WhatsApp Chat Analysis Project | End to End Project with Heroku Deployment

[@adeebarashid361]

Thank you so much sir for this video. I've completed this project and deployed it on heroku. The way you explain things is top notch. Whenever there was an error during the video, you didn't skipped that part and taught what was the reason behind the error and how we can rectify that. Learnt a lot from you sir.

[@tejusingh6888]

My Dataframe is not creating..why it is showing error can u tell me?

[@tejusingh6888]

Same thing I m doing

[@nandyravi4090]

hey hii ... can u plss help me in the project. im finding difficult in separating the msgs and date

[@SimranCE-]

@@tejusingh6888 my data frame is not displayed .can u help me

[@sunnybari716]

@@tejusingh6888 problem solve hua ky

[@uniquesellingpoint9376]

Recently I have completed this amazing project as for my final year thank you so much sir.

[@codeitup6010]

can u share the git hub link

[@John-is2ce]

can u share the link of the code

[@ayeshahabib3060]

Do you have this project with you ? I want it urgently for my semester project... Kindly reply to me .. i will be really thankful

[@srishtigupta7964]

can you please tell the tech skill required to make this project.

[@razexamvs8756]

@@srishtigupta7964 data analysis,knowind libs like pandas and numpy , matplotlib,straemlit use ,seaborn too ..

[@gowthamsr3545]

Followed this video and successfully deployed... Working... Thank you

[@avinashbiradar9953]

hii sir , i am getting error at word cloud 1:12:50 please help me

[@angle2493]

Hello

[@angle2493]

​@@avinashbiradar9953have you done these project? Can you help me?

[@Forever._.curious..]

Yr skills , teaching and content qualities are marvelous 🤩

[@ankitmaddheshiyacs-1014]

df = pd.DataFrame({'user_message': messages, 'message_date': dates}) # Convert message_date type df['message_date'] = pd.to_datetime(df['message_date'], format='%d/%m/%Y, %H:%M -') df.rename(columns={'message_date': 'date'}, inplace=True) df.head() SHOWS VALUE ERROR- ALL ARRAY MUST BE OF SAME LENGTH PLS HELP

[@sachinsolanki1073]

Thank you so so much Sir... I have just completed this amazing Python project, once again amazing explanation and easy understandable project. Thank You

[@avinashbiradar9953]

hii sir , i am getting error at word cloud 1:12:50

[@ajitnayak2919]

df["message_date"] = pd.to_datetime(df["message_date"], format = "%d/%m/%y, %I:%M %p - ") m not getting AM PM plzz help

[@murderousoich669]

hello if your project is working can u help me

[@anupammishra994]

@@murderousoich669 sure, please say the issue

[@murderousoich669]

@@anupammishra994 3 mahine ho gaye bhai, dusra project de dia college me. anyway thanks ✌️

[@ishujain9343]

Thank you very much sir, you make things look simpler. You are the best teacher for Data Science on KZbin.

[@ShikhaSingh-ow2eo]

Hii my whatsupp chat txt file to other formats

[@ShikhaSingh-ow2eo]

Can u help me

[@ishujain9343]

@@ShikhaSingh-ow2eo The problem is with the time format??

[@ShikhaSingh-ow2eo]

Can u send your contact no mam .

[@tejale3584]

@@ishujain9343 yes, I am not able to get the correct regular expression

[@ankitsharma_77]

love from Haldia institute of technology just started machine learning now looking for some project as now I am currently in 3rd year. Love to see alumni of our reaching so much heights in their designated field.

[@bhaskarjha6620]

bit se hai wo

[@avengersstudios8190]

One of the biggest project i am doing in my engineering life!! thanks man you nailed it

[@SkinnyBitch22]

bhai complete hua project

[@MeeraDevi-mm4cr]

Great work please create more end to end projects like this.

[@pkrajanraj1315]

Apne banyhe hai kyaa ishe project ko

[@nbbhatt1695]

Great project, lot's for learn. please keep it up. ❤

[@hassanrevel]

Love your style man, makes me feel I'm watching a live stream.

[@vanshgupta9729]

pattern='\d{1,2}\/\d{1,2}\/\d{2},\s\d{1,2}:\d{2}\s(?:AM|PM)' this regular expression u can use for date and time in am and pm format

[@MP-mp2fr]

thanks

[@anubhawraj1231]

Does not work.

[@shwetkumar8370]

@@anubhawraj1231 '\d{1,2}/\d{1,2}/\d{2,4}, \s\d{1,2}:\d{2}\s(?:am|pm)\s-\s' try this

[@meetvasa6955]

Thanks Bro....Its workingg!!!!

[@ankitmaddheshiyacs-1014]

df = pd.DataFrame({'user_message': messages, 'message_date': dates}) # Convert message_date type df['message_date'] = pd.to_datetime(df['message_date'], format='%d/%m/%Y, %H:%M -') df.rename(columns={'message_date': 'date'}, inplace=True) df.head() SHOWS VALUE ERROR- ALL ARRAY MUST BE OF SAME LENGTH PLS HELP

[@Malayalam_learner]

I saw upto 42 min , ill finish it later 😊 Your good bro🔥

[@aaloo_ka_paratha]

give github repo link when completed

[@SkinnyBitch22]

bhai complete hua please reply

[@rohanr8819]

Good project and great explanation i understood every line of the code👍

[@Siddu013]

Thanks for the such a wonderful lecture SIR❤

[@KishanSingh-cv7dp]

Thank U so much Sir for amazing end to end NLP project

[@104_shikha4]

what technologies are used in this project can u tell?

[@abdulqadar9580]

That was amazing Projexts thanks a lot Sir Love from Pakistan

[@abhaycode]

bro you are a genius!!

[@handhikayp]

Thank you sir, at least I could upload this project in heroku

[@campusx-official]

Glad to help

[@ayeshahabib3060]

Hi .. do u have this project with you? Please i want this for my semester project.

[@VishalRathourMPH]

The heroku link you have given in the description is not working neither the movie recommender system link working. What could be the problem with heroku?

[@aakif153]

i usually dont commment but brother your teaching was amazing and detailed as well..keep it upppp....

[@jyothic8347]

Very helpful thank you sir

[@arijitmajumdar7787]

Thank u very muchhh sir.😍 Worth watching

[@chiragkarnwal6740]

Thanks for these great projects bhaiya💓

[@razz831]

Yeahh ....Its working well but can someone pls suggest me the platform whre i can deploy this project becoz heroku is taking charges for this...pls suggest any free platform to deploy 😐

[@isaar-hm2ep]

Have you deployed @razz831?

[@vigneswarareddyburra5572]

can u please help me for doing this project

[@khushimattu9653]

st.dataframe(df) at 30:50 is returning an empty table even though the previous step displays the data correctly

[@gautamkrishna1273]

For me also

[@vrushalisalvi3476]

Thank you so much sir for this amazing project

[@itsme1674]

Thank you so much for wonderful project

[@DiegoLlorente-y1e]

Was exited at the beginning then you started to speak hindi then I realized most of the world speaks hindi and better than any programming language I should just learn hindi , started learning then figure out there are over 200 accents, so might as well look for other tutorials. 😢

[@pandeygaming5716]

At 30:51 my dataframe is only not loading on the app screen . I tried everything from yesterday. Please someone help Up till that step everything was correct but after the same implementation even it shows empty

[@logicscomputing]

Same! Have you any solution??

[@kyadampradeep122]

Hello bro Can you give me 25:00 25:02 your Github link

[@MuhammadSadiq-n8r]

this video is very helpful

[@aakif153]

why isnt the working demo opening up..any issues

[@rbk.technology4747]

U r next level man.... Can we do sentiment analysis on the chat ??

[@meruvahemalatha6008]

Hi Could you please tell how did u consolidated all hindi & English stop words in 1 file

[@lakshitakamboj198]

Hello. Instead of using streamlit, can we also use tableu or powerbi????

[@sagarjoshi8084]

Great project sir thanks a lot

[@SchrodingerMan]

if you have 12 hour format , firstly change from phone setting time fomat to 24 hour format , then export the chat , and then check if your date is in 31/12/2022 then it will work, if it is in 31/12/22 change it to 2022 format by opening the chat file and then replace /22 to /2022 . it will work

[@NeelamGautam-o8p]

i changed my phn setting time then export the chat it is also showing error

[@SchrodingerMan]

@@NeelamGautam-o8p open that file and check the format of date 31/12/2024

[@rambhaktuchihaobito7987]

bro how can we change the format of date from /22 to /2022

[@SchrodingerMan]

@@rambhaktuchihaobito7987 open that chat text file and then change using find and replace in text editor

[@Himanshu-lp3bt]

Bhai isme ml use hui h ya nhi Or ye project shi h kya !

[@somarchivee]

hi i am najiib from somalia this project awesom thanks i try to make it

[@Riya-zb1iz]

Thank you for this amazing project sir! Also can you please explain me the [\w\W]+? :\s this regex expression ?

[@shaikhfaizahmed9415]

Meko kohi bata Sakta hai kya Waise yeh project to Bohat accha hai Jaise iska real life use kaise aayega Or jaide iska objective kya hai ???

[@rhl_ai]

I am getting this error -> "AttributeError: module 'emoji' has no attribute 'UNICODE_EMOJI' ". what should i do?

[@anupammishra994]

Dude, did you find any solution for this ? I am facing the same issue.

[@anupammishra994]

Hi bro, just found the issue: Its a bit long, so read and copy paste the code from this comment. The unicode_emoji[ ] attribute was present in the emoji library in 1.7.0 version, not in the latest version, i.e. 2.0, So either you can uninstall the emoji library version 2.0 and install emoji library 1.7.0 version. other solution: please use the function: emoji.emoji_list(string in which the emojis are present) I have created a custom code which gives you a list of all the emojis in df['message'], you can use that too: import emoji #the goal is to create a string to be put in the function emoji.emoji_list(string) words=[] for messages in df['message']: words.extend(messages.split()) #now we have a list which contains all the words in df['message'] of dataframe #now the goal is to convert it into a string mystr="" for x in words: mystr=mystr + " "+ x mystr #now we have to put this string into the emoji function myemoji=emoji.emoji_list(mystr) #myemoji is a list with the following type of elements #[{'match_start': 5712, 'match_end': 5714, 'emoji': '👍🏻'}, #{'match_start': 6896, 'match_end': 6897, 'emoji': '👆'}, #{'match_start': 6897, 'match_end': 6898, 'emoji': '👆'}, #{'match_start': 8097, 'match_end': 8098, 'emoji': '👆'}] #now we have to extract each emoji from this type of list pre_final_emoji_list=[] for i in range(len(myemoji)): pre_final_emoji_list.extend(myemoji[i]['emoji']) #now we have another list which contains all the emojis but it also contains some extra emojis which need to be removed #we create two new list, one where removal characters are present and another one where final emojis are. emojis_to_be_removed=['','🏻'] final_emoji_list=[] for items in pre_final_emoji_list: if items not in emojis_to_be_removed: final_emoji_list.append(items) final_emoji_list Please copy paste the code and use the final_emoji_list as an input to the counter function. In one of my chats this was the result of the above code: ['👍', '👆', '👆', '👆', '👆', '👆', '👆', '👍', '👍', '😊', '👍', '😊', '👏', '🎊', '🎉', '👍', '👍', '👍', '👏', '👏', '👆', '👆', '✅', '✅', '✅', '✅', '👆', '✅', '✅', '✅', '✅', '👇', '👇', '👇', '👇', '👇', '👇', '👇', '👆', '♥', '✨', '💘', '♥', '🌸', '👍', '💐', '💐', '💐', '💐', '⏳', '🕐', '🥇', '💐', '💐', '⏳', '🕐', '🥇', '🥇', '👍', '💃', '🎤', '🎼', '⏰'] Note: I am still a noobie, so my code may not be efficient, and has many 'for' loops, but it is easy to understand, also i have placed various #readables in the code for you top easily understand this. This took me more than 3 hours, so If you find this helpful, so connect with me on Linked in (www.linkedin.com/in/anupam00/) and text me. Regards.

[@harshitporwaliitb5268]

What the hell dude why did you use 24 hour format??? It is such a pain to figure out how to convert for 12 hour

[@abhirajsinghrajpurohit2464]

Done by me

[@mohitkashyap1302]

​@@abhirajsinghrajpurohit2464can you share the code,of am pm One ??

[@harshagrawal9274]

​@@abhirajsinghrajpurohit2464bro can you please tell how to convert to 12 hrs format

[@infinitestudy4153]

I find it annoying af when I don't know whether it's 12 am or 12pm so I use 24hrs clock

[@dassandip2915]

You can either put some effort and search for regex about the 12 hours format or you can just change your mobile 12 hours format to 24 hours format and then export the chat. And after that you can again go back to your 12 hours settings lol.

[@Goms_1804]

If I simply clone the code form repo , does it start working or I have toh something else more

[@mumbaikachallenge5526]

This is amazing thank you❤️

[@SonuKumar_IT]

16:57 I am getting an error "all arrays should be the same length". Please help anyone, how can I resolve this error.

[@ignalone5199]

bro i am also getting same problem did you find any solution?

[@ansharora5698]

same. What's the solution?

[@sanjanaepari9173]

@@ignalone5199 did you find any solution?

[@sanjanaepari9173]

did you find any solution?

[@shaurya6981]

@@sanjanaepari9173 did you ? getting the same error

[@raghavaggarwal5628]

Great project sir, sir could you please tell me after deploying I have get problem in app they say emoji doesn't have attribute unicode_emoji.. How can I figure out this?

[@anupammishra994]

Hi bro, just found the issue: The unicode_emoji[ ] attribute was present in the emoji library in 1.7.0 version, not in the latest version, i.e. 2.0, So either you can uninstall the emoji library version 2.0 and install emoji library 1.7.0 version. other solution: please use the function: emoji.emoji_list(string in which the emojis are present) I have created a custom code which gives you a list of all the emojis in df['message'], you can use that too: import emoji #the goal is to create a string to be put in the function emoji.emoji_list(string) words=[] for messages in df['message']: words.extend(messages.split()) #now we have a list which contains all the words in df['message'] of dataframe #now the goal is to convert it into a string mystr="" for x in words: mystr=mystr + " "+ x mystr #now we have to put this string into the emoji function myemoji=emoji.emoji_list(mystr) #myemoji is a list with the following type of elements #[{'match_start': 5712, 'match_end': 5714, 'emoji': '👍🏻'}, #{'match_start': 6896, 'match_end': 6897, 'emoji': '👆'}, #{'match_start': 6897, 'match_end': 6898, 'emoji': '👆'}, #{'match_start': 8097, 'match_end': 8098, 'emoji': '👆'}] #now we have to extract each emoji from this type of list pre_final_emoji_list=[] for i in range(len(myemoji)): pre_final_emoji_list.extend(myemoji[i]['emoji']) #now we have another list which contains all the emojis but it also contains some extra emojis which need to be removed #we create two new list, one where removal characters are present and another one where final emojis are. emojis_to_be_removed=['','🏻'] final_emoji_list=[] for items in pre_final_emoji_list: if items not in emojis_to_be_removed: final_emoji_list.append(items) final_emoji_list Please copy paste the code and use the final_emoji_list as an input to the counter function. In one of my chats this was the result of the above code: ['👍', '👆', '👆', '👆', '👆', '👆', '👆', '👍', '👍', '😊', '👍', '😊', '👏', '🎊', '🎉', '👍', '👍', '👍', '👏', '👏', '👆', '👆', '✅', '✅', '✅', '✅', '👆', '✅', '✅', '✅', '✅', '👇', '👇', '👇', '👇', '👇', '👇', '👇', '👆', '♥', '✨', '💘', '♥', '🌸', '👍', '💐', '💐', '💐', '💐', '⏳', '🕐', '🥇', '💐', '💐', '⏳', '🕐', '🥇', '🥇', '👍', '💃', '🎤', '🎼', '⏰'] Note: I am still a noobie, so my code may not be efficient, and has many 'for' loops, but it is easy to understand, also i have placed various #readables in the code for you top easily understand this. If you find this helpful, so connect with me on Linked in (www.linkedin.com/in/anupam00/) and text me. Regards.

[@abhijeetsaha9211]

16:35 the data frame creating code isn’t working, someone please help

[@juststudy5836]

same bro have u figured it out

[@priyadharshini-cr7xn]

It will be more helpful for People from other language to understand easily if u keep ur videos in English..this is the best video for beginners...but I couldn't understand many of Ur terms in Hindi

[@abhishekkeshri3974]

Said to hear 🥲 you should learn Hindi

[@shwetkumar8370]

@@abhishekkeshri3974 😂😂

[@programmer6649]

I'm from South, we have hindi as second language from my 5th to 10th grade I learnt hindi in my academics, i don't know why they are teaching me hindi at that time I used to hate hindi, now I'm very thankful to my academics which will help me to understand campusx nitish sir videos 😂

[@priyadharshini-cr7xn]

@@programmer6649 Excuse me it is not mandatory to learn hindi it's completely an optional language.. mother language and english is enough to get a job...I'm just posted my opinion.. if the vid in English every one can make use of it right...then what's wrong with u

[@programmer6649]

@@priyadharshini-cr7xn dont you have any habit of reading comments properly, I posted my opinion here I'm not opposed you, even I also asked him to make content in English, I said that learning hindi in my school days ,helped me now that's it

[@rakeshpatil4505]

can you please do deployment on other platform. As heroku is not free now.

[@thanosvillans5195]

How it is ML !? Not Data Analysis instead ?

[@muditgupta5836]

this is what I was wondering. this seems to be a da project not ML

[@Malayalam_learner]

😂

[@shubhamrane944]

Great Video! Thank you!

[@infamous_SUSIL]

Sir there are so many missings in this code, there are the individual persons those didn't send any message only media files,for them i can't build the word cloud

[@anikethgattupelli8764]

While printing the text file I'm getting phone no also how to eliminate it

[@isaquesayyad3513]

Vsir I Need to Analyze Silent Members in my WhatsApp Group to Remove them Can I Analyze it here ?

[@suyashbaranwal4656]

Sir, I want to summarise the unseen group chat irrespective of any language or slangs, can you please please help to out 🙏

[@bashabjyotidas7805]

why so much errors are occuring??????

[@vedangivyas5567]

why unicode_emoji is not running to find the emoji analysis

[@aaryasrigurudattadarsi1705]

downgrade the emoji pack pip install emoji==1.7.0 use this

[@subhasishsahoo-x3o]

hi sir is it helpful for data analyst

[@tech-red24]

also sir ..make a video on ml model to differentiate a bot and a human comment in youtube ...in kaggle

[@rneditz3250]

My WordCloud is only running for Overall and Most Common Words are only running for individual users...Any Solution???Why it is happening?

[@ranarajput206]

The error in your wordcloud is because of your syntax error Write the code on exact place as shown in video then it's working

[@satyajeetrai6529]

what are the skills required to do this analysis efficiently ?

