PythonCookbook-data structures and algorithms

PythonCookbook learning Notes Chapter 1 data structure and Algorithm 1.1 splits sequences into separate variables p (91.1) x, ypprintxprintydata [ACME, 50, (, 21)] name, shares, price, datedataprintnamepri... chapter 1 data structures and algorithms

1.1 Split the sequence into separate variables

P = (4, 5) x, y = pprint x print y data = ['Acme ', 50, 91.1, (2012, 12, 21)] name, shares, price, date = dataprint nameprint shares print price print date name, shares, price, (year, mon, day) = dataprint year p = (4, 5) # x, y, z = p error !!! S = 'Hello! 'A, B, c, d, e, f = sprint aprint fdata = ['Acme ', 50, 91.1, (2012, 12, 21)] _, shares, price, _ = data print your sprint price # Other data can be discarded

1.2 break down elements from iteratable objects of any length

from audioop import avgdef drop_first_last(grades):    first, *middle, last = grades    return avg(middle)record = ('Dave', 'dave@example.com', '777-333-2323', '234-234-2345')name, email, *phone_numbers = recordprint name print emailprint phone_numbers*trailing, current = [10, 8, 7, 2, 5]print trailing  #[10, 8, 7, 2, ]print current #5records = [           ('foo', 1, 2),           ('bar', 'hello'),           ('foo', 5, 3)           ]def do_foo(x, y):    print ('foo', x, y)def do_bar(s):    print ('bar', s)for tag, *args in records:    if tag == 'foo':        do_foo(*args)    elif tag == 'bar':        do_bar(*args)        line = 'asdf:fedfr234://wef:678d:asdf'uname, *fields, homedir, sh = line.split(':')print uname print homedirrecord = ('ACME', 50, 123.45, (12, 18, 2012))name, *_, (*_, year) = recordprint nameprint yearitems = [1, 10, 7, 4, 5, 9]head, *tail = itemsprint head #1print tail #[10, 7, 4, 5, 9]def sum(items):    head, *tail = items    return head + sum(tail) if tail else headsum(items)

1.3 Save the Last N elements

from _collections import dequedef 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 fileif __name__ == '__main__':    with open('somefile.txt') as f:        for line, prevlines in search(f, 'python', 5):            for pline in prevlines:                print (pline) #print (pline, end='')            print (line) #print (pline, end='')            print ('-'*20)            q = deque(maxlen=3)q.append(1)q.append(2)q.append(3)print qq.append(4)print qq = deque()q.append(1)q.append(2)q.append(3)print qq.appendleft(4)print qq_pop = q.pop()print q_popprint qq_popleft = q.popleft()print q_popleftprint q

1.4 Find N elements at the maximum or minimum

import heapqnums = [1,30,6,2,36,33,46,3,23,43]print (heapq.nlargest(3, nums))print (heapq.nsmallest(3, nums))portfolio = [                 {'name':'IBM', 'shares':100, 'price':2.4},                 {'name':'A', 'shares':1040, 'price':12.4},                 {'name':'S', 'shares':40, 'price':23.4},                 {'name':'D', 'shares':1, 'price':2.49},                 {'name':'F', 'shares':9, 'price':24}             ]cheap = heapq.nsmallest(3, portfolio, key=lambda s: s['price'])expensive = heapq.nlargest(3, portfolio, key=lambda s: s['price'])print cheapprint expensivenums = [1,8,2,23,7,-4,18,23,42,37,2]heap = list(nums)print heapheapq.heapify(heap)print heapprint heapq.heappop(heap)print heapq.heappop(heap)print heapq.heappop(heap)

