Python Chat Bot Tutorial - Chatbot with Deep Learning (Part 2)

[@TechWithTim]

All of the code available on techwithtim.net! techwithtim.net/tutorials/ai-chatbot/part-2/

[@nabihassan7576]

Traceback (most recent call last): File "main.py", line 51, in output_row[labels.index(docs_y[x])] = 1 IndexError: list index out of range How do i fix this error. Pls help btw love your videos

[@jemimahsioson4351]

@@nabihassan7576 Hi , I seem to have a similar problem, did you find a way to fix the error?

[@khaleda.s761]

Tim isn't great at explaining, but I really appreciate his tutorials since they're straight to the point

[@Innoox]

line 37: out_empty = [0 for _ in range(len(classes))] #should be: out_empty = [0 for _ in range(len(labels))] line 57: output = numpy.array(output) #or change import numpy as np line 56: trainig = np.array(trainig) line 57: output = np.array(output)

[@tasktoday9892]

Thank you so much!!

[@bfkmnemonic]

Can't wait for it to be done.. I really need someone to talk to!

[@TechWithTim]

Haha

[@bfkmnemonic]

@@TechWithTim Seriously though. Thank you. These are great videos.

[@rmt3589]

@@bfkmnemonic That's why I'm here!

[@dr.mikeybee]

Good job. Some of the code is very dense; so that makes it a bit more difficult to learn the important topics like bag of word. If you do some of the single line statements as multiline loops, rather than enumerations, it would make things more easily understandable for more levels of programmers. It's hard to teach a lot of people if you don't simplify where you can. Nevertheless, I appreciate your direct style. You get to the point quickly.

[@everything8095]

Great. You make the things clear very well.

[@nikhilambavaram6006]

Thank you, Tim for making these awesome videos! I have learned so much!

[@josueal.1]

Has anyone considered using a python dictionary to store our "docs_x" and "docs_y"? A dictionary feels like a more intuitive data structure. In essence, we can search the patterns using the tags as keys.

[@funy0n583]

so is an encoded bag of words kind of like a hash in which different patterns will always output a different encoded bag of words

[@deepakrathi5160]

Resource punkt not found. Please use the NLTK Downloader to obtain the resource: what's this error?

[@nstcg7271]

stem() missing 1 required positional argument: 'word' did anyone had the same error?

[@sahilahuja6574]

stemmer = LancasterStemmer() add the brackets after LancasterStemmer, they were not added in the video I guess.....

[@shweta8492]

@@sahilahuja6574 thanks 😊

[@channeljukebox4539]

Amazing tutorial. Thanks bro. Can you make some tutorial on RASA as well? Thanks in advance.

[@tonytoeknee3192]

Why did you use the LancasterStemmer?

[@TRIPDoesItAll]

hi, amazing tutorial.i have one question, if i wanted my bot to be able to recognize synonyms using wordnet's sysnsets, how would i implement that?

[@hemanko007]

on line 37 what is classes where did he declare it?

[@parthyadav3177]

replace out_empty=[0 for _ in range(len(classes))] with out_empty=[0 for _ in range(len(labels))] and output=np.array(output) with output=numpy.array(output)

[@naveenagrawal_nice]

hey tim, it is asked by another user but you haven't answered it so i am asking again please reply asap for x, doc in enumerate(docs_x): bag = [] wrds = [stemmer.stem(w.lower()) for w in doc] isn't that part wrong? We get a sentence for doc in each loop. Then we put doc in a loop. Problem occurs here. w gets letter in each loop and stem of letter is the same as letter. But we want w gets a word and wrds will be stem of words.

[@eugenechua7239]

just a quick question..i still dont quite get the part when he did output_row[abels.index(doc_y[x])]=1. what is the doc_y[x] trying to accomplish? converting the tags to 1?

[@renanmoura2125]

normalizing all the vector, where the maximun value ll be 1 on every sample analised by ia

[@dilanurkok5316]

in my code when i write "output = np.array(output)" i got "Undefined variable 'np'" errror. can you help me ?

[@secretr5024]

I get an error with tensor flow saying cudart is not found My version of tensorflow is 2.6.2 can you help me?

[@lightningtechnologie7730]

Amazing 🌸❤

[@basketballgirl023]

What is the difference between the words list and wrds? Seems like both are list of words from pattern. If so how does the for w in words if w in wrds: to get the 0 and 1 work? Wouldn’t all be one because they are the same list. Super basic question would really appreciate a response!!! Mine is working but I don’t get the logic :(

[@kudurukk]

Thanks a lot!

[@masonqian6964]

Hey Tim, great series. I had a question about the enumeration loop specifically. Does it matter that duplicates aren't being addressed? Within a pattern the same word might be seen more than once ie: "THE weather today is THE hottest it has been", and the conditional "if w in wrds" would evaluate twice and append twice. Also is the one hot encoding model for a bag of words appropriate for a more complex chatbot? How much data does it handle well? Edit: I think it might have implications in this line as well: "output_row[labels.index(docs_y[x])] = 1" since .index() will only return the index of the first occurrence.

