LDA Topic Model output (20 Topics):
Topic #13 and #17 can be interpreted as “armed provocation” and “nuclear provocation”, respectively. Each of #14 and #18 can be interpreted as “South-North Dialogue” and “international talks”.
The numbers of articles that belong to each category are shown in the graph below
Independent variable: the inverse degree of support for the unification of the people (1: necessary / 5: unnecessary)
NER with word vectors.
Word vectors are particularly useful for terms which aren’t well represented in your labelled training data. For instance, if you’re doing named entity recognition, there will always be lots of names that you don’t have examples of. For instance, imagine your training data happens to contain some examples of the term “Microsoft”, but it doesn’t contain any examples of the term “Symantec”. In your raw text sample, there are plenty of examples of both terms, and they’re used in similar contexts. The word vectors make that fact available to the entity recognition model. It still won’t see examples of “Symantec” labelled as a company. However, it’ll see that “Symantec” has a word vector that usually corresponds to company terms, so it can make the inference.
-https://spacy.io/usage/vectors-similarity
INPUT data : All of 10-K, 10-Q filings available on SEC, with basic preprocessing steps except for lemmatization, N grams.
CODE :
As my RAM was restricted to 16 GB, I found the Data Streaming technique is especially useful in my case. (Helpful introductions on training Word Vectors using Gensim : https://rare-technologies.com/word2vec-tutorial/ , https://rare-technologies.com/data-streaming-in-python-generators-iterators-iterables/)
import os
import sys
import re
from gensim.models import Word2Vec
import logging
logging.basicConfig(
format='%(asctime)s : %(levelname)s : %(message)s',
level=logging.INFO) #Display the progress of training word vectors
dirname = 'D:/10_k' # directory where 10-K/Q filings are downloaded
class MySentences(object):
def __init__(self, dirname):
self.dirname = dirname
def __iter__(self):
for f_dir in os.listdir(self.dirname):
for qname in os.listdir(os.path.join(self.dirname, f_dir, 'EDGAR\\10-X_C', f_dir[-4:])):
#print(os.path.join(dirname, f_dir, 'EDGAR\\10-X_C', f_dir[-4:]))
for fname in os.listdir(os.path.join(self.dirname, f_dir, 'EDGAR\\10-X_C', f_dir[-4:], qname)):
if fname.endswith(".txt"):
for line in open(os.path.join(self.dirname, f_dir, 'EDGAR\\10-X_C', f_dir[-4:], qname, fname), 'r', encoding = 'utf-8'):
yield line.split()
sentences_ = MySentences(dirname)
model = Word2Vec(min_count = 10, size = 200)
model.build_vocab(sentences_) # to test multiple parameters later, it is much convenient to first build vocabulary and save it
#model.save('D:/mltool/word2vec/LMLM_word2vec_MIN_10')
#model = Word2Vec.load('D:/mltool/word2vec/LMLM_word2vec_MIN_10')
sentences_ = MySentences(dirname)
model.window = 5
model.workers = 5
model.size = 200
model.sg = 0 # allows faster training
model.train(sentences__, total_examples = model.corpus_count, epochs = 10)
model.wv.save_word2vec_format('D:/mltool/kv_LMLM_dim_200_MIN_10', binary = False) # save keyed vector from the model
Now, finally build spacy model using keyed vector constructed right before.
