Day 5-Training Word2Vec From Scratch And AvgWord2vec Indepth Inutuition|Krish Naik

[@princejindal3618]

For the people who are trying to implement the train_test_split and getting error. The reason for this is when you apply lemmatize some sentences in the corpus are turned to blanks. Try running the below code after lemmatizer code: [[i,j,k] for i,j,k in zip(list(map(len,corpus)),corpus, messages['message']) if i0 ,corpus))] y=pd.get_dummies(y['label']) y=y.iloc[:,1].values y.shape

[@iamthejims]

Thank you so much. This helped.

[@user-9bk]

After train-test-split when I want to fit X_train,y_train it shows me error : from sklearn.naive_bayes import MultinomialNB model_NB= MultinomialNB() model_NB.fit(X_train,y_train) pls help me to slv this assignment. provide me git-hub link

[@Pradoom45]

bro how did you got this and how did you know how to solve this problem

[@ajayrathore7045]

​@@Pradoom45maybe chatgpt

[@devkumaracharyaiitbombay5341]

16:27 yes sir you are doing very good to people thank you sir. god will bless you for helping others.

[@rajujadhav1392]

You have been doing excellent work by helping thousands of students learn the advanced technologies, please keep doing for the betterment of society.

[@nikhilgupta4859]

Heyy Krish, I am your subscriber from past 1.5 year and I feel honoured to tell you, after following you I finally got a job transition as a senior data scientist at an MNC 6 month back. Now I have understood the datascience project ecosystem in my company. You are one of the contributors for my success. Thanks a Ton!!!!! Also I would like to open my hands for helping learners. So learners you can tag me asking any doubts. I would be more than happy helping you.

[@klaus_aj5895]

Hi @nikhil i have a query, i want to do address abbreviation expansion using this approach. For example, i have address "123, silver lane St., Nr Mapple Cir., " Kind off to expanded expected output "123, silver lane Street., Near Mapple Circle." Any help would be appreciated. Thanks

[@jayashreepaul3890]

@@klaus_aj5895 u can use contractions library. i m not sure while dealing with huge amount of real time data but u can search for the same.

[@ravichoudhary2365]

Thank you Krish for your Amazing Video. I have learn a lot from your videos. Since last 2 years I have been following you. Thank for everything

[@datasciencegyan5145]

You can continue with the quiz it's really fun and getting to know how much knowledge we are getting.

[@saimanohar3363]

Thanks, Krish for providing free sessions. Really appreciate your guidance. 👏

[@alankarsharma4550]

you are perfect!

[@mihirparmar9441]

Thank you so much sir :) !!

[@progamer0256]

sir i dont attend your live session becuase of job but later i watch your every videos to catch each and every word u says

[@bigbossdailydrama]

Thank you Sir 🎉

[@kshitijnishant4968]

There is some flaw in the self-trained Word2Vec model, I was not able to convert and store X as array in X_new like shown in the video. Any reasons?

[@litonpaul6133]

Hi Krish..Please share interview questions regarding the topic which you are teaching after completing the teaching every session. It will be helpful. Day by day people will be ready for interviews. That is the idea.

[@pankajkumarbarman765]

Thank you sir for this amazing session 👌👌👌👌👌👌

[@ShubhamKumar-tj5jw]

Thnaks krish

[@AnkitSharma-yh3nm]

Awesome Session😊

[@WahranRai]

By taking the average, 2 different sentences (input) could have the same AvgWord2vec

[@kartiksood8105]

I am getting this error while training my avgWord2Vec model. Any fixes? TypeError: only size-1 arrays can be converted to Python scalars

[@MM-vx8go]

Informative 🎉

[@anirudhagrawal5044]

Krish, I'll be as honest as possible. There is no better educator who teaches soo well about data science and also gives the more profound knowledge of concept that is not even available on any platform that is paid thank you so much for teaching .I am really grateful to you.

[@sagarbp-2854]

Hi Krish, Ineuron link is showing 404 error. I wanted to download resources

[@ratnak1058]

Thank you sir

[@hargovind2776]

Awesome stuff

[@technicaljethya993]

Thanks 🙏

[@mallikamehta3928]

how to open an account on github and post our projects

[@sandipansarkar9211]

finished watching

[@vijayalaxmimchatter6650]

Hi Sir, actually I tried building model which was part of assignment.. but I was getting error while splitting the data into train and test.. can you please do it in next class...

[@nishanandal-e4f]

how we can get the data?

[@aditya7042]

TypeError: only length-1 arrays can be converted to Python scalars The above exception was the direct cause of the following exception: How to solve this error for training machine learning model?

[@ratnak1058]

Sir please explain interview questions with answers

[@aakashpanda2412]

Hi Krish , there is one doubt, you explained that window size will be the dimension of the word in your previous video of nlp explaining word2vec but here you are explicitly providing vector_size?Why?

[@venkatasubbareddykachiredd9343]

Hey Krish, I am not sure if you have clarified this, but I have a question. When we train our own model for Word2Vec, do we have to 1) split the corpus even before lemmatizing and generating word2vec model or 2) include the entire corpus (because lemmatization requires the entire vocabulary) and then split only when training the model. If we follow the first method, will we have an out-of-vocabulary issue?

[@saurabharbal2684]

Hi sir hat's off to you, I am facing errors while implementation of word2vec and avg_word2vec on mails dataset. Please help me solving this error

[@user-kz4xe5to1g]

44:05 45:02 lol

[@swamiranjit754]

🤣🤣🤣🤣

[@Vansh-v2k]

When we are creating our own Word2Vec model, then after training the word2vec you have written many times "model.wv.index_to_key" or "model.wv['king'].similar" but wv is a variable where we have loaded the "word2vec-google-news-300" model. So why is it so ? Why we are writing the wv? In avg word2vec model you are also writing the "wv" variable ?

[@adityanarendra5886]

When doing TrainTest Split for the AvgWord2Vec in the day5 notebook at the end one. Its showing: Found input variables with inconsistent numbers of samples: [5564, 5572] My code: from sklearn.model_selection import train_test_split X_train,X_test,y_train,y_test = train_test_split(X,y,test_size=0.2,random_state=0) Please Help. Btw Loved the Session👍🏽.

[@princejindal3618]

The reason for this is when you apply lemmatize some sentences in the corpus are turned to blanks. Try running the below code after lemmatizer code: [[i,j,k] for i,j,k in zip(list(map(len,corpus)),corpus, messages['message']) if i0 ,corpus))] y=pd.get_dummies(y['label']) y=y.iloc[:,1].values y.shape

[@shubhsharma4016]

@@princejindal3618 I LOVE YOU BROTHER. I was stuck on this for sometime, I knew the solution but couldn't figure out how to find those missing values and remove them. Thankyou so much