# top right
result.append(((x+1, y-1), neighbor))
if y < GRID_SIZE:
# bottom
result.append(((x, y+1), neighbor))
if x > 1:
# bottom left
result.append(((x-1, y+1), neighbor))
return result
def reducer1(coords, neighborsList):
return coords, neighborsList
result_mapred1 = simul.map_red(data, mapper1, reducer1)
print("result_mapred1")
for item in result_mapred1:
print("\t", item)
def mapper2(coords, neighborsList):
result = []
for x, neighbor1 in enumerate(neighborsList):
for neighbor2 in neighborsList[x:]:
result.append(((neighbor1, neighbor2), 1))
return result
table_users_records = []
table_orders_records = []
for table_name, records in table_records:
if table_name == ORDERS:
table_orders_records.append(records)
continue
# else it has to be from the users table
table_users_records.append(records)
result = []
for record in table_users_records:
user_id, user_name = record
order_id = None
orders_hash = {}
for record in table_orders_records:
order_id, _, product_name = record
if order_id not in orders_hash:
orders_hash[order_id] = []
orders_hash[order_id].append(product_name)
for order_id, products_list in orders_hash.items():
key = (user_id, order_id)
result.append((key, products_list))
return result
result_mapred = simul.map_red(data, mapper, reducer)
print('result_mapred')
for item in result_mapred:
print("\t", item)
# -*- coding: UTF-8 -*-
from mredu.simul import map_red, input_file, run
from re import split
def mymap(k, v):
words = list(filter(lambda s: s != '', split(r'\W', v)))
return len(words), 1
def myred(k, vs):
return k, sum(vs)
if __name__ == '__main__':
process = map_red(input_file('data/quijote.txt'),
mapper=mymap,
reducer=myred)
run(process)
# -*- coding: UTF-8 -*-
from mredu.simul import map_red, input_kv_file, run
from re import split
def mymap(k, v):
return v, k
def myred(k, vs):
return k, len(vs)
if __name__ == '__main__':
process = map_red(input_kv_file('data/palabras.txt'), mymap, myred)
run(process)
def mapper1(number, _):
return ('all', number)
result_mapper1 = list(simul.process_mapper(data, mapper1))
print('')
print("result_mapper1:\n", sorted(result_mapper1))
def reducer1(k, numbersList):
return 'max-min', (min(numbersList), max(numbersList))
result_reducer1 = list(simul.map_red(data, mapper1, reducer1))
print("result_reducer1:\n", result_reducer1)
print('')
MIN, MAX = result_reducer1[0][1]
DELTA = MAX - MIN
def mapper2(number, _):
column_size = DELTA / BARS_NUM
column = BARS_NUM - 1 if number == MAX else floor(
(number - MIN) / column_size)
range_from = number - number % column_size
range_to = range_from + column_size
def mapper1(customer, product):
return customer, product
def reducer1(customer, productsList):
result = []
for products_pair in itertools.combinations(productsList, 2):
result.append((tuple(sorted(products_pair)), 1))
return result
result_mapred1 = list(simul.map_red(data, mapper1, reducer1))
print("result_mapred1:\n")
for item in result_mapred1:
print(item)
def mapper2(products_pair, amount):
return products_pair, amount
def reducer2(products_pair, amountsList):
return products_pair, sum(amountsList)
result_mapred2 = list(simul.map_red(result_mapred1, mapper2, reducer2))
# -*- coding: UTF-8 -*-
from mredu import simul
l = [('a', 1), ('b', 2), ('a', 3), ('c', 9), ('b', 6)]
print('Sum all values by key...')
print('-' * 50)
process = simul.map_red(l, reducer=lambda k, v: (k, sum(v)))
simul.run(process, sep=',')
print()
print('Unrolls key by value...')
print('-' * 50)
process = simul.map_red(l, mapper=lambda k, v: [(k, 1) for _ in range(v)])
simul.run(process, sep=',')
# -*- coding: utf-8 -*-
from mredu import simul
import re
data = list(simul.input_file('quijote.txt'))
def mapper(k, v):
line = re.sub(r'[^a-záéíóúüñç\s]', '', v.lower()).strip()
if line == '':
return None
return [(word, 1) for word in re.split(r' +', line)]
def reducer(k, vList):
return (k, sum(vList))
result_map = list(simul.map_red(data, mapper, reducer))
print("top 50\n")
for item in sorted(result_map, key=lambda item: item[1], reverse=True)[:50]:
print("\t", item)
# -*- coding: UTF-8 -*-
from mredu.simul import map_red, input_file, run
import re
stopwords = [
u'así', u'para', u'sus', u'una', u'ni', u'porque', u'sin', u'tan', u'al',
u'si', u'me', u'un', u'más', u'es', u'del', u'lo', u'las', u'le', u'mas',
u'por', u'su', u'con', u'los', u'se', u'no', u'en', u'el', u'la', u'a',
u'y', u'de', u'que', u'muy', u'qué', u'como', u'mi', u'o', u'aquel', u'ya',
u'pues', u'cuando', u'cual', u'pero', u'este', u'esto', u'aquí',
u'aquella', u'aquello'
]
def mymap(_, v):
words = list(
filter(lambda s: s != '', re.split(r'\W', v, flags=re.UNICODE)))
return [(word.lower(), 1) for word in words if word not in stopwords]
def myred(k, vs):
return k, len(vs)
if __name__ == '__main__':
process = map_red(input_file('data/quijote.txt'), mymap, myred)
run(process)
