00:14 Day 2 agenda: NLP for machine learning and deep learning 02:27 Discussing techniques for converting words to vectors 07:16 Key NLP terminologies and their relevance. 09:41 Understanding the concepts of corpus, documents, and vocabulary in NLP 13:44 NLP Text Preprocessing Steps 15:50 Focus on converting words into vectors. 20:13 Document encoding using one hot encoding 22:14 One hot encoded format for NLP. 25:44 Sparse matrix and out of vocabulary in NLP 27:36 Issues with out of vocabulary and sparse matrix 31:20 Bag of Words and its application in NLP 33:31 Stop words are generic and can be removed for efficient text analysis. 37:23 Counting word occurrences in documents 39:07 Binary Bag of Words simplifies word representation as 1 or 0. 43:06 Bag of Words, TF-IDF, and Word2Vec have advantages but also come with disadvantages. 45:00 Understanding the importance of word ordering in NLP 48:40 Calculating cosine similarity between points 50:24 Cosine similarity and its limitations 54:37 N-grams represent combinations of features for text analysis. 56:37 Explaining the concept of bigrams and trigrams in NLP. 1:01:45 Demonstration of using NLTK for text processing 1:04:52 Installing basic NLTK libraries for stemming and tokenization 1:09:08 Using Porter Stemmer for word stemming 1:11:13 Using regular expressions to clean the text for NLP analysis. 1:15:08 Applying stemming and bag of words in NLP 1:17:09 Stemming process using NLTK in NLP 1:21:19 Explaining bag of words and index visualization 1:23:20 Using binary bag of words and applying stop words in NLP 1:28:45 Troubleshooting joining issues on Instagram and Mentimeter 1:30:57 Live quiz participation and technical issues 1:39:31 Text pre-processing techniques discussed in quiz 1:41:57 Bigrams can be created from the sentence 'cat eat food'. 1:47:28 Competition tight, final quiz question 1:50:32 Transfer of quiz prize money and verification process
Hi Krish, Its a pleasure to watch your videos and learn the concepts .Please teach in your own pace and thanks so much for your great service .Keep up your good work!
Can't imagine my masters without you. Can't thank you enough 🙏 Don't know what to say. Out of the words which is a disadvantage in many techniques like OHE, BOW etc but this OOW is bcz of the advantage we are gaining from your sessions.
@Krish Naik, please complete this session. Its a delight for us to learn for more than 2-3hrs of a single live session, if it is a possibility(I respect that it may be tiring for u).
@@geekyprogrammer4831 nothing greedy, some folks are not interested for a longer session when Krish asks on live session and Krish got demotivated a bit one time. To show there are guys like me are quite awaiting for his long sessions too. Also I had put “only if possible u can take” and mentioned it’s a tiring thing.
Sir once request please don't leave your course midway as some one has some other commitment. If anyone has any other work he/she can watch it later in youtube and in community. Please complete your daily agenda whatever the time is.
Time: 1:25:25 to run the code: X=cv.fit_transform(corpus) Error is Here: ValueError Traceback (most recent call last) in () ----> 1 X=cv.fit_transform(corpus) 1 frames /usr/local/lib/python3.10/dist-packages/sklearn/feature_extraction/text.py in _count_vocab(self, raw_documents, fixed_vocab) 1292 vocabulary = dict(vocabulary) 1293 if not vocabulary: -> 1294 raise ValueError( 1295 "empty vocabulary; perhaps the documents only contain stop words" 1296 ) ValueError: empty vocabulary; perhaps the documents only contain stop words
One thing I did not get that in bigram 1st example you told good boy good girl but in second example you told Kris eat ,eat food , not krish food why is it so??
Thanks!
00:14 Day 2 agenda: NLP for machine learning and deep learning
02:27 Discussing techniques for converting words to vectors
07:16 Key NLP terminologies and their relevance.
09:41 Understanding the concepts of corpus, documents, and vocabulary in NLP
13:44 NLP Text Preprocessing Steps
15:50 Focus on converting words into vectors.
20:13 Document encoding using one hot encoding
22:14 One hot encoded format for NLP.
25:44 Sparse matrix and out of vocabulary in NLP
27:36 Issues with out of vocabulary and sparse matrix
31:20 Bag of Words and its application in NLP
33:31 Stop words are generic and can be removed for efficient text analysis.
37:23 Counting word occurrences in documents
39:07 Binary Bag of Words simplifies word representation as 1 or 0.
43:06 Bag of Words, TF-IDF, and Word2Vec have advantages but also come with disadvantages.
45:00 Understanding the importance of word ordering in NLP
48:40 Calculating cosine similarity between points
50:24 Cosine similarity and its limitations
54:37 N-grams represent combinations of features for text analysis.
56:37 Explaining the concept of bigrams and trigrams in NLP.
1:01:45 Demonstration of using NLTK for text processing
1:04:52 Installing basic NLTK libraries for stemming and tokenization
1:09:08 Using Porter Stemmer for word stemming
1:11:13 Using regular expressions to clean the text for NLP analysis.
1:15:08 Applying stemming and bag of words in NLP
1:17:09 Stemming process using NLTK in NLP
1:21:19 Explaining bag of words and index visualization
1:23:20 Using binary bag of words and applying stop words in NLP
1:28:45 Troubleshooting joining issues on Instagram and Mentimeter
1:30:57 Live quiz participation and technical issues
1:39:31 Text pre-processing techniques discussed in quiz
1:41:57 Bigrams can be created from the sentence 'cat eat food'.
1:47:28 Competition tight, final quiz question
1:50:32 Transfer of quiz prize money and verification process
Please don't stop adding videos to the playlist, its awesome 💌
yaaaaas
Hi Krish, Its a pleasure to watch your videos and learn the concepts .Please teach in your own pace and thanks so much for your great service .Keep up your good work!
Can't imagine my masters without you. Can't thank you enough 🙏
Don't know what to say. Out of the words which is a disadvantage in many techniques like OHE, BOW etc but this OOW is bcz of the advantage we are gaining from your sessions.
@Krish Naik, please complete this session. Its a delight for us to learn for more than 2-3hrs of a single live session, if it is a possibility(I respect that it may be tiring for u).
stop being greedy
@@geekyprogrammer4831 nothing greedy, some folks are not interested for a longer session when Krish asks on live session and Krish got demotivated a bit one time. To show there are guys like me are quite awaiting for his long sessions too. Also I had put “only if possible u can take” and mentioned it’s a tiring thing.
@@ganps87269 stop being greedy
@@geekyprogrammer4831 nooooooooooooooooooooo
Congratulations for 1 Million Subscribers.....
Really thankful to you for all these free session. These all are the topics on pre-requisite of gen-ai, so learning. Once again thank you
Go to the documentation to understand the implementation of bag of words more preciously.(Suggestion) shift + tab
Hi Krish I have studied ml from many sources udemy ,statquest, andrew ng ,nptel but your way of explanation is awesome honestly.
very very clear though learning for first time..excellent way of teaching
Krish sir, You are just awesome!
thank you so mch for encouraging me .
Super Happy always hear you !
sir, please make a video containing all NLP playlists in one video. As you do for another video also..that is much help full for us...
your teaching so amazing
Great! Explanation.
Sir once request please don't leave your course midway as some one has some other commitment. If anyone has any other work he/she can watch it later in youtube and in community. Please complete your daily agenda whatever the time is.
Time: 1:25:25
to run the code:
X=cv.fit_transform(corpus)
Error is Here:
ValueError Traceback (most recent call last)
in ()
----> 1 X=cv.fit_transform(corpus)
1 frames
/usr/local/lib/python3.10/dist-packages/sklearn/feature_extraction/text.py in _count_vocab(self, raw_documents, fixed_vocab)
1292 vocabulary = dict(vocabulary)
1293 if not vocabulary:
-> 1294 raise ValueError(
1295 "empty vocabulary; perhaps the documents only contain stop words"
1296 )
ValueError: empty vocabulary; perhaps the documents only contain stop words
Can we use lemettization without stemming?
yes he said already in the video but we need to understand where we can use stemming and lemmatization
Thank you krish❤
so stemming and bag of words both have same disadvantage i.e meaning is lost but are simple
Thank u Krish
its awesome
sir,
dashboard link is not working so where we find code notes and all ,
I need some basic code examples for that sir will u provide for us
Pls add a disclaimer to your old playlist that a new one is uploaded, since a few things are missing in it.
from where I can access the files ?
I am getting an error while removing stopwords from the corpus in 1:25:27, it says Word List Corpus Reader not callable , how do we solve it ?
Why my codes aren't running this is frustrating
Add live courses u. Tech neruon too after live courses end
i am not able to find the course material can someone pls help. the links are provided are invalid
Hi Krish, when DevOps course will be started ??
When lemmatizing, wouldn't we want in the word "drinking" to get "drink" ?? Since we're looking for the root of the word...
It depends on the pos tag used, in stemming it will be converted into root word, but it isn't the case with lemmatization. It checks for grammar too.
1:09:31 😳😳
Notes cannot be accessed..it says page not found
yes same problm,did u get it?
Hi Krish, Where can I find this live session notes?
Sir their is no access to notes of this sesson from where could I get notes of all days Live reaching
42:46 Wait so what was even the point of calculating the frequency of each word? It wasn't utilized anywhere
don't we do tokenization while dealing with ngrams?
thx
finished watching
where can I find the code materials for this session?
One thing I did not get that in bigram 1st example you told good boy good girl but in second example you told Kris eat ,eat food , not krish food why is it so??
Cosine similarity formula is incorrect
Then which one is the correct one then
Best nlp course
where is the link for the jupyter notebook
Unable to find the notes in the dashboard...kindly enable
any guidance link for aspect extraction in NLP? @krishnaik
Where is the dashboard sir is talking about??
❤
the dashboard is not accessible sir
can anyone share the practical session file link
nltk.download() is not working. showing WinError 10060 everytime ie. connection attempt failed...plz provide a solution
Execute ni horaha
Wordnet lemmitizater error
can somebody share todays live streaming link
Same here Bro, the link emailed is an incomplete one. I have emailed iNeuron as well as DMed Krish on his Insta but sadly none replied :(
I think no live class today...
@@murarikumar346 @JEM's playground. I just now received a DM from Krish Sir that today's class is cancelled. Tomorrow there will be live session.
Sir error h
❤