Machine Learning :: Text feature extraction (tf-idf) – Part II

阅读本教程的第一部分:Text feature extraction (tf-idf) – Part I

This post is a延续在哪里,我们开始学习有关文本特征提取和向量空间模型表示的理论和实践的第一部分。我真的建议你阅读第一部分后一系列以遵循这个第二。

Since a lot of people liked the first part of this tutorial, this second part is a little longer than the first.

介绍

在第一篇文章中,我们学会了如何使用长期频以表示在矢量空间的文本信息。然而,与术语频率方法的主要问题是,它大大加快了频繁的条款和规模下降,这比高频方面经验更丰富罕见的条款。基本的直觉是,在许多文件中经常出现的一个术语不太好鉴别,真正有意义的(至少在许多实验测试);这里最重要的问题是:你为什么会在例如分类问题,强调术语,是在你的文档的整个语料库几乎礼物?

The tf-idf weight comes to solve this problem. What tf-idf gives is how important is a word to a document in a collection, and that’s why tf-idf incorporates local and global parameters, because it takes in consideration not only the isolated term but also the term within the document collection. What tf-idf then does to solve that problem, is to scale down the frequent terms while scaling up the rare terms; a term that occurs 10 times more than another isn’t 10 times more important than it, that’s why tf-idf uses the logarithmic scale to do that.

但是,让我们回到我们的定义\ mathrm {TF}(T,d)which is actually the term count of the termŤ在文档中d。The use of this simple term frequency could lead us to problems like滥用关键字,which is when we have a repeated term in a document with the purpose of improving its ranking on an IR (Information Retrieval)系统,甚至对创建长文档偏见,使他们看起来比他们只是因为手册中出现的高频更重要。

为了克服这个问题,词频\ mathrm {TF}(T,d)of a document on a vector space is usually also normalized. Let’s see how we normalize this vector.

矢量归

Suppose we are going to normalize the term-frequency vector\ {VEC V_ {D_4}}我们在本教程的第一部分已经计算。该文件D4from the first part of this tutorial had this textual representation:

D4:我们可以看到闪亮的阳光,明亮的阳光下。

和使用该文件的非归一化项频向量空间表示为:

\ {VEC V_ {D_4}} =(0,2,1,0)

规范化的向量,是一样的说话g theUnit Vectorof the vector, and they are denoted using the “hat” notation:\帽子{V}。The definition of the unit vector\帽子{V}一个向量的\ VEC {V}是:

\的DisplayStyle \帽子{V} = \压裂{\ vec的{V}} {\ | \ vec的{V} \ | _p}

\帽子{V}是单位矢量,或者归一化矢量,所述\ VEC {V}在矢量将被归一化和\ | \ VEC {V} \ | _p是矢量的范数(大小,长度)\ VEC {V}in theL^pspace (don’t worry, I’m going to explain it all).

The unit vector is actually nothing more than a normalized version of the vector, is a vector which the length is 1.

The normalization process (Source: http://processing.org/learning/pvector/)
The normalization process (Source: http://processing.org/learning/pvector/)

但这里的重要问题是如何向量的长度来计算,并明白这一点,你必须了解的动机L^p空间,也被称为Lebesgue spaces

Lebesgue spaces

多久这个载体?(来源:来源:http://processing.org/learning/pvector/)
多久这个载体?(来源:来源:http://processing.org/learning/pvector/)

Usually, the length of a vector\ {VEC U】=(U_1,U_2,U_3,\ ldots,u_n)is calculated using the欧几里得范-一个准则是在矢量空间中分配一个严格正长度或大小于所有矢量的函数-, which is defined by:

(Source: http://processing.org/learning/pvector/)
(Source: http://processing.org/learning/pvector/)

\ | \ VEC【U} \ |= \ SQRT【U ^ 2_1 + U ^ 2_2 + U ^ 2_3 + \ ldots + U ^ 2_n}

但是,这不是定义长度的唯一途径,这就是为什么你看到(有时)的数p符合规范的符号,就像在了一起\ | \ VEC【U} \ |_p。That’s because it could be generalized as:

\的DisplayStyle \ | \ VEC【U} \ | _p =(\左| U_1 \右| ^ P + \左| U_2 \右| ^ P + \左| U_3 \右| ^ P + \ ldots + \左|u_n \右| ^ p)^ \压裂{1} {p}

和simplified as:

\displaystyle \|\vec{u}\|_p = (\sum\limits_{i=1}^{n}\left|\vec{u}_i\right|^p)^\frac{1}{p}

所以,当你阅读有关L2-norm,you’re reading about the欧几里得范,具有规范p = 2时用于测量的矢量的长度的最常用标准,通常称为“大小”;其实,当你有一个不合格的长度测量(不p号),你有L2-norm(欧几里得范数)。

当你阅读一L1-norm你正在阅读与规范P = 1,defined as:

\的DisplayStyle \ | \ VEC【U} \ | _1 =(\左| U_1 \右| + \左| U_2 \右| + \左| U_3 \右| + \ ldots + \左| u_n \右|)

这无非是向量的组件的简单相加,也被称为Taxicab distance,also called Manhattan distance.

出租车几何与欧几里得距离:在出租车几何所有三个描绘线具有对于相同的路径具有相同的长度(12)。在欧几里德几何,绿色的线有长度,6 \倍\ SQRT {2} \约8.48,并且是唯一的最短路径。
资源:维基百科::出租车几何

Note that you can also use any norm to normalize the vector, but we’re going to use the most common norm, the L2-Norm, which is also the default in the 0.9 release of thescikits.learn。You can also find papers comparing the performance of the two approaches among other methods to normalize the document vector, actually you can use any other method, but you have to be concise, once you’ve used a norm, you have to use it for the whole process directly involving the norm (a unit vector that used a L1-norm isn’t going to have the length 1 if you’re going to take its L2-norm later).

返回矢量归

现在你知道了矢量正常化进程是什么,我们可以尝试一个具体的例子,使用L2范数的过程(我们现在使用正确的术语),以规范我们的矢量\ {VEC V_ {D_4}} =(0,2,1,0)in order to get its unit vector\ {帽子V_ {D_4}}。To do that, we’ll simple plug it into the definition of the unit vector to evaluate it:

\帽子{V}= \frac{\vec{v}}{\|\vec{v}\|_p} \\ \\  \hat{v_{d_4}} = \frac{\vec{v_{d_4}}}{||\vec{v_{d_4}}||_2} \\ \\ \\  \hat{v_{d_4}} = \frac{(0,2,1,0)}{\sqrt{0^2 + 2^2 + 1^2 + 0^2}} \\ \\  \hat{v_{d_4}} = \frac{(0,2,1,0)}{\sqrt{5}} \\ \\  \small \hat{v_{d_4}} = (0.0, 0.89442719, 0.4472136, 0.0)

这就是它!我们的法矢\ {帽子V_ {D_4}}现在有一个L2范\ | \帽子{V_ {D_4}} \ | _2 = 1.0

请注意,这里我们归我们词频文档向量,但后来我们要做的是,TF-IDF的计算后。

The term frequency – inverse document frequency (tf-idf) weight

现在您已经了解如何向量normalization works in theory and practice, let’s continue our tutorial. Suppose you have the following documents in your collection (taken from the first part of tutorial):

火车文档集:D1:天空是蓝色的。D2:阳光灿烂。测试文档集:D3:在天空,阳光灿烂。D4:我们可以看到闪亮的阳光,明亮的阳光下。

您的文档空间可以那么作为被定义d = \ {D_1,D_2,\ ldots,D_N \}whereñ是个文件数in your corpus, and in our case asD_ {火车} = \ {D_1,D_2 \}D_ {测试} = \ {D_3,D_4 \}。我们的文档空间的基数被定义\left|{D_{train}}\right| = 2\左| {{D_测试}} \右|= 2,因为我们只有2两个用于训练和测试文档,但他们显然并不需要有相同的基数。

现在让我们看看,然后是如何IDF(逆文档频率)定义:

\displaystyle \mathrm{idf}(t) = \log{\frac{\left|D\right|}{1+\left|\{d : t \in d\}\right|}}

where\left|\{d : t \in d\}\right|是个文件数其中术语Ť看来,当term-frequency function satisfies\ mathrm {TF}(T,d)\neq 0,我们只加1代入公式,以避免零分。

为TF-IDF式则是:

\ mathrm {TF \ MBOX { - } IDF}(T)= \ mathrm {TF}(T,d)\倍\ mathrm {IDF}(t)的

和该公式具有重要的后果:当你有给定文档中高词频(TF)达到TF-IDF计算的高权重(本地参数)和整个集合中的术语的低文档频率(global parameter).

