（1.1）GloVe源码解析

安装

在github上找到源码下载编译即可

$ git clone http://github.com/stanfordnlp/glove
$ cd glove && make
$ ./demo.sh

执行顺序

GloVe代码包括了四个.c文件

1. 首先执行vocab_count.c这个文件的功能是扫一遍语料，建立一个字典。
2. 执行cooccur.c文件。它的功能是从语料中建立共现矩阵，GloVe是在共现矩阵上面进行训练的。所谓共现矩阵，在GloVe中是大量的三元组<eat, food, 150>,<of, the, 100000>…cooccur.c文件生成的三元组的顺序是根据词频排好序的。比如<of, the, 100000>在<eat, food, 150>前面，因为of的频数大于eat。<of, the, 100000>在<of, mine, 1000>前面，因为the的频数大于mine。
3. 执行第三个文件shuffle.c。这个文件是用来打乱之前生成的共现矩阵（也就是打乱三元组的顺序）。
4. 最后执行glove.c。它会在打乱顺序的三元组上面训练词向量。

评价指标

eval文件中给出了评估词向量的代码。评估的方法和word2vec是一模一样的。数据集也是一模一样的。只不过GloVe评估的代码是用python去写的。运行GloVe的话就执行demo.sh脚本。下面是demo.sh的代码，从中也可以看到我们上面说的GloVe执行的流程。

下面脚本会自动下载一些一个测试用的语料库，如果自己使用的话，可以选择去掉这一部分

#!/bin/bash
set -e

# Makes programs, downloads sample data, trains a GloVe model, and then evaluates it.
# One optional argument can specify the language used for eval script: matlab, octave or [default] python

make
if [ ! -e text8 ]; then
  if hash wget 2>/dev/null; then
    wget http://mattmahoney.net/dc/text8.zip
  else
    curl -O http://mattmahoney.net/dc/text8.zip
  fi
  unzip text8.zip
  rm text8.zip
fi
# 注释掉以上  

CORPUS=text8   #换成自己的语料库
VOCAB_FILE=vocab.txt
COOCCURRENCE_FILE=cooccurrence.bin
COOCCURRENCE_SHUF_FILE=cooccurrence.shuf.bin
BUILDDIR=build
SAVE_FILE=vectors
VERBOSE=2 #冗余输出参数 设置为2 可以查看程序运行进度
MEMORY=4.0
VOCAB_MIN_COUNT=5
VECTOR_SIZE=50
MAX_ITER=15
WINDOW_SIZE=15
BINARY=2
NUM_THREADS=8
X_MAX=10


echo
echo "$ $BUILDDIR/vocab_count -min-count $VOCAB_MIN_COUNT -verbose $VERBOSE < $CORPUS > $VOCAB_FILE"
$BUILDDIR/vocab_count -min-count $VOCAB_MIN_COUNT -verbose $VERBOSE < $CORPUS > $VOCAB_FILE
echo "$ $BUILDDIR/cooccur -memory $MEMORY -vocab-file $VOCAB_FILE -verbose $VERBOSE -window-size $WINDOW_SIZE < $CORPUS > $COOCCURRENCE_FILE"
$BUILDDIR/cooccur -memory $MEMORY -vocab-file $VOCAB_FILE -verbose $VERBOSE -window-size $WINDOW_SIZE < $CORPUS > $COOCCURRENCE_FILE
echo "$ $BUILDDIR/shuffle -memory $MEMORY -verbose $VERBOSE < $COOCCURRENCE_FILE > $COOCCURRENCE_SHUF_FILE"
$BUILDDIR/shuffle -memory $MEMORY -verbose $VERBOSE < $COOCCURRENCE_FILE > $COOCCURRENCE_SHUF_FILE
echo "$ $BUILDDIR/glove -save-file $SAVE_FILE -threads $NUM_THREADS -input-file $COOCCURRENCE_SHUF_FILE -x-max $X_MAX -iter $MAX_ITER -vector-size $VECTOR_SIZE -binary $BINARY -vocab-file $VOCAB_FILE -verbose $VERBOSE"
$BUILDDIR/glove -save-file $SAVE_FILE -threads $NUM_THREADS -input-file $COOCCURRENCE_SHUF_FILE -x-max $X_MAX -iter $MAX_ITER -vector-size $VECTOR_SIZE -binary $BINARY -vocab-file $VOCAB_FILE -verbose $VERBOSE
if [ "$CORPUS" = 'text8' ]; then
   if [ "$1" = 'matlab' ]; then
       matlab -nodisplay -nodesktop -nojvm -nosplash < ./eval/matlab/read_and_evaluate.m 1>&2 
   elif [ "$1" = 'octave' ]; then
       octave < ./eval/octave/read_and_evaluate_octave.m 1>&2
   else
       echo "$ python eval/python/evaluate.py"
       python eval/python/evaluate.py
   fi
fi

参考：https://me.csdn.net/u011793737