When reading on methods of textual analysis, some eliminate documents with "10% lowest density score", that is, documents that are relatively long compared to the occurrence of a certain keyword. How can I achieve a similar result in quanteda?
I've created a corpus using a query of the words "refugee" and "asylum seeker". Now I would like to remove all documents where the count frequency of refugee|asylum_seeker is below 3. However, I imagine it is also possible to use the relative frequency if document length is to be taken into account.
Could someone help me? The solution in my head looks like this, however I don't know how to implement it.
For count frequency: Add counts of occurrences of refugee|asylum_seeker per document and remove documents with an added count below 3.
For relative frequency: Inspect the overall average relative frequency of both words refugee and asylum_seeker, to then calculate the per row relative frequencies of the features and apply a function to remove all documents with a relative frequency of both features below X.
Create a dfm from your tokenised corpus, using dfmat <- dfm(your tokens).
Remove the documents features this way:
dfm_remove(dfmat,
as.logical(dfmat[, c("refugee")] < 3 |
dfmat[, c("asylum_seeker")] < 3)
)
Related
I am trying to understand how tf and idf scores are calculated when we vectorize a text document usign TfidfVectorizer.
I am understanding how tf-idf ranks in 2 ways, which I am writing below.
tf = ranking a single word based on how often it repeats in this document and idf = ranking the same word on how often it gets repeated in a built-in 'database-like' collection in scikit learn where almost all possible words are collected. Here I assume this built in database to be the corpus.
tf = ranking a single work how often it repeats in the line in the document which is currently being read by tfidfvectorize and idf = ranking based on how many times it is repeated in the entire document that is being vectorized.
Could someone please explain if any of my understanding is correct? And if not please correct what is wrong in my understanding.
The exact answer is in sklearn documentation:
... the term frequency, the number of times a term occurs in a given document, is multiplied with idf component, which is computed as
idf(t) = log[(1 + n_d) / (1+df(d,t))] + 1,
where n_d is the total number of documents, and df(d,t) is the number of documents that contain term t.
So your first item is correct about the tf, but both items miss the point that idf is the inverse document frequency, so it's the ratio of the number of documents (all documents vs documents that contain the term at least once). The formula is taking the log of the ratio to make the ratio function more "flat", and can be adjusted by the class arguments.
Lets say I have "n" number of documents over a specific topic giving certain details. I want to get those documents who are not similar to the majority of the documents. As vague as this might seem, I know how to find cosine similarity between 2 documents. But lets say, I "know" I have 10 documents that are similar to each other, I introduce an 11th document and I need a way to judge how similar is this document with those 10 collectively and not just with every individual document.
I am working with scikit learn, so an answer or technique with its reference will help!
Represent each document as a bag of words and use tf-idf weight to represent a word in a particular document. Then compute cosine similarity with all n documents. Sum all similarity values and then normalize (divide the final sim value by n). It should give you a reasonable similarity between the n documents and your target document.
You can also consider mutual information (sklearn.metrics.mutual_info_score), KL-divergence to measure similarity/difference between two documents. Note that if you want to use them, you need to represent documents as a probability distribution. To compute probability of a term in a document, you can simply use the following formula:
Probability(w) = TF(w) / TTF(w)
where,
TF(w) = term frequency of word, w in a document, d
TTF(w) = total term frequency of word, w [sum of tf in all documents]
I believe any one of them will give you reasonable idea about similarity/dissimilarity between the n documents and your target document.
I have a large data set containing as variables fileid, year and about 1000 words (each word is a separate variable). All line entries come from company reports indicating the year, an unique fileid and the respective absolute frequency for each word in that report. Now I want some descriptive statistics: Number of words not used at all, Mean of words, variance of words, top percentile of words. How can I program that in Stata?
Caveat: You are probably better off using a text processing package in R or another program. But since no one else has answered, I'll give it a Stata-only shot. There may be an ado file already built that is much better suited, but I'm not aware of one.
