event.get(pg.QUIT):
deltas = {pg.K_UP: (0, -20), pg.K_RIGHT: (20, 0), pg.K_DOWN: (0, 20), pg.K_LEFT: (-20, 0)}
for event in pg.event.get(pg.KEYDOWN):
dx, dy = deltas.get(event.key, (0, 0))
rect = rect.move((dx, dy))
screen.fill(pg.Color('black'))
pg.draw.rect(screen, pg.Color('white'), rect)
pg.display.flip()
Object for storing rectangular coordinates.
<Rect> = pg.Rect(x, y, width, height) # Creates Rect object. Truncates passed floats.
<int> = <Rect>.x/y/centerx/centery/… # Top, right, bottom, left. Allows assignments.
<tup.> = <Rect>.topleft/center/… # Topright, bottomright, bottomleft. Same.
<Rect> = <Rect>.move((delta_x, delta_y)) # Use move_ip() to move in-place.
<bool> = <Rect>.collidepoint((x, y)) # Checks if rectangle contains the point.
<bool> = <Rect>.colliderect(<Rect>) # Checks if the two rectangles overlap.
<int> = <Rect>.collidelist(<list_of_Rect>) # Returns index of first colliding Rect or -1.
<list> = <Rect>.collidelistall(<list_of_Rect>) # Returns indices of all colliding rectangles.
Object for representing images.
<Surf> = pg.display.set_mode((width, height)) # Opens new window and returns its surface.
<Surf> = pg.Surface((width, height)) # New RGB surface. RGBA if `flags=pg.SRCALPHA`.
<Surf> = pg.image.load(<path/file>) # Loads the image. Format depends on source.
<Surf> = pg.surfarray.make_surface(<np_array>) # Also `<np_arr> = surfarray.pixels3d(<Surf>)`.
<Surf> = <Surf>.subsurface(<Rect>) # Creates a new surface from the cutout.
<Surf>.fill(color) # Tuple, Color('#rrggbb[aa]') or Color(<name>).
<Surf>.set_at((x, y), color) # Updates pixel. Also <Surf>.get_at((x, y)).
<Surf>.blit(<Surf>, (x, y)) # Draws passed surface at specified location.
from pygame.transform import scale, ...
<Surf> = scale(<Surf>, (width, height)) # Returns scaled surface.
<Surf> = rotate(<Surf>, anticlock_degrees) # Returns rotated and scaled surface.
<Surf> = flip(<Surf>, x_bool, y_bool) # Returns flipped surface.
from pygame.draw import line, ...
line(<Surf>, color, (x1, y1), (x2, y2), width) # Draws a line to the surface.
arc(<Surf>, color, <Rect>, from_rad, to_rad) # Also ellipse(<Surf>, color, <Rect>, width=0).
rect(<Surf>, color, <Rect>, width=0) # Also polygon(<Surf>, color, points, width=0).
<Font> = pg.font.Font(<path/file>, size) # Loads TTF file. Pass None for default font.
<Surf> = <Font>.render(text, antialias, color) # Background color can be specified at the end.
<Sound> = pg.mixer.Sound(<path/file/bytes>) # WAV file or bytes/array of signed shorts.
<Sound>.play/stop() # Also set_volume(<float>), fadeout(msec).