[@sandalagrawal8587]

@CampusX sir, I tried to deploy this project on heroku and when I shared the link with my friends, it gave zero value error and nothing but zero zero in insights was displayed. Can you please help as to how should I resolve it?

[@ayeshahabib3060]

Do you have this project?

[@ghulamdastgir9828]

Plz make a video on deployment of lung segmentation model via website

[@zizo8737]

You are lifesaver♥️

[@SkillWisKnowlege]

sir setup kaise kiya hai jupyter mai vscode mai kaise banaye sir bata na

[@13_mihirladani45]

ValueError: time data '8/19/19, 13:17 - ' does not match format '%m/%d/%Y, %H:%M - ' (match)

[@jaiprakash184]

bhai meri problem bhi aa rahi hai same pls solution batao agar ho gaya ho to

[@13_mihirladani45]

@@jaiprakash184 agar year 2 digit me he to y use karo

[@jaiprakash184]

thank you brother ho gaya reply karne k liye bhut thanks

[@sahilpadave9831]

@@jaiprakash184 bhai kaise solve kiya vo problem ??

[@SayaliTawade-v2i]

@@13_mihirladani45 thanks!

[@smileshs1]

Thank you sir, but I am stuck in the middle. Can you please guide ? StreamlitAPIException: ('cannot mix list and non-list, non-null values', 'Conversion failed for column message with type object') File "C:\Users\smile\PycharmProjects\whatsapchats\app.py", line 12, in st.dataframe(df)

[@KhairulMia-tr2jv]

how can i find this dataset ?

[@snehalpawar9995]

After i give git add . Command my terminal constantly runs while showing warning message and doesn't stop... Does anyone know how to resolve this

[@pravithanishanth1577]

Sir, please make your videos in English that will be helpful for everyone

[@AnmolSahu-c6z]

Someone please tell me upto which day of machine learning from 100 days i want to learn so that i can make this poject

[@kanakagrawal4930]

Sir, we should also try to include sentiment analysis in this project. So, it will be more useful and practical, otherwise who will like to show such stats

[@campusx-official]

Yes that would be a great addition to this project

[@seneca5556]

Have you done that? Update the web if yes, it would be fun! I am not that good in this 🙃

[@ShahbazKhan-ph3vd]

mostly regional language pe hi baat karte h groups aur zyadatar hindi pe hi baat karte h, hindi k upar work nhi karega

[@tech-red24]

sir , the deployed project link is not opening ....pls check at your end........................

[@dassandip2915]

You can either put some effort and search for regex about the 12 hours format or you can just change your mobile 12 hours format to 24 hours format and then export the chat. And after that you can again go back to your 12 hours settings lol.

[@priyachoudhary2390]

emoji' has no attribute 'UNICODE_EMOJI' I am getting this error for emoji analysis. Can you please help me out in this. Rest all I have done only in the emoji section i got stuck. please look into this asap.

[@SKILLCRYSTAL]

Use emoji.distinct_emoji_list(str) this will extract emoji from your string

[@anupammishra994]

