I only want to count words in spark (pyspark), but I can either map the letters or the whole string.
I tried: (whole string)
v1='Hi hi hi bye bye bye word count'
v1_temp=sc.parallelize([v1])
v1_map = v1_temp.flatMap(lambda x: x.split('\t'))
v1_counts = v1_map.map(lambda x: (x, 1))
v1_counts.collect()
or (just letters)
v1='Hi hi hi bye bye bye word count'
v1_temp=sc.parallelize(v1)
v1_map = v1_temp.flatMap(lambda x: x.split('\t'))
v1_counts = v1_map.map(lambda x: (x, 1))
v1_counts.collect()
When you do sc.parallelize(sequence)
you are are creating an RDD that will be operated on in parallel. In the first case you sequence is a list containing a single element (the whole sentence). In the second case your sequence is a string, which in python is similar to a list of characters.
If you want to count words in parallel you could do:
from operator import add
s = 'Hi hi hi bye bye bye word count'
seq = s.split() # ['Hi', 'hi', 'hi', 'bye', 'bye', 'bye', 'word', 'count']
sc.parallelize(seq)\
.map(lambda word: (word, 1))\
.reduceByKey(add)\
.collect()
Will get you:
[('count', 1), ('word', 1), ('bye', 3), ('hi', 2), ('Hi', 1)]
If you only want to count alphanumeric words, this may be a solution:
import time, re
from pyspark import SparkContext, SparkConf
def linesToWordsFunc(line):
wordsList = line.split()
wordsList = [re.sub(r'\W+', '', word) for word in wordsList]
filtered = filter(lambda word: re.match(r'\w+', word), wordsList)
return filtered
def wordsToPairsFunc(word):
return (word, 1)
def reduceToCount(a, b):
return (a + b)
def main():
conf = SparkConf().setAppName("Words count").setMaster("local")
sc = SparkContext(conf=conf)
rdd = sc.textFile("your_file.txt")
words = rdd.flatMap(linesToWordsFunc)
pairs = words.map(wordsToPairsFunc)
counts = pairs.reduceByKey(reduceToCount)
# Get the first top 100 words
output = counts.takeOrdered(100, lambda (k, v): -v)
for(word, count) in output:
print word + ': ' + str(count)
sc.stop()
if __name__ == "__main__":
main()
There have been many versions of wordcount online, below is just of them;
#to count the words in a file hdfs:/// of file:/// or localfile "./samplefile.txt"
rdd=sc.textFile(filename)
#or you can initialize with your list
v1='Hi hi hi bye bye bye word count'
rdd=sc.parallelize([v1])
wordcounts=rdd.flatMap(lambda l: l.split(' ')) \
.map(lambda w:(w,1)) \
.reduceByKey(lambda a,b:a+b) \
.map(lambda (a,b):(b,a)) \
.sortByKey(ascending=False)
output = wordcounts.collect()
for (count,word) in output:
print("%s: %i" % (word,count))
The technical post webpages of this site follow the CC BY-SA 4.0 protocol. If you need to reprint, please indicate the site URL or the original address.Any question please contact:yoyou2525@163.com.