Python decomposition.LatentDirichletAllocation类代码示例

    def applyLDA2(self, number_of_clusters, country_specific_tweets):
        train, feature_names = self.extractFeatures(country_specific_tweets,False)
        
        name = "lda"
        if self.results:
            print("Fitting LDA model with tfidf", end= " - ")
        t0 = time()     
        lda = LatentDirichletAllocation(n_topics=number_of_clusters, max_iter=5,
                                        learning_method='online', learning_offset=50.,
                                        random_state=0)

        lda.fit(train)
        
        if self.results:
            print("done in %0.3fs." % (time() - t0))
        
        parameters = lda.get_params()
        topics = lda.components_
        doc_topic = lda.transform(train)
        top10, labels = self.printTopicCluster(topics, doc_topic, feature_names)
        labels = numpy.asarray(labels)
        
        if self.results:
            print("Silhouette Coefficient {0}: {1}".format(name, metrics.silhouette_score(train, labels)))
        
        return name, parameters, top10, labels

def score_lda(src, dst):
	##read sentence pairs to two lists
	b1 = []
	b2 = []
	lines = 0
	with open(src) as p:
		for i, line in enumerate(p):
			s = line.split('\t')
			b1.append(s[0])
			b2.append(s[1][:-1]) #remove \n
			lines = i + 1

	vectorizer = CountVectorizer()
	vectors=vectorizer.fit_transform(b1 + b2)

	lda = LatentDirichletAllocation(n_topics=n_topics, max_iter=5,
                                learning_method='online', learning_offset=50.,
                                random_state=0)
	X = lda.fit_transform(vectors)
	print X.shape
	b1_v = vectorizer.transform(b1)
	b2_v = vectorizer.transform(b2)
	b1_vecs = lda.transform(b1_v)
	b2_vecs = lda.transform(b2_v)

	res = [round(5*(1 - spatial.distance.cosine(b1_vecs[i], b2_vecs[i])),2) for i in range(lines)]
	with open(dst, 'w') as thefile:
		thefile.write("\n".join(str(i) for i in res))

def plot_perplexity_batch(A_tfidf, num_docs):
    
    print "computing perplexity vs batch size..."
    max_iter = 5
    num_topics = 10
    batch_size = np.logspace(6, 10, 5, base=2).astype(int)
    perplexity = np.zeros((len(batch_size),max_iter))
    em_iter = np.zeros((len(batch_size),max_iter))
    for ii, mini_batch in enumerate(batch_size):
        for jj, sweep in enumerate(range(1,max_iter+1)):
            lda = LatentDirichletAllocation(n_topics = num_topics, max_iter=sweep, learning_method='online', batch_size = mini_batch, random_state=0, n_jobs=-1)
            tic = time()
            lda.fit(A_tfidf)  #online VB
            toc = time()
            print "sweep %d, elapsed time: %.4f sec" %(sweep, toc - tic)
            perplexity[ii,jj] = lda.perplexity(A_tfidf)
            em_iter[ii,jj] = lda.n_batch_iter_
        #end
    #end
    np.save('./data/perplexity.npy', perplexity)
    np.save('./data/em_iter.npy', em_iter)    
    
    f = plt.figure()
    for mb in range(len(batch_size)):
        plt.plot(em_iter[mb,:], perplexity[mb,:], color=np.random.rand(3,), marker='o', lw=2.0, label='mini_batch: '+str(batch_size[mb]))
    plt.title('Perplexity (LDA, online VB)')
    plt.xlabel('EM iter')
    plt.ylabel('Perplexity')
    plt.grid(True)
    plt.legend()
    plt.show()
    f.savefig('./figures/perplexity_batch.png')

    def get_features(vocab):
        vectorizer_head = TfidfVectorizer(vocabulary=vocab, use_idf=False, norm='l2')
        X_train_head = vectorizer_head.fit_transform(headlines)

        vectorizer_body = TfidfVectorizer(vocabulary=vocab, use_idf=False, norm='l2')
        X_train_body = vectorizer_body.fit_transform(bodies)