import collections, dataclasses, enum, io, itertools as it, pygame as pg, urllib.request
from random import randint
P = collections.namedtuple('P', 'x y') # Position
D = enum.Enum('D', 'n e s w') # Direction
W, H, MAX_S = 50, 50, P(5, 10) # Width, Height, Max speed
def main():
def get_screen():
pg.init()
return pg.display.set_mode((W*16, H*16))
def get_images():
url = 'https://gto76.github.io/python-cheatsheet/web/mario_bros.png'
img = pg.image.load(io.BytesIO(urllib.request.urlopen(url).read()))
return [img.subsurface(get_rect(x, 0)) for x in range(img.get_width() // 16)]
def get_mario():
Mario = dataclasses.make_dataclass('Mario', 'rect spd facing_left frame_cycle'.split())
return Mario(get_rect(1, 1), P(0, 0), False, it.cycle(range(3)))
def get_tiles():
border = [(x, y) for x in range(W) for y in range(H) if x in [0, W-1] or y in [0, H-1]]
platforms = [(randint(1, W-2), randint(2, H-2)) for _ in range(W*H // 10)]
return [get_rect(x, y) for x, y in border + platforms]
def get_rect(x, y):
return pg.Rect(x*16, y*16, 16, 16)
run(get_screen(), get_images(), get_mario(), get_tiles())
def run(screen, images, mario, tiles):
clock = pg.time.Clock()
pressed = set()
while not pg.event.get(pg.QUIT) and clock.tick(28):
keys = {pg.K_UP: D.n, pg.K_RIGHT: D.e, pg.K_DOWN: D.s, pg.K_LEFT: D.w}
pressed |= {keys.get(e.key) for e in pg.event.get(pg.KEYDOWN)}
pressed -= {keys.get(e.key) for e in pg.event.get(pg.KEYUP)}
update_speed(mario, tiles, pressed)
update_position(mario, tiles)
draw(screen, images, mario, tiles)
def update_speed(mario, tiles, pressed):
x, y = mario.spd
x += 2 * ((D.e in pressed) - (D.w in pressed))
x += (x < 0) - (x > 0)
y += 1 if D.s not in get_boundaries(mario.rect, tiles) else (D.n in pressed) * -10
mario.spd = P(x=max(-MAX_S.x, min(MAX_S.x, x)), y=max(-MAX_S.y, min(MAX_S.y, y)))
def update_position(mario, tiles):
x, y = mario.rect.topleft
n_steps = max(abs(s) for s in mario.spd)
for _ in range(n_steps):
mario.spd = stop_on_collision(mario.spd, get_boundaries(mario.rect, tiles))
x, y = x + (mario.spd.x / n_steps), y + (mario.spd.y / n_steps)
mario.rect.topleft = x, y
def get_boundaries(rect, tiles):
deltas = {D.n: P(0, -1), D.e: P(1, 0), D.s: P(0, 1), D.w: P(-1, 0)}
return {d for d, delta in deltas.items() if rect.move(delta).collidelist(tiles) != -1}
def stop_on_collision(spd, bounds):
return P(x=0 if (D.w in bounds and spd.x < 0) or (D.e in bounds and spd.x > 0) else spd.x,
y=0 if (D.n in bounds and spd.y < 0) or (D.s in bounds and spd.y > 0) else spd.y)
def draw(screen, images, mario, tiles):
screen.fill((85, 168, 255))
mario.facing_left = mario.spd.x < 0 if mario.spd.x else mario.facing_left
is_airborne = D.s not in get_boundaries(mario.rect, tiles)
image_index = 4 if is_airborne else (next(mario.frame_cycle) if mario.spd.x else 6)
screen.blit(images[image_index + (mario.facing_left * 9)], mario.rect)
for t in tiles:
is_border = t.x in [0, (W-1)*16] or t.y in [0, (H-1)*16]
screen.blit(images[18 if is_border else 19], t)
pg.display.flip()
if __name__ == '__main__':
main()
Data analysis library. For examples see Plotly.
# $ pip3 install pandas matplotlib
import pandas as pd, matplotlib.pyplot as plt
Ordered dictionary with a name.
>>> s = pd.Series([1, 2], index=['x', 'y'], name='a'); s
x 1
y 2
Name: a, dtype: int64
<S> = pd.Series(<list>) # Uses list's indices for 'index'.
<S> = pd.Series(<dict>) # Uses dictionary's keys for 'index'.
<el> = <S>.loc[key] # Or: <S>.iloc[i]
<S> = <S>.loc[coll_of_keys] # Or: <S>.iloc[coll_of_i]
<S> = <S>.loc[from_key : to_key_inc] # Or: <S>.iloc[from_i : to_i_exc]
<el> = <S>[key/i] # Or: <S>.<key>
<S> = <S>[coll_of_keys/coll_of_i] # Or: <S>[key/i : key/i]
<S> = <S>[bools] # Or: <S>.loc/iloc[bools]
<S> = <S> > <el/S> # Returns S of bools. Pairs items by keys.
<S> = <S> + <el/S> # Items with non-matching keys get value NaN.
<S> = pd.concat(<coll_of_S>) # Concats multiple series into one long Series.
<S> = <S>.combine_first(<S>) # Adds items that are not yet present.
<S>.update(<S>) # Updates items that are already present.
<S>.plot.line/area/bar/pie/hist() # Generates a plot. `plt.show()` displays it.
