2.7. Wordcount Solution (With reduce)

Complete version

import os

import pycompss.interactive as ipycompss

from pycompss.api.task import task

from pycompss.api.parameter import *

if 'BINDER_SERVICE_HOST' in os.environ:
    ipycompss.start(graph=True, trace=True, debug=False,
                    project_xml='../xml/project.xml',
                    resources_xml='../xml/resources.xml')
else:
    ipycompss.start(graph=True, monitor=1000, trace=True, debug=False)

******************************************************
*************** PyCOMPSs Interactive *****************
******************************************************
*          .-~~-.--.           _____       ________  *
*         :         )         |____ \     |____   /  *
*   .~ ~ -.\       /.- ~~ .     ___) |        /  /   *
*   >       `.   .'       <    / ___/        /  /    *
*  (         .- -.         )  | |___   _    /  /     *
*   `- -.-~  `- -'  ~-.- -'   |_____| |_|  /__/      *
*     (        :        )           _ _ .-:          *
*      ~--.    :    .--~        .-~  .-~  }          *
*          ~-.-^-.-~ \_      .~  .-~   .~            *
*                   \ \ '     \ '_ _ -~              *
*                    \`.\`.    //                    *
*           . - ~ ~-.__\`.\`-.//                     *
*       .-~   . - ~  }~ ~ ~-.~-.                     *
*     .' .-~      .-~       :/~-.~-./:               *
*    /_~_ _ . - ~                 ~-.~-._            *
*                                     ~-.<           *
******************************************************
* - Starting COMPSs runtime...                       *
* - Log path : /home/user/.COMPSs/Interactive_01/
* - PyCOMPSs Runtime started... Have fun!            *
******************************************************

@task(returns=list)
def read_file(file_path):
    """ Read a file and return a list of words.
    :param file_path: file's path
    :return: list of words
    """
    data = []
    with open(file_path, 'r') as f:
        for line in f:
            data += line.split()
    return data

Found task: read_file

@task(returns=dict)
def wordCount(data):
    """ Construct a frequency word dictorionary from a list of words.
    :param data: a list of words
    :return: a dictionary where key=word and value=#appearances
    """
    partialResult = {}
    for entry in data:
        if entry in partialResult:
            partialResult[entry] += 1
        else:
            partialResult[entry] = 1
    return partialResult

Found task: wordCount

@task(returns=dict, priority=True)
def merge_dicts(*dictionaries):
    import Queue
    q = Queue.Queue()
    for i in dictionaries:
        q.put(i)
    while not q.empty():
        x = q.get()
        if not q.empty():
            y = q.get()
            for k in y:
                if k in x:
                    x[k] += y[k]
                else:
                    x[k] = y[k]
            q.put(x)
    return(x)

Found task: merge_dicts

from pycompss.api.api import compss_wait_on

# Get the dataset path
pathDataset = os.getcwd() + '/dataset'

# Construct a list with the file's paths from the dataset
partialResult = []
for fileName in os.listdir(pathDataset):
    p = os.path.join(pathDataset, fileName)
    data=read_file(p)
    partialResult.append(wordCount(data))

# Accumulate the partial results to get the final result.
result=merge_dicts(*partialResult)

# Wait for result
result = compss_wait_on(result)

print("Result:")
from pprint import pprint
pprint(result)
print("Words: {}".format(sum(result.values())))

Result:
{'Adipisci': 227,
 'Aliquam': 233,
 'Amet': 207,
 'Consectetur': 201,
 'Dolor': 198,
 'Dolore': 236,
 'Dolorem': 232,
 'Eius': 251,
 'Est': 197,
 'Etincidunt': 232,
 'Ipsum': 228,
 'Labore': 229,
 'Magnam': 195,
 'Modi': 201,
 'Neque': 205,
 'Non': 226,
 'Numquam': 253,
 'Porro': 205,
 'Quaerat': 217,
 'Quiquia': 212,
 'Quisquam': 214,
 'Sed': 225,
 'Sit': 220,
 'Tempora': 189,
 'Ut': 217,
 'Velit': 218,
 'Voluptatem': 235,
 'adipisci': 1078,
 'aliquam': 1107,
 'amet': 1044,
 'consectetur': 1073,
 'dolor': 1120,
 'dolore': 1065,
 'dolorem': 1107,
 'eius': 1048,
 'est': 1101,
 'etincidunt': 1114,
 'ipsum': 1061,
 'labore': 1070,
 'magnam': 1096,
 'modi': 1127,
 'neque': 1093,
 'non': 1099,
 'numquam': 1094,
 'porro': 1101,
 'quaerat': 1086,
 'quiquia': 1079,
 'quisquam': 1144,
 'sed': 1109,
 'sit': 1130,
 'tempora': 1064,
 'ut': 1070,
 'velit': 1105,
 'voluptatem': 1121}
Words: 35409

ipycompss.stop()

****************************************************
*************** STOPPING PyCOMPSs ******************
****************************************************
Warning: some of the variables used with PyCOMPSs may
         have not been brought to the master.
****************************************************