Hi bro, just found the issue: The unicode_emoji[ ] attribute was present in the emoji library in 1.7.0 version, not in the latest version, i.e. 2.0, So either you can uninstall the emoji library version 2.0 and install emoji library 1.7.0 version. other solution: please use the function: emoji.emoji_list(string in which the emojis are present) I have created a custom code which gives you a list of all the emojis in df['message'], you can use that too: import emoji #the goal is to create a string to be put in the function emoji.emoji_list(string) words=[] for messages in df['message']: words.extend(messages.split()) #now we have a list which contains all the words in df['message'] of dataframe #now the goal is to convert it into a string mystr="" for x in words: mystr=mystr + " "+ x mystr #now we have to put this string into the emoji function myemoji=emoji.emoji_list(mystr) #myemoji is a list with the following type of elements #[{'match_start': 5712, 'match_end': 5714, 'emoji': '👍🏻'}, #{'match_start': 6896, 'match_end': 6897, 'emoji': '👆'}, #{'match_start': 6897, 'match_end': 6898, 'emoji': '👆'}, #{'match_start': 8097, 'match_end': 8098, 'emoji': '👆'}] #now we have to extract each emoji from this type of list pre_final_emoji_list=[] for i in range(len(myemoji)): pre_final_emoji_list.extend(myemoji[i]['emoji']) #now we have another list which contains all the emojis but it also contains some extra emojis which need to be removed #we create two new list, one where removal characters are present and another one where final emojis are. emojis_to_be_removed=['','🏻'] final_emoji_list=[] for items in pre_final_emoji_list: if items not in emojis_to_be_removed: final_emoji_list.append(items) final_emoji_list Please copy paste the code and use the final_emoji_list as an input to the counter function. In one of my chats this was the result of the above code: ['👍', '👆', '👆', '👆', '👆', '👆', '👆', '👍', '👍', '😊', '👍', '😊', '👏', '🎊', '🎉', '👍', '👍', '👍', '👏', '👏', '👆', '👆', '✅', '✅', '✅', '✅', '👆', '✅', '✅', '✅', '✅', '👇', '👇', '👇', '👇', '👇', '👇', '👇', '👆', '♥', '✨', '💘', '♥', '🌸', '👍', '💐', '💐', '💐', '💐', '⏳', '🕐', '🥇', '💐', '💐', '⏳', '🕐', '🥇', '🥇', '👍', '💃', '🎤', '🎼', '⏰'] Note: I am still a noobie, so my code may not be efficient, and has many 'for' loops, but it is easy to understand, also i have placed various #readables in the code for you top easily understand this. Regards.

[@raj-nq8ke]

very good. really very good.

[@humnaab887]

the split function with that pattern is not working and it did not split the message.Kindly update the pattern

[@davinskyCopperfield]

in the number of media part what could be the code for ios whatsapp since the format is different from android num_media_messages = df[df['message'] == ' '].shape[0] i am getting issue here

[@technoscience2229]

same problem

[@prasadbhandarkar7757]

Sir please upload it in better quality 🙏

[@campusx-official]

It will improve after some time. KZbin takes some time to process the HD version

[@prasadbhandarkar7757]

@@campusx-official okk sir and thank you so much for this amazing project series

[@readymadehouse1133]

Sir I don't know why it's show only frame on website not all data

[@mankeeratsinghsidhu3952]

that was absolutely insane like woah

[@angle2493]

Is these nlp project?

[@increasinglevel5013]

It's a great project but can it some optimization just like background, analysis area...

[@increasinglevel5013]

And please if you can share or make video on it's customisation

[@SaandhilAgarwal]

how do i get the whattsapp chats used by sir in the video dataset files?

[@deepnarayanbhagat9126]

Stop words ka link de dijye uss mahan bande ka...plz

[@kshitijmeshram9073]

can anyone share the regular expression here

[@sanjanasanju2449]

Which algorithm is used here???

[@priyanshuashar6479]

Date time is not showing am and pm...in my data column

[@ashekmahady4929]

Who will be the target market for this product?

[@zichi9570]

ig there is not target market for this project. Its just for learning purpose.

[@DivyaniDawar-t4e]

module 'emoji' has no attribute 'UNICODE_EMOJI' ..someone please help

[@jnnki]

I am getting the same problem 😅,may anyone help on this point

[@avadeshsingh3533]

​@@jnnkiinstall version 1.2.0 run pip install emoji==1.2.0 in pycharm terminal

[@TahirKhan-id3dc]

This project working or not bro

[@pratikshagangane3252]

Instead of UNICODE_EMOJI['en'] write EMOJI_DATA

[@ashutoshdas7417]

Can anyone help ...im unable to remove padded zeroes from date and month how can it be done ...??

