word_count

#!/bin/bash
HADOOP_HOME=/usr/local/webserver/hadoop
INPUT_PATH=/data/archive/app_oeudjgn5872a7c3aaa54_datamine/george/inputs
INPUT_PATH2=/user/resys/projects/image/koudai_img/d_img/reduced/2015-taobao
OUTPUT_PATH=/data/archive/app_oeudjgn5872a7c3aaa54_datamine/george/output/may30
#OUTPUT_PATH=output
#echo "Clearing output path: $OUTPUT_PATH"
$HADOOP_HOME/bin/hadoop fs -rmr $OUTPUT_PATH

${HADOOP_HOME}/bin/hadoop jar\
   ${HADOOP_HOME}/share/hadoop/tools/lib/hadoop-streaming-2.6.0.jar\
  -file mapper1.py\
  -file reducer1.py\
  -mapper mapper1.py\
  -reducer reducer1.py\
  -input $INPUT_PATH\
  -input $INPUT_PATH2\
  -output $OUTPUT_PATH\
  -jobconf mapreduce.jobtracker.split.metainfo.maxsize=-1\
  -jobconf mapred.job.queue.name="offline"\
  -jobconf mapred.job.priority="NORMAL"\
  -jobconf mapred.reduce.tasks="10"\
在下面这段代码的基础上进行修改import math from collections import defaultdict corpus =["二价 二价 二价 四价 预约", "四价 四价 四价 九价 预约", "九价 九价 九价 九价 预约"] words = [] for sentence in corpus: words.append(sentence.strip().split()) # 进行词频统计 def Counter(words): word_count = [] for sentence in words: word_dict = defaultdict(int) for word in sentence: word_dict[word] += 1 word_count.append(word_dict) return word_count word_count = Counter(words) # 计算TF(word代表被计算的单词,word_dict是被计算单词所在句子分词统计词频后的字典) def tf(word, word_dict): return word_dict[word] / sum(word_dict.values()) # 统计含有该单词的句子数 def count_sentence(word, word_count): return sum([1 for i in word_count if i.get(word)]) # i[word] >= 1 # 计算IDF def idf(word, word_count): return math.log((len(word_count) / (count_sentence(word, word_count) + 1)),10) # 计算TF-IDF def tfidf(word, word_dict, word_count): return tf(word, word_dict) * idf(word, word_count) p = 1 for word_dict in word_count: print("part:{}".format(p)) p += 1 for word, cnt in word_dict.items(): print("word: {} ---- TF-IDF:{}".format(word, tfidf(word, word_dict, word_count))) print("word: {} ---- TF:{}".format(word, tf(word, word_dict))) print("word: {} ---- IDF:{}".format(word, idf(word, word_count))) print("word: {} ---- count_sentence:{}".format(word, count_sentence(word, word_count))),将IDF进行改进,其中自定义热度权重文件weight.txt中我想存入的是每一个文档的热度权重,改进的idf值就是总文档热度权重总和除以包含某词所在的文档的热度权重之和然后再取对数,请写出改进后的python代码
06-07
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值