Hi Siddhardhan It's a really really nice lecture. Very considerate and detailed, explaining everything the learners need / want to know! Happy new year to you!
Love your videos man, you have a great way of explaining your code and the concepts. I wanted to ask 2 questions; firstly, does it make sense to add the array of clusters back to the original dataframe so you can identify which customers the clusters represent? It would make graphing the clusters easier and also allow you to optimize hyperparameters without needing to retype the code. Secondly, can you do videos on deploying models? I couldn't find any good videos of that. - Thanks a lot!
This one was superbly explained, especially the difficult to understand syntax of .iloc[ ] and one in the scatter plot too. Also I'm a huge fan of Data Visualisation, absolutely love it. I had a question: how can we plot a similar scatterplot using Seaborn? Could you please show it in one of the future Unsupervised Learning project videos? As always, thanks a lot!🙌🏻
Can i use this in my resume and linked in profile .. If i use what are the hashtags and conditions to be followed..By the way you are supporting pillar to all upcomers for candidates like me.. thank you
hi! i don't demand any citation and credit. Just understand the project completely before putting it in your resume, so that you can answer the questions related to this project asked by the interviewer.
your lecture series very good for understating and nicely explain, i request to you please increase the font size or increase the screen size. t very small font so its difficult to read. thanks sir . please continue....
thanks for video. For clustering problem we no need to split data into train and test set? we are not used other features variables.. if in dataset having more columns then also we can use few columns?
we generally don't split the data for K-Means. if we want to predict new Values, we may need to split it. it depends... and yes, if we have more suitable columns, we would use them. let's say that there are 3 features. in that case, we would make a 3d scatter plot.
Sir here you are comparing annual income and spending score here. If i want to compare all the attributes ( age, gender, annual income)vs spending score how to proceed sir? Can I get the code for that?
hi! I explained it in a short way while implementing the model. you can check that out. I'll make a detailed video on this later while discussing about ML models. it's hard to explain it in the comments.
I am confused, what if we have more than 2 features/columns,, then while plotting clusters,, then x[y_pred=0, 0] is for 1st cluster and 1st colum on x-axis,, then what about more than 2 columns while plots? I hope you would reply this comment and solve my confusion😢😢😢
What are the shortcomings in this project? Are there any areas of improvement in this project and what are they? Can you please suggest how can we make this project even better?
Hello Brother. I'm going through all your Machine Learning playlist. I could find videos for Supervised Learning algorithms from Intuition, math behind it and building models from scratch. But I couldn't find the same for Unsupervised Learning algorithms brother. If there are videos regarding Unsupervised Learning algorithms from scratch. Could you please share the link here? Or else could you please do videos on Unsupervised Learning from Scratch, because that would be a great use to us bro. Could you please do videos on Unsupervised Learning too?
Hi! Thanks for the content. Really appreciate your work. Can you do a video on ML project personality Prediction system by analyzing CVs? It would be really helpful.
hi! thanks for your positive words! I am using dell g5. i won't recommend it for Deep Learning. you can watch this video of Siraj Raval. He has explained which laptop is best for ML: ruclips.net/video/dtFZrFKMiPI/видео.html
it's because I wanted to create a 2 dimensional cluster. and annual income is a good parameter to choose from. of course, you can consider more parameters as well.
plt.scatter(clustering_data[y_pred==0,0],clustering_data[y_pred==0,1],s=50, c='green',label="cluster 1") plt.scatter(clustering_data[y_pred==1,0],clustering_data[y_pred==1,1],s=50, c='red',label="cluster 2") plt.scatter(clustering_data[y_pred==2,0],clustering_data[y_pred==2,1],s=50, c='blue',label="cluster 3") this code is showing an error sir. can you fix it? this is the error: TypeError Traceback (most recent call last) ~\anaconda3\lib\site-packages\pandas\core\indexes\base.py in get_loc(self, key, method, tolerance) 3628 try: -> 3629 return self._engine.get_loc(casted_key) 3630 except KeyError as err: ~\anaconda3\lib\site-packages\pandas\_libs\index.pyx in pandas._libs.index.IndexEngine.get_loc() ~\anaconda3\lib\site-packages\pandas\_libs\index.pyx in pandas._libs.index.IndexEngine.get_loc() TypeError: '(array([False, False, False, ..., False, True, False]), 0)' is an invalid key During handling of the above exception, another exception occurred: InvalidIndexError Traceback (most recent call last) ~\AppData\Local\Temp\ipykernel_17080\3756939222.py in 1 ## plotting all the clusters and their centriods: 2 plt.figure(figsize=(12,6)) ----> 3 plt.scatter(X[y==0,0],X[y==0,1],s=50, c='green',label="cluster 1") 4 plt.scatter(X[y==1,0],X[y==1,1],s=50, c='red',label="cluster 2") 5 plt.scatter(X[y==2,0],X[y==2,1],s=50, c='blue',label="cluster 3") ~\anaconda3\lib\site-packages\pandas\core\frame.py in __getitem__(self, key) 3503 if self.columns.nlevels > 1: 3504 return self._getitem_multilevel(key) -> 3505 indexer = self.columns.get_loc(key) 3506 if is_integer(indexer): 3507 indexer = [indexer] ~\anaconda3\lib\site-packages\pandas\core\indexes\base.py in get_loc(self, key, method, tolerance) 3634 # InvalidIndexError. Otherwise we fall through and re-raise 3635 # the TypeError. -> 3636 self._check_indexing_error(key) 3637 raise 3638 ~\anaconda3\lib\site-packages\pandas\core\indexes\base.py in _check_indexing_error(self, key) 5649 # if key is not a scalar, directly raise an error (the code below 5650 # would convert to numpy arrays and raise later any way) - GH29926 -> 5651 raise InvalidIndexError(key) 5652 5653 @cache_readonly InvalidIndexError: (array([False, False, False, ..., False, True, False]), 0)
Massive respect mate!!! Thanks for sharing your knowledge
easy understanding about the k mean clustering
Really good ! If you could provide in future an example of segmentation for a B2B business , it would be great. Thanks !
You are an absolute savior
thanks 😊
Clear explanation 👍
Thank you 🙂
Really Amazing!
I watched many videos but none of them has better explanation than yours. Great job!!
Thanks a ton, brother 😇
Thank you sir. You are doing great work.
You just solved a problem. Thank you for sharing this.
Awesome video 💯💯...understood each and every line you said....just wonderful.....keep going...all the best 👍
Hi Siddhardhan
It's a really really nice lecture. Very considerate and detailed, explaining everything the learners need / want to know!
Happy new year to you!
Thanks a ton! Happy New year!
Love your videos man, you have a great way of explaining your code and the concepts.
I wanted to ask 2 questions; firstly, does it make sense to add the array of clusters back to the original dataframe so you can identify which customers the clusters represent? It would make graphing the clusters easier and also allow you to optimize hyperparameters without needing to retype the code.
Secondly, can you do videos on deploying models? I couldn't find any good videos of that. - Thanks a lot!
bro your videos are helping very much pls continue bro..and attach handwritten material it will help a lot
Hi! Thanks for your positive words 😇 I'll see what I can do about the notes
Sooo helpful.
You gave explanation precisely with points.
Thank you so much 👍🏻
Thank u for making such good videos. PLease keep making more videos on different projects of other unsupervised learning models.
Thanks
Like Your method to teach basics alongwith advance topics.
Appreciate
Awesome tutorial! Amazing and clear explanation.
Thanks for your amazing content❤🎉.
This one was superbly explained, especially the difficult to understand syntax of .iloc[ ] and one in the scatter plot too. Also I'm a huge fan of Data Visualisation, absolutely love it.
I had a question: how can we plot a similar scatterplot using Seaborn? Could you please show it in one of the future Unsupervised Learning project videos?
As always, thanks a lot!🙌🏻
sure! will do that. use sns.scatterplot( )
@@Siddhardhan are all the arguments the same?
Can i use this in my resume and linked in profile .. If i use what are the hashtags and conditions to be followed..By the way you are supporting pillar to all upcomers for candidates like me.. thank you
hi! i don't demand any citation and credit. Just understand the project completely before putting it in your resume, so that you can answer the questions related to this project asked by the interviewer.
@@Siddhardhan thank you so much
So nice explanation
Super video and good explanation
What is the accuracy
Thanks . This one really helped
Only one doubt ,how canwe display the clustered dataitems in tabular form instead of scatter plot?
Why we did not check for Outliers ?
Highly helpful. Awesome explanation !!
Glad to hear that!😇
excellent video and explanation too. Thank you so much and definitely will watch the rest of the videos.
Sir i can't understand where in the entire code the centroid are being calculated before finding out the WCSS from the data set ?? please explain
your lecture series very good for understating and nicely explain, i request to you please increase the font size or increase the screen size. t very small font so its difficult to read. thanks sir . please continue....
sure! will look into it.
Hello Siddhardhan, How many dataset r u taking for Training and Testing?
Do i need to scale independent variables before clustering?
finished watching
Thank you so much man you really helped me a lot.
sir i got an error while plotting elbow graph
it was showing that X and Y should be in same dimension!!
pl suggest what to do!!!
I have a doubt... here for plotting the clusters we used 2 data in x array... but what if i have more than 2 features? plz suggest
Your work was awesome and really appreciated sir.
Thanks a ton😇
@@Siddhardhan sir in this project I can't understand KMeans syntax sir. (Video is blur sir)
@@Siddhardhan sir in this project I can't understand KMeans syntax sir. (Video is blur sir)
i hope you make a project for image segmentation using k-means clustering algorithm .Thank you for all the projects done
It's really helpful to me...
my pleasure 😇
Is there any video explaining the theory of k-means clustering? I would like to watch that but couldn't find in your playlist.
thanks for video.
For clustering problem we no need to split data into train and test set?
we are not used other features variables.. if in dataset having more columns then also we can use few columns?
we generally don't split the data for K-Means. if we want to predict new Values, we may need to split it. it depends...
and yes, if we have more suitable columns, we would use them. let's say that there are 3 features. in that case, we would make a 3d scatter plot.