'obj[x, y]'
is converted to 'obj[(x, y)]'
!'np.int64'
. Series is converted to 'float64'
if we assign np.nan to any item. Use '<S>.astype(<str/type>)'
to get converted Series.'pd.Series([100], dtype="int8") + 100'
.<el> = <S>.sum/max/mean/idxmax/all() # Or: <S>.agg(lambda <S>: <el>)
<S> = <S>.rank/diff/cumsum/ffill/interpol…() # Or: <S>.agg/transform(lambda <S>: <S>)
<S> = <S>.isna/fillna/isin([<el/coll>]) # Or: <S>.agg/transform/map(lambda <el>: <el>)
┏━━━━━━━━━━━━━━┯━━━━━━━━━━━━━┯━━━━━━━━━━━━━┯━━━━━━━━━━━━━━━┓
┃ │ 'sum' │ ['sum'] │ {'s': 'sum'} ┃
┠──────────────┼─────────────┼─────────────┼───────────────┨
┃ s.apply(…) │ 3 │ sum 3 │ s 3 ┃
┃ s.agg(…) │ │ │ ┃
┗━━━━━━━━━━━━━━┷━━━━━━━━━━━━━┷━━━━━━━━━━━━━┷━━━━━━━━━━━━━━━┛
┏━━━━━━━━━━━━━━┯━━━━━━━━━━━━━┯━━━━━━━━━━━━━┯━━━━━━━━━━━━━━━┓
┃ │ 'rank' │ ['rank'] │ {'r': 'rank'} ┃
┠──────────────┼─────────────┼─────────────┼───────────────┨
┃ s.apply(…) │ │ rank │ ┃
┃ s.agg(…) │ x 1.0 │ x 1.0 │ r x 1.0 ┃
┃ │ y 2.0 │ y 2.0 │ y 2.0 ┃
┗━━━━━━━━━━━━━━┷━━━━━━━━━━━━━┷━━━━━━━━━━━━━┷━━━━━━━━━━━━━━━┛
'inplace=True'
.'<S>[key_1, key_2]'
to get its values.Table with labeled rows and columns.
>>> df = pd.DataFrame([[1, 2], [3, 4]], index=['a', 'b'], columns=['x', 'y']); df
x y
a 1 2
b 3 4
<DF> = pd.DataFrame(<list_of_rows>) # Rows can be either lists, dicts or series.
<DF> = pd.DataFrame(<dict_of_columns>) # Columns can be either lists, dicts or series.
<el> = <DF>.loc[row_key, col_key] # Or: <DF>.iloc[row_i, col_i]
<S/DF> = <DF>.loc[row_key/s] # Or: <DF>.iloc[row_i/s]
<S/DF> = <DF>.loc[:, col_key/s] # Or: <DF>.iloc[:, col_i/s]
<DF> = <DF>.loc[row_bools, col_bools] # Or: <DF>.iloc[row_bools, col_bools]
<S/DF> = <DF>[col_key/s] # Or: <DF>.<col_key>
<DF> = <DF>[<S_of_bools>] # Filters rows. For example `df[df.x > 1]`.
<DF> = <DF>[<DF_of_bools>] # Assigns NaN to items that are False in bools.
<DF> = <DF> > <el/S/DF> # Returns DF of bools. S is treated as a row.
<DF> = <DF> + <el/S/DF> # Items with non-matching keys get value NaN.
<DF> = <DF>.set_index(col_key) # Replaces row keys with column's values.
<DF> = <DF>.reset_index(drop=False) # Drops or moves row keys to column named index.
<DF> = <DF>.sort_index(ascending=True) # Sorts rows by row keys. Use `axis=1` for cols.
<DF> = <DF>.sort_values(col_key/s) # Sorts rows by passed column/s. Also `axis=1`.
<DF> = <DF>.head/tail/sample(<int>) # Returns first, last, or random n rows.
<DF> = <DF>.describe() # Describes columns. Also info(), corr(), shape.
<DF> = <DF>.query('<query>') # Filters rows. For example `df.query('x > 1')`.
<DF>.plot.line/area/bar/scatter(x=col_key, …) # `y=col_key/s`. Also hist/box(by=col_key).
plt.show() # Displays the plot. Also plt.savefig(<path>).