        # calculates n most important topics of the bodies. Each topic contains all words but ordered by importance. The
        # more important topic words a body contains of a certain topic, the higher its value for this topic
        lda_body = LatentDirichletAllocation(n_topics=n_topics, learning_method='online', random_state=0, n_jobs=3)

        print("latent_dirichlet_allocation_cos: fit and transform body")
        t0 = time()
        lda_body_matrix = lda_body.fit_transform(X_train_body)
        print("done in %0.3fs." % (time() - t0))

        print("latent_dirichlet_allocation_cos: transform head")
        # use the lda trained for body topcis on the headlines => if the headlines and bodies share topics
        # their vectors should be similar
        lda_head_matrix = lda_body.transform(X_train_head)

        #print_top_words(lda_body, vectorizer_body.get_feature_names(), 100)

        print('latent_dirichlet_allocation_cos: calculating cosine distance between head and body')
        # calculate cosine distance between the body and head
        X = []
        for i in range(len(lda_head_matrix)):
            X_head_vector = np.array(lda_head_matrix[i]).reshape((1, -1)) #1d array is deprecated
            X_body_vector = np.array(lda_body_matrix[i]).reshape((1, -1))
            cos_dist = cosine_distances(X_head_vector, X_body_vector).flatten()
            X.append(cos_dist.tolist())
        return X

def plot_perplexity_iter(A_tfidf, num_topics):
    
    print "computing perplexity vs iter..."
    max_iter = 5
    perplexity = []
    em_iter = []
    for sweep in range(1,max_iter+1):
        lda = LatentDirichletAllocation(n_topics = num_topics, max_iter=sweep, learning_method='online', batch_size = 512, random_state=0, n_jobs=-1)    
        tic = time()
        lda.fit(A_tfidf)  #online VB
        toc = time()
        print "sweep %d, elapsed time: %.4f sec" %(sweep, toc - tic)
        perplexity.append(lda.perplexity(A_tfidf))
        em_iter.append(lda.n_batch_iter_)
    #end    
    np.save('./data/perplexity_iter.npy', perplexity)
    
    f = plt.figure()
    plt.plot(em_iter, perplexity, color='b', marker='o', lw=2.0, label='perplexity')
    plt.title('Perplexity (LDA, online VB)')
    plt.xlabel('EM iter')
    plt.ylabel('Perplexity')
    plt.grid(True)
    plt.legend()
    plt.show()
    f.savefig('./figures/perplexity_iter.png')

def LDA(tf,word):
    lda = LatentDirichletAllocation(n_topics=30, max_iter=5,
                                learning_method='online',
                                learning_offset=50.,
                                random_state=0)
    lda.fit(tf)
    print_top_words(lda,word,20)

def lda_tuner(ingroup_otu, best_models):

    best_score = -1*np.inf
    dtp_series = [0.0001, 0.001, 0.01, 0.1, 0.2]
    twp_series = [0.0001, 0.001, 0.01, 0.1, 0.2]
    topic_series = [3]
    X = ingroup_otu.values
    eval_counter = 0

    for topics in topic_series: 
        for dtp in dtp_series:
            for twp in twp_series:
                eval_counter +=1
                X_train, X_test = train_test_split(X, test_size=0.5)
                lda = LatentDirichletAllocation(n_topics=topics, 
                                                doc_topic_prior=dtp, 
                                                topic_word_prior=twp, 
                                                learning_method='batch',
                                                random_state=42,
                                                max_iter=20)
                lda.fit(X_train)
                this_score = lda.score(X_test)
                this_perplexity = lda.perplexity(X_test)
                if this_score > best_score:
                    best_score = this_score
                    print "New Max Likelihood: {}".format(best_score)

                print "#{}: n:{}, dtp:{}, twp:{}, score:{}, perp:{}".format(eval_counter, 
                                                                 topics, dtp, twp,
                                                                 this_score, this_perplexity)

                best_models.append({'n': topics, 'dtp': dtp, 'twp': twp,
                                    'score': this_score, 'perp': this_perplexity})
                if (dtp == dtp_series[-1]) and (twp == twp_series[-1]):
                    eval_counter +=1
                    X_train, X_test = train_test_split(X, test_size=0.5)
                    lda = LatentDirichletAllocation(n_topics=topics, 
                                                    doc_topic_prior=1./topics, 
                                                    topic_word_prior=1./topics, 
                                                    learning_method='batch',
                                                    random_state=42,
                                                    max_iter=20)
                    lda.fit(X_train)
                    this_score = lda.score(X_test)
                    this_perplexity = lda.perplexity(X_test)
                    if this_score > best_score:
                        best_score = this_score
                        print "New Max Likelihood: {}".format(best_score)