Now let’s calculate the idf for each feature present in the feature matrix with the term frequency we have calculated in the first tutorial:

M_ {}列车=  \begin{bmatrix}  0 & 1 & 1 & 1\\  0 & 2 & 1 & 0  \end{bmatrix}

因为我们有4个特点,我们要计算\ mathrm {IDF}(T_1)\ mathrm {IDF}(T_2)\ mathrm {IDF}(t_3处)\mathrm{idf}(t_4)

\ mathrm {IDF}(T_1)= \log{\frac{\left|D\right|}{1+\left|\{d : t_1 \in d\}\right|}} = \log{\frac{2}{1}} = 0.69314718

\ mathrm {IDF}(T_2)= \日志{\压裂{\左| d \右|} {1+ \左| \ {d:T_2 \在d \} \右|}} = \日志{\压裂{2} {3}} = -0.40546511

\ mathrm {IDF}(t_3处)= \日志{\压裂{\左| d \右|} {1+ \左| \ {d:t_3处\在d \} \右|}} = \日志{\压裂{2} {3}} = -0.40546511

\ mathrm {IDF}(T_4)= \日志{\压裂{\左| d \右|} {1+ \左| \ {d:T_4 \在d \} \右|}} = \日志{\压裂{2} {2}} = 0.0

这些IDF权重可以由矢量作为表示:

vec {idf_ \{火车}}= (0.69314718, -0.40546511, -0.40546511, 0.0)

现在,我们有我们的词频矩阵(M_ {}列车)和表示我们的矩阵的每个特征的IDF(矢量vec {idf_ \{火车}}),我们可以计算出我们的TF-IDF权重。我们要做的是矩阵中的每一列的简单乘法M_ {}列车with the respectivevec {idf_ \{火车}}向量维度。要做到这一点,我们可以创建一个正方形diagonal matrixM_ {} IDFwith both the vertical and horizontal dimensions equal to the vectorvec {idf_ \{火车}}尺寸:

M_ {} IDF=   \begin{bmatrix}   0.69314718 & 0 & 0 & 0\\   0 & -0.40546511 & 0 & 0\\   0 & 0 & -0.40546511 & 0\\   0 & 0 & 0 & 0   \end{bmatrix}

然后将它乘到术语频率矩阵,因此最终结果然后可以定义为:

M_ {TF \ MBOX { - }} IDF= M_{train} \times M_{idf}

请注意,矩阵乘法是不可交换的,结果A \乘以Bwill be different than the result of theB \times A,这就是为什么M_ {} IDFis on the right side of the multiplication, to accomplish the desired effect of multiplying each idf value to its corresponding feature:

\begin{bmatrix}   \mathrm{tf}(t_1, d_1) & \mathrm{tf}(t_2, d_1) & \mathrm{tf}(t_3, d_1) & \mathrm{tf}(t_4, d_1)\\   \mathrm{tf}(t_1, d_2) & \mathrm{tf}(t_2, d_2) & \mathrm{tf}(t_3, d_2) & \mathrm{tf}(t_4, d_2)   \end{bmatrix}   \times   \begin{bmatrix}   \mathrm{idf}(t_1) & 0 & 0 & 0\\   0 & \mathrm{idf}(t_2) & 0 & 0\\   0 & 0 & \mathrm{idf}(t_3) & 0\\   0 & 0 & 0 & \mathrm{idf}(t_4)   \end{bmatrix}   \\ =   \begin{bmatrix}   \mathrm{tf}(t_1, d_1) \times \mathrm{idf}(t_1) & \mathrm{tf}(t_2, d_1) \times \mathrm{idf}(t_2) & \mathrm{tf}(t_3, d_1) \times \mathrm{idf}(t_3) & \mathrm{tf}(t_4, d_1) \times \mathrm{idf}(t_4)\\   \mathrm{tf}(t_1, d_2) \times \mathrm{idf}(t_1) & \mathrm{tf}(t_2, d_2) \times \mathrm{idf}(t_2) & \mathrm{tf}(t_3, d_2) \times \mathrm{idf}(t_3) & \mathrm{tf}(t_4, d_2) \times \mathrm{idf}(t_4)   \end{bmatrix}

Let’s see now a concrete example of this multiplication:

M_ {TF \ MBOX { - }} IDF= M_{train} \times M_{idf} = \\   \begin{bmatrix}   0 & 1 & 1 & 1\\   0 & 2 & 1 & 0   \end{bmatrix}   \times   \begin{bmatrix}   0.69314718 & 0 & 0 & 0\\   0 & -0.40546511 & 0 & 0\\   0 & 0 & -0.40546511 & 0\\   0 & 0 & 0 & 0   \end{bmatrix} \\   =   \begin{bmatrix}   0 & -0.40546511 & -0.40546511 & 0\\   0 & -0.81093022 & -0.40546511 & 0   \end{bmatrix}

And finally, we can apply our L2 normalization process to theM_ {TF \ MBOX { - }} IDF矩阵。Please note that this normalization is“逐行”因为我们要处理矩阵的每一行作为一个分离向量进行归一化,而不是矩阵作为一个整体:

M_ {TF \ MBOX { - }} IDF= \frac{M_{tf\mbox{-}idf}}{\|M_{tf\mbox{-}idf}\|_2} = \begin{bmatrix}   0 & -0.70710678 & -0.70710678 & 0\\   0 & -0.89442719 & -0.4472136 & 0   \end{bmatrix}

And that is our pretty normalized tf-idf weight of our testing document set, which is actually a collection of unit vectors. If you take the L2-norm of each row of the matrix, you’ll see that they all have a L2-norm of 1.

Python的实践

环境中使用Python的v.2.7.2NumPy的1.6.1SciPy的v.0.9.0Sklearn(Scikits.learn)v.0.9

现在,你在等待的部分!在本节中,我将使用Python的使用,以显示TF-IDF计算的每一步Scikit.learn特征提取模块。

第一步是创建我们的训练和测试文档集和计算词频矩阵:

从sklearn.feature_extraction.text进口CountVectorizer train_set =(“天空是蓝色的。”,“阳光灿烂”。)TEST_SET =(“在天空中的太阳是光明的。”,“我们可以看到闪耀的太阳,。明亮的太阳“)count_vectorizer = CountVectorizer()count_vectorizer.fit_transform(train_set)打印 ”词汇“,count_vectorizer.vocabulary#词汇:{ '蓝':0, '太阳':1, '鲜艳':2 '天空':3} freq_term_matrix = count_vectorizer.transform(TEST_SET)打印freq_term_matrix.todense()#[[0 1 1 1]#[0 2 1 0]]

现在,我们有频率项矩阵(称为freq_term_matrix), we can instantiate theTfidfTransformer,which is going to be responsible to calculate the tf-idf weights for our term frequency matrix:

from sklearn.feature_extraction.text import TfidfTransformer tfidf = TfidfTransformer(norm="l2") tfidf.fit(freq_term_matrix) print "IDF:", tfidf.idf_ # IDF: [ 0.69314718 -0.40546511 -0.40546511 0. ]

请注意,我所指定的标准为L2,这是可选的(实际上默认为L2范数),但我已经添加了参数,使其明确向你表示,它会使用L2范数。还要注意的是,你可以通过访问称为内部属性看IDF计算权重idf_。现在fit()我Ťhod has calculated the idf for the matrix, let’s transform thefreq_term_matrix到TF-IDF权重矩阵:

Ťf_idf_matrix = tfidf.transform(freq_term_matrix) print tf_idf_matrix.todense() # [[ 0. -0.70710678 -0.70710678 0. ] # [ 0. -0.89442719 -0.4472136 0. ]]

And that is it, theŤf_idf_matrix其实我们以前M_ {TF \ MBOX { - }} IDF矩阵。您可以通过使用达到相同的效果Vectorizer类Scikit.learn的这是一个矢量器自动结合CountVectorizer和ŤheTfidfTransformer给你。看到Ťhis example要知道如何使用它的文本分类过程。

I really hope you liked the post, I tried to make it simple as possible even for people without the required mathematical background of linear algebra, etc. In the next Machine Learning post I’m expecting to show how you can use the tf-idf to calculate the cosine similarity.

如果你喜欢,随时提出意见和建议,修改等。

引用本文为:基督教S. Perone,“机器学习::文本特征提取(TF-IDF) - 第二部分”,在亚洲金博宝未知领域,03/10/2011,//www.cpetem.com/2011/10/machine-learning-text-feature-extraction-tf-idf-part-ii/

References

理解逆文档频率:对IDF理论论证

Wikipedia :: tf-idf

The classic Vector Space Model

Sklearn文本特征提取码

更新

13Mar 2015-格式化,固定图像的问题。
2011 10月3日-Added the info about the environment used for Python examples

103个想法“机器学习::文本特征提取(TF-IDF) - 第二部分”

  1. Wow!
    完美的前奏在TF-IDF,非常感谢你!亚洲金博宝亚洲金博宝很有意思,我想学这个领域很长一段时间,你的职位是一个真正的礼物。这将是非常有趣的阅读更多亚洲金博宝关于该技术的使用情况。而且可能是你有兴趣,请,摆脱对文本语料库表示的其他方法的一些光,如果他们存在?
    (对不起,糟糕的英语,我正在努力对其进行改进,但仍然有很多工作要做的)

  2. Excellent work Christian! I am looking forward to reading your next posts on document classification, clustering and topics extraction with Naive Bayes, Stochastic Gradient Descent, Minibatch-k-Means and Non Negative Matrix factorization

    Also, the documentation of scikit-learn is really poor on the text feature extraction part (I am the main culprit…). Don’t hesitate to join the mailing list if you want to give a hand and improve upon the current situation.

    1. Great thanks Olivier. I really want to help sklearn, I just have to get some more time to do that, you guys have done a great work, I’m really impressed by the amount of algorithms already implemented in the lib, keep the good work !

  3. I like this tutorial better for the level of new concepts i am learning here.
    这就是说,学习scikits您正在使用哪个版本?
    最新通过的easy_install安装似乎有不同的模块层次结构(即没有找到sklearn feature_extraction)。如果你能提到你使用的版本,我只是尝试用这些例子。

    1. 您好阿南德,我很高兴你喜欢它。我已经增加了大约只用一节“的Python惯例”之前,我使用的是scikits.learn 0.9(发布在几个星期前)环境的信息。

  4. 哪里是第3部分?我必须提交在4天内向量空间模型的分配。把它在周末的希望吗?

  5. 再次感谢这个完整和明确的教程和我在等待即将到来的部分。

  6. 由于基督徒!与s亚洲金博宝klearn向量空间很不错的工作。我只有一个问题,假设我已经计算了“tf_idf_matrix”,我想计算成对余弦相似性(每行之间)。我是有问题的稀疏矩阵格式,你可以请给出这样的例子?也是我的基质是相当大的,由60K说25K。非常感谢!

  7. 伟大的职位......我明白了什么TF-IDF以及如何与一个具体的例子实施。但我发现2周的事情,我不知道:
    1- You called the 2 dimensional matrix M_train, but it has the tf values of the D3 and D4 documents, so you should’ve called that matrix M_test instead of M_train. Because D3 and D4 are our test documents.
    2 - 当你计算IDF值的T2(这是“太阳”),它应该是日志(2/4)。因为文件的数目是2 D3有词“太阳” 1次,D4有它的2倍。这使得3,但是我们也加1到值摆脱0分的问题。这使得4 ...我说得对不对还是我失去了一些东西?
    谢谢。

    1. 你是正确的:这些都是优秀的博客文章,但作者真的有责任/责任回去和纠正错误,这样的(和其他人,例如,第1部分; ...):缺席训练下划线;设置STOP_WORDS参数;还我的电脑上,词汇索引是不同的。

      正如我们赞赏的努力(荣誉的作者!),它也是一个显著伤害那些谁斗争过去在原有材料的(未修正)的错误。

      1. re: my ‘you are correct comment’ (above), I should have added:

        “… noting also Frédérique Passot’s comment (below) regarding the denominator:

        “......我们用的是什么确实是在发生的一个术语,无论任何给定的文档中出现的术语次数的文件数量。在这种情况下,然后,在用于T2(“太阳”)的IDF值分母确实2 + 1(2个文件具有“太阳”术语,1以避免潜在的零分割误差)。“

    2. 哈立德,
      This is a response to a very old question. However, I still want to respond to communicate what I understand from the article.
      Your question 2: “When you calculate the idf value for the t2 (which is ‘sun’) it should be log(2/4)”
      我的理解:在数项的分母应该是(一些文件,其中术语出现+ 1),而不是长期的频率。术语“太阳”出现的文件的数目是2(1次在D3和D4中的2倍 - 完全出现3次在两个文件3是频率和2是文件号)。因此,分母为2 + 1 = 3。

  8. 优秀的帖子!
    I have some question. From the last tf-idf weight matrix, how can we get the importance of term respectively(e.g. which is the most important term?). How can we use this matrix to classify documents

  9. 非常感谢。你在这样一个简单的方法来解释它。这是非常有用的。再次感谢了很多。

  10. 我有同样的疑问,杰克(最后的评论)。从上个TF-IDF权重矩阵,我们怎么能拿到各自任期的重要性(例如,这是最重要的用语?)。我们如何利用这个矩阵来区分文档。

  11. 我有个问题..
    在TF-IDF操作后,我们得到与值的numpy的阵列。假设我们需要从阵列中获得最高50个值。我们怎样才能做到这一点?

    1. high value of f(idf) denotes that the particular vector(or Document) has high local strength and low global strength, in which case you can assume that the terms in it has high significance locally and cant be ignored. Comparing against funtion(tf) where only the term repeats high number of times are the ones given more importance,which most of the times is not a proper modelling technique.

  12. 嘿,
    Thanx fr d code..was very helpful indeed !

    1.适用于文档聚类,计算反相的术语频率之后,shud我使用任何关联性系数等Jaccards系数,然后应用聚类算法中像k均值或shud我计算反转术语频率后直接适用d k均值到文档向量?

    2.您是如何评价倒词频为calcuating文档向量文本聚类?

    谢谢a ton fr the forth coming reply!

  13. @Khalid:你在1-指出什么让我困惑过了一分钟(M_train VS M_test)。我想你误会了你的第二点,不过,因为我们用的是什么是真正发生的一个术语,无论任何给定的文档中出现的术语次数的文件数量。在这种情况下,那么,在为T2(“太阳”)的IDF值分母确实2 + 1(2个文件具有的术语“太阳”,1以避免潜在的零分割误差)。

    I’d love to read the third installment of this series too! I’d be particularly interested in learning more about feature selection. Is there an idiomatic way to get a sorted list of the terms with the highest tf.idf scores? How would you identify those terms overall? How would you get the terms which are the most responsible for a high or low cosine similarity (row by row)?

    Thank you for the _great_ posts!

  14. 优秀文章和一个伟大的介绍TD-IDF正常化。

    你必须解释这些复杂的概亚洲金博宝念非常清晰,结构化的方法。

    谢谢!

      1. very good & infomative tutorial…. please upload more tutorials related to documents clustering process.

  15. 您可以为使用TFIDF所以我们有TFIDF的矩阵,我们怎么可以用它来计算余弦做余弦相似度任何引用。感谢神奇的物品。

  16. 谢谢so much for this and for explaining the whole tf-idf thing thoroughly.

  17. Please correct me if i’m worng
    从“频率后的公式Calculated in the first tutorial:” should Mtest not Mtrain. also after starting ‘These idf weights can be represented by a vector as:” should be idf_test not idf_train.

    Btw great series, can you give an simple approach for how to implement classification?

  18. Very good post. Congrats!!

    Showing your results, I have a question:

    我读了维基百科:
    成比例的TF-IDF值增加到的次数的字出现在文档中,但是通过在语料库中的字,这有助于控制的事实,一些词语通常比另一些更常见的频率偏移。

    当我看到它,我明白,如果一个字中的所有文档apperars就是一个字只出现在一个文档中不太重要的:

    然而,在结果中,“太阳”或“明亮”是比“天空”最重要的。

    我不知道的完全地理解它。

  19. Terrific! I was familiar with tf-idf before but I found your scikits examples helpful as I’m trying to learn that package.

  20. 优秀的帖子!一次偶然的机会找上CountVectorizer更多信息,无意中发现了这一点,但我很高兴我通过两个您的文章(第1部分和第2部分)的读取。

    现在用书签您的博客

  21. Does not seem to fit_transform() as you describe..
    任何想法,为什么?
    >>> TS
    (“天空是蓝色的”,“阳光灿烂”)
    >>> v7 = CountVectorizer()
    >>> v7.fit_transform(ts)
    <2×2 sparse matrix of type '’
    用4个存储元件在坐标格式>
    >>>打印v7.vocabulary_
    {u'is’:0,u'the”:1}

    1. 其实,还有第一个Python样本中的两个小错误。
      1. CountVectorizer应该被实例化,如下所示:
      count_vectorizer = CountVectorizer(STOP_WORDS = '英语')
      这将确保“是”,“的”等被删除。

      2.要打印的词汇,你必须在末尾添加下划线。
      打印“词汇:” count_vectorizer.vocabulary_

      Excellent tutorial, just small things. hoep it helps others.

      1. 由于灰。虽然文章是相当自我解释的,您的评论使整个差异。

  22. 感谢您抽出时间来写这篇文章。发现它非常有用。亚洲金博宝

  23. 谢谢for the great explanation.

    I have a question about calculation of the idf(t#).
    在第一种情况下,你写的IDF(T1)=日志(2/1),因为我们没有我们收集此类条款,因此,我们添加1分母。现在,在T2的情况下,你写的日志(2/3),所以分母等于3,而不是4(= 1 + 2 + 1)?万一t3时,你写:日志(2/3),从而分母等于3(= 1 + 1 + 1)。我在这里看到的那种不一致性。你能不能,请解释一下,你是怎么计算的分母值。

    谢谢。

    1. 你理解错了,分母你不把这个词的总和每个文档中,你只是总结所有具有词的至少一个aparition的文件。

  24. it is good if you can provide way to know how use ft-idf in classification of document. I see that example (python code) but if there is algorithm that is best because no all people can understand this language.

    谢谢

  25. 尼斯。一种解释有助于正确看待这个事情。是TF-IDF的好办法做聚类(例如,从已知的语料用杰卡德分析或方差相对于平均值设定)?

    Keep writing:)

  26. 嗨基督徒,

    这让我非常兴奋和幸运,读亚洲金博宝这篇文章。你理解的清晰反映了文件的清晰度。这让我重拾我的信心在机器学习领域。

    谢谢a ton for the beautiful explanation.

    Would like to read more from you.

    谢谢,
    Neethu

  27. 谢谢你的良好的收官之作。你提到一些这比较L1和L2规范的论文,我计划研究,多一点深入。你还知道他们的名字?

  28. 我如何能计算TF IDF为自己的文本文件,它位于一些地方在我的电脑?

  29. Brilliant article.

    By far the easiest and most sound explanation of tf-tdf I’ve read. I really liked how you explained the mathematics behind it.

  30. 嗨,伟大的职位!我使用的是TfidVectorizer模块scikit学习产生与规范= L2的TF-IDF矩阵。我把它叫做tfidf_matrix语料的fit_transform后,我一直在检查TfidfVectorizer的输出。我总结了行,但他们并不总和为1的代码是VECT = TfidfVectorizer(use_idf =真,sublunar_tf =真,规范=” L2)。tfidf_matrix = vect.fit_transform(数据)。当我运行tfidf_matrix.sum(轴= 1)的载体是大于1也许我看错矩阵或我误解如何正常化的作品。我希望有人能澄清这一点!谢谢

  31. Can I ask when you calculated the IDF, for example, log(2/1), did you use log to base 10 (e) or some other value? I’m getting different calculations!

