{ "cells": [ { "cell_type": "markdown", "metadata": { "slideshow": { "slide_type": "slide" } }, "source": [ "***\n", "***\n", "# 主题模型\n", "\n", "***\n", "***\n", "\n", "王成军\n", "\n", "wangchengjun@nju.edu.cn\n", "\n", "计算传播网 http://computational-communication.com" ] }, { "cell_type": "markdown", "metadata": { "slideshow": { "slide_type": "slide" } }, "source": [ "2014年高考前夕,百度“基于海量作文范文和搜索数据,利用概率主题模型,预测2014年高考作文的命题方向”。如上图所示,共分为了六个主题:时间、生命、民族、教育、心灵、发展。而每个主题下面又包括了一些具体的关键词。比如,生命的主题对应:平凡、自由、美丽、梦想、奋斗、青春、快乐、孤独。\n", "\n", "[Read more](https://site.douban.com/146782/widget/notes/15462869/note/356806087/)" ] }, { "cell_type": "markdown", "metadata": { "slideshow": { "slide_type": "fragment" } }, "source": [ "![](./img/baidu_gaokao.jpg)" ] }, { "cell_type": "markdown", "metadata": { "slideshow": { "slide_type": "slide" } }, "source": [ "# latent Dirichlet allocation (LDA)\n", "\n", "The simplest topic model (on which all others are based) is latent Dirichlet allocation (LDA). \n", "- LDA is a generative model that infers unobserved meanings from a large set of observations. \n", "\n", "## Reference\n", "\n", "- Blei DM, Ng J, Jordan MI. Latent dirichlet allocation. J Mach Learn Res. 2003; 3: 993–1022.\n", "- Blei DM, Lafferty JD. Correction: a correlated topic model of science. Ann Appl Stat. 2007; 1: 634. \n", "- Blei DM. Probabilistic topic models. Commun ACM. 2012; 55: 55–65.\n", "- Chandra Y, Jiang LC, Wang C-J (2016) Mining Social Entrepreneurship Strategies Using Topic Modeling. PLoS ONE 11(3): e0151342. doi:10.1371/journal.pone.0151342" ] }, { "cell_type": "markdown", "metadata": { "slideshow": { "slide_type": "slide" } }, "source": [ "" ] }, { "cell_type": "markdown", "metadata": { "collapsed": true, "slideshow": { "slide_type": "subslide" } }, "source": [ "- Topic models assume that each document contains a mixture of topics\n", " - Topics are considered latent/unobserved variables that stand between the documents and terms\n", "\n", "It is impossible to directly assess the relationships between topics and documents and between topics and terms. \n", "- What can be directly observed is the distribution of terms over documents, which is known as the document term matrix (DTM).\n", "\n", "Topic models algorithmically identify the best set of latent variables (topics) that can best explain the observed distribution of terms in the documents. " ] }, { "cell_type": "markdown", "metadata": { "slideshow": { "slide_type": "subslide" } }, "source": [ "The DTM is further decomposed into two matrices:\n", "- a term-topic matrix (TTM) \n", "- a topic-document matrix (TDM)\n", "\n", "Each document can be assigned to a primary topic that demonstrates the highest topic-document probability and can then be linked to other topics with declining probabilities." ] }, { "cell_type": "markdown", "metadata": { "slideshow": { "slide_type": "subslide" } }, "source": [ "Assume K topics are in D documents, and each topic is denoted with $\\phi_{1:K}$. \n", "\n", "Each topic $\\phi_K$ is a distribution of fixed words in the given documents. \n", "\n", "The topic proportion in the document is denoted as $\\theta_d$. \n", "- e.g., the kth topic's proportion in document d is $\\theta_{d, k}$. \n", "\n", "Let $w_{d,n}$ denote the nth term in document d. \n", "\n", "Further, topic models assign topics to a document and its terms. \n", "- For example, the topic assigned to document d is denoted as $z_d$, \n", " - and the topic assigned to the nth term in document d is denoted as $z_{d,n}$. " ] }, { "cell_type": "markdown", "metadata": { "slideshow": { "slide_type": "subslide" } }, "source": [ "According to Blei et al. the joint distribution of $\\phi_{1:K}$,$\\theta_{1:D}$, $z_{1:D}$ and $w_{d, n}$ plus the generative process for LDA can be expressed