                    print "#{}: n:{}, dtp:{}, twp:{}, score:{} perp: {}".format(eval_counter, 
                                                                                topics, 
                                                                                (1./topics), 
                                                                                (1./topics),
                                                                                this_score,
                                                                                this_perplexity)

                    best_models.append({'n': topics, 'dtp': (1./topics), 
                                        'twp': (1./topics), 'score': this_score,
                                        'perp': this_perplexity})
    return best_models

 def _get_model_LDA(self, corpus):
     #lda = models.LdaModel(corpus, id2word=self.corpus.dictionary, num_topics=5, alpha='auto', eval_every=50)
     lda = LatentDirichletAllocation(n_topics=self.num_of_clusters, max_iter=20,
                                     learning_method='online',
                                     learning_offset=50.,
                                     random_state=1)
     return lda.fit_transform(corpus)

def produceLDATopics():
    '''
    Takes description of each game and uses sklearn's latent dirichlet allocation and count vectorizer
    to extract topics.
    :return: pandas data frame with topic weights for each game (rows) and topic (columns)
    '''
    data_samples, gameNames = create_game_profile_df(game_path)
    tf_vectorizer = CountVectorizer(max_df=0.95, min_df=2, max_features=n_features, stop_words='english')
    tf = tf_vectorizer.fit_transform(data_samples)
    lda = LatentDirichletAllocation(n_topics=n_topics, max_iter=5,
                                    learning_method='online', learning_offset=50.,
                                    random_state=0)
    topics = lda.fit_transform(tf)
    # for i in range(50):
    #     gameTopics = []
    #     for j in range(len(topics[0])):
    #         if topics[i,j] > 1.0/float(n_topics):
    #             gameTopics.append(j)
    #     print gameNames[i], gameTopics
    topicsByGame = pandas.DataFrame(topics)
    topicsByGame.index = gameNames
    print topicsByGame

    tf_feature_names = tf_vectorizer.get_feature_names()
    for topic_idx, topic in enumerate(lda.components_):
        print("Topic #%d:" % topic_idx)
        print(" ".join([tf_feature_names[i]
                        for i in topic.argsort()[:-n_top_words - 1:-1]]))

    return topicsByGame

def fit_lda(tf):
    '''takes in a tf sparse vector and finds the top topics'''
    lda = LatentDirichletAllocation(n_topics=n_topics, max_iter=5, learning_method='online', learning_offset=50., random_state=0)
    lda.fit(tf)
    tf_feature_names = tf_vectorizer.get_feature_names()
    lda_topic_dict = print_top_words(lda, tf_feature_names, n_top_words)
    return lda, lda_topic_dict

def basic_lda(df, n_topics=200, max_df=0.5, min_df=5):
    '''
    Basic LDA model for album recommendations

    Args:
        df: dataframe with Pitchfork reviews
        n_topics: number of lda topics
        max_df: max_df in TfidfVectorizer
        min_df: min_df in TfidfVectorizer
    Returns:
        tfidf: sklearn fitted TfidfVectorizer
        tfidf_trans: sparse matrix with tfidf transformed data
        lda: sklearn fitted LatentDirichletAllocation
        lda_trans: dense array with lda transformed data

    '''

    X = df['review']
    cv = CountVectorizer(stop_words='english',
                         min_df=5,
                         max_df=0.5)
    cv_trans = cv.fit_transform(X)

    lda = LatentDirichletAllocation(n_topics=n_topics, max_iter=7)
    lda_trans = lda.fit_transform(cv_trans)

    return cv, cv_trans, lda, lda_trans

def plot_perplexity_topics(A_tfidf):
    
    print "computing perplexity vs K..."
    max_iter = 5    #based on plot_perplexity_iter()
    #num_topics = np.linspace(2,20,5).astype(np.int)
    num_topics = np.logspace(1,2,5).astype(np.int)
    perplexity = []
    em_iter = []
    for k in num_topics:
        lda = LatentDirichletAllocation(n_topics = k, max_iter=max_iter, learning_method='online', batch_size = 512, random_state=0, n_jobs=-1)
        tic = time()
        lda.fit(A_tfidf)  #online VB
        toc = time()
        print "K= %d, elapsed time: %.4f sec" %(k, toc - tic)
        perplexity.append(lda.perplexity(A_tfidf))
        em_iter.append(lda.n_batch_iter_)
    #end
    