  32. 伟大的教程,刚开始在ML一份新工作,这很清楚,因为它应该是解释的事情。亚洲金博宝

  33. Execellent帖子...。!非常感谢这篇文章。

    But I need more information, As you show the practical with python, Can you provide it with JAVA language..

  34. I’m a little bit confused why tf-idf gives negative numbers in this case? How do we interpret them? Correct me if I am wrong, but when the vector has a positive value, it means that the magnitude of that component determines how important that word is in that document. If the it is negative, I don’t know how to interpret it. If I were to take the dot product of a vector with all positive components and one with negative components, it would mean that some components may contribute negatively to the dot product even though on of the vectors has very high importance for a particular word.

  35. 嗨,
    非常感谢您对这个主题这个详细的解释,真是太好了。无论如何,你可以给我一个提示,这可能是我的错误,我不断看到的来源:

    freq_term_matrix = count_vectorizer.transform(TEST_SET)
    AttributeError: ‘matrix’ object has no attribute ‘transform’

    Am I using a wrong version of sklearn?

  36. Awesome simple and effective explaination.Please post more topics with such awesome explainations.Looking forward for upcoming articles.
    谢谢

  37. 谢谢克里斯,你是唯一一个谁是明确了对角矩阵在网络上。

  38. Great tutorial for Tf-Idf. Excellent work . Please add for cosine similarity also:)

  39. 我明白了TF-IDF计算处理。不过这是什么矩阵均值,以及我们如何使用TFIDF矩阵计算相似度让我困惑。你能解释一下,我们如何利用TFIDF矩阵.thanks

  40. 最好的解释..非常有帮助。亚洲金博宝你能告诉我如何绘制矢量文本分类的SVM ..我在微博分类工作。我很困惑,请帮助我。

  41. 您好,我很抱歉,如果我有错,但我不明白是怎么|| VD4 || 2 = 1。
    D4 =的值(0.0,0.89,0.44,0.0),因此归一化将是= SQRT(正方形(0.89)+平方(0.44))= SQRT(0.193)= 0.44
    so what did i missed ? please help me to understand .

  42. 嗨,这是一个伟大的博客!
    If I need to do bi-gram cases, how can I use sklearn to finish it?

  43. 这是非常大的亚洲金博宝。我喜欢你教。亚洲金博宝非常非常好

  44. 我没有得到相同的结果,当我执行相同的脚本。
    print (“IDF:”, tfidf.idf_) : IDF: [ 2.09861229 1. 1.40546511 1. ]

    My python version is: 3.5
    Scikit了解的版本是:o.18.1

    什么我需要改变?可能是什么可能的错误?

    谢谢,

    1. 它可以是很多东西,因为你使用的是不同的Python解释器的版本也不同Scikit-学习版,你应该会在结果的差异,因为他们可能已经改变了默认参数,算法,圆等

  45. 完美的介绍!
    No hocus pocus. Clear and simple, as technology should be.
    亚洲金博宝很有帮助
    Thank you very much.
    请发帖!
    Obrigado

  46. 为什么| d |= 2,在IDF方程。它不应该是4,因为| d |代表的审议的文件数量,我们有2从测试,2个来自火车。

  47. hey , hii Christian
    your post is really helpful to me to understand tfd-idf from the basics. I’m working on a project of classification where I’m using vector space model which results in determining the categories where my test document should be present. its a part of machine learning . it would be great if you suggest me something related to that. I’m stuck at this point.
    Ťhank you

  48. 看到这个例子就知道如何使用它的文本分类过程。“这个”链接不起作用了。能否请您提供相关链接,例如。

    谢谢

  49. There is certainly a great deal to learn about this subject. I really like all the points you made.

  50. 1vbXlh你提出了一个非常美妙的细节,欣赏它的职位。亚洲金博宝

  51. I know this site provides quality based articles or
    reviews and additional data, is there any other web page which presents these kinds of
    在质量信息?

  52. 在第一个例子。IDF(T1),日志(2/1)由计算器= 0.3010。为什么他们获得0.69 ..请有什么不对?

发表回复Bonnie VargheseCancel reply

Your email address will not be published.

This site uses Akismet to reduce spam.了解您的意见如何处理数据