Created
April 11, 2024 19:40
-
-
Save brabemi/96925d399be835089e515608ae6fedd7 to your computer and use it in GitHub Desktop.
PyLadies - Praha - jaro 2024 - Lekce - Lineární a kvadratická časová složitost (2024-04-08)
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# Osnova lekce - https://github.com/PetraVidnerova/PyLadies_pokr/tree/main/lesson_time | |
from pprint import pprint | |
from random import randrange | |
from time import time | |
# import string | |
retezec = 'skakal pes pres oves' | |
def vygeneruj_retezec(delka): | |
ABECEDA = 'abcdefghiklmnopqrstuvwxyz' | |
ABECEDA += ABECEDA.upper() | |
ABECEDA += '0123456789' | |
# Aternativně pomocí proměnných ze standardní knihovny | |
# ABECEDA = string.ascii_letters + string.digits | |
vysledek = [] | |
delka_abecedy = len(ABECEDA) | |
for pismeno in range(delka): | |
vysledek.append(ABECEDA[randrange(delka_abecedy)]) | |
return ''.join(vysledek) | |
def read_bible_lines(num=10): | |
text = "" | |
# stažení bible https://github.com/PetraVidnerova/PyLadies_pokr/blob/main/lesson_time/bible_part.txt.zip | |
with open("bible_part.txt", "r", encoding="utf-8") as f: | |
for i, line in enumerate(f): | |
if i > num: | |
return text | |
text += line | |
return text | |
def count_sequence(input_string, seq_len=2): | |
result = {} | |
for i in range(len(input_string)-seq_len+1): | |
pismena = input_string[i:i+seq_len] | |
if pismena in result: | |
continue | |
pocet = input_string.count(pismena) | |
result[pismena] = pocet | |
return result | |
def count_sequence_v2(input_string, seq_len=2): | |
result = {} | |
for i in range(len(input_string)-seq_len+1): | |
pismena = input_string[i:i+seq_len] | |
if pismena in result: | |
result[pismena] += 1 | |
else: | |
result[pismena] = 1 | |
return result | |
def count_letters(input_string): | |
result = {} | |
for pismeno in input_string: | |
if pismeno in result: | |
continue | |
pocet = input_string.count(pismeno) | |
result[pismeno] = pocet | |
return result | |
def count_letters_v2(input_string): | |
result = {} | |
for pismeno in input_string: | |
if pismeno in result: | |
result[pismeno] += 1 | |
else: | |
result[pismeno] = 1 | |
return result | |
# retezec = vygeneruj_retezec(50_000_000) | |
retezec = read_bible_lines(10_000) | |
# ukol nejčaštější a nejméně časté písmeno v bibli | |
def najdi_minimum(slovnik): | |
min_znak = None | |
minimum = None | |
for znak in slovnik: | |
if minimum is None: | |
min_znak = znak | |
minimum = slovnik[znak] | |
if minimum > slovnik[znak]: | |
min_znak = znak | |
minimum = slovnik[znak] | |
return min_znak | |
def najdi_maximim(slovnik): | |
max_znak = None | |
maximum = None | |
for znak in slovnik: | |
if znak in ' ': | |
continue | |
if maximum is None: | |
max_znak = znak | |
maximum = slovnik[znak] | |
if maximum < slovnik[znak]: | |
max_znak = znak | |
maximum = slovnik[znak] | |
return max_znak | |
start = time() | |
# print(retezec) | |
# Pro jeden znak obě funkce fungují stehně rychle | |
pocty_znaku = count_letters(retezec) | |
# pocty_znaku = count_letters_v2(retezec) | |
# Domácí úkol | |
# prohlédněte si funkce count_sequence a count_sequence_v2 | |
# jsou prakticky stejné jako funkce z hodiny ale umí zjistit sekvenci několika znaků | |
# vyzkoušejte si, jak se situace změní pro seq_len = 1, 2 a 3 | |
# pocty_znaku = count_sequence(retezec, seq_len=3) | |
# pocty_znaku = count_sequence_v2(retezec, seq_len=3) | |
pprint(pocty_znaku) | |
print(najdi_minimum(pocty_znaku)) | |
print(najdi_maximim(pocty_znaku)) | |
stop = time() | |
celkovy_cas = stop - start | |
print(celkovy_cas, 'sekund') |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment