pip로 패키지 install 중, 아래와 같은 오류가 발생할 때 해결법
- 에러메시지
Cannot uninstall 'pytz (pkg name)'. It is a distutils installed project and thus we cannot accurately determine which files belong to it which would lead to only a partial uninstall.
- 해결방법 : 걍 설치된 버전 무시해버려!
pip install --ignore-installed pytz
# coding: utf-8 # # #### Gensim model building # In[98]: # Import required modules import gensim, codecs import re # In[99]: sentences_vocab = [] for line in codecs.open('impeachment_sentence.txt', encoding='utf-8'): sentences = [word+'다.' for word in line.split('다. ') if word!='\n'] for sentence in sentences: sentence = re.sub('\\n다.' , '' ,sentence) sentence = re.sub('\\u3000.' , '' ,sentence) sentences_vocab.append(sentence) # In[101]: from konlpy.tag import Twitter pos_tagger = Twitter() def tokenize(doc): return ['/'.join(t) for t in pos_tagger.pos(doc, norm=True, stem=True) ] # In[102]: tokenize('전국경제인연합회(다음부터 \'전경련\'이라 한다)가 주도하여 만든 것으로 알려져있던') # In[103]: # Preprocessing sentences_vocab = [] for line in codecs.open('impeachment_sentence.txt', encoding='utf-8'): sentences = [word+'다.' for word in line.split('다. ') if word!='\n'] for sentence in sentences: sentences_vocab.append(tokenize(sentence)) # In[104]: sentences_vocab[41] # In[105]: import multiprocessing config = { 'min_count': 1, 'size': 300, 'sg': 1, 'batch_words': 10, 'iter': 100, 'workers': multiprocessing.cpu_count(), } model = gensim.models.Word2Vec(**config) # In[106]: model.build_vocab(sentences_vocab) # In[140]: num_w2v = len(model.wv.index2word) print (num_w2v) # In[141]: import numpy as np w2v = np.zeros((num_w2v,300)) with open("./projector/metadata.tsv", 'w+') as file_metadata: for i,word in enumerate(model.wv.index2word): w2v[i] = model[word] file_metadata.write(word + '\n') # #### Tensorflow Visualization # In[134]: import tensorflow as tf from tensorflow.contrib.tensorboard.plugins import projector import numpy as np # setup a TensorFlow session tf.reset_default_graph() sess = tf.InteractiveSession() X = tf.Variable([0.0], name='embedding') place = tf.placeholder(tf.float32, shape=[None, 300]) set_x = tf.assign(X, place, validate_shape=False) sess.run(tf.global_variables_initializer()) sess.run(set_x, feed_dict={place: w2v}) # create a TensorFlow summary writer summary_writer = tf.summary.FileWriter('projector', sess.graph) config = projector.ProjectorConfig() embedding_conf = config.embeddings.add() embedding_conf.tensor_name = 'embedding:0' embedding_conf.metadata_path = './projector/metadata.tsv' projector.visualize_embeddings(summary_writer, config) # save the model saver = tf.train.Saver() saver.save(sess, './projector/model.ckpt') sess.close()
 |
| Docker image Pull & Run |
 |
| localhost 접속 결과. 안된다. |
 |
| virtual ip를 확인하자! |
 |
| port forwarding과 함께하는 docker |
 |
| 노트북 리스트가 떴다! |
import requests as rq import bs4 header = {'User-Agent':'Mozilla/5.0'} def get_html_title(url): request = rq.Request('Get', url, headers = header) r = request.prepare() s = rq.Session() try: response = s.send(r) except rq.exceptions.ConnectionError: return '' if response == None: return '' html_content = response.text navigator = bs4.BeautifulSoup(html_content, "html.parser") title = navigator.find('title') if title == None: return '' return title.get_text()
ConnectionError exception.HTTPError exception.Timeout exception is raised.TooManyRedirects exception is raised.requests.exceptions.RequestException.