#!/usr/bin/env python
# coding: utf-8

# # 실습하기

# In[1]:


# "\t \n"를 기준으로 작업을 진행하기


# In[2]:


with open('data/war_of_flower.txt', 'r') as f:
    text = f.readlines()


# In[3]:


import re
result, tokenizer = [], re.compile(r"^\d+")
for t in text:
    if t.replace(" ","").find('곽철용') != -1:
        if "".join(tokenizer.findall(t)):
            pass
        elif t.replace(" ","").find(':') != -1:
            result.append(" ".join(t.split(":")[1:]))
        else:
            result.append(t.replace('\t', ''))


# In[4]:


from konlpy.tag import Mecab
result    = " ".join(result)
token_kcw = [_ for _ in Mecab().nouns(result) if len(_) >2]
token_kcw_unique = list(set(token_kcw))
len(token_kcw_unique)


# In[5]:


"// ".join(token_kcw_unique)


# In[7]:


get_ipython().run_line_magic('matplotlib', 'inline')
import matplotlib.pyplot as plt
from wordcloud import WordCloud
font_file = "data/D2Coding.ttf"
wcloud    = WordCloud(font_file, relative_scaling=0, collocations=False).generate(" ".join(token_kcw))
plt.figure(figsize=(12,12))
plt.imshow(wcloud)
plt.axis("off")


# In[8]:


from konlpy.tag import Mecab
result    = " ".join(text)
tokens = [_ for _ in Mecab().nouns(result) if len(_) >2]
len(tokens)


# In[9]:


get_ipython().run_line_magic('matplotlib', 'inline')
import matplotlib.pyplot as plt
from wordcloud import WordCloud
font_file = "data/D2Coding.ttf"
wcloud    = WordCloud(font_file, relative_scaling=0, collocations=False).generate(" ".join(tokens))
plt.figure(figsize=(12,12))
plt.imshow(wcloud)
plt.axis("off")


# In[ ]: