amc6

class6.ipynb

class6.py

# coding: utf-8

# In[1]:

import os
print os.getcwd()
os.listdir('.')


# In[2]:

with open('data/private-cities.txt') as f:
    lines = f.readlines()


# In[3]:

# headlines 1
[line for line in lines if len(line) < 80]


# In[4]:

# headlines 2
[line for line in lines if '.' not in line]


# In[5]:

# beolvasas soronkent mashogy
with open('data/private-cities.txt') as f:
    sections = [line for line in f if len(line) < 80]


# In[6]:

sections


# In[7]:

# karakterek szama
with open('data/private-cities.txt') as f:
    print len(f.read())


# In[8]:

# sorok szama
with open('data/private-cities.txt') as f:
    print len(f.readlines())


# In[9]:

# szavak szama
with open('data/private-cities.txt') as f:
    words = f.read().split()

print len(words)


# In[10]:

# leghosszabb szo hossza
max_length = max(len(w) for w in words)
print max_length


# In[11]:

# leghosszabb szo/szavak
[word for word in words if len(word) == max_length]


# In[12]:

# jo az elozo megoldas?
long_words4 = [word for word in words if len(word) == max_length - 4]
long_words4


# In[13]:

# ismetlodesek!
set(long_words4)


# In[14]:

# leggyakoribb szavak
word_count = {}
for word in words:
    if word in word_count:
        previous_count = word_count[word]
    else:
        previous_count = 0
    word_count[word] = previous_count + 1

count_to_words = {}

for word, count in word_count.items():
    if count in count_to_words:
        word_list = count_to_words[count]
    else:
        word_list = []
        count_to_words[count] = word_list
    word_list.append(word)

highest_count = max(count_to_words)
print highest_count, count_to_words[highest_count]
high_counts = sorted(count_to_words, reverse=True)[:20]
print high_counts
for count in high_counts:
    print count, count_to_words[count]


# In[15]:

with open('data/private-cities.txt') as f:
    text = f.read()


# In[16]:

'!' in text


# In[17]:

'?' in text


# In[18]:

text.splitlines()[:5]


# In[19]:

print lines[5]


# In[20]:

# sentences
def sentences(lines):
    separations=(
        ('. ', '.'),
        ('? ', '?'),
    )
    for separator, tail in separations:
        sentences = []
        for line in lines:
            sentences += split_by_separator(line, separator, tail)
        lines = sentences
    return lines

def split_by_separator(line, separator, tail):
    fragments = line.split(separator)
    sentences = [
        s + tail
        for s in fragments[:-1]
    ] + fragments[-1:]
    return sentences
    
sentences(lines)[:20]


## Homework

# - Reformat the text, so that there are two spaces before sections, one after section start, and one between paragraphs.
# - Report the number of sentences per section.
# - Write sections into file named *{two-digit-section-number}-{section-name}.txt* e.g. *01-Private-Cities-101.txt*

plan.txt

tools
	ipython
		- live environment
		- completion on names
		- help on names

	ipython notebook
		- ipython in browser
		- later in course

	http://pythontutor.com/visualize.html#mode=edit


dict (map, mapping)
	key -> value

	- keys are immutable - tuples vs lists
	- value - anything

	- create
		- empty: {}
		- {'a': 1, 1: 'a'}
		- dict(a=2, b=4)
		- dict(
				(
				(1, 2),
				(3, 4),
				(5, 6)
				)
			)
	- value access - normal indexing:
		d[key]
	- setting value:
		d[key] = value
	- deleting value:
		del d[key]
	- key existence check:
		key in d
	- get with default value:
		d.get(key, default_if_key_unknown)
	- all keys:
		d.keys()
	- iterate over keys:
		for key in d:
			d[key]
		# keys are NOT ordered:
		for key in dict(a=1, b=2, c=3, d=4): print key
	-  can be thought of as a finite function


set
	- values are immutable!

	.add
	.union
	.difference
	.intersection

set vs dict

sorting:
	- inplace
		list.sort()
	- new list
		sorted(iterable)

File IO
	reading:
		f.read()
		f.readlines()
		for line in f:
			...

	writing:
		f.write(what)
		f.flush()


Predefined files
	sys.stdin
	sys.stdout
	sys.stderr


FileSystem
	os.listdir(dir) -> filenames

	open(filename, mode) -> file
		file.read() -> text
		file.readlines() -> [lines]
		file.write(what)
		file.close()

	file.close()

	with open() as f:
		f.read()

	with open() as f:
		f.write()

	os.remove()
		shutil.rmtree()


??? where to get filenames ???
	- scripts embed in the source
	- tools
		- from command line
			sys.argv
		- known configuration file name

typoglicemia.py

from random import shuffle

DOUBLE = (u'cs', u'dz', u'gy', u'ly', u'ny', u'sz', u'ty', u'zs')
TRIPLE = (u'dzs',)


def typoglicemia(text):
    words = split_to_words(text)
    typoglicemia_words = [word_typoglicemia(word) for word in words]
    return u' '.join(typoglicemia_words)


def word_typoglicemia(word):
    characters = convert_text_to_list(word)
    typoglicemia_characters = list_typoglicemia(characters)
    return u''.join(typoglicemia_characters)


def list_typoglicemia(characters):
    # shorter lists need not be reshuffled
    if len(characters) >= 4:
        middle = characters[1:-1]
        # 'shuffle' shuffles in place, does not return a value!
        shuffle(middle)
        return [characters[0]]+middle+[characters[-1]]
    else:
        return characters


def convert_text_to_list(text):
    # never forget to stop a recursion
    if text == u'':
        return []

    # important: do triple before double before single
    # so that 'dzs' does not become 'dz' + 's', or 'dz' to 'd' + 'z'
    if text[0:3].lower() in TRIPLE:
        return [text[0:3]] + convert_text_to_list(text[3:])
    if text[0:2].lower() in DOUBLE:
        return [text[0:2]] + convert_text_to_list(text[2:])
    return [text[0]] + convert_text_to_list(text[1:])


def split_to_words(text):
    return text.split()