由于编辑器总是崩溃，我只能直接把代码贴上了。
import numpy #first step import pandas as pd import numpy as np # Read data from files #这三行的目的就是读入文件，pd.read_csv()这个API里面参数还是比较多的，可以查阅官方文档 #人工标记过的训练数据 train = pd.read_csv( "data/labeledTrainData.tsv", header=0, delimiter="\t", quoting=3 ) #测试集 test = pd.read_csv( "data/testData.tsv", header=0, delimiter="\t", quoting=3 ) #未标记的训练数据，其实和测试集没什么区别，可以作为word2vec训练的时候的语料 unlabeled_train = pd.read_csv( "data/unlabeledTrainData.tsv", header=0,delimiter="\t", quoting=3 ) # Verify the number of reviews that were read (100,000 in total) #显示读入数据的行数 print "Read %d labeled train reviews, %d labeled test reviews, and %d unlabeled reviews\n" % \ (train["review"].size,test["review"].size, unlabeled_train["review"].size ) # second strp # Import various modules for string cleaning from bs4 import BeautifulSoup import re from nltk.corpus import stopwords #数据预处理，主要是网页标签，去数字和去停用词 def review_to_wordlist( review, remove_stopwords=False ): # Function to convert a document to a sequence of words, # optionally removing stop words. Returns a list of words. # # 1. Remove HTML #BeautifulSoup这个库是一个在做爬虫是经常使用的库，主要作用除去爬下来的文档标签， #大家可以看到原始句子里面含有<br /><br />这些标签，这是由于这些评论是从网页里面爬取出来的 #我们后续的处理是必须要去掉这些标签的，get_text()这个API可以轻松实现这个功能 review_text = BeautifulSoup(review,"html.parser").get_text() # # 2. Remove non-letters #这里就需要正则表达式的知识了，这句话实现的功能就是将数字去掉并且用一个空格去替换 review_text = re.sub("[^a-zA-Z]"," ", review_text) # # 3. Convert words to lower case and split them #将大写字母转换为小写字母，也许大小写不同会影响到处理吧，不太清楚 #这也是中英文自然语言处理的区别之一，中文不必考虑大小写问题，但是中文分词比英文分词麻烦很多 words = review_text.lower().split() # # 4. Optionally remove stop words (false by default) #除去停用词，这是自然语言处理里面经常会做的，不过为什么是Optionally remove #后面有答案 if remove_stopwords: stops = set(stopwords.words("english")) words = [w for w in words if not w in stops] # # 5. Return a list of words # print words return(words) # Download the punkt tokenizer for sentence splitting #nltk是python里面常用的自然语言处理的工具包，但是这一步会出问题 #原因貌似是nltk_data的网址变了，我是自己手动在网上找到了nltk_data #然后放在特定的路径就可以了 import nltk.data # Load the punkt tokenizer tokenizer = nltk.data.load('tokenizers/punkt/english.pickle') # Define a function to split a review into parsed sentences def review_to_sentences( review, tokenizer, remove_stopwords=False ): # Function to split a review into parsed sentences. Returns a # list of sentences, where each sentence is a list of words # # 1. Use the NLTK tokenizer to split the paragraph into sentences #使用nltk将每一条评论都分成一个个句子，比如利用英文的句号'.'进行划分. #'review.strip()'的作用是进行分词，不得补羡慕英文分词是真么简单高效 raw_sentences = tokenizer.tokenize(review.strip()) # # 2. Loop over each sentence #每个评论都被分成了几个句子，这里就是去掉那些长度为0的句子 sentences = [] for raw_sentence in raw_sentences: # If a sentence is empty, skip it if len(raw_sentence) > 0: # Otherwise, call review_to_wordlist to get a list of words #这里调用review_to_wordlist()实现数据清洗 sentences.append( review_to_wordlist( raw_sentence, \ remove_stopwords )) # # Return the list of sentences (each sentence is a list of words, # so this returns a list of lists #也就是说，输出是sentence的列表，而每个sentence也是一个单词的列表 return sentences sentences = [] # Initialize an empty list of sentences #这个处理就是把标记的训练数据进行处理，都放入sentences这个列表里面，这个列表每个元素 #其实是原来评论里面的一句话，不过是经过了数据清洗和分词 #注意到review_to_sentences(review.decode("utf8"), tokenizer)这个调用remove_stopwords=False #也就是说不除去停用词，为什么呢？这个就和word2vec这个方法有关了，有停用词可以保留完整的语料信息 #传统表示文本的方式都是BOW，也就是词袋模型，但是这种方法有两个的缺点：1.无法表征出词的关系，比如“篮球”“足球”“鸡腿” #明显“篮球”和“足球”含义相近，但是词袋模型并不能体现出来。2.维度过高，计算量过大，一般利用互信息，卡方检验等等进行降维处理 #word2vec也是将词表示成一种向量的办法，但是利用word2vec表示同意后的优点在于：1.词意相近的词语距离会更近（可以进算向量之间的距离） #2.维度低，可以人工指定维数。理解word2vec需要很多的数学知识，我在这里就不讲了 print "Parsing sentences from training set" for review in train["review"]: sentences += review_to_sentences(review.decode("utf8"), tokenizer) #为什么未标记的数据也能用呢，因为word2vec是无监督的，只是将这笔资料用作训练word2vec的语料库 #因此，这也体现出word2vec一个优点，因为未标记的预料是比标记预料容易获取到的 print "Parsing sentences from unlabeled set" for review in unlabeled_train["review"]: sentences += review_to_sentences(review.decode("utf8"), tokenizer) # Import the built-in logging module and configure it so that Word2Vec # creates nice output messages #输出日志信息，level一共是五级，这里level=logging.INFO import logging logging.basicConfig(format='%(asctime)s : %(levelname)s : %(message)s',\ level=logging.INFO) # Set values for various parameters #设定word2vec的参数，具体每个参数含义需要理解word2vec数学原理以及查阅API文档 num_features = 300 # Word vector dimensionality指定维度 min_word_count = 40 # Minimum word count num_workers = 4 # Number of threads to run in parallel四个线程 context = 10 # Context window size滑动窗口大小 downsampling = 1e-3 # Downsample setting for frequent words负采样 # Initialize and train the model (this will take some time) from gensim.models import word2vec print "Training model..." model = word2vec.Word2Vec(sentences, workers=num_workers, \ size=num_features, min_count = min_word_count, \ window = context, sample = downsampling) # If you don't plan to train the model any further, calling # init_sims will make the model much more memory-efficient. #保存模型，因为跑word2vec还是需要花时间的，因此在训练好之后保存下来，下次就可以直接使用了 model.init_sims(replace=True) # It can be helpful to create a meaningful model name and # save the model for later use. You can load it later using Word2Vec.load() model_name = "300features_40minwords_10context" model.save(model_name) #"man woman child kitchen"四个单词里面哪个和其他三个差距最大 # print model.doesnt_match("man woman child kitchen".split()) # print model.doesnt_match("france england germany berlin".split()) # print model.doesnt_match("paris berlin london austria".split()) #和"man"最像的单词 # print model.most_similar("man") # print model.most_similar("queen") # print model.most_similar("awful") # **************************************************************** # Calculate average feature vectors for training and testing sets, # using the functions we defined above. Notice that we now use stop word # removal. def makeFeatureVec(words, model, num_features): # Function to average all of the word vectors in a given # paragraph # # Pre-initialize an empty numpy array (for speed) featureVec = np.zeros((num_features,),dtype="float32") # nwords = 0. # # Index2word is a list that contains the names of the words in # the model's vocabulary. Convert it to a set, for speed index2word_set = set(model.wv.index2word) # # Loop over each word in the review and, if it is in the model's # vocaublary, add its feature vector to the total for word in words: if word in index2word_set: nwords = nwords + 1. #从模型里面取出相应单词的向量值 featureVec = np.add(featureVec,model[word]) # # Divide the result by the number of words to get the average featureVec = np.divide(featureVec,nwords) return featureVec #利用word2vec建模的关键就是如何给一个表示一个样本，在这个问题里面也就是如何表示一条评论？ #BOW词袋模型由于其高维度，可以轻松表示，而且还是稀疏的 #我们知道，经过word2vec，每个单词可以用长度为300的向量表示，假设某一条评论有100个单词，也就是100个向量 #我们的处理是将100个向量加起来再除去100，结果是一个300维测向量，也就是每条评论用300维向量表示 #看起来这种方法不是很靠谱，比较简单粗暴，我说说自己的两点理解：1.BOW词袋模型表示一个句子其实也是用的这个方法 #2.这样最起码保证了每个评论可以用相同维度的数据来表示 def getAvgFeatureVecs(reviews, model, num_features): # Given a set of reviews (each one a list of words), calculate # the average feature vector for each one and return a 2D numpy array # # Initialize a counter counter = 0 # # Preallocate a 2D numpy array, for speed reviewFeatureVecs = np.zeros((len(reviews),num_features),dtype="float32") # # Loop through the reviews for review in reviews: # # Print a status message every 1000th review if counter%1000 == 0: print "Review %d of %d" % (counter, len(reviews)) # # Call the function (defined above) that makes average feature vectors reviewFeatureVecs[counter] = makeFeatureVec(review, model, \ num_features) # # Increment the counter counter = counter + 1 return reviewFeatureVecs #这里为什么又要除去停用词呢？前面是利用word2vec表示单词，语料越完整越好 #这里是利用向量化的单词去表示文本，而在文本中，停用词对于文本表示几乎毫无作用，因此要去掉 clean_train_reviews = [] for review in train["review"]: clean_train_reviews.append( review_to_wordlist( review, \ remove_stopwords=True )) trainDataVecs = getAvgFeatureVecs( clean_train_reviews, model, num_features ) print "Creating average feature vecs for test reviews" clean_test_reviews = [] for review in test["review"]: clean_test_reviews.append( review_to_wordlist( review, \ remove_stopwords=True )) testDataVecs = getAvgFeatureVecs( clean_test_reviews, model, num_features ) print type(testDataVecs) print len(testDataVecs) print testDataVecs[0] print len(testDataVecs[0]) # Fit a random forest to the training data, using 100 trees #利用随机森林去建模 from sklearn.ensemble import RandomForestClassifier from sklearn.svm import SVC forest = RandomForestClassifier( n_estimators = 100 ) print "Fitting a random forest to labeled training data..." forest = forest.fit( trainDataVecs, train["sentiment"] ) # Test & extract results result = forest.predict( testDataVecs ) # Write the test results output = pd.DataFrame( data={"id":test["id"], "sentiment":result} ) output.to_csv( "Word2Vec_AverageVectors.csv", index=False, quoting=3 ) result = forest.predict( testDataVecs ) # Write the test results #利用率SVC去建模 model_svc = SVC.fit( trainDataVecs, train["sentiment"] ) result = model_svc.predict( testDataVecs ) output = pd.DataFrame( data={"id":test["id"], "sentiment":result} ) output.to_csv( "okcing.csv", index=False, quoting=3 ) #SVC的效果确实比随机森林要好一些
5万+
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
