words = lines.flatMap(parseContext)
words_swap = words.map(lambda (x, y): (y, x))
wordcount = words.map(lambda s: (s, 1)).reduceByKey(lambda a, b: a + b)
wordcount_page = words_swap.map(lambda s: (s, 1)).reduceByKey(lambda a, b: a + b)
count_page = words.map(lambda (a, b): (a, 1)).reduceByKey(lambda a, b: a + b)
doc_word = words_swap.distinct().map(lambda (a, b): (a, 1)).reduceByKey(lambda a, b: a + b)
app = []
for (((id, title), word), n) in wordcount.collect():
word_page = words.filter(lambda x: (id, title) in x).count()
word_all_page = words.filter(lambda x: word in x).distinct().count()
tf_idf = (n / word_page) * math.log((doc_count / word_all_page))
app.append([(id, title, word, tf_idf)])
##part2 read as RDD
v = sc.parallelized(app)
trans = v.map(lambda (a, b): (a, list(b))).groupByKey() ##apend word as list by id
##key pair similarity(e-distance)
def similar(wf):
fun_result = []
list1 = {}
list2 = {}
for item in v[0][1]:
fun_result.append(item[0])
list1.setdefault(item[0],item[1])
for item in v[1][1]:
if item[0] not in fun_result:
fun_result.append(item[0])
list2.setdefault(item[0],item[1])
result1 = []
result2 = []