>>> df_2 = pd.DataFrame([[4, 5], [6, 7]], index=['b', 'c'], columns=['y', 'z']); df_2
y z
b 4 5
c 6 7
┏━━━━━━━━━━━━━━━━━━━━━━━┯━━━━━━━━━━━━━━━┯━━━━━━━━━━━━┯━━━━━━━━━━━━┯━━━━━━━━━━━━━━━━━━━━━━━━━━━┓
┃ │ 'outer' │ 'inner' │ 'left' │ Description ┃
┠───────────────────────┼───────────────┼────────────┼────────────┼───────────────────────────┨
┃ df.merge(df_2, │ x y z │ x y z │ x y z │ Merges on column if 'on' ┃
┃ on='y', │ 0 1 2 . │ 3 4 5 │ 1 2 . │ or 'left_on/right_on' are ┃
┃ how=…) │ 1 3 4 5 │ │ 3 4 5 │ set, else on shared cols. ┃
┃ │ 2 . 6 7 │ │ │ Uses 'inner' by default. ┃
┠───────────────────────┼───────────────┼────────────┼────────────┼───────────────────────────┨
┃ df.join(df_2, │ x yl yr z │ │ x yl yr z │ Merges on row keys. ┃
┃ lsuffix='l', │ a 1 2 . . │ x yl yr z │ 1 2 . . │ Uses 'left' by default. ┃
┃ rsuffix='r', │ b 3 4 4 5 │ 3 4 4 5 │ 3 4 4 5 │ If Series is passed, it ┃
┃ how=…) │ c . . 6 7 │ │ │ is treated as a column. ┃
┠───────────────────────┼───────────────┼────────────┼────────────┼───────────────────────────┨
┃ pd.concat([df, df_2], │ x y z │ y │ │ Adds rows at the bottom. ┃
┃ axis=0, │ a 1 2 . │ 2 │ │ Uses 'outer' by default. ┃
┃ join=…) │ b 3 4 . │ 4 │ │ A Series is treated as a ┃
┃ │ b . 4 5 │ 4 │ │ column. To add a row use ┃
┃ │ c . 6 7 │ 6 │ │ pd.concat([df, DF([s])]). ┃
┠───────────────────────┼───────────────┼────────────┼────────────┼───────────────────────────┨
┃ pd.concat([df, df_2], │ x y y z │ │ │ Adds columns at the ┃
┃ axis=1, │ a 1 2 . . │ x y y z │ │ right end. Uses 'outer' ┃
┃ join=…) │ b 3 4 4 5 │ 3 4 4 5 │ │ by default. A Series is ┃
┃ │ c . . 6 7 │ │ │ treated as a column. ┃
┗━━━━━━━━━━━━━━━━━━━━━━━┷━━━━━━━━━━━━━━━┷━━━━━━━━━━━━┷━━━━━━━━━━━━┷━━━━━━━━━━━━━━━━━━━━━━━━━━━┛
<S> = <DF>.sum/max/mean/idxmax/all() # Or: <DF>.apply/agg(lambda <S>: <el>)
<DF> = <DF>.rank/diff/cumsum/ffill/interpo…() # Or: <DF>.apply/agg/transform(lambda <S>: <S>)
<DF> = <DF>.isna/fillna/isin([<el/coll>]) # Or: <DF>.applymap(lambda <el>: <el>)
┏━━━━━━━━━━━━━━━━━┯━━━━━━━━━━━━━━━┯━━━━━━━━━━━━━━━┯━━━━━━━━━━━━━━━┓
┃ │ 'sum' │ ['sum'] │ {'x': 'sum'} ┃
┠─────────────────┼───────────────┼───────────────┼───────────────┨
┃ df.apply(…) │ x 4 │ x y │ x 4 ┃
┃ df.agg(…) │ y 6 │ sum 4 6 │ ┃
┗━━━━━━━━━━━━━━━━━┷━━━━━━━━━━━━━━━┷━━━━━━━━━━━━━━━┷━━━━━━━━━━━━━━━┛
┏━━━━━━━━━━━━━━━━━┯━━━━━━━━━━━━━━━┯━━━━━━━━━━━━━━━┯━━━━━━━━━━━━━━━┓
┃ │ 'rank' │ ['rank'] │ {'x': 'rank'} ┃
┠─────────────────┼───────────────┼───────────────┼───────────────┨
┃ df.apply(…) │ │ x y │ ┃
┃ df.agg(…) │ x y │ rank rank │ x ┃
┃ df.transform(…) │ a 1.0 1.0 │ a 1.0 1.0 │ a 1.0 ┃
┃ │ b 2.0 2.0 │ b 2.0 2.0 │ b 2.0 ┃
┗━━━━━━━━━━━━━━━━━┷━━━━━━━━━━━━━━━┷━━━━━━━━━━━━━━━┷━━━━━━━━━━━━━━━┛
'axis=1'
to process the rows instead.'<DF>.loc[row_key, (col_key_1, col_key_2)]'
.<DF> = <DF>.xs(row_key, level=<int>) # Rows with key on passed level of multi-index.
<DF> = <DF>.xs(row_keys, level=<ints>) # Rows that have first key on first level, etc.
<DF> = <DF>.set_index(col_keys) # Combines multiple columns into a multi-index.
<S/DF> = <DF>.stack/unstack(level=-1) # Combines col keys with row keys or vice versa.
<DF> = <DF>.pivot_table(index=col_key/s) # `columns=key/s, values=key/s, aggfunc='mean'`.
<DF> = pd.read_json/html('<str/path/url>') # Run `$ pip3 install beautifulsoup4 lxml`.
<DF> = pd.read_csv('<path/url>') # `header/index_col/dtype/usecols/…=<obj>`.
<DF> = pd.read_pickle/excel('<path/url>') # Use `sheet_name=None` to get all Excel sheets.
<DF> = pd.read_sql('<table/query>', <conn.>) # SQLite3/SQLAlchemy connection (see #SQLite).
<dict> = <DF>.to_dict('d/l/s/…') # Returns columns as dicts, lists or series.
<str> = <DF>.to_json/html/csv/latex() # Saves output to a file if path is passed.
<DF>.to_pickle/excel(<path>) # Run `$ pip3 install "pandas[excel]" odfpy`.
<DF>.to_sql('<table_name>', <connection>) # Also `if_exists='fail/replace/append'`.
'<S> = pd.to_datetime(<S>, errors="coerce")'
, which uses pd.NaT.'<S>.dt.year/date/…'
.Object that groups together rows of a dataframe based on the value of the passed column.
<GB> = <DF>.groupby(col_key/s) # Splits DF into groups based on passed column.
<DF> = <GB>.apply(<func>) # Maps each group. Func can return DF, S or el.
<DF> = <GB>.filter(<func>) # Drops a group if function returns False.
<DF> = <GB>.get_group(<el>) # Selects a group by grouping column's value.
<S> = <GB>.size() # S of group sizes. Same keys as get_group().
<GB> = <GB>[col_key] # Single column GB. All operations return S.
<DF> = <GB>.sum/max/mean/idxmax/all() # Or: <GB>.agg(lambda <S>: <el>)
<DF> = <GB>.rank/diff/cumsum/ffill() # Or: <GB>.transform(lambda <S>: <S>)
<DF> = <GB>.fillna(<el>) # Or: <GB>.transform(lambda <S>: <S>)
'z'
on reset_index():>>> df = pd.DataFrame([[1, 2, 3], [4, 5, 6], [7, 8, 6]], list('abc'), list('xyz'))
>>> gb = df.groupby('z'); gb.apply(print)
x y z
a 1 2 3
x y z
b 4 5 6
c 7 8 6
>>> gb.sum()
x y
z
3 1 2
6 11 13
Object for rolling window calculations.
<RS/RDF/RGB> = <S/DF/GB>.rolling(win_size) # Also: `min_periods=None, center=False`.
<RS/RDF/RGB> = <RDF/RGB>[col_key/s] # Or: <RDF/RGB>.col_key
<S/DF> = <R>.mean/sum/max() # Or: <R>.apply/agg(<agg_func/str>)
# $ pip3 install plotly kaleido pandas
import plotly.express as px, pandas as pd
<Fig> = px.line(<DF>, x=col_key, y=col_key) # Or: px.line(x=<list>, y=<list>)
<Fig>.update_layout(margin=dict(t=0, r=0, b=0, l=0)) # Also `paper_bgcolor='rgb(0, 0, 0)'`.
<Fig>.write_html/json/image('<path>') # <Fig>.show() displays the plot.
<Fig> = px.area/bar/box(<DF>, x=col_key, y=col_key) # Also `color=col_key`.
<Fig> = px.scatter(<DF>, x=col_key, y=col_key) # Also `color/size/symbol=col_key`.
<Fig> = px.scatter_3d(<DF>, x=col_key, y=col_key, …) # `z=col_key`. Also color/size/symbol.
