es102 dictionaries tuples files

7/25/2019 ES102 Dictionaries Tuples Files

1/24

Introduction to Computing

Dictionaries, Tuples, Files


2/24

Dictionaries

>>> eng2sp = dict()

>>> eng2sp

{}

>>> eng2sp['one'] = 'uno>>> eng2sp

{'one': 'uno'}

>>> eng2sp = {'one': 'uno', 'two': 'dos', 'three': 'tres'}>>> eng2sp

{'one': 'uno', 'three': 'tres', 'two': 'dos'}


3/24

>>> eng2sp['two']

'dos

>>> eng2sp['four']

KeyError: 'four

>>> len(eng2sp)

3

>>> 'one' in eng2spTrue

>>> 'uno' in eng2sp

False


4/24

>>> vals = eng2sp.values()

>>> 'uno' in vals

True


5/24

Tuples

>>> t = 'a', 'b', 'c', 'd', 'e

>>> t = ('a', 'b', 'c', 'd', 'e')

>>> t1 = 'a',

>>> type(t1)

>>> t2 = ('a')

>>> type(t2)


6/24

>>> t = tuple()

>>> t

()

>>> t = tuple('lupins')>>> t

('l', 'u', 'p', 'i', 'n', 's')

>>> t = ('a', 'b', 'c', 'd', 'e')

>>> t[0]

'a'


7/24

>>> t[1:3]

('b', 'c')

>>> t[0] = 'A'

TypeError: object doesn't support itemassignment

>>> t = ('A',) + t[1:]

>>> t

('A', 'b', 'c', 'd', 'e')


8/24

Tuple assignment

>>> temp = a

>>> a = b

>>> b = temp

>>> a, b = b, a

>>> a, b = 1, 2, 3ValueError: too many values to unpack


9/24

>>> addr = '[email protected]'

>>> uname, domain = addr.split('@')

>>> uname'monty'

>>> domain

'python.org


10/24

Dictionaries and tuples

>>> d = {'a':0, 'b':1, 'c':2}

>>> t = d.items()

>>> t

dict_items([('c', 2), ('a', 0), ('b', 1)])

>>> for key, value in d.items():

... print(key, value)

...

c 2a 0

b 1


11/24

>>> t = [('a', 0), ('c', 2), ('b', 1)]

>>> d = dict(t)

>>> d{'a': 0, 'c': 2, 'b': 1}


12/24

Dictionaries and lists

def histogram(s):

d = dict()

for c in s:

if c not in d:

d[c] = 1

else:

d[c] += 1

return d


13/24

>>> h = histogram('brontosaurus')

>>> h

{'a': 1, 'b': 1, 'o': 2, 'n': 1, 's': 2, 'r': 2, 'u': 2, 't': 1}

>>> h = histogram('a')

>>> h

{'a': 1}

>>> h.get('a', 0)

1

>>> h.get('b', 0)

0


14/24

Dictionaries and lists

def histogram(s):

d = dict()

for c in s:

# if c not in d:# d[c] = 1

# else:

# d[c] += 1

d[c]=d.get(c,0)+1

return d


15/24

def print_hist(h):

for c in h:

print(c, h[c])

>>> h = histogram('parrot')

>>> print_hist(h)

a 1

p 1

r 2

t 1

o 1


16/24

>>> t = ['a', 'a', 'b']

>>> hist = histogram(t)

>>> hist{'a': 2, 'b': 1}


17/24

Reverse lookup

def invert_dict(d):

inverse = dict()

for key in d:

val = d[key]if val not in inverse:

inverse[val] = [key]

else:

inverse[val].append(key)

return inverse


18/24

>>> hist = histogram('parrot')

>>> hist

{'a': 1, 'p': 1, 'r': 2, 't': 1, 'o': 1}>>> inverse = invert_dict(hist)

>>> inverse

{1: ['a', 'p', 't', 'o'], 2: ['r']}


19/24

Application dictionaries

Word histogramimport string

def process_file(filename):

hist = dict()

fp = open(filename)

for line in fp:

process_line(line, hist)return hist

def process_line(line, hist):

line = line.replace('-', ' ')

for word in line.split():

word = word.strip(string.punctuation + string.whitespace)word = word.lower()

hist[word] = hist.get(word, 0) + 1

hist = process_file('emma.txt')


20/24

def total_words(hist):

return sum(hist.values())

def different_words(hist):

return len(hist)

print('Total number of words:', total_words(hist))

print('Number of different words:',

different_words(hist))Total number of words: 161080

Number of different words: 7214


21/24

def most_common(hist):

t = []

for key, value in hist.items():

t.append((value, key))

t.sort(reverse=True)

return t

t = most_common(hist)

print('The most common words are:')

for freq, word in t[0:10]:

print(word, '\t', freq)


22/24

The most common words are:

to 5242

the 5205

and 4897

of 4295i 3191

a 3130

it 2529

her 2483was 2400

she 2364


23/24

Files

>>> fout = open('output.txt', 'w')

>>> line1 = "This here's the wattle,\n"

>>> fout.write(line1)

24

>>> line2 = "the emblem of our land.\n"

>>> fout.write(line2)

24

>>> fout.close()


24/24

Format operator

>>> x = 52

>>> fout.write(str(x))

>>> camels = 42

>>> '%d' % camels'42

>>> 'I have spotted %d camels.' % camels

'I have spotted 42 camels.

>>> 'In %d years I have spotted %g %s.' % (3, 0.1,'camels')

'In 3 years I have spotted 0.1 camels.

es102 dictionaries tuples files

Documents