as:\n", "\n", "$ p(\\phi_{1:K}, \\theta_{1:D}, z_{1:D}, w_{d, n}) $ = \n", "\n", "$\\prod_{i=1}^{K} p(\\phi_i) \\prod_{d =1}^D p(\\theta_d)(\\prod_{n=1}^N p(z_{d,n} \\mid \\theta_d) \\times p(w_{d, n} \\mid \\phi_{1:K}, Z_{d, n}) ) $\n" ] }, { "cell_type": "markdown", "metadata": { "slideshow": { "slide_type": "subslide" } }, "source": [ "Note that $\\phi_{1:k},\\theta_{1:D},and z_{1:D}$ are latent, unobservable variables. Thus, the computational challenge of LDA is to compute the conditional distribution of them given the observable specific words in the documents $w_{d, n}$. \n", "\n", "Accordingly, the posterior distribution of LDA can be expressed as:\n", "\n", "## $p(\\phi_{1:K}, \\theta_{1:D}, z_{1:D} \\mid w_{d, n}) = \\frac{p(\\phi_{1:K}, \\theta_{1:D}, z_{1:D}, w_{d, n})}{p(w_{1:D})}$" ] }, { "cell_type": "markdown", "metadata": { "slideshow": { "slide_type": "subslide" } }, "source": [ "Because the number of possible topic structures is exponentially large, it is impossible to compute the posterior of LDA. Topic models aim to develop efficient algorithms to approximate the posterior of LDA. \n", "- There are two categories of algorithms: \n", " - sampling-based algorithms\n", " - variational algorithms \n", " \n", "Using the Gibbs sampling method, we can build a Markov chain for the sequence of random variables (see Eq 1). The sampling algorithm is applied to the chain to sample from the limited distribution, and it approximates the posterior. " ] }, { "cell_type": "markdown", "metadata": { "collapsed": true, "slideshow": { "slide_type": "slide" } }, "source": [ "\n", "# Gensim\n", "\n", "Unfortunately, scikit-learn does not support latent Dirichlet allocation.\n", "\n", "Therefore, we are going to use the gensim package in Python. \n", "\n", "Gensim is developed by Radim Řehůřek,who is a machine learning researcher and consultant in the Czech Republic. We must start by installing it. We can achieve this by running one of the following commands:\n", "\n", "> # pip install gensim\n" ] }, { "cell_type": "code", "execution_count": 21, "metadata": { "collapsed": false, "slideshow": { "slide_type": "slide" } }, "outputs": [], "source": [ "%matplotlib inline\n", "from __future__ import print_function\n", "from wordcloud import WordCloud\n", "from gensim import corpora, models, similarities, matutils\n", "import matplotlib.pyplot as plt\n", "import numpy as np" ] }, { "cell_type": "markdown", "metadata": { "slideshow": { "slide_type": "slide" } }, "source": [ "# Download data\n", "\n", "http://www.cs.princeton.edu/~blei/lda-c/ap.tgz\n", "\n", "Unzip the data and put them into /Users/chengjun/bigdata/ap/" ] }, { "cell_type": "code", "execution_count": 22, "metadata": { "collapsed": false, "slideshow": { "slide_type": "slide" } }, "outputs": [], "source": [ "# Load the data\n", "corpus = corpora.BleiCorpus('/Users/chengjun/bigdata/ap/ap.dat', '/Users/chengjun/bigdata/ap/vocab.txt')" ] }, { "cell_type": "code", "execution_count": 23, "metadata": { "collapsed": false, "slideshow": { "slide_type": "subslide" } }, "outputs": [ { "data": { "text/plain": [ "'__class__ __delattr__ __dict__ __doc__ __format__ __getattribute__ __getitem__ __hash__ __init__ __iter__ __len__ __module__ __new__ __reduce__ __reduce_ex__ __repr__ __setattr__ __sizeof__ __str__ __subclasshook__ __weakref__ _smart_save docbyoffset fname id2word index length line2doc load save save_corpus serialize'" ] }, "execution_count": 23, "metadata": {}, "output_type": "execute_result" } ], "source": [ "' '.join(dir(corpus))" ] }, { "cell_type": "code", "execution_count": 24, "metadata": { "collapsed": false, "slideshow": { "slide_type": "subslide" } }, "outputs": [ { "data": { "text/plain": [ "[(0, u'i'), (1, u'new'), (2, u'percent')]" ] }, "execution_count": 