from IPython import display

display.YouTubeVideo('csyL9EC0S0c?t=24m47s')

%load python_tour.md

import this

def is_even(a):
    if a % 2 == 0:
        print('Even!')
        return True
    print('Odd!')
    return False

#multiple assignment

a, b, c = 'spam', 'eggs', 'parrot'
print(a, b, c)

for (i=0; i < mylist_length; i++) {
   do_something(mylist[i]);
}

#The direct equivalent in Python would be this:

i = 0
while i < mylist_length:
    do_something(mylist[i])
    i += 1

#That, however, while it works, is not considered Pythonic. It's not an idiom the Python language encourages. We could improve it. A typical idiom in Python to generate all numbers in a list would be to use something like the built-in range() function:

for i in range(mylist_length):
    do_something(mylist[i])

#This is however not Pythonic either. Here is the Pythonic way, encouraged by the language itself:

for element in mylist:
    do_something(element)


numbers = [1,2,3,4]
for number in numbers:
    print(number)

#Hacker School

rice_crispies.items()

rice_crispies = {3:'Crackle', 5:'Pop'}
for i in range(101):
    print(i)
    for flake in rice_crispies.keys():
        if i % flake == 0:
            print(rice_crispies[flake])

ahundred = range(101)
new_list = [i*2 for i in ahundred if i % 2 == 0]
print(new_list)

new_list[0:10]

tel = {'jack': 4098, 'sape': 4139}
tel['guido']


words = ['spam', 'spam', 'eggs', 'spam']


from collections import defaultdict
word_counter = defaultdict(int)

words = ['spam', 'spam', 'eggs', 'spam', 'parrot']

for word in words:
    word_counter[word] += 1

print(word_counter)

!wget  http://norvig.com/spell-correct.html

#90% of the google spelling corrector in 21 lines of Python

!head -n20 big.txt

import re, collections

def words(text): 
    return re.findall('[a-z]+', text.lower()) 

def train(features):
    model = collections.defaultdict(int)
    for f in features:
        model[f] += 1
    return model

NWORDS = train(words(file('big.txt').read()))

alphabet = 'abcdefghijklmnopqrstuvwxyz'

def edits(word):
    splits   = [(word[:i], word[i:]) for i in range(len(word) + 1)]
    deletes    = [a + b[1:] for a, b in splits if b]
    transposes = [a + b[1] + b[0] + b[2:] for a, b in splits if len(b)>1]
    replaces   = [a + c + b[1:] for a, b in splits for c in alphabet if b]
    inserts    = [a + c + b     for a, b in splits for c in alphabet]
    return set(deletes + transposes + replaces + inserts)

def known_edits(word):
    edits_of_edits = set()
    for e1 in edits(word):
        for e2 in edits(e1):
            if e2 in NWORDS:
                edits_of_edits.add(e2)
    return edits_of_edits
   
    #norvigs way
    #return set(e2 for e1 in edits(word) for e2 in edits(e1) if e2 in NWORDS)

def known(words): 
    return set(w for w in words if w in NWORDS)

def correct(word):
    candidates = known([word]) or known(edits(word)) or known_edits(word) or [word]
    return max(candidates, key=NWORDS.get)

correct('spam')

word = 'spam'
splits   = [(word[:i], word[i:]) for i in range(len(word) + 1)]
deletes    = [a + b[1:] for a, b in splits if b]
transposes = [a + b[1] + b[0] + b[2:] for a, b in splits if len(b)>1]
replaces   = [a + c + b[1:] for a, b in splits for c in alphabet if b]
inserts    = [a + c + b     for a, b in splits for c in alphabet]
print(splits)
print(deletes)
print(transposes)
print(replaces)
print(inserts)

!wget https://www.gutenberg.org/cache/epub/468/pg468.txt manon.txt

manon_string = open('pg468.txt','r').read()

manon_words = manon_string.split()[1000:2000]

transform_words #do list comprehension here to to put `correct` on all the words in the list manon_words

outfile = open('transformed_manon.txt','w')
transform_string = ' '.join(transform_words)
outfile.write(transform_string)