<Fig> = px.histogram(<DF>, x=col_key [, nbins=<int>]) # Number of bins depends on DF size.
covid = pd.read_csv('https://raw.githubusercontent.com/owid/covid-19-data/8dde8ca49b'
'6e648c17dd420b2726ca0779402651/public/data/owid-covid-data.csv',
usecols=['iso_code', 'date', 'total_deaths', 'population'])
continents = pd.read_csv('https://gto76.github.io/python-cheatsheet/web/continents.csv',
usecols=['Three_Letter_Country_Code', 'Continent_Name'])
df = pd.merge(covid, continents, left_on='iso_code', right_on='Three_Letter_Country_Code')
df = df.groupby(['Continent_Name', 'date']).sum().reset_index()
df['Total Deaths per Million'] = df.total_deaths * 1e6 / df.population
df = df[df.date > '2020-03-14']
df = df.rename({'date': 'Date', 'Continent_Name': 'Continent'}, axis='columns')
px.line(df, x='Date', y='Total Deaths per Million', color='Continent').show()
import pandas as pd, plotly.graph_objects as go
def main():
covid, bitcoin, gold, dow = scrape_data()
df = wrangle_data(covid, bitcoin, gold, dow)
display_data(df)
def scrape_data():
def get_covid_cases():
url = 'https://covid.ourworldindata.org/data/owid-covid-data.csv'
df = pd.read_csv(url, usecols=['location', 'date', 'total_cases'])
df = df[df.location == 'World']
return df.set_index('date').total_cases
def get_ticker(symbol):
url = (f'https://query1.finance.yahoo.com/v7/finance/download/{symbol}?'
'period1=1579651200&period2=9999999999&interval=1d&events=history')
df = pd.read_csv(url, usecols=['Date', 'Close'])
return df.set_index('Date').Close
out = get_covid_cases(), get_ticker('BTC-USD'), get_ticker('GC=F'), get_ticker('^DJI')
names = ['Total Cases', 'Bitcoin', 'Gold', 'Dow Jones']
return map(pd.Series.rename, out, names)
def wrangle_data(covid, bitcoin, gold, dow):
df = pd.concat([bitcoin, gold, dow], axis=1) # Creates table by joining columns on dates.
df = df.sort_index().interpolate() # Sorts rows by date and interpolates NaN-s.
df = df.loc['2020-02-23':] # Discards rows before '2020-02-23'.
df = (df / df.iloc[0]) * 100 # Calculates percentages relative to day 1.
df = df.join(covid) # Adds column with covid cases.
return df.sort_values(df.index[-1], axis=1) # Sorts columns by last day's value.
def display_data(df):
figure = go.Figure()
for col_name in reversed(df.columns):
yaxis = 'y1' if col_name == 'Total Cases' else 'y2'
trace = go.Scatter(x=df.index, y=df[col_name], name=col_name, yaxis=yaxis)
figure.add_trace(trace)
figure.update_layout(
yaxis1=dict(title='Total Cases', rangemode='tozero'),
yaxis2=dict(title='%', rangemode='tozero', overlaying='y', side='right'),
legend=dict(x=1.08),
width=944,
height=423
)
figure.show()
if __name__ == '__main__':
main()
Library that compiles Python code into C.
# $ pip3 install cython
import pyximport; pyximport.install()
import <cython_script>
<cython_script>.main()
'cdef'
definitions are optional, but they contribute to the speed-up.'pyx'
extension.cdef <ctype> <var_name> [= <obj>]
cdef <ctype>[n_elements] <var_name> [= <collection>]
cdef <ctype/void> <func_name>(<ctype> <arg_name>): ...
cdef class <class_name>:
cdef public <ctype> <attr_name>
def __init__(self, <ctype> <arg_name>):
self.<attr_name> = <arg_name>
System for installing libraries directly into project's directory.
$ python3 -m venv NAME # Creates virtual environment in current directory.
$ source NAME/bin/activate # Activates env. On Windows run `NAME\Scripts\activate`.
$ pip3 install LIBRARY # Installs the library into active environment.
$ python3 FILE # Runs the script in active environment. Also `./FILE`.
$ deactivate # Deactivates the active virtual environment.
Run the script with '$ python3 FILE'
or '$ chmod u+x FILE; ./FILE'
. To automatically start the debugger when uncaught exception occurs run '$ python3 -m pdb -cc FILE'
.
#!/usr/bin/env python3
#
# Usage: .py
#
from sys import argv, exit
from collections import defaultdict, namedtuple
from dataclasses import make_dataclass
from enum import Enum
import functools as ft, itertools as it, operator as op, re
def main():
pass
###
## UTIL
#
def read_file(filename):
with open(filename, encoding='utf-8') as file:
return file.readlines()
if __name__ == '__main__':
main()