Data Structures and Algorithms

defaultdict.py

# Mapping Keys to Multiple Values in a Dictionary

from collections import defaultdict
d = defaultdict(list)
d['a'].append(1)
d['a'].append(2)
d['b'].append(4)

d = defaultdict(set)
d['a'].add(1)
d['a'].add(2)
d['b'].add(4)

# USAGE:
# Instead of this:
d={}
for key, value in pairs:
  if key not in d:
    d[key] = []
  d[key].append(value)

# do this:
d = defaultdict(list)
for key, value in pairs:
  d[key].append(value)

deque.py

# Keeping the Last N Items

from collections import deque

def search(lines, pattern, history=5):
  previous_lines = deque(maxlen=history)
  for line in lines:
    if pattern in line:
      yield line, previous_lines
    previous_lines.append(line)

# Example use on a file
if __name__ == '__main__':
  with open('somefile.txt') as f:
    for line, prevlines in search(f, 'python', 5):
      for pline in prevlines:
        print(pline, end='')
      print(line, end='')
      print('-'*20)
      
# Example 1:
>>> q = deque(maxlen=3)
>>> q.append(1)
>>> q.append(2)
>>> q.append(3)
>>> q
deque([1, 2, 3], maxlen=3)
>>> q.append(4)
>>> q
deque([2, 3, 4], maxlen=3)
>>> q.append(5)
>>> q

# Example 2:
>>> q = deque()
>>> q.append(1)
>>> q.append(2)
>>> q.append(3)
>>> q
deque([1, 2, 3])
>>> q.appendleft(4)
>>> q
deque([4, 1, 2, 3])
>>> q.pop()
3
>>> q
deque([4, 1, 2])
>>> q.popleft()
4

filtering.py

# Filtering Sequence Elements

# using list cmprehension:
mylist = [1, 4, -5, 10, -7, 2, 3, -1]
[n for n in mylist if n > 0] # [1, 4, 10, 2, 3]

# using generator expression:
pos = (n for n in mylist if n > 0) # <generator object <genexpr> at 0x1006a0eb0>
for x in pos:
  print(x)
  
# using filter function:
values = ['1', '2', '-3', '-', '4', 'N/A', '5']

def is_int(val):
  try:
    x = int(val)
    return True
  except ValueError:
    return False
  
ivals = list(filter(is_int, values))
print(ivals)
# Outputs ['1', '2', '-3', '4', '5']

OrderedDict.py

# Keeping Dictionaries in Order

from collections import OrderedDict
d = OrderedDict()
d['foo'] = 1
d['bar'] = 2
d['spam'] = 3
d['grok'] = 4

# Outputs "foo 1", "bar 2", "spam 3", "grok 4"
for key in d: print(key, d[key])

sorted_and_attrgetter.py

# Sorting Objects Without Native Comparison Support
class User:
  def __init__(self, user_id):
    self.user_id = user_id

  def __repr__(self):
    return 'User({})'.format(self.user_id) ...

users = [User(23), User(3), User(99)]

from operator import attrgetter
sorted(users, key=attrgetter('user_id')) # [User(3), User(23), User(99)]

unpacking_elements.py

# Unpacking Elements from Iterables of Arbitrary Length

record = ('Dave', '[email protected]', '773-555-1212', '847-555-1212')
name, email, *phone_numbers = user_record
# name: 'Dave'
# email: '[email protected]'
# phone_numbers: ['773-555-1212', '847-555-1212']

*trailing, current = [10, 8, 7, 1, 9, 5, 10, 3]
# trailing: [10,8,7,1,9,5,10]
# current: 3

line = 'nobody:*:-2:-2:Unprivileged User:/var/empty:/usr/bin/false'
uname, *fields, homedir, sh = line.split(':')
# uname: 'nobody'
# homedir: '/var/empty'
# sh: '/usr/bin/false'