python从零开始构建知识图谱

又是帮着做作业。用Python实现了一个简单的知识图谱小demo。非常感谢这篇文章，对这篇文章做了一个复现，并记录遇到的问题。
开发工具：jupyter notebook
开发环境：
Python 3.7
en_core_web_sm 2.3.0
spacy 2.2.5
数据集在文章中有，自行下载。

# coding: utf-8

# In[11]:


import re
import pandas as pd
import bs4
import requests
import spacy
from spacy import displacy
nlp = spacy.load('en_core_web_sm')


from spacy.matcher import Matcher 
from spacy.tokens import Span 


import networkx as nx


import matplotlib.pyplot as plt
from tqdm import tqdm


pd.set_option('display.max_colwidth', 200)
get_ipython().run_line_magic('matplotlib', 'inline')


# In[12]:


candidate_sentences = pd.read_csv("wiki_sentences_v2.csv")
candidate_sentences.shape


# In[13]:


candidate_sentences['sentence'].sample(5)


# In[14]:


doc = nlp("the drawdown process is governed by astm standard d823")


for tok in doc:
  print(tok.text, "...", tok.dep_)


# In[16]:


def get_entities(sent):
 ## chunk 1
 # 我在这个块中定义了一些空变量。prv tok dep和prv tok text将分别保留句子中前一个单词和前一个单词本身的依赖标签。前缀和修饰符将保存与主题或对象相关的文本。
    ent1 = ""
    ent2 = ""


    prv_tok_dep = "" # dependency tag of previous token in the sentence
    prv_tok_text = "" # previous token in the sentence


    prefix = ""
    modifier = ""


 #############################################################
 
    for tok in nlp(sent):
        ## chunk 2
        # 接下来，我们将遍历句子中的记号。我们将首先检查标记是否为标点符号。如果是，那么我们将忽略它并转移到下一个令牌。如果标记是复合单词的一部分(dependency tag = compound)，我们将把它保存在prefix变量中。复合词是由多个单词组成一个具有新含义的单词(例如“Football Stadium”, “animal lover”)。
        # 当我们在句子中遇到主语或宾语时，我们会加上这个前缀。我们将对修饰语做同样的事情，例如“nice shirt”, “big house”


        # if token is a punctuation mark then move on to the next token
        if tok.dep_ != "punct":
        # check: token is a compound word or not
            if tok.dep_ == "compound":
                prefix = tok.text
        # if the previous word was also a 'compound' then add the current word to it
        if prv_tok_dep == "compound":
            prefix = prv_tok_text + " "+ tok.text

        # check: token is a modifier or not
        if tok.dep_.endswith("mod") == True:
            modifier = tok.text
        # if the previous word was also a 'compound' then add the current word to it
        if prv_tok_dep == "compound":
            modifier = prv_tok_text + " "+ tok.text

        ## chunk 3
        # 在这里，如果令牌是主语，那么它将作为ent1变量中的第一个实体被捕获。变量如前缀，修饰符，prv tok dep，和prv tok文本将被重置。
        if tok.dep_.find("subj") == True:
            ent1 = modifier +" "+ prefix + " "+ tok.text
            prefix = ""
            modifier = ""
            prv_tok_dep = ""
            prv_tok_text = "" 


        ## chunk 4
        # 在这里，如果令牌是宾语，那么它将被捕获为ent2变量中的第二个实体。变量，如前缀，修饰符，prv tok dep，和prv tok文本将再次被重置。
        if tok.dep_.find("obj") == True:
            ent2 = modifier +" "+ prefix +" "+ tok.text

        ## chunk 5  
        # 一旦我们捕获了句子中的主语和宾语，我们将更新前面的标记和它的依赖标记。
        # update variables
        prv_tok_dep = tok.dep_
        prv_tok_text = tok.text
        #############################################################


    return [ent1.strip(), ent2.strip()]

get_entities('the film had 200 patents')


# In[17]:


entity_pairs = []


for i in tqdm(candidate_sentences["sentence"]):
    entity_pairs.append(get_entities(i))




entity_pairs[10:20]


# In[19]:


def get_relation(sent):


    doc = nlp(sent)


   # Matcher class object 
    matcher = Matcher(nlp.vocab)


   #define the pattern 
    pattern = [{'DEP':'ROOT'}, 
              {'DEP':'prep','OP':"?"},
              {'DEP':'agent','OP':"?"},  
              {'POS':'ADJ','OP':"?"}] 


    matcher.add("matching_1", None, pattern) 


    matches = matcher(doc)
    k = len(matches) - 1


    span = doc[matches[k][1]:matches[k][2]] 


    return(span.text)

get_relation("John completed the task")


# In[20]:


relations = [get_relation(i) for i in tqdm(candidate_sentences['sentence'])]


pd.Series(relations).value_counts()[:50]


# In[21]:


# extract subject
source = [i[0] for i in entity_pairs] 
# extract object
target = [i[1] for i in entity_pairs] 


kg_df = pd.DataFrame({'source':source, 'target':target, 'edge':relations})  


# In[22]:


# create a directed-graph from a dataframe
G=nx.from_pandas_edgelist(kg_df, "source", "target", edge_attr=True, create_using=nx.MultiDiGraph())  


# In[23]:


plt.figure(figsize=(12,12))


pos = nx.spring_layout(G)
nx.draw(G, with_labels=True, node_color='skyblue', edge_cmap=plt.cm.Blues, pos = pos)
plt.show()


# In[24]:


G=nx.from_pandas_edgelist(kg_df[kg_df['edge']=="composed by"], "source", "target", 
                          edge_attr=True, create_using=nx.MultiDiGraph())


plt.figure(figsize=(12,12))
pos = nx.spring_layout(G, k = 0.5) # k regulates the distance between nodes
nx.draw(G, with_labels=True, node_color='skyblue', node_size=1500, edge_cmap=plt.cm.Blues, pos = pos)
plt.show()


# In[25]:


G=nx.from_pandas_edgelist(kg_df[kg_df['edge']=="written by"], "source", "target", 
                          edge_attr=True, create_using=nx.MultiDiGraph())


plt.figure(figsize=(12,12))
pos = nx.spring_layout(G, k = 0.5)
nx.draw(G, with_labels=True, node_color='skyblue', node_size=1500, edge_cmap=plt.cm.Blues, pos = pos)
plt.show()


# In[26]:


G=nx.from_pandas_edgelist(kg_df[kg_df['edge']=="released in"], "source", "target", 
                          edge_attr=True, create_using=nx.MultiDiGraph())


plt.figure(figsize=(12,12))
pos = nx.spring_layout(G, k = 0.5)
nx.draw(G, with_labels=True, node_color='skyblue', node_size=1500, edge_cmap=plt.cm.Blues, pos = pos)
plt.show()