def test_build_word_ego_graph():
sys.stdout, expected = open(get_current_function_name()+"_current","w"), open(get_current_function_name()+"_expected").read()
import networkx as nx
import matplotlib.pyplot as plt
plt.rcParams['font.sans-serif'] = ['SimHei'] # 步骤一（替换sans-serif字体）
plt.rcParams['axes.unicode_minus'] = False # 步骤二（解决坐标轴负数的负号显示问题）
from harvesttext import get_sanguo, get_sanguo_entity_dict, get_baidu_stopwords
ht0 = HarvestText()
entity_mention_dict, entity_type_dict = get_sanguo_entity_dict()
ht0.add_entities(entity_mention_dict, entity_type_dict)
sanguo1 = get_sanguo()[0]
stopwords = get_baidu_stopwords()
docs = ht0.cut_sentences(sanguo1)
G = ht0.build_word_ego_graph(docs,"刘备",min_freq=3,other_min_freq=2,stopwords=stopwords)
pos = nx.kamada_kawai_layout(G)
nx.draw(G,pos)
nx.draw_networkx_labels(G,pos)
G = ht0.build_entity_ego_graph(docs, "刘备", min_freq=3, other_min_freq=2)
pos = nx.spring_layout(G)
nx.draw(G, pos)
nx.draw_networkx_labels(G, pos)
sys.stdout.close()
assert open(get_current_function_name() + "_current").read() == expected
def build_word_ego_graph():
import networkx as nx
import matplotlib.pyplot as plt
plt.rcParams['font.sans-serif'] = ['SimHei'] # 步骤一（替换sans-serif字体）
plt.rcParams['axes.unicode_minus'] = False # 步骤二（解决坐标轴负数的负号显示问题）
from harvesttext import get_sanguo, get_sanguo_entity_dict, get_baidu_stopwords
ht0 = HarvestText()
entity_mention_dict, entity_type_dict = get_sanguo_entity_dict()
ht0.add_entities(entity_mention_dict, entity_type_dict)
sanguo1 = get_sanguo()[0]
stopwords = get_baidu_stopwords()
docs = ht0.cut_sentences(sanguo1)
G = ht0.build_word_ego_graph(docs,
"刘备",
min_freq=3,
other_min_freq=2,
stopwords=stopwords)
pos = nx.kamada_kawai_layout(G)
nx.draw(G, pos)
nx.draw_networkx_labels(G, pos)
plt.show()
G = ht0.build_entity_ego_graph(docs, "刘备", min_freq=3, other_min_freq=2)
pos = nx.spring_layout(G)
nx.draw(G, pos)
nx.draw_networkx_labels(G, pos)
plt.show()
def using_typed_words():
from harvesttext.resources import get_qh_typed_words, get_baidu_stopwords
ht0 = HarvestText()
typed_words, stopwords = get_qh_typed_words(), get_baidu_stopwords()
ht0.add_typed_words(typed_words)
print("加载清华领域词典，并使用停用词")
print("全部类型", typed_words.keys())
sentence = "THUOCL是自然语言处理的一套中文词库，词表来自主流网站的社会标签、搜索热词、输入法词库等。"
print(sentence)
print(ht0.posseg(sentence, stopwords=stopwords))
print("一些词语被赋予特殊类型IT,而“是”等词语被筛出。")
def test_using_typed_words():
sys.stdout, expected = open(get_current_function_name()+"_current","w"), open(get_current_function_name()+"_expected").read()
from harvesttext.resources import get_qh_typed_words,get_baidu_stopwords
ht0 = HarvestText()
typed_words, stopwords = get_qh_typed_words(), get_baidu_stopwords()
ht0.add_typed_words(typed_words)
print("加载清华领域词典，并使用停用词")
print("全部类型",typed_words.keys())
sentence = "THUOCL是自然语言处理的一套中文词库，词表来自主流网站的社会标签、搜索热词、输入法词库等。"
print(sentence)
print(ht0.posseg(sentence,stopwords=stopwords))
print("一些词语被赋予特殊类型IT,而“是”等词语被筛出。")
sys.stdout.close()
assert open(get_current_function_name() + "_current").read() == expected
def load_resources():
from harvesttext.resources import get_qh_sent_dict, get_baidu_stopwords, get_sanguo, get_sanguo_entity_dict
sdict = get_qh_sent_dict() # {"pos":[积极词...],"neg":[消极词...]}
print("pos_words:", list(sdict["pos"])[10:15])
print("neg_words:", list(sdict["neg"])[5:10])
stopwords = get_baidu_stopwords()
print("stopwords:", list(stopwords)[5:10])
docs = get_sanguo() # 文本列表，每个元素为一章的文本
print("三国演义最后一章末16字:\n", docs[-1][-16:])
entity_mention_dict, entity_type_dict = get_sanguo_entity_dict()
print("刘备 指称：", entity_mention_dict["刘备"])
print("刘备 类别：", entity_type_dict["刘备"])
print("蜀 类别：", entity_type_dict["蜀"])
print("益州 类别：", entity_type_dict["益州"])
def test_load_resources():
sys.stdout, expected = open(get_current_function_name()+"_current","w"), open(get_current_function_name()+"_expected").read()
from harvesttext.resources import get_qh_sent_dict,get_baidu_stopwords,get_sanguo,get_sanguo_entity_dict
sdict = get_qh_sent_dict() # {"pos":[积极词...],"neg":[消极词...]}
print("pos_words:",list(sdict["pos"])[10:15])
print("neg_words:",list(sdict["neg"])[5:10])
stopwords = get_baidu_stopwords()
print("stopwords:", list(stopwords)[5:10])
docs = get_sanguo() # 文本列表，每个元素为一章的文本
print("三国演义最后一章末16字:\n",docs[-1][-16:])
entity_mention_dict, entity_type_dict = get_sanguo_entity_dict()
print("刘备 指称：",entity_mention_dict["刘备"])
print("刘备 类别：",entity_type_dict["刘备"])
print("蜀 类别：", entity_type_dict["蜀"])
print("益州 类别：", entity_type_dict["益州"])
sys.stdout.close()
