in this the starting code array = [1,1,1,0,0] this is a number which we have given after reading our text weather it is negetive and positive but if there are many sentences or it is in a file how do we handle this? example 1000 words in a file?? and what is bigrams?
Not understanding of some concepts
Hello Kushal,
We have taken that just as an example of how our data generally is. In this case we have just made these sentence and thus the labels ourselves, to simply understand how we work through text data. In the coming videos and in real applications we’ll be dealing with complete datasets which will have the sentences in the X data and the labels in the Y data.
Bigrams refers to extracting two words together from the text data. For example there’s a sentence ‘India lost to New Zealand in the world cup match yesterday’, here there are certain words which make no sense when used alone, they add more value when used along with another word, like ‘New Zealand’ and ‘world cup’. We use bigrams to include such pairs in our vocabulary.