w2v/
`-- trunk
|-- LICENSE
|-- README.txt
|-- compute-accuracy.c
|-- demo-analogy.sh
|-- demo-classes.sh
|-- demo-phrase-accuracy.sh
|-- demo-phrases.sh
|-- demo-train-big-model-v1.sh
|-- demo-word-accuracy.sh
|-- demo-word.sh
|-- distance.c
|-- makefile
|-- questions-phrases.txt
|-- questions-words.txt
|-- word-analogy.c
|-- word2phrase.c
`-- word2vec.c
CC = gcc
#Using -Ofast instead of -O3 might result in faster code, but is supported only by newer GCC versions
CFLAGS = -lm -pthread -O3 -march=native -Wall -funroll-loops -Wno-unused-result
all: word2vec word2phrase distance word-analogy compute-accuracy
word2vec : word2vec.c
$(CC) word2vec.c -o word2vec $(CFLAGS)
word2phrase : word2phrase.c
$(CC) word2phrase.c -o word2phrase $(CFLAGS)
distance : distance.c
$(CC) distance.c -o distance $(CFLAGS)
word-analogy : word-analogy.c
$(CC) word-analogy.c -o word-analogy $(CFLAGS)
compute-accuracy : compute-accuracy.c
$(CC) compute-accuracy.c -o compute-accuracy $(CFLAGS)
chmod +x *.sh
clean:
rm -rf word2vec word2phrase distance word-analogy compute-accuracy
Enter word or sentence (EXIT to break): china
Word: china Position in vocabulary: 486
Word Cosine distance
------------------------------------------------------------------------
japan 0.648631
taiwan 0.630534
manchuria 0.599535
tibet 0.583566
prc 0.560898
kalmykia 0.558937
xiamen 0.556037
jiang 0.553501
chinese 0.547065
liao 0.543676
india 0.536273
korea 0.534758
roc 0.530741
thailand 0.529334
hunan 0.527629
liang 0.527374
shanghai 0.526314
chongqing 0.525559
nanjing 0.521342
yunnan 0.518669
wuhan 0.516914
zhao 0.513246
xinjiang 0.509939
tuva 0.507322
guangdong 0.507288
hubei 0.505540
guangxi 0.501068
taipei 0.497673
macao 0.497303
hainan 0.494808
shandong 0.493323
shenzhen 0.491871
hangzhou 0.489323
balhae 0.488846
guangzhou 0.486907
fujian 0.485473
zhejiang 0.485011
harbin 0.483171
原文：http://www.cnblogs.com/xiaodi914/p/4872180.html