24, "metadata": {}, "output_type": "execute_result" } ], "source": [ "corpus.id2word.items()[:3]" ] }, { "cell_type": "markdown", "metadata": { "slideshow": { "slide_type": "slide" } }, "source": [ "# Build the topic model" ] }, { "cell_type": "code", "execution_count": 25, "metadata": { "collapsed": true, "slideshow": { "slide_type": "fragment" } }, "outputs": [], "source": [ "NUM_TOPICS = 100" ] }, { "cell_type": "code", "execution_count": 26, "metadata": { "collapsed": false, "slideshow": { "slide_type": "fragment" } }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "/Users/chengjun/anaconda/lib/python2.7/site-packages/gensim/models/ldamodel.py:379: VisibleDeprecationWarning: non integer (and non boolean) array-likes will not be accepted as indices in the future\n", " expElogbetad = self.expElogbeta[:, ids]\n", "/Users/chengjun/anaconda/lib/python2.7/site-packages/gensim/models/ldamodel.py:404: VisibleDeprecationWarning: non integer (and non boolean) array-likes will not be accepted as indices in the future\n", " sstats[:, ids] += numpy.outer(expElogthetad.T, cts / phinorm)\n", "/Users/chengjun/anaconda/lib/python2.7/site-packages/gensim/models/ldamodel.py:659: VisibleDeprecationWarning: using a non-integer number instead of an integer will result in an error in the future\n", " score += numpy.sum(cnt * logsumexp(Elogthetad + Elogbeta[:, id]) for id, cnt in doc)\n" ] } ], "source": [ "model = models.ldamodel.LdaModel(\n", " corpus, num_topics=NUM_TOPICS, id2word=corpus.id2word, alpha=None)" ] }, { "cell_type": "code", "execution_count": 27, "metadata": { "collapsed": false, "slideshow": { "slide_type": "subslide" } }, "outputs": [ { "data": { "text/plain": [ "'__class__ __delattr__ __dict__ __doc__ __format__ __getattribute__ __getitem__ __hash__ __init__ __module__ __new__ __reduce__ __reduce_ex__ __repr__ __setattr__ __sizeof__ __str__ __subclasshook__ __weakref__ _apply _smart_save alpha bound chunksize clear decay dispatcher distributed do_estep do_mstep eta eval_every expElogbeta gamma_threshold id2word inference iterations load log_perplexity num_terms num_topics num_updates numworkers offset optimize_alpha passes print_topic print_topics save show_topic show_topics state sync_state top_topics update update_alpha update_every'" ] }, "execution_count": 27, "metadata": {}, "output_type": "execute_result" } ], "source": [ "' '.join(dir(model))" ] }, { "cell_type": "markdown", "metadata": { "slideshow": { "slide_type": "slide" } }, "source": [ "# We can see the list of topics a document refers to \n", "\n", "by using the model[doc] syntax:" ] }, { "cell_type": "code", "execution_count": 28, "metadata": { "collapsed": true, "slideshow": { "slide_type": "fragment" } }, "outputs": [], "source": [ "document_topics = [model[c] for c in corpus]" ] }, { "cell_type": "code", "execution_count": 29, "metadata": { "collapsed": false, "slideshow": { "slide_type": "fragment" } }, "outputs": [ { "data": { "text/plain": [ "[(1, 0.012173218478465178),\n", " (5, 0.010844598121070434),\n", " (9, 0.017341043056838871),\n", " (11, 0.024468311850992307),\n", " (13, 0.011713551338282521),\n", " (17, 0.12008191700644692),\n", " (26, 0.2653896038945065),\n", " (36, 0.016205103283848322),\n", " (40, 0.063642155983975865),\n", " (42, 0.10912551497030909),\n", " (43, 0.18969307606619615),\n", " (54, 0.029152810319599372),\n", " (70, 0.027382335898959255),\n", " (73, 0.079544001401190376)]" ] }, "execution_count": 29, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# how many topics does one document cover?\n", "document_topics[2]" ] }, { "cell_type": "code", "execution_count": 30, "metadata": { "collapsed": false, "slideshow": { "slide_type": "slide" } }, "outputs": [ { "data": { "text/plain": [ "[(0.010029947066157719, u'cents'),\n", " (0.0084518751921951272, u'sheet'),\n", " (0.006971130612136031, u'people'),\n", " (0.0069681226790944068, u'videos'),\n", " (0.0061501028198266746, u'designs'),\n", " (0.0059801669571577327, u'threeway'),\n", " (0.0051079365521994723, u'mca'),\n", " (0.0042408541343766145, u'new'),\n", " (0.0038503471959112092, u'today'),\n", " (0.0034815721467352559, u'year')]" ] }, "execution_count": 30, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# The first topic\n", "# format: weight, term\n", "model.show_topic(0, 10)" ] }, { "cell_type": "code", "execution_count": 31, "metadata": { "collapsed": false, "slideshow": { "slide_type": "subslide" } }, "outputs": [ { "data": { "text/plain": [ "[(0.012503720479598517, u'billion'),\n", " (0.0093416080644276624, u'bomber'),\n", " (0.0080440160210163321, u'fiscal'),\n", " (0.0073821380604033784, u'defense'),\n", " (0.0059336615162439077, u'air'),\n", " (0.0057387426153885654, u'safety'),\n", " (0.005239704830984784, u'year'),\n", " (0.0047342102096198735, u'nuclear'),\n", " (0.0046810109846632626, u'north'),\n", " (0.004498783524243005, u'million')]" ] }, "execution_count": 31, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# The 100 topic\n", "# format: weight, term\n", "model.show_topic(99, 10)" ] }, { "cell_type": "code", "execution_count": 32, "metadata": { "collapsed": false, "slideshow": { "slide_type": "subslide" } }, "outputs": [ { "data": { "text/plain": [ "[(0.010029947066157719, u'cents'),\n", " (0.0084518751921951272, u'sheet'),\n", " (0.006971130612136031, u'people'),\n", " (0.0069681226790944068, u'videos'),\n", " (0.0061501028198266746, u'designs')]" ] }, "execution_count": 32, "metadata": {}, "output_type": "execute_result" } ], "source": [ "words = model.show_topic(0, 5)\n", "words" ] }, { "cell_type": "code", "execution_count": 33, "metadata": { "collapsed": false, "slideshow": { "slide_type": "subslide" } }, "outputs": [ { "data": { "text/plain": [ "[u'0.011*government + 0.010*hughes + 0.009*communist + 0.008*party + 0.007*fellows + 0.006*leader + 0.006*cordon + 0.005*people + 0.005*president + 0.005*fair',\n", " u'0.132*cdy + 0.118*clr + 0.042*rn + 0.011*m + 0.010*rome + 0.008*frankfurt + 0.005*new + 0.004*paris + 0.004*tokyo + 0.003*i',\n", " u'0.033*percent + 0.012*year + 0.011*billion + 0.009*states + 0.006*last + 0.005*ec + 0.005*years + 0.005*new + 0.005*tax + 0.005*orders',\n", " u'0.014*percent + 0.011*million + 0.007*africa + 0.007*south + 0.007*sales + 0.006*share + 0.006*year + 0.005*wednesdays + 0.005*new + 0.005*mandela']" ] }, "execution_count": 33, "metadata": {}, "output_type": "execute_result" } ], "source": [ "model.show_topics(4)" ] }, { "cell_type": "code", "execution_count": 34, "metadata": { "collapsed": false, "slideshow": { "slide_type": "subslide" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "0.0100299470662 cents\n", "0.0084518751922 sheet\n", "0.00697113061214 people\n", "0.00696812267909 videos\n", "0.00615010281983 designs\n" ] } ], "source": [ "for f, w in words[:10]:\n", " print(f, w)" ] }, { "cell_type": "code", "execution_count": 39, "metadata": { "collapsed": false, "slideshow": { "slide_type": "slide" } }, "outputs": [], "source": [ "# write out topcis with 10 terms with weights\n", "for ti in range(model.num_topics):\n", " words = model.show_topic(ti, 10)\n", " tf = sum(f for f, w in words)\n", " with open('/Users/chengjun/github/cjc2016/data/topics_term_weight.txt', 'a') as output:\n", " for f, w in words:\n", " line = str(ti) + '\\t' + w + '\\t' + str(f/tf) \n", " output.write(line + '\\n')" ] }, { "cell_type": "code", "execution_count": 40, "metadata": { "collapsed": true, "slideshow": { "slide_type": "fragment" } }, "outputs": [], "source": [ "# We first identify the most discussed topic, i.e., the one with the\n", "# highest total weight\n", "topics = matutils.corpus2dense(model[corpus], num_terms=model.num_topics)\n", "weight = topics.sum(1)\n", "max_topic = weight.argmax()" ] }, { "cell_type": "code", "execution_count": 216, "metadata": { "collapsed": false, "slideshow": { "slide_type": "subslide" } }, "outputs": [], "source": [ "# Get the top 64 words for this topic\n", "# Without the argument, show_topic would return only 10 words\n", "words = model.show_topic(max_topic, 64)\n", "words = np.array(words).T\n", "words_freq=[float(i)*10000000 for i in words[0]]\n", "words = zip(words[1], words_freq)" ] }, { "cell_type": "code", "execution_count": 219, "metadata": { "collapsed": false, "slideshow": { "slide_type": "fragment" } }, "outputs": [ { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAX4AAADICAYAAADvPoogAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nAAAASUVORK5CYII=\n", "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "wordcloud = WordCloud().generate_from_frequencies(words)\n", "plt.imshow(wordcloud)\n", "plt.axis(\"off\")\n", "plt.show()" ] }, { "cell_type": "code", "execution_count": 104, "metadata": { "collapsed": false, "slideshow": { "slide_type": "slide" } }, "outputs": [ { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAakAAAEbCAYAAABgLnslAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nYII=\n", "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "num_topics_used = [len(model[doc]) for doc in corpus]\n", "\n", "fig,ax = plt.subplots()\n", "ax.hist(num_topics_used, np.arange(42))\n", "ax.set_ylabel('Nr of documents')\n", "ax.set_xlabel('Nr of topics')\n", "fig.tight_layout()\n", "#fig.savefig('Figure_04_01.png')" ] }, { "cell_type": "markdown", "metadata": { "slideshow": { "slide_type": "subslide" } }, "source": [ "# We can see that about 150 documents have 5 topics, \n", "- while the majority deal with around 10 to 12 of them. \n", " - No document talks about more than 20 topics." ] }, { "cell_type": "code", "execution_count": 109, "metadata": { "collapsed": false, "slideshow": { "slide_type": "fragment" } }, "outputs": [], "source": [ "# Now, repeat the same exercise using alpha=1.0\n", "# You can edit the constant below to play around with this parameter\n", "ALPHA = 1.0\n", "model1 = models.ldamodel.LdaModel(\n", " corpus, num_topics=NUM_TOPICS, id2word=corpus.id2word, alpha=ALPHA)\n", "\n", "num_topics_used1 = [len(model1[doc]) for doc in corpus]" ] }, { "cell_type": "code", "execution_count": 108, "metadata": { "collapsed": false, "slideshow": { "slide_type": "subslide" } }, "outputs": [ { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAakAAAEbCAYAAABgLnslAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n/TeBIm9TgZaZ8gAAAABJRU5ErkJggg==\n", "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "fig,ax = plt.subplots()\n", "ax.hist([num_topics_used, num_topics_used1], np.arange(42))\n", "ax.set_ylabel('Nr of documents')\n", "ax.set_xlabel('Nr of topics')\n", "# The coordinates below were fit by trial and error to look good\n", "plt.text(9, 223, r'default alpha')\n", "plt.text(26, 156, 'alpha=1.0')\n", "fig.tight_layout()" ] }, { "cell_type": "markdown", "metadata": { "slideshow": { "slide_type": "slide" } }, "source": [ "# 使用pyLDAvis可视化主题模型\n", "http://nbviewer.jupyter.org/github/bmabey/pyLDAvis/blob/master/notebooks/pyLDAvis_overview.ipynb\n", "\n", "> # pip install pyldavis" ] }, { "cell_type": "markdown", "metadata": { "slideshow": { "slide_type": "slide" } }, "source": [ "# 读取并清洗数据" ] }, { "cell_type": "code", "execution_count": 1, "metadata": { "collapsed": false, "slideshow": { "slide_type": "fragment" } }, "outputs": [], "source": [ "with open('/Users/chengjun/bigdata/ap/ap.txt', 'r') as f:\n", " dat = f.readlines()" ] }, { "cell_type": "code", "execution_count": 2, "metadata": { "collapsed": false, "slideshow": { "slide_type": "subslide" } }, "outputs": [ { "data": { "text/plain": [ "['\\n',\n", " ' AP881218-0003 \\n',\n", " '\\n',\n", " \" A 16-year-old student at a private Baptist school who allegedly killed one teacher and wounded another before firing into a filled classroom apparently ``just snapped,'' the school's pastor said. ``I don't know how it could have happened,'' said George Sweet, pastor of Atlantic Shores Baptist Church. ``This is a good, Christian school. We pride ourselves on discipline. Our kids are good kids.'' The Atlantic Shores Christian School sophomore was arrested and charged with first-degree murder, attempted murder, malicious assault and related felony charges for the Friday morning shooting. Police would not release the boy's name because he is a juvenile, but neighbors and relatives identified him as Nicholas Elliott. Police said the student was tackled by a teacher and other students when his semiautomatic pistol jammed as he fired on the classroom as the students cowered on the floor crying ``Jesus save us! God save us!'' Friends and family said the boy apparently was troubled by his grandmother's death and the divorce of his parents and had been tormented by classmates. Nicholas' grandfather, Clarence Elliott Sr., said Saturday that the boy's parents separated about four years ago and his maternal grandmother, Channey Williams, died last year after a long illness. The grandfather also said his grandson was fascinated with guns. ``The boy was always talking about guns,'' he said. ``He knew a lot about them. He knew all the names of them _ none of those little guns like a .32 or a .22 or nothing like that. He liked the big ones.'' The slain teacher was identified as Karen H. Farley, 40. The wounded teacher, 37-year-old Sam Marino, was in serious condition Saturday with gunshot wounds in the shoulder. Police said the boy also shot at a third teacher, Susan Allen, 31, as she fled from the room where Marino was shot. He then shot Marino again before running to a third classroom where a Bible class was meeting. The youngster shot the glass out of a locked door before opening fire, police spokesman Lewis Thurston said. When the youth's pistol jammed, he was tackled by teacher Maurice Matteson, 24, and other students, Thurston said. ``Once you see what went on in there, it's a miracle that we didn't have more people killed,'' Police Chief Charles R. Wall said. Police didn't have a motive, Detective Tom Zucaro said, but believe the boy's primary target was not a teacher but a classmate. Officers found what appeared to be three Molotov cocktails in the boy's locker and confiscated the gun and several spent shell casings. Fourteen rounds were fired before the gun jammed, Thurston said. The gun, which the boy carried to school in his knapsack, was purchased by an adult at the youngster's request, Thurston said, adding that authorities have interviewed the adult, whose name is being withheld pending an investigation by the federal Bureau of Alcohol, Tobacco and Firearms. The shootings occurred in a complex of four portable classrooms for junior and senior high school students outside the main building of the 4-year-old school. The school has 500 students in kindergarten through 12th grade. Police said they were trying to reconstruct the sequence of events and had not resolved who was shot first. The body of Ms. Farley was found about an hour after the shootings behind a classroom door.\\n\",\n", " ' \\n',\n", " '\\n']" ] }, "execution_count": 2, "metadata": {}, "output_type": "execute_result" } ], "source": [ "dat[:6]" ] }, { "cell_type": "code", "execution_count": 3, "metadata": { "collapsed": false, "slideshow": { "slide_type": "subslide" } }, "outputs": [ { "data": { "text/plain": [ "'<'" ] }, "execution_count": 3, "metadata": {}, "output_type": "execute_result" } ], "source": [ "dat[4].strip()[0]" ] }, { "cell_type": "code", "execution_count": 4, "metadata": { "collapsed": false, "slideshow": { "slide_type": "subslide" } }, "outputs": [], "source": [ "docs = []\n", "for i in dat[:100]:\n", " if i.strip()[0] != '<':\n", " docs.append(i)" ] }, { "cell_type": "code", "execution_count": 5, "metadata": { "collapsed": false, "slideshow": { "slide_type": "subslide" } }, "outputs": [], "source": [ "def clean_doc(doc):\n", " doc = doc.replace('.', '').replace(',', '')\n", " doc = doc.replace('``', '').replace('\"', '')\n", " doc = doc.replace('_', '').replace(\"'\", '')\n", " doc = doc.replace('!', '')\n", " return doc\n", "docs = [clean_doc(doc) for doc in docs]" ] }, { "cell_type": "code", "execution_count": 6, "metadata": { "collapsed": false, "slideshow": { "slide_type": "subslide" } }, "outputs": [], "source": [ "texts = [[i for i in doc.lower().split()] for doc in docs]" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "collapsed": true, "slideshow": { "slide_type": "subslide" } }, "outputs": [], "source": [ "import nltk\n", "nltk.download()\n", "# 会打开一个窗口,选择book,download,待下载完毕就可以使用了。" ] }, { "cell_type": "code", "execution_count": 7, "metadata": { "collapsed": true, "slideshow": { "slide_type": "fragment" } }, "outputs": [], "source": [ "from nltk.corpus import stopwords\n", "stop = stopwords.words('english') # 如果此处出错,请执行上一个block的代码" ] }, { "cell_type": "code", "execution_count": 8, "metadata": { "collapsed": false, "slideshow": { "slide_type": "subslide" } }, "outputs": [ { "data": { "text/plain": [ "u'i me my myself we our ours ourselves you your yours yourself yourselves he him his himself she her hers herself it its itself they them their theirs themselves what which who whom this that these those am is are was were be been being have has had having do does did doing a an the and but if or because as until while of at by for with about against between into through during before after above below to from up down in out on off over under again further then once here there when where why how all any both each few more most other some such no nor not only own same so than too very s t can will just don should now d ll m o re ve y ain aren couldn didn doesn hadn hasn haven isn ma mightn mustn needn shan shouldn wasn weren won wouldn'" ] }, "execution_count": 8, "metadata": {}, "output_type": "execute_result" } ], "source": [ "' '.join(stop)" ] }, { "cell_type": "code", "execution_count": 9, "metadata": { "collapsed": true, "slideshow": { "slide_type": "subslide" } }, "outputs": [], "source": [ "stop.append('said')" ] }, { "cell_type": "code", "execution_count": 10, "metadata": { "collapsed": true, "slideshow": { "slide_type": "subslide" } }, "outputs": [], "source": [ "from collections import defaultdict\n", "frequency = defaultdict(int)\n", "for text in texts:\n", " for token in text:\n", " frequency[token] += 1\n", "\n", "texts = [[token for token in text if frequency[token] > 1 and token not in stop]\n", " for text in texts]" ] }, { "cell_type": "code", "execution_count": 11, "metadata": { "collapsed": false, "slideshow": { "slide_type": "subslide" } }, "outputs": [ { "data": { "text/plain": [ "' Here is a summary of developments in forest and brush fires in Western states:\\n'" ] }, "execution_count": 11, "metadata": {}, "output_type": "execute_result" } ], "source": [ "docs[8]" ] }, { "cell_type": "code", "execution_count": 12, "metadata": { "collapsed": false, "slideshow": { "slide_type": "fragment" } }, "outputs": [ { "data": { "text/plain": [ "'stirbois 2 man extreme-right national front party le pen died saturday