def wordCountMapper(document):
"""for each word in the document, emit (word,1)"""
for word in tokenize(document):
yield (word, 1)
def wordCountMapper(document):
"""for each word in the document, emit (word,1)"""
for word in tokenize(document):
yield (word, 1)
def wordCount_old(documents):
"""word count not using MapReduce"""
return Counter(word
for document in documents
for word in tokenize(document))
def wordCount_old(documents):
"""word count not using MapReduce"""
return Counter(word for document in documents
for word in tokenize(document))