# coding: utf-8# # graphlab对中文的支持简直无解,怎么办?求解决方法# In[34]:import sys
reload(sys)
sys.setdefaultencoding('utf8')
import graphlab
import datetime# In[35]:# Limit number of worker processes. This preserves system memory, which prevents hosted notebooks from crashing.
graphlab.set_runtime_config('GRAPHLAB_DEFAULT_NUM_PYLAMBDA_WORKERS', 4)# In[36]:

douban = graphlab.SFrame.read_json('data/douban.json')# In[37]:

douban.head()# In[38]:

len(douban)# In[41]:

weicheng = douban[douban['name'] == '围城']# In[42]:

weicheng# In[43]:

weicheng['intro']# In[44]:

weicheng['word_count'] = graphlab.text_analytics.count_words(weicheng['intro'])# In[46]:

weicheng['word_count']# In[47]:#创建一张新表,stack可以将k-v转换为2列
weicheng_word_count_table = weicheng[['word_count']].stack('word_count', new_column_name = ['word','count'])# In[48]:

weicheng_word_count_table.head()# In[49]:#排序,降序
weicheng_word_count_table.sort('count',ascending=False)# In[50]:#TF-IDF取决于所有文本
douban['word_count'] = graphlab.text_analytics.count_words(douban['intro'])
douban.head()# In[51]:#计算tf-idf
tfidf = graphlab.text_analytics.tf_idf(douban['word_count'])# Earlier versions of GraphLab Create returned an SFrame rather than a single SArray
# This notebook was created using Graphlab Create version 1.7.1
if graphlab.version <= '1.6.1':tfidf = tfidf['docs']tfidf# In[52]:

douban['tfidf'] = tfidf# In[53]:

weicheng = douban[douban['name'] == '围城']# In[54]:#创建一个围城的tfidf列并排序
weicheng[['tfidf']].stack('tfidf',new_column_name=['word','tfidf']).sort('tfidf',ascending=False)# In[55]:#创建一个临近模型
knn_model = graphlab.nearest_neighbors.create(douban,features=['tfidf'],label='name')# In[56]:

knn_model.query(weicheng)# In[ ]: