Skip to content

Latest commit

 

History

History
349 lines (250 loc) · 13.8 KB

python.md

File metadata and controls

349 lines (250 loc) · 13.8 KB

python3

The confusing brackets

  • []

    • create lists pre-populated
    • list comprehensions (loops)
    • selecting (slicing)
    • selecting from dicts!

  • ()

    • create tuples pre-populated
      • ('',) single element!
      • or (''), !
    • generators!
    • Logical grouping
      • multiline

  • {}

    • create dicts
    • dict comprehensions
    • sets !
      • not interoperable with dicts?
    • set comprehensions !

  • <>

    • no used?

  • and, or, not, ^ wtf python!

  • 0x11==17 0b11==3 0o11==9

  • hex() bin() oct() to string f'0b{number:08b}'

python arrays/lists are janky - it would be nice to use chainable functions

  • funct enhanced functions for lists

https://book.pythontips.com/en/latest/index.html

Google DocString Guide sphinx docstring format

See lanaguageEdgeCases https://github.com/satwikkansal/wtfpython

See [dynamic-languages] for a great breakdown of compiler for dict() and {}

Professional Interview Screening

what is PEP8 -> style guide what is a decorator -> function wrapper what is the difference between list & tuple -> mutability

    >>> aa=(x+1 for x in range(3)) ; print(tuple(aa), tuple(aa))
    ((1, 2, 3), ())
    # Q: Why? - A: The generator is exhausted

    >>> aa=[1,2,3] ; bb=aa ; aa[:]=[4,5,6] ; print(aa, bb)
    ([4, 5, 6], [4, 5, 6])
    # Q: Why? - A: aa an bb reference the same list

    >>> dd = {i for i in (1,2,2,3)} ; dd &= {2,3,4} ; print(dd)
    set([2, 3])
    # Q: Why? - A: sets have no duplicates `&=` is union_in-place modification

I asked ChatGPT on 24/04/2023 these interview screening questions

I have a set of questions I use to screen professional python programmers before inviting them to a job interview. I have listed three mini programs and their output. I ask candidates to describe why each program creates these outputs. Can you explain why these python snippets produce the outputs they do?

>>> aa=(x+1 for x in range(3)) ; print(tuple(aa), tuple(aa))
((1, 2, 3), ())

>>> aa=[1,2,3] ; bb=aa ; aa[:]=[4,5,6] ; print(aa, bb)
([4, 5, 6], [4, 5, 6])

>>> dd = {i for i in (1,2,2,3)} ; dd &= {2,3,4} ; print(dd)
set([2, 3])

Sure, I'd be happy to explain these snippets!

  1. aa=(x+1 for x in range(3)) ; print(tuple(aa), tuple(aa))

In this code, a generator expression is created with (x+1 for x in range(3)) and assigned to the variable aa. A generator is a special type of iterable that allows you to iterate over its elements one at a time.

Then, tuple(aa) is called twice: the first time, it creates a tuple with the first three values of the generator (1, 2, 3) and prints it. The second time, tuple(aa) creates an empty tuple because all the values in the generator have already been exhausted by the previous tuple(aa) call.

So the output of this program is ((1, 2, 3), ()).

  1. aa=[1,2,3] ; bb=aa ; aa[:]=[4,5,6] ; print(aa, bb)

This code creates a list aa containing the values 1, 2, and 3, and then assigns aa to the variable bb. The third line is where the interesting stuff happens: aa[:]=[4,5,6]. This is a slice assignment, which means it replaces the entire contents of aa with the new list [4,5,6]. Since bb is just a reference to the same list object as aa, it also gets updated with the new values.

So the output of this program is ([4, 5, 6], [4, 5, 6]).

  1. dd = {i for i in (1,2,2,3)} ; dd &= {2,3,4} ; print(dd)

In this code, a set comprehension is used to create a new set dd containing the unique values from the tuple (1,2,2,3). Since sets can only contain unique values, this set contains the values 1, 2, and 3.

Then, dd &= {2,3,4} performs an in-place intersection of dd with the set {2,3,4}. This means that any elements in dd that are not also in {2,3,4} are removed, leaving only the values 2 and 3.

So the output of this program is set([2, 3]).