Type into CMD window:
python -m spacy init-model en your_spacy_model_name --vectors-loc keyed vector location
CODE:
import re
import os
import sys
import pandas as pd
import numpy as np
import pandas as pd
from pprint import pprint
import random
import gensim
import gensim.corpora as corpora
from konlpy.tag import Twitter
from operator import itemgetter
import datetime as dt
import logging
logging.basicConfig(format='%(asctime)s : %(levelname)s : %(message)s', level=logging.INFO)
import warnings
warnings.filterwarnings("ignore",category=DeprecationWarning)
data = []
dirname = 'D://nk//data'
header = {}
k = 0
for f_dir in os.listdir(dirname):
for fname in os.listdir(os.path.join(dirname, f_dir)):
k += 1
if k % 10000 == 0:
print(k)
f = open(os.path.join(dirname, f_dir, fname), 'r', encoding = 'utf-8')
data.append([f_dir, f.read()])
f.close()
#Document specific Preprocessing
a1 = re.compile('등록\s*\:\s*(\d{4}\s*\-\s*\d{2}\s*\-\s*\d{2})')
a2 = re.compile('입력\s*(\d{4}\s*[\.\-]\s*\d{2}\s*[\.\-]\s*\d{2})')
a2_2 = re.compile('(\d{4}\s*[\.\-]\s*\d{2}\s*[\.\-]\s*\d{2})')
a2_3 = re.compile('등록\s*\:\(\d{4}\-\d{2}\-\d{2})')
a3 = re.compile('((?:19|20)\d{6})')
a4 = re.compile('(\d{4}\s*\-\s*\d{2}\s*\-\s*\d{2})')
for item in data:
k = 0
for a in [a1, a2, a2_2, a2_3, a4, a3]:
if a.search(item[1]):
date = re.sub('[\s\-\.]', '', a.search(item[1])[1])
k = 1
data_date.append([item[0], date, item[1]])
if len(str(date)) != 8:
print(item[1][:100])
break
#if k == 0 :
#print(item[1][:30])
twitter = Twitter()
def sent_to_words(sentences):
return twitter.morphs(sentences) # deacc=True removes punctuations
def remove_stopwords(texts):
return [[word for word in preprocess(str(doc)) if word not in stopwords] for doc in texts]
def make_bigrams(texts):
return [bigram_mod[doc] for doc in texts]
def make_trigrams(texts):
return [trigram_mod[bigram_mod[doc]] for doc in texts]
def preprocess(doc):
doc = re.sub('\s+', ' ', doc)
doc = re.sub('[A-Za-z]+[0-9]+', '', doc)
doc = re.sub('[a-zA-Z]+', ' ', doc)
doc = re.sub('\s+', ' ', doc)
return doc
#Remove all the one character words except for the name of country
country_list = ['미', '북', '러', '중', '일', '한', '군', '핵', '당', '말', '남']
data = [[re.sub('[^가-힣\s\_]', '', word) for word in item] for item in data]
data = [[word for word in item if (len(word) > 1) or (word in country_list)] for item in data]
data_words = list(zip(header, data))
#Remove document specific stopwords
stop_words = ['아티클', '중앙일보', '조선일보', '동아일보', '한겨레', '구독', '관련기사', '아티', '클관련', '추가', '지면보기',
'종합', '뉴스', '사진', '밝혔', '이라고', '등록', '라고', '라며', '내용', '보다', '경우', '지역', '위해', '이라는', '그런', '처럼', '이나', '같은', '보다', '는데', '다면', '그것', '이제',
'때문', '다시', '많은', '정도', '일이', '없었', '되었', '인가', '않는', '베스트추천', '기자', '수정']
data_words = [[item[0], item[1], [word for word in item[2] if word not in stop_words]] for item in data_words]
def get_topic(txt):
corpus = id2word.doc2bow(txt)
topic = list(lda_model.get_document_topics(corpus))
return sorted(topic, key=itemgetter(1))[-1][0]
#return topics and the corresponding words and weights.
lda_model.print_topics()
#Drawing Graph
result = [[item[0], item[1], get_topic(item[2])] for item in data_words]
df = pd.DataFrame(result)
df.columns = ['news', 'date', 'topic']
df.date = df.date.astype(int)
df = df[df.date >= 199501]
#Remove errors in date information
for i in range(len(df)):
if int(str(df['date'].iloc[i])[4:6]) > 12 or int(str(df['date'].iloc[i])[4:6]) == 0:
print(i, df['date'].iloc[i])
for i in range(len(df)):
try:
x = df['date'].iloc[i]
dt.date(int(str(x)[0:4]), int(str(x)[4:6]), int(str(x)[6:]))
except:
print(i, df['date'].iloc[i])
df.drop(df.index[[42981, 43438]], inplace = True)
df.drop(df.index[[65986, 74283]], inplace = True)
#Process date information
df['date'] = df['date'].apply(lambda x: dt.date(int(str(x)[0:4]), int(str(x)[4:6]), int(str(x)[6:])))
df['date'] = pd.to_datetime(df['date'])
#Adjust sample ratio by putting different weight.