I'm assuming that
each word is a separate variable
means that there is a variable word_profit that takes a value k from 0 to K where word_profit[i] is the number of times profit is written in the i-th report, fileid[i].
Mean of words
collapse (mean) word_* will give you the average number of times the words are used. Adding a by(year) option will give you those means by year. To make this more manageable than a very wide one observation dataset, you'll want to run the following after the collapse:
gen temp = 1
reshape long word_, i(temp) j(str) string
rename word_ count
drop temp
Variance of words
collapse (std) word_* will give you the standard deviation. To get variances, just square the standard deviation.
Number of words not used at all
Without a bit more clarity, I don't have a good idea of what you want here. You could count zeros for each word with:
foreach var of varlist word_* {
gen zero_`var' = (`var' == 0)
}
collapse (sum) zero_*
I want to know the best way to rank sentences based on similarity from a set of documents.
For e.g lets say,
1. There are 5 documents.
2. Each document contains many sentences.
3. Lets take Document 1 as primary, i.e output will contain sentences from this document.
4. Output should be list of sentences ranked in such a way that sentence with FIRST rank is the most similar sentence in all 5 documents, then 2nd then 3rd...
Thanks in advance.
I'll cover the basics of textual document matching...
Most document similarity measures work on a word basis, rather than sentence structure. The first step is usually stemming. Words are reduced to their root form, so that different forms of similar words, e.g. "swimming" and "swims" match.
Additionally, you may wish to filter the words you match to avoid noise. In particular, you may wish to ignore occurances of "the" and "a". In fact, there's a lot of conjunctions and pronouns that you may wish to omit, so usually you will have a long list of such words - this is called "stop list".
Furthermore, there may be bad words you wish to avoid matching, such as swear words or racial slur words. So you may have another exclusion list with such words in it, a "bad list".
So now you can count similar words in documents. The question becomes how to measure total document similarity. You need to create a score function that takes as input the similar words and gives a value of "similarity". Such a function should give a high value if the same word appears multiple times in both documents. Additionally, such matches are weighted by the total word frequency so that when uncommon words match, they are given more statistical weight.
Apache Lucene is an open-source search engine written in Java that provides practical detail about these steps. For example, here is the information about how they weight query similarity:
http://lucene.apache.org/java/2_9_0/api/all/org/apache/lucene/search/Similarity.html
Lucene combines Boolean model (BM) of Information Retrieval with
Vector Space Model (VSM) of Information Retrieval - documents
"approved" by BM are scored by VSM.
All of this is really just about matching words in documents. You did specify matching sentences. For most people's purposes, matching words is more useful as you can have a huge variety of sentence structures that really mean the same thing. The most useful information of similarity is just in the words. I've talked about document matching, but for your purposes, a sentence is just a very small document.
Now, as an aside, if you don't care about the actual nouns and verbs in the sentence and only care about grammar composition, you need a different approach...
First you need a link grammar parser to interpret the language and build a data structure (usually a tree) that represents the sentence. Then you have to perform inexact graph matching. This is a hard problem, but there are algorithms to do this on trees in polynomial time.
As a starting point you can compute soundex for each word and then compare documents based on soundexes frequencies.
Tim's overview is very nice. I'd just like to add that for your specific use case, you might want to treat the sentences from Doc 1 as documents themselves, and compare their similarity to each of the four remaining documents. This might give you a quick aggregate similarity measure per sentence without forcing you to go down the route of syntax parsing etc.
Can any one suggest me the best way to get Hits( no of occurrences ) of a word per document in Lucene?..
Lucene uses a field-based, rather than document-based, index.
In order to get term counts per document:
Iterate over documents using IndexReader.document() and isDeleted().
In document d, iterate over fields using Document.getFields().
For each field f, get terms using getTermFreqVector().
Go over the term vector and sum frequencies per terms.
The sum of term frequencies per field will give you the document's term frequency vector.
SpanTermQuery.getSpans will give an enumeration of docs and where the terms appears. The docs are sorted, so you can just count the number of times each doc appears, ignoring the position info.