#将本地id_rsa.pub复制到远程服务器
scp ~/.ssh/id_rsa.pub ruben@cpp.pub:/tmp/id_rsa.pub
#下面的步骤在服务器上操作
ssh ruben@cpp.pub
cat /tmp/id_rsa.pub >> ~/.ssh/authorized_keys

ssh-copy-id ruben@cpp.pub

sudo apt-get install git
sudo apt-get install openssh

cd ~
git init --bare about.git

ssh-keygen
cd ~/.ssh
ls

authorized_keys  id_rsa  id_rsa.pub

ssh-keygen
cd ~/.ssh
ls

authorized_keys  id_rsa  id_rsa.pub

cat ~/.ssh/id_rsa.pub

ssh-rsa AAAAB3NzaC1yc2EAAAADAQABAAABAQC5LdkvYM4+NT3kTcr.......

cd ~
vim ~/.ssh/authorized_keys

git clone 服务器用户名@ip:/about.git

ruben@ruben:~$ git clone root@cpp.pub:about.git
Cloning into 'about'...
warning: You appear to have cloned an empty repository.

#clone 源码
git clone https://github.com/mit-nlp/MITIE.git
cd MITIE
python setup.py install

from mitie import *

cd MITIE/tools/wordrep
mkdir build
cd build
cmake ..
make

-MITIE/tools/wordrep/build
 - CMakeCache.txt  
 - CMakeFiles  
 - cmake_install.cmake  
 - dlib_build  
 - Makefile  
 - mitie_build  
 - wordrep

cd ~
mkdir temp
cd temp
mv MITIE/tools/wordrep/build/wordrep .
mkdir zh
cp ~/text.txt ./zh
wordrep -e ./zh

你 可 不要 小看 我 
你 的 身高 是 多少
我 只有 二十厘米 高 ， 现在 还 在 买 半价票 呢 
你 有 多 高
我 个子 不高 呢 ， 只有 二十厘米 ， 出门 要 把 我 抱 在 怀里

/temp
 - substring_set.dat
 - top_word_counts.dat
 - total_word_feature_extractor.dat
 - wordrep
 - zh/
 - substrings.txt
 - top_words.txt
 - word_morph_feature_extractor.dat
 - word_vects.dat

from mitie import *

print ("loading Total Word Feature Extractor...")

twfe = total_word_feature_extractor('zh/total_word_feature_extractor.dat')

# Get fingerprint of feature dictionary
print ("Fingerprint of feature dictionary", twfe.fingerprint)
print ()
# Get number of dimensions of feature vectors
print ("Number of dimensions of feature vectors", twfe.num_dimensions)
print ()
# Get number of words in the dictionary
print ("Number of words in the dictionary", twfe.num_words_in_dictionary)
print ()
# Get list of words in the dictionary
words=twfe.get_words_in_dictionary()
print ("First 10 words in dictionary", words[0:200])
print ()
# Get features for one word
feats = twfe.get_feature_vector("我")
print ("First 5 features of word 'home'", feats[0:])
# The total word feature extractor will generate feature vectors for words not
# in its dictionary as well.  It does this by looking at word morphology.  
feats = twfe.get_feature_vector("_word_not_in_dictionary_")
print ("First 5 features of word '_word_not_in_dictionary_'", feats[0:50])

Number of dimensions of feature vectors 271
Number of words in the dictionary 2582
.....
...

pip install -U spacy

conda install -c conda-forge spacy

#命令行
python -m spacy download xx #xx表示上面表格中的的NAME
#pip
pip install https://github.com/explosion/spacy-models/releases/download/en_core_web_md-1.2.0/en_core_web_md-1.2.0.tar.gz
#本地文件
pip install /Users/you/en_core_web_md-1.2.0.tar.gz

import spacy
nlp = spacy.load('en')                       # load model with shortcut link "en"
nlp = spacy.load('en_core_web_sm')           # load model package "en_core_web_sm"
nlp = spacy.load('/path/to/en_core_web_sm')  # load package from a directory

doc = nlp(u'This is a sentence.')

doc = nlp(u'Apple is looking at buying U.K. startup for $1 billion')

for token in doc:
    print(token.text, token.lemma_, token.pos_, token.tag_, token.dep_,
          token.shape_, token.is_alpha, token.is_stop)

doc = nlp(u'Autonomous cars shift insurance liability toward manufacturers')
for token in doc:
    print(token.text, token.dep_, token.head.text, token.head.pos_,
          [child for child in token.children])

doc = nlp(u'Apple is looking at buying U.K. startup for $1 billion')

for ent in doc.ents:
    print(ent.text, ent.start_char, ent.end_char, ent.label_)

for token in doc:
    print(token.text)

E: Unable to locate package postgresql-9.5

wget --quiet -O - https://www.postgresql.org/media/keys/ACCC4CF8.asc | sudo apt-key add -
sudo sh -c 'echo "deb http://apt.postgresql.org/pub/repos/apt/ precise-pgdg main 9.5" >> /etc/apt/sources.list.d/postgresql.list'
sudo apt-get update
sudo apt-get install postgresql-9.5

list_sen=['今天这个菜真好吃！','嗨！今天天气不错！','今天很开心，明天见！']

dict_voc=dict()
for s in list_sen:
    for w in s:
        if w in dict_voc.keys():
            dict_voc[w]+=1
        else:
            dict_voc[w]=1

