Stop Words: NLP Tutorial For Beginners - S2 E4

[@codebasics]

Check out our premium machine learning course with 2 Industry projects: codebasics.io/courses/machine-learning-for-data-science-beginners-to-advanced

[@asmarasheid]

In the tutorial ipynb, Why are we getting this error while loading the dataset ? ValueError: Unmatched ''"' when when decoding 'string'

[@insil_]

Sir ..need a tutorial video on sentiment analysis

[@dikshyakasaju7541]

Great content! Your videos always help me revise what I had previously learned and implement on the projects I work on.👌

[@anirbanc88]

yahoo i learned so much cool stuff and i do all the exercises you give on my fork from your github repo!

[@joanneenj2042]

Thank you for the playlist Sir. I hope you would be able to launch a course in Computer Vision soon. I'm so thrilled that you will be launching courses about DS, ML and NLP. Here to support. Best regards. 🍀

[@hardikvaghela6031]

Hello sir, Appreciate for your efforts and the teaching methods, really learning NLP from your playlist, Want to request you for the end to end project in nlp which almost covers all the topics in it.... Thank you in advance

[@codebasics]

Yes I will cover end to end project

[@prabhutirukumaran7537]

Great work

[@khaledsamir2667]

Great work , pls I need a reference for nlp video recognition

[@AarushiJain-j7e]

The files uploaded in exercises are not supported by github's rich display feature and because of that I am unable to access them

[@amanpatel-it4mn]

if two words are connected with underscore like 'hello_nlp' then '_' is not removing after the preprocessing ?

[@sudipkumarnandi9094]

when this playlist will end ? how many more videos will come ? please give me the answer as soon as possible because i don"t have too much time .....because you giving 1 video per week.

[@codebasics]

There are at least 20 to 30 videos left. Making good quality tutorials is quite a bit of work my friend hence it will take time.

[@chaitanyabasotra8830]

I m btech in civil (2015 passout) having 4 years of experience as a site engineer (2015-19) thn i left the job and starting preparing for civil services but after 3 years of hand work in could not get through. Now I want to switch my career into private sector. Pls suggest me which SKILL COURSE should I learn which would be beneficial for me. Actually I m in confusing between DATA ANALYST, DATA SCIENCE & FULL STACK DEVELOPMENT. Pls suggest me which would be beneficial for me to get a good job.

[@ashish905]

Today i got msc in DS AI and i am one of the biggest fool around here who say no and now i regret . Because i love finance . But when i realised data science

[@viralvibes1997]

Cloud computing , Salesforce, aws any of these, high pay less effort profile are these, ML is hugely large

[@amitasharma2109]

Hello sir...can i make a career transition into data analyst after working in 13 years in operations and m only b.com graduate and m 34 years old...is it still possible?

[@codebasics]

yes it is possible

[@jaganathreddygfkkwvvlly7325]

Great content sir. Each topic seems easy when taught by you. Love your modules. But I request you to do videos on Forecasting as soon as possible. I am also waiting for powerful content like Statistical techniques like ANOVA, CHI SQUARE , etc.. using python.

[@ashokthulluri4748]

I have answed 3 question on below. Could you please provide excerise of NLP and re problems. # Question : 1 import spacy nlp = spacy.load("en_core_web_sm") def preprocessing(text): doc = nlp(text) count = 0 count1 = 0 temp = [i.text for i in doc if i.is_stop] for i in temp: count += 1 for i in text.split(' '): count1 += 1 percentage = count/count1*100 return percentage preprocessing(text) # Question : 2 from spacy.lang.en.stop_words import STOP_WORDS def pre_processing2(text): doc = nlp(text) temp1 = [] temp = [i.text for i in doc] stopwords = [i for i in STOP_WORDS if i != 'not'] for i in temp: for j in stopwords: if i != j: temp1.append(i) return temp1 pre_processing2("this is a good movie") #pre_processing2("this is not a good movie") #Question : 3 def preprocessing3(text): doc = nlp(text) add = [] temp = [i.text for i in doc if not i.is_stop and not i.is_punct] temp1 = {i : temp.count(i) for i in temp} get_max_values = max(list(temp1.values())) for key,value in temp1.items(): if value == get_max_values: add.append(key) return ''.join(add) preprocessing3(text)