#day
count_d = df.groupby(['date', 'topic']).size().reset_index(name = 'count')
count_d['adj'] = count_d['count']
mask1 = (count_d['date'] < dt.date(2005, 1, 1))
mask2 = (dt.date(2005, 1, 1) < count_d['date']) & (count_d['date']< dt.date(2009, 10, 17))
count_d.loc[mask1, 'adj'] = count_d.loc[mask1, 'count'] * 2
count_d.loc[mask2, 'adj'] = count_d.loc[mask2, 'count'] * (4/3)
#month
df_ = df.copy()
df_.reset_index()
df_['date'] = pd.to_datetime(df_['date'])
df_.set_index('date', inplace = True)
df_ = df_.to_period('M').to_timestamp('M')
count_m = df_.groupby(['date', 'topic']).size().reset_index(name = 'count')
count_m['adj'] = count_m['count']
mask1 = (count_m['date'] < dt.date(2005, 1, 1))
mask2 = (dt.date(2005, 1, 1) < count_m['date']) & (count_m['date']<dt>= dt.date(2000,1,1)) & (count_d.date = dt.date(2000,1,1)) & (count_m.date = dt.date(2000,1,1)) & (count_y.date = dt.date(2018, 1, 1))
count_y.loc[mask3, 'adj'] = count_y.loc[mask3, 'count'] * 6/5
else:
return None
#color = '#00BFFF'
x = xy['date']
if adj:
y = xy['adj']
else:
y = xy['count']
#ax.plot(x, y, alpha = 0.8, c = color, linewidth=1.3)
#print(label, topic)
ax.plot(x, y, alpha = 0.7, linewidth=1.3, label = 'topic # : %s(%s)'%(label, str(topic)))
ax.set_xlim(dt.date(2000, 1,1), dt.date(2018, 12, 31))
#ax.set_xlim(min(x), max(x))
#ax.set_title("Spread and GDP", fontsize = 20)
ax.set_xlabel('year', fontsize = 20)
ax.set_ylabel('Number of Ariticles' , fontsize= 24)
ax.spines['top'].set_visible(False)
ax.spines['right'].set_visible(False)
ax.grid(color='grey', linestyle='-', linewidth=0, alpha = 1)
#ax.set_xticks([1995, 1997, 1999, 2001, 2003, 2005, 2007, 2009, 2011, 2013, 2015, 2017])
ax.tick_params(axis = 'both', labelsize = 17)
ax.legend()
#if period == 'Y':
# plt.xticks(np.arange(dt.date(2000, 12, 31), dt.date(2018, 12, 31), dt.timedelta(731)))
#else:
plt.xticks(np.arange(dt.date(2000, 1,1), dt.date(2018, 12, 31), dt.timedelta(731)))
plt.show()
#Draw Graphs (Day, Month, Year frequency on provocation and peace topics respectively)
dp([12, 16], ['provocation', 'nuclear'], 'D', adj = True)
dp([13, 14], ['South-North', 'Global'], 'D', adj = True)
dp([12, 16], ['provocation', 'nuclear'], 'M', adj = True)
dp([13, 14], ['South-North', 'Global'], 'M', adj = True)
dp([12, 16], ['provocatoin', 'nuclear'], 'Y', adj = True)
dp([13, 14], ['South-North', 'US-North'], 'Y', adj = True)
#Number of Total Articles
plt.style.use('seaborn-whitegrid')
fig, ax = plt.subplots(figsize = (9.5, 6.5), dpi = 100)
xy = df.groupby(['date']).size().reset_index(name = 'count')
xy = xy[xy['date'] > dt.date(1995, 1, 1)]
#color = '#00BFFF'
x = xy['date']
y = xy['count']
#ax.plot(x, y, alpha = 0.8, c = color, linewidth=1.3<code>)
#print(label, topic)
ax.plot(x, y, alpha = 0.8, linewidth=1.3, label = 'total')
ax.set_xlim(min(x), max(x))
#ax.set_title("Spread and GDP", fontsize = 20)
ax.set_xlabel('year', fontsize = 20)
ax.set_ylabel('Number of Ariticles' , fontsize= 24)
ax.spines['top'].set_visible(False)
ax.spines['right'].set_visible(False)
ax.grid(color='grey', linestyle='-', linewidth=0, alpha = 1)
#ax.set_xticks([1995, 1997, 1999, 2001, 2003, 2005, 2007, 2009, 2011, 2013, 2015, 2017])
#ax.tick_params(axis = 'both', labelsize = 17)
ax.legend()
plt.xticks(np.arange(min(x), max(x), dt.timedelta(730)))
plt.show()
I recall that installing Caffe on Window was one of the hardest steps on this project.