1.5 implement priority queue

import heapqclass PriorityQueue:    def __init__(self):        self._queue = []        self._index = 0    def push(self, item, priority):        heapq.heappush(self._queue, (-priority, self._index, item))        self._index += 1    def pop(self):        return heapq.heappop(self._queue)[-1]#Exampleclass Item:    def __init__(self, name):        self.name = name    def __repr__(self):        return 'Item({!r})'.format(self.name)q = PriorityQueue()q.push(Item('foo'), 1)q.push(Item('spam'), 4)q.push(Item('bar'), 5)q.push(Item('grok'), 1)print q.pop()print q.pop()print q.pop()a = Item('foo')b = Item('bar')#a < b    errora = (1, Item('foo'))b = (5, Item('bar'))print a < bc = (1, Item('grok'))#a < c  errora = (1, 0, Item('foo'))b = (5, 1, Item('bar'))c = (1, 2, Item('grok'))print a < bprint a < c

1.6 map the value in the dictionary to multiple values

d = {          'a' : [1, 2, 3],          'b' : [4, 5]       }  e = {          'a' : {1, 2, 3},          'b' : {4, 5}       }    from collections import defaultdict    d = defaultdict(list)  d['a'].append(1)  d['a'].append(2)  d['a'].append(3)  print d    d = defaultdict(set)  d['a'].add(1)  d['a'].add(2)  d['a'].add(3)  print d    d = {}  d.setdefault('a', []).append(1)  d.setdefault('a', []).append(2)  d.setdefault('b', []).append(3)  print d     d = {}  for key, value in d:#pairs:      if key not in d:          d[key] = []      d[key].append(value)    d = defaultdict(list)  for key, value in d:#pairs:      d[key].append(value)

1.7 keep the dictionary in order

from collections import OrderedDict    d = OrderedDict()  d['foo'] = 1  d['bar'] = 2  d['spam'] = 3  d['grol'] = 4  for key in d:      print (key, d[key])        import json    json.dumps(d)

1.8 Dictionary-related computing problems

Price = {'Acme ': 23.45, 'IBM': 25.45, 'FB ': 13.45, 'io': 4.45, 'Java': 45.45, 'Av': 38.38 ,} min_price = min (zip (price. values (), price. keys () print min_price max_price = max (zip (price. values (), price. keys () print max_price price_sorted = sorted (zip (price. values (), price. keys () print price_sorted price_and_names = zip (price. values (), price. keys () print (min (price_and_names) # print (max (price_and_names) error zip () creates an iterator and the content can only be consumed once print min (price) print max (price) print min (price. values () print max (price. values () print min (price, key = lambda k: price [k]) print max (price, key = lambda k: price [k]) min_value = price [min (price, key = lambda k: price [k])] print min_value price = {'AAA': 23, 'zzz': 23 ,} print min (zip (price. values (), price. keys () print max (zip (price. values (), price. keys ()))

1.9 look for similarities between the two dictionaries

a = {          'x':1,          'y':2,          'z':3       }  b = {          'x':11,          'y':2,          'w':10       }    print a.keys() & b.keys() #{'x','y'}  print a.keys() - b.keys() #{'z'}  print a.items() & b.items() #{('y', 2)}    c = {key: a[key] for key in a.keys() - {'z', 'w'} }  print c #{'x':1, 'y':2}

1.10 remove duplicate items from the sequence and keep the order between elements unchanged

def dedupe(items):      seen = set()      for item in items:          if item not in seen:              yield item              seen.add(item)  #example  a = [1,5,2,1,9,1,5,10]  print list(dedupe(a))    def dedupe2(items, key = None):      seen = set()      for item in items:          val = item if key is None else key(item)          if val not in seen:              yield item              seen.add(val)   #example  a = [           {'x':1, 'y':2},           {'x':1, 'y':3},           {'x':1, 'y':2},           {'x':2, 'y':4},        ]  print list( dedupe2(a, key=lambda d : (d['x'], d['y']) ) )  print list( dedupe2(a, key=lambda d : (d['x']) ) )    a = [1,5,2,1,9,1,5,10]  print set(a)

1.11 name slice

items = [0,1,2,3,4,5,6]  a = slice(2,4)  print items[2:4]  print items[a]  items[a] = [10,11]  print items    print a.start  print a.stop  print a.step