[@shinigamishow1702]

'emoji' has no attribute 'UNICODE_EMOJI' this error came after i deployed in Heroku... while working in local host there wasn't any issue

[@nikhilpoojary287]

Instead of UNICODE_EMOJI['en'] try to use EMOJI_DATA

[@akshatkharema1569]

Thanks

[@anupammishra994]

Hi bro, just found the issue: Please read the full solution, its a bit long, but you can still copy paste the code. The unicode_emoji[ ] attribute was present in the emoji library in 1.7.0 version, not in the latest version, i.e. 2.0, So either you can uninstall the emoji library version 2.0 and install emoji library 1.7.0 version. other solution: please use the function: emoji.emoji_list(string in which the emojis are present) I have created a custom code which gives you a list of all the emojis in df['message'], you can use that too: import emoji #the goal is to create a string to be put in the function emoji.emoji_list(string) words=[] for messages in df['message']: words.extend(messages.split()) #now we have a list which contains all the words in df['message'] of dataframe #now the goal is to convert it into a string mystr="" for x in words: mystr=mystr + " "+ x mystr #now we have to put this string into the emoji function myemoji=emoji.emoji_list(mystr) #myemoji is a list with the following type of elements #[{'match_start': 5712, 'match_end': 5714, 'emoji': '👍🏻'}, #{'match_start': 6896, 'match_end': 6897, 'emoji': '👆'}, #{'match_start': 6897, 'match_end': 6898, 'emoji': '👆'}, #{'match_start': 8097, 'match_end': 8098, 'emoji': '👆'}] #now we have to extract each emoji from this type of list pre_final_emoji_list=[] for i in range(len(myemoji)): pre_final_emoji_list.extend(myemoji[i]['emoji']) #now we have another list which contains all the emojis but it also contains some extra emojis which need to be removed #we create two new list, one where removal characters are present and another one where final emojis are. emojis_to_be_removed=['','🏻'] final_emoji_list=[] for items in pre_final_emoji_list: if items not in emojis_to_be_removed: final_emoji_list.append(items) final_emoji_list Please copy paste the code and use the final_emoji_list as an input to the counter function. In one of my chats this was the result of the above code: ['👍', '👆', '👆', '👆', '👆', '👆', '👆', '👍', '👍', '😊', '👍', '😊', '👏', '🎊', '🎉', '👍', '👍', '👍', '👏', '👏', '👆', '👆', '✅', '✅', '✅', '✅', '👆', '✅', '✅', '✅', '✅', '👇', '👇', '👇', '👇', '👇', '👇', '👇', '👆', '♥', '✨', '💘', '♥', '🌸', '👍', '💐', '💐', '💐', '💐', '⏳', '🕐', '🥇', '💐', '💐', '⏳', '🕐', '🥇', '🥇', '👍', '💃', '🎤', '🎼', '⏰'] Note: I am still a noobie, so my code may not be efficient, and has many 'for' loops, but it is easy to understand, also i have placed various #readables in the code for you top easily understand this. Regards.

[@SayaliTawade-v2i]

@@nikhilpoojary287 thanks!

[@madhurabhalke2344]

What if we have not saved the contact numbers in the users list... Will it still work??

[@harshitporwaliitb5268]

Why to upload on heroku?

[@edlabadkarsameer]

edit the requirements.txt of git pip install emoji==1.7.0

[@ShivamSharma-if1oh]

Sir I'm trying to replicate the whatsapp chat analyser project But list mai sare messages store hi ni ho pare..

[@mandyuniverse5090]

How to deploy now?

[@y.xo2times]

Sir how you use 2 basic interpreter in pycharm (I'm beginner) Plz help

[@amanprajapati0112]

time data '12/10/20, 6:05 PM - ' does not match format '%d/%m/%y, %H:%M - ' (match) yha pr AM/PM ki jgh kya lagayege

[@anupammishra994]

try this: df['dates']=pd.to_datetime(df['dates'], format='%d/%m/%y, %H:%M - ') if it still doesn't work, replace %y with %Y

[@ms_007_]

​@@anupammishra994 Thank