# aa=[1,2,3];bb=aa;aa=[4,5,6];print(aa,bb)

t = 10 + 1, 20 + 2 ; assert t == 11, 22
# https://twitter.com/raymondh/status/1318242020461367296

See [interview]

def fizzbuzz(i):
    """
    * [FizzBuzz](https://en.wikipedia.org/wiki/Fizz_buzz#Programming_interviews) [_](https://imranontech.com/2007/01/24/using-fizzbuzz-to-find-developers-who-grok-coding/)
        * > Write a program that prints the numbers from 1 to 100. But for multiples of three print “Fizz” instead of the number and for the multiples of five print “Buzz”. For numbers which are multiples of both three and five print “FizzBuzz”.
        * In under 5min (Pro) - in under 10min (A Grade)
        * [Tom Scott commentary and solution](https://www.youtube.com/watch?v=QPZ0pIK_wsc)

    >>> tuple(map(fizzbuzz, range(100)))
    ('fizzbuzz', 1, 2, 'fizz', 4, 'buzz', 'fizz', 7, 8, 'fizz', 'buzz', 11, 'fizz', 13, 14, 'fizzbuzz', 16, 17, 'fizz', 19, 'buzz', 'fizz', 22, 23, 'fizz', 'buzz', 26, 'fizz', 28, 29, 'fizzbuzz', 31, 32, 'fizz', 34, 'buzz', 'fizz', 37, 38, 'fizz', 'buzz', 41, 'fizz', 43, 44, 'fizzbuzz', 46, 47, 'fizz', 49, 'buzz', 'fizz', 52, 53, 'fizz', 'buzz', 56, 'fizz', 58, 59, 'fizzbuzz', 61, 62, 'fizz', 64, 'buzz', 'fizz', 67, 68, 'fizz', 'buzz', 71, 'fizz', 73, 74, 'fizzbuzz', 76, 77, 'fizz', 79, 'buzz', 'fizz', 82, 83, 'fizz', 'buzz', 86, 'fizz', 88, 89, 'fizzbuzz', 91, 92, 'fizz', 94, 'buzz', 'fizz', 97, 98, 'fizz')
    """
    r = ''
    if i % 3 == 0:
        r += 'fizz'
    if i % 5 == 0:
        r += 'buzz'
    if not r:
        r = i
    return r

What happens if

dd={'a':1, 'b':2}
for k in dd.keys():
    dd[k]=2
print(dd)


for i in (1,2,3):
    if i == 4:
        break
else:
    


ff = [1,2,3]
gg = [3,4,5]
hh = [5,6,7]
ii = ff
jj = ii
kk = hh

# What is ff, gg, hh, ii, jj, kk?
jj.append(10)

gg.append(11)

kk = gg + gg
kk.append(12)
from itertools import chain, cycle, permutations
from functools partial, lru_cache, reduce, wraps
from collections import defaultdict, namedtuple, ChainMap, deque

https://github.com/SigmaQuan/Better-Python-59-Ways

Type checking in python

Useful? Or unneeded complexity? Surely this defeats the purpose of a dynamic language?

  • Python's type checking renaissance
  • Python’s “Type Hints” are a bit of a disappointment to me
  • json2pyi
    • web service to take json and suggest python typeddicts
  • pydantic
    • has some wholes - mypy and pydantic don't quite see eye to eye
  • msgspec
    • msgspec is a fast serialization and validation library, with builtin support for JSON, MessagePack, YAML, and TOML. It features:
    • 🚀 High performance encoders/decoders for common protocols. The JSON and MessagePack implementations regularly benchmark as the fastest options for Python.
    • 🎉 Support for a wide variety of Python types. Additional types may be supported through extensions.
    • 🔍 Zero-cost schema validation using familiar Python type annotations. In benchmarks msgspec decodes and validates JSON faster than orjson can decode it alone.
    • ✨ A speedy Struct type for representing structured data. If you already use dataclasses or attrs, Structs should feel familiar. However, they’re 5-60x faster for common operations.

Advanced Modules

Techniques

Reference Implementation

Performance logging - google chrome devtools viewer format? - automatically attach/analyse program

Elegant Example

def predict(unlabeled_point, points, labels, *, k=5):
  "K nearest neighbors classifier"
  knn = set(nsmallest(k, points, key=partial(dist, unlabeled_point)))
  lnn = [label for label, point in zip(labels, points) if point in knn]
  return mode(lnn)

I like it because the powerful lego building blocks (set, nsmallest, partial, dist, zip, and mode) fit together so nicely to express a machine learning algorithm economically and (to my eyes) clearly.

Features

  • python-syntax-errors - This is a collection of no-op statements that are syntactically valid only since Python X.Y, for most X.Y ≥ 2.4.
    • 0_0 # Python >= 3.6 is required

Structural Pattern Matching

Compiled Python?

Compile LLVM Python https://github.com/exaloop/codon Includes GPU processing!

Concurrency

GUI

Python has built in TK.

  • pywebview
    • python #electron bundler - can even bundle for android

    • jQuery like DOM manipulation, traversal and event handling straight from Python.

Embedded in other software

Package Manager

pip is showing it's problems. poetry came in to save th day but seems to have limited take-up. We still have problems where two dependencies want different versions of a library.

Tools

  • tach

    • A Python tool to visualize + enforce dependencies, using modular architecture 🌎 Open source 🐍 Installable via pip 🔧 Able to be adopted incrementally - ⚡ Implemented with no runtime impact ♾️ Interoperable with your existing systems 🦀 Written in rust