1.12 find the most frequently occurring element in the sequence

words = [              'look', 'into', 'my', 'eyes', 'look', 'into', 'my', 'eyes',              'the', 'look'           ]    from collections import Counter    word_counts = Counter(words)  top_three = word_counts.most_common(3)  print top_three    print word_counts['look']  print word_counts['the']    morewords = ['why', 'are', 'you', 'not', 'looking', 'in', 'my', 'eyes']  for word in morewords:      word_counts[word] += 1  print word_counts['eyes']  print word_counts['why']    word_counts.update(morewords)  print word_counts['eyes']  print word_counts['why']    a = Counter(words)  b = Counter(morewords)  print a  print b  c = a + b  print c  d = a - b  print b

1.13 sort dictionary lists by public keys

rows = [              {'fname':'Brian', 'lname':'Jones', 'uid':1003},              {'fname':'David', 'lname':'Beazley', 'uid':1002},              {'fname':'John', 'lname':'Cleese', 'uid':1001},              {'fname':'Big', 'lname':'Jones', 'uid':1004}          ]    from operator import itemgetter    rows_by_fname = sorted(rows, key=itemgetter('fname'))  rows_by_uid = sorted(rows, key=itemgetter('uid'))  print rows_by_fname  print rows_by_uid  rows_by_lfname = sorted(rows, key=itemgetter('lname', 'fname'))  print rows_by_lfname    rows_by_fname = sorted(rows, key=lambda r: r['fname'])  rows_by_lfname = sorted(rows, key=lambda r: (r['fname'], r['lname']))  print rows_by_fname  print rows_by_lfname    print min(rows, key=itemgetter('uid'))  print max(rows, key=itemgetter('uid'))

1.14 sorting of objects that do not support native comparison operations

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)]  print users  print sorted(users, key = lambda u: u.user_id)    from operator import attrgetter  print sorted(users, key=attrgetter('user_id'))    print min(users, key=attrgetter('user_id'))  print max(users, key=attrgetter('user_id'))

1.15 group records by field

rows = [              {'address':'5412 N CLARK', 'data':'07/01/2012'},              {'address':'5232 N CLARK', 'data':'07/04/2012'},              {'address':'5542 E 58ARK', 'data':'07/02/2012'},              {'address':'5152 N CLARK', 'data':'07/03/2012'},              {'address':'7412 N CLARK', 'data':'07/02/2012'},              {'address':'6789 w CLARK', 'data':'07/03/2012'},              {'address':'9008 N CLARK', 'data':'07/01/2012'},              {'address':'2227 W CLARK', 'data':'07/04/2012'}          ]    from operator import itemgetter  from itertools import groupby    rows.sort(key=itemgetter('data'))  for data, items in groupby(rows, key=itemgetter('data')):      print (data)      for i in items:          print (' ', i)            from collections import defaultdict  rows_by_date = defaultdict(list)  for row in rows:      rows_by_date[row['data']].append(row)  for r in rows_by_date['07/04/2012']:      print(r)

1.16 filter elements in a sequence

Mylist = [,-, 3, -1] print [n for n in mylist if n> 0] # List derivation print [n for n in mylist if n <0] pos = (n for n in mylist if n> 0) # generator expression print pos for x in pos: print (x) values = ['1', '2', '-3','-', '4 ', 'n'/A', '5'] def is_int (val): try: x = int (val) return True expect T ValueError: return False ivals = list (filter (is_int, values) print (ivals) mylist = [,-,-, 3,-1] import math print [math. sqrt (n) for n in mylist if n> 0] clip_neg = [n if n> 0 else 0 for n in mylist] print clip_neg clip_pos = [n if n <0 else 0 for n in mylist] print clip_pos addresses = ['A ', 'B', 'C', 'D', 'e', 'F', 'G', 'H'] counts = [0, 3, 10, 4, 1, 7, 6, 1] from itertools import compress more5 = [n> 5 for n in counts] print more5 print list (compress (addresses, more5 ))