    np.save('./data/perplexity_topics.npy', perplexity)
    np.save('./data/perplexity_topics2.npy', num_topics)    
    
    f = plt.figure()
    plt.plot(num_topics, perplexity, color='b', marker='o', lw=2.0, label='perplexity')
    plt.title('Perplexity (LDA, online VB)')
    plt.xlabel('Number of Topics, K')
    plt.ylabel('Perplexity')
    plt.grid(True)
    plt.legend()
    plt.show()
    f.savefig('./figures/perplexity_topics.png')

def extractTopicLDA(func_message_dic, store_cloumn):
    if len(func_message_dic) == 0:
        print "func_message_dic is null"
        return False
    try:
        conn=MySQLdb.connect(host='192.168.162.122',user='wangyu',passwd='123456',port=3306)
        cur=conn.cursor()
        cur.execute('set names utf8mb4')
        conn.select_db('codeAnalysis')
        for function in func_message_dic:
            message = func_message_dic[function]
            np_extractor = nlp.semantics_extraction.NPExtractor(message)
            text = np_extractor.extract()
            if len(text) == 0:
                continue
            tf_vectorizer = CountVectorizer(max_df=1.0, min_df=1, max_features=n_features, stop_words='english')
            tf = tf_vectorizer.fit_transform(text)
            print("Fitting LDA models with tf features, n_samples=%d and n_features=%d..." % (n_samples, n_features))
            lda = LatentDirichletAllocation(n_topics=n_topics, max_iter=5, learning_method='online', learning_offset=50.,
                                                                    random_state=0)
            lda.fit(tf)
            tf_feature_names = tf_vectorizer.get_feature_names()
            seprator = " "
            for topic_idx, topic in enumerate(lda.components_):
                keywords = seprator.join([tf_feature_names[i] for i in topic.argsort()[:-n_top_words - 1:-1]])
            sql = "update func_semantic set "+store_cloumn+" = '"+keywords+"' where func_name = '"+function+"'"
            print sql
            cur.execute(sql)
            conn.commit()
        cur.close()
        conn.close()
        return True
    except MySQLdb.Error,e:
        print e
        raise

def topicmodel( comments ):

    _texts = []
    texts = []

    for c in comments:

        c = c['text']
        _texts.append( c )
        texts.append( c )



    tf_vectorizer = CountVectorizer(
                max_df=.20,
                min_df=10,
                stop_words = stopwords )
    texts = tf_vectorizer.fit_transform( texts )

    ## test between 2 and 20 topics
    topics = {}

    for k in range(2, 10):

        print "Testing", k

        model = LatentDirichletAllocation(
                    n_topics= k ,
                    max_iter=5,
                    learning_method='batch',
                    learning_offset=50.,
                    random_state=0
                )
        model.fit( texts )
        ll = model.score( texts )
        topics[ ll ] = model

    topic = max( topics.keys() )

    ret = collections.defaultdict( list )

    ## ugly, rewrite some day
    model = topics[ topic ]

    ## for debug pront chosen models' names
    feature_names = tf_vectorizer.get_feature_names()
    for topic_idx, topic in enumerate(model.components_):
        print "Topic #%d:" % topic_idx
        print " ".join( [feature_names[i].encode('utf8') for i in topic.argsort()[:-5 - 1:-1]])
        print

    for i, topic in enumerate( model.transform( texts ) ):

        topic = numpy.argmax( topic )
        text = _texts[ i ].encode('utf8')

        ret[ topic ].append( text )

    return ret

def latdirall(content):
    lda = LatentDirichletAllocation(n_topics=10)
    tf_vectorizer = TfidfVectorizer(max_df=0.99, min_df=1,
                                stop_words='english')
    tf = tf_vectorizer.fit_transform(content)
    lolz = lda.fit_transform(tf)
    tfidf_feature_names = tf_vectorizer.get_feature_names()
    return top_topics(lda, tfidf_feature_names, 10)