数据挖掘---推荐算法(Mahout工具)

wget http://archive.apache.org/dist/mahout/0.9/mahout-distribution-0.9.tar.gz

tar -zxvf  mahout-distribution-0.9.tar.gz

# set mahout environment
export MAHOUT_HOME=/usr/local/src/mahout-distribution-0.9
export MAHOUT_CONF_DIR=$MAHOUT_HOME/conf
export PATH=$MAHOUT_HOME/conf:$MAHOUT_HOME/bin:$PATH

# set hadoop environment
export HADOOP_HOME=/usr/local/src/hadoop-1.2.1
export HADOOP_CONF_DIR=$HADOOP_HOME/conf
export PATH=$PATH:$HADOOP_HOME/bin
export HADOOP_HOME_WARN_SUPPRESS=not_null

数据格式：
1,100001,5
1,100002,3
1,100003,4
1,100004,3
1,100005,3
1,100007,4
1,100008,1
1,100009,5
1,1000011,2

INPUT="/movie_lens.data"
TMP_DIR="/mahout_temp"
OUTPUT="/cf_mahout_output"
MAHOUT_CMD="/usr/local/src/mahout-distribution-0.9/bin/mahout“
$MAHOUT_CMD itemsimilarity
-i $INPUT
-o $OUTPUT
--maxSimilaritiesPerItem 1000
--threshold 0.0000001
--similarityClassname SIMILARITY_COSINE
--tempDir $TMP_DIR