automobile police 43 stirbois political meeting friday city dreux miles west paris traveling toward capital car ran police stirbois national front member party since born paris law headed business stirbois several extreme-right political joining national front 1977 percent vote local elections west paris highest vote percentage candidate year half later deputy dreux stirbois deputy national 1986 lost elections last national front founded le pen frances government death priority first years presidential elections le pen percent vote national front could'" ] }, "execution_count": 12, "metadata": {}, "output_type": "execute_result" } ], "source": [ "' '.join(texts[9])" ] }, { "cell_type": "code", "execution_count": 15, "metadata": { "collapsed": false, "slideshow": { "slide_type": "slide" } }, "outputs": [], "source": [ "dictionary = corpora.Dictionary(texts)\n", "lda_corpus = [dictionary.doc2bow(text) for text in texts]\n", "#The function doc2bow() simply counts the number of occurences of each distinct word, \n", "# converts the word to its integer word id and returns the result as a sparse vector. " ] }, { "cell_type": "code", "execution_count": 18, "metadata": { "collapsed": false, "slideshow": { "slide_type": "slide" } }, "outputs": [], "source": [ "lda_model = models.ldamodel.LdaModel(\n", " lda_corpus, num_topics=NUM_TOPICS, id2word=dictionary, alpha=None)" ] }, { "cell_type": "code", "execution_count": 19, "metadata": { "collapsed": false, "slideshow": { "slide_type": "slide" } }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "/Users/chengjun/anaconda/lib/python2.7/site-packages/skbio/stats/ordination/_principal_coordinate_analysis.py:102: RuntimeWarning: The result contains negative eigenvalues. Please compare their magnitude with the magnitude of some of the largest positive eigenvalues. If the negative ones are smaller, it's probably safe to ignore them, but if they are large in magnitude, the results won't be useful. See the Notes section for more details. The smallest eigenvalue is -0.199959128474 and the largest is 0.763806504314.\n", " RuntimeWarning\n" ] } ], "source": [ "import pyLDAvis.gensim\n", "\n", "ap_data = pyLDAvis.gensim.prepare(lda_model, lda_corpus, dictionary)" ] }, { "cell_type": "code", "execution_count": 20, "metadata": { "collapsed": false, "slideshow": { "slide_type": "slide" } }, "outputs": [ { "data": { "text/html": [ "\n", "\n", "\n", "\n", "
\n", "" ], "text/plain": [ "" ] }, "execution_count": 20, "metadata": {}, "output_type": "execute_result" } ], "source": [ "pyLDAvis.enable_notebook()\n", "pyLDAvis.display(ap_data)" ] }, { "cell_type": "code", "execution_count": 220, "metadata": { "collapsed": true, "slideshow": { "slide_type": "slide" } }, "outputs": [], "source": [ "pyLDAvis.save_html(ap_data, '/Users/chengjun/github/cjc2016/vis/ap_ldavis.html')" ] }, { "cell_type": "markdown", "metadata": { "slideshow": { "slide_type": "slide" } }, "source": [ "# 阅读材料" ] }, { "cell_type": "markdown", "metadata": { "collapsed": true, "slideshow": { "slide_type": "fragment" } }, "source": [ "Willi Richert, Luis Pedro Coelho, 2013, Building Machine Learning Systems with Python. Chapter 4. Packt Publishing.\n", "\n", "东风夜放花千树:对宋词进行主题分析初探 http://chengjun.github.io/cn/2013/09/topic-modeling-of-song-peom/\n", "\n", "\n", "Chandra Y, Jiang LC, Wang C-J (2016) Mining Social Entrepreneurship Strategies Using Topic Modeling. PLoS ONE 11(3): e0151342. doi:10.1371/journal.pone.0151342" ] } ], "metadata": { "celltoolbar": "Slideshow", "kernelspec": { "display_name": "Python 2", "language": "python", "name": "python2" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 2 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython2", "version": "2.7.11" } }, "nbformat": 4, "nbformat_minor": 0 }