[@classic5307]

What software has used to code .py and .json files

[@naren1561]

please tell me what font do you use ??

[@ticosanjr]

nice work

[@samuelmartins9470]

File "/home/samuel/anaconda3/envs/aubrey/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1063, in _run raise RuntimeError('Attempted to use a closed Session.') RuntimeError: Attempted to use a closed Session. errors galore. can anyone help? I can't go editing a module I don't fully understand

[@mengyingliu5097]

I have the same error have you fixed it yet?

[@samuelmartins9470]

@@mengyingliu5097 not yet but i will let you know once i get it fixed. been a little occupied

[@haswanthaekula7656]

Why should not we shuffle our data? I did not get that part. It would be great if you can explain that. Thanks

[@Γιάννηςγγλέζος]

When i am running the code the is a ValueError: ['tag'] is not in list. Does anyone have any idea why is this happening??

[@adriansamper2547]

Hello Tim! Hey, thanks a lot for your series, have been very helpful. I’m watching this series and I got a question.. Why before this line the phrase is not tokenized? wrds = [stemmer.stem(w.lower()) for w in doc] Because from the phrase “posting error” I get ['p', 'o', 's', 't', 'i', 'n', 'g', ' ', 'e', 'r', 'r', 'o', 'r'] Is that correct? I mean, in this line shouldn’t be compared words and not characters?

[@Tom-kg6qe]

Your word classifier is very similar to the Pandas.Get_Dummies function, except I'm not sure that it would take into account the labels part...

[@osama0061]

Why did you use enumerate function?

[@nishantgarg6141]

Best video ever

[@tharuntejreddythodimi2142]

How can we train our model to respond to the dynamic values

[@harlequinsamoranos8210]

What kind of algorithm are you using bro?

[@siddhartamahanta8275]

TypeError: _append_dispatcher() missing 1 required positional argument: 'values' please help with this

[@ifredpingplay468]

line number or something please :)

[@gauravsarawgi6727]

Traceback (most recent call last): File "C:\Users\admin\PycharmProjects\my\main.py", line 31, in words = [stemmer.stem(w.lower()) for w in words if w not in "?"] File "C:\Users\admin\PycharmProjects\my\main.py", line 31, in words = [stemmer.stem(w.lower()) for w in words if w not in "?"] TypeError: stem() missing 1 required positional argument: 'word' help pls

[@ahmedqoreichi5468]

hi i am new to python when i tried to do like your code i had this error from google.protobuf.pyext import _message ImportError: DLL load failed: The specified procedure could not be found. can you help please.

[@Adi02]

I had the same problem still haven't found the solution

[@nstcg7271]

@@Adi02 me too

[@sainco3036]

Thanks.

[@imtiazahmad7826]

nice video

[@vsp540]

u dont have enough likes dude

[@hemanko007]

Can someone tell me how to embedd this in wabpage

[@philip3278]

Can you also make this project in one file?

[@uliveulearnandregret]

imma include all 58,000 words in the english language document but only in lower case

[@nikhilkashyap8701]

I m getting scipy not supported error

[@l4w676]

I like the how you act while looking your 2nd screen and pretending like you are not sure about the code lol. Well it's a year old tut. so I hope you are improved yourself.

[@hrirks]

yeah i noticed because he wrote numpy.array and np.array without importing numpy , lol

[@EliasNilssonComposer]

You are probably a very good coder, but you really need to explain what you are doing, not just write down what is in your "script file". I have no clue what is going on which is not very satisfying. "Then we write this, then we write this..." Yes okay, but WHY?

[@sitthiphongprompalit4977]

Can I add a Json tag file?

[@tarunsankhla2328]

I'm getting error in classes

[@rahhulkumardas]

Type labels instead of classes

[@asilkanvar7199]

he made a mistake by writing classes instead of labels at there.

[@ewaldsteven]

why not just import numpy as np? you know you want to... ;)

[@ma3ty109]

Please, continue the pygames tutorial!!!

[@TechWithTim]

I have a ton !

[@owaiseimdad6640]

It's showing me FileNotFoundError = tensorflow.contrib

[@SoumyadevRoy]

Are you using tensorflow 2.0? Downgrade to 1.14.

[@owaiseimdad6640]

@@SoumyadevRoy and how can I do that??

[@owaiseimdad6640]

@@SoumyadevRoy it is Pip install tensorflow 1.16?

[@hansimglueck4026]

use pipenv. Pipenv install tensorflow==1.15.0

[@therainbird9189]

I keep getting errors when I try to skip ahead of you XP

[@RahulBarman15]

did not understand the output_row lines the rest was well explained

[@samhebda5388]

fuck I started too many different tutorials xP

[@Zirno_]

Your var naming doesn't make sense at all

[@priyamprasad624]

nah man, you are not explaining a damn thing. you are just writing on your own by seeing side ways.

[@yearlight-p2y]

It would be better if you used some legible names for the variables. This was the most confusing tutorial of yours that I watched so far!!