1.17 extract subset from dictionary

Prices = {'acne': 45.23, 'aap': 612.78, 'IBM ': 205.55, 'hpq': 37.20, 'FB': 10.75} p1 = {key: value for key, value in prices. items () if value> 200} print p1 tech_names = {'aapl ', 'IBM', 'hpq'} p2 = {key: value for key, value in prices. items () if key in tech_names} print p2 p3 = dict (key, value) for key, value in prices. items () if value> 200) # slow print p3 tech_names = {'aapl ', 'IBM', 'hpq'} p4 = {key: prices [key] for key in prices. keys () if key in tech_names} # slow print p4

1.18 map the name to the element of the sequence

from collections import namedtuple    Subscriber = namedtuple('Subscriber', ['addr', 'joined'])  sub = Subscriber('wang@qq.com', '2020-10-10')  print sub  print sub.joined  print sub.addr    print len(sub)  addr, joined = sub  print addr  print joined    def compute_cost(records):      total = 0.0      for rec in records:          total += rec[1]*rec[2]      return total    Stock = namedtuple('Stock', ['name', 'shares', 'price'])  def compute_cost2(records):      total = 0.0      for rec in records:          s = Stock(*rec)          total += s.shares * s.price      return total    s = Stock('ACME', 100, 123.45)  print s  #s.shares = 75    #error  s = s._replace(shares=75)  print s    Stock = namedtuple('Stock', ['name', 'shares', 'price', 'date', 'time'])  stock_prototype = Stock('',0, 0.0, None, None)  def dict_to_stock(s):      return stock_prototype._replace(**s)  a = {'name':'ACME', 'shares':100, 'price':123.45}  print dict_to_stock(a)  b = {'name':'ACME', 'shares':100, 'price':123.45, 'date':'12/12/2012'}  print dict_to_stock(b)

1.19 convert and convert data simultaneously

Nums = [1, 2, 3, 4, 5] s = sum (x * x for x in nums) print s import OS files = OS. listdir ('dirname') if any (name. endswith ('. py ') for name in files): print ('There be Python! ') Else: print ('Sorry, no Python! ') S = ('Acme', 50,123.45) print (','. join (str (x) for x in s) portfolio = [{'name': 'goog', 'shares': 50}, {'name': 'yhoo ', 'shares': 75}, {'name': 'AOL ', 'shares': 20}, {'name': 'scox', 'shares ': 65}] min_shares = min (s ['shares'] for s in portfolio) print min_shares = min (portfolio, key = lambda s: s ['shares']) print min_shares 1.20 combines multiple mappings into a single Java ing Java code a = {'X': 1, 'Z': 3} B = {'Y': 2, 'Z': 4} # from collections import ChainMap from pip. _ vendor. distlib. compat import ChainMap c = ChainMap (a, B) print (c ['x']) print (c ['Y']) print (c ['Z']) # print len (c) print list (c. values ()) c ['Z'] = 10 c ['w'] = 40 del c ['x'] print a # del c ['Y'] # The error operation always modifies the ING. it will apply to the first ing structure in the list. values = ChainMap () values ['x'] = 1 values = values. new_child () # add a new map values ['x'] = 2 values = values. new_child () values ['x'] = 3 # print values ['x'] values = values. parents print values ['x'] values = values. parents print values ['x'] a = {'X': 1, 'Z': 3} B = {'Y': 2, 'Z ': 4} merged = dict (B) merged. update () print merged ['x'] print merged ['Y'] print merged ['Z'] a ['x'] = 13 print merged ['x'] # No Response in the merged dictionary, a = {'X ': 1, 'Z': 3} B = {'Y': 2, 'Z': 4} merged = ChainMap (a, B) print merged ['x'] a ['x'] = 42 print merged ['x'] # returns to the merged Dictionary.