{'这': 1.0, '嗨': 1.0, '好': 1.0, '气': 1.0, '真': 1.0, '错': 1.0, '不': 1.0, '个': 1.0, '心': 1.0, '天': 0.2, '菜': 1.0, '今': 0.3333333333333333, '，': 1.0, '！': 0.25, '吃': 1.0, '明': 1.0, '见': 1.0, '很': 1.0, '开': 1.0}

features_one=dict()#吃饭  {字：频率}
features_two=dict()#打招呼
features_three=dict()#再见
for w in list_sen[0]:
    if w in features_one.keys():
        features_one[w]+=1
    else:
        features_one[w]=1
for w in list_sen[1]:
    if w in features_two.keys():
        features_two[w]+=1
    else:
        features_two[w]=1
for w in list_sen[2]:
    if w in features_three.keys():
        features_three[w]+=1
    else:
        features_three[w]=1
print(features_one)
print(features_two)
print(features_three)

#{'好': 1, '天': 1, '真': 1, '吃': 1, '！': 1, '菜': 1, '今': 1, '个': 1, '这': 1}
#{'不': 1, '！': 2, '气': 1, '嗨': 1, '错': 1, '今': 1, '天': 2}
#{'明': 1, '心': 1, '开': 1, '见': 1, '，': 1, '很': 1, '今': 1, '天': 2, '！': 1}

特征命中：今、天、这、天
类别：吃饭
得分：4

特征命中：今、天、天
类别：打招呼
得分：3

特征命中：今、天、明、天、，、，
类别：再见
得分：6

特征命中：今（0.3）、天（0.2）、这（1）、天（0.2）
类别：吃饭
得分：1.73

特征命中：今（0.3）、天（0.2）、天（0.2）
类别：打招呼
得分：1.13

特征命中：今（0.3）、天（0.2）、明（1.0）、天（0.2）、，（1.0）、，（1.0）
类别：再见
得分：4.13

sen='今天的工作就到这里吧，大家早点回去，明天再继续吧。'
score1=0.0
score2=0.0
score3=0.0
print('class1:')
for w in sen:
    if w in features_one:
        print('word:',w,features_one[w],dict_voc[w])
        score1+=features_one[w]*dict_voc[w]
print('score1:',score1)
print('---------------------')
print('class2:')
for w in sen:
    if w in features_two:
        print('word', w,features_two[w],dict_voc[w])
        score2+=features_two[w]*dict_voc[w]
print('score2:',score2)
print('---------------------')
print('class3:')
for w in sen:
    if w in features_three:
        print('word', w,features_three[w],dict_voc[w])
        score3+=features_three[w]*dict_voc[w]
print('score3:',score3)
print('---------------------')

class1:
word: 今 1 0.3333333333333333
word: 天 1 0.2
word: 这 1 1.0
word: 天 1 0.2
score1: 1.7333333333333332
---------------------
class2:
word 今 1 0.3333333333333333
word 天 2 0.2
word 天 2 0.2
score2: 1.1333333333333333
---------------------
class3:
word 今 1 0.3333333333333333
word 天 2 0.2
word ， 1 1.0
word ， 1 1.0
word 明 1 1.0
word 天 2 0.2
score3: 4.133333333333334
---------------------

import torch
import torch.nn as nn
import torch.autograd as autograd
import torch.functional as F

data = [("我 的 家 乡 在 哪 里".split(), "CHINESE"),
        ("Give it to me".split(), "ENGLISH"),
        ("今 天 天 气 怎 么 样".split(), "CHINESE"),
        ("No it is not a good idea to get lost at sea".split(), "ENGLISH")]

test_data = [("天 气 在 哪 里".split(), "CHINESE"),
             ("it is lost on me".split(), "ENGLISH")]
word2index={}
for sen,_ in data+test_data:
    for word in sen:
        if word not in word2index:
            word2index[word]=len(word2index)
print(word2index)
VOCAB_SIZE=len(word2index)
NUM_CLASSES=2
label2index={'CHINESE':0,'ENGLISH':1}

class BoWClassifier(torch.nn.Module):
    def __init__(self,num_labels,vocab_size):
        super(BoWClassifier,self).__init__()
        self.linear=nn.Linear(vocab_size,num_labels)
        self.softmax=nn.Softmax()
    def forward(self,bow_vec):
        return self.softmax(self.linear(bow_vec))
def make_bow_vector(sentence,word2index):
    vec=torch.zeros(len(word2index))
    for word in sentence:
        vec[word2index[word]]+=1
    return vec.view(1,-1)
def make_target(label,label2index):
    return torch.LongTensor([label2index[label]])

model=BoWClassifier(NUM_CLASSES,VOCAB_SIZE)

# for param in model.parameters():
#     print(param)
log_prob=model(autograd.Variable(make_bow_vector(data[0][0],word2index)))
print(log_prob)

loss_function=nn.NLLLoss()
optimizer=torch.optim.SGD(model.parameters(),lr=0.1)

for epoch in range(100):
    for instance,label in data:
        model.zero_grad()
        bow_vec=autograd.Variable(make_bow_vector(instance,word2index))
        target=autograd.Variable(make_target(label,label2index))
        # print(target)
        log_prob=model(bow_vec)
        # print(log_prob)
        loss=loss_function(log_prob,target)
        loss.backward()
        optimizer.step()
for instance,label in test_data:
    bow_vec=autograd.Variable(make_bow_vector(instance,word2index))
    log_prob=model(bow_vec)
#     print(log_prob)
print(model(autograd.Variable(make_bow_vector(['Give','good','good','good','good'],word2index))))