Sir here you are comparing annual income and spending score here. If i want to compare all the attributes ( age, gender, annual income)vs spending score how to proceed sir? Can I get the code for that?
hi! I don't have the code for it at the moment. you can consider multiple dimensions. but you may not get proper clusters.
can we use only one column i.e based on spending score?
Please show the silhouette score for unsupervised learning!
Hi bro glad to see but waiting for neural network video
hi! those will be covered in deep learning course.
Sir if we had more than two featured columns in k means clustering then how will we plot the clusters in multi dimension like 4d 5d?
Mr Siddhardhan can u do a project on Handwritten Digits recognition with convolution neural networks.
can u explain how the centroids are placed in the graph and how the labels like 0,1,2,3,4 is assigned to data points
hi! I explained it in a short way while implementing the model. you can check that out. I'll make a detailed video on this later while discussing about ML models. it's hard to explain it in the comments.
bro also upload a video on EDA and its DTALE tool
I'll try to include that in future courses
How to use KMeans for more than 2 features?
Thank you very much
I am confused, what if we have more than 2 features/columns,, then while plotting clusters,, then x[y_pred=0, 0] is for 1st cluster and 1st colum on x-axis,, then what about more than 2 columns while plots? I hope you would reply this comment and solve my confusion😢😢😢
What are the shortcomings in this project? Are there any areas of improvement in this project and what are they? Can you please suggest how can we make this project even better?
hi! you can do some model optimization. after that you can work on deployment.
Brilliant....thanks
You're welcome!😇
how to get accuracy in unsupervised learning?
Bro what are the pros and cons that made you to do this project
Thanks for uploading this video. Can you please upload a video on how this customer segmentation works in any domain with end to end implementation?
hi! I am planning to make videos on deployment after ML and DL course.
Sir can we keep these projects in our resume
Thanks
Hi, how can we visualize the clusters it via tsne?
hi! you can go through this documentation: scikit-learn.org/stable/modules/generated/sklearn.manifold.TSNE.html
Please post the vedio about DBSCAN projects bro
Can we download the clustered file with Names,Ages?? if yes can you explain
I don't get you. can you please elaborate
Thanks a lot.
Feature scaling karna hoga..
amazing!
Hello Brother. I'm going through all your Machine Learning playlist. I could find videos for Supervised Learning algorithms from Intuition, math behind it and building models from scratch. But I couldn't find the same for Unsupervised Learning algorithms brother. If there are videos regarding Unsupervised Learning algorithms from scratch. Could you please share the link here? Or else could you please do videos on Unsupervised Learning from Scratch, because that would be a great use to us bro. Could you please do videos on Unsupervised Learning too?
What are you using Pandas or Jupiter?
google colaboratory
Why didn't you run 10th shell?
That was awesome video bro. Can you teach us like where to start and basics of Python. Like from the scratch to learn. thanks in advance
hi! you can learn from this playlist: ruclips.net/p/PLfFghEzKVmjsNtIRwErklMAN8nJmebB0I
it is from basics and also contains python basics.
Bro do you have any report based on this project or any research Paper on this project?
hi! I don't make reports for my project videos
@@Siddhardhan Bro Can you send your email so that I can contact with you?
Hi! Thanks for the content. Really appreciate your work.
Can you do a video on ML project personality Prediction system by analyzing CVs?
It would be really helpful.
can i run the same code in ides like vs code??
yes, u can
@@Siddhardhan can i link a csv file from drive directly to this code with its url??
Doing a great job man! Can you suggest me a nice laptop for building complex ML and DL projects? Which laptop are you using?
hi! thanks for your positive words! I am using dell g5. i won't recommend it for Deep Learning. you can watch this video of Siraj Raval. He has explained which laptop is best for ML: ruclips.net/video/dtFZrFKMiPI/видео.html
Thanks for your video sir.Would you pls share the dataset and source code 🙏
Sir please start one series(theory + projects) of Deep learning like ML... We are waiting...
hi! I'll make DL course separately after completing ML
Nice one really helpful!! Can you do anything on student performance predictions using machine learning ??
hi! I'll include it in my curriculum
what is the main object of this project
Sir please tell clear explanation of spending scores ?
Spending score means what?
higher score means that a person is spending more money to buy more products.
Thanks a lot !
Hey bro - do you teach? Ready to get classes
hi! I am mainly focusing on teaching in RUclips. at the moment, I am not giving individual tutoring.
But this data is labeled right?
Code to find accuracy for the model
Why you are considering only the last two columns? you have to consider all the columns as gender and age play a role as well.
it's because I wanted to create a 2 dimensional cluster. and annual income is a good parameter to choose from. of course, you can consider more parameters as well.
What video can we expect on Monday
Monday & Wednesday ML Course videos will be posted. this Monday, video will be on vectors & vector operations..
plt.scatter(clustering_data[y_pred==0,0],clustering_data[y_pred==0,1],s=50, c='green',label="cluster 1")
plt.scatter(clustering_data[y_pred==1,0],clustering_data[y_pred==1,1],s=50, c='red',label="cluster 2")
plt.scatter(clustering_data[y_pred==2,0],clustering_data[y_pred==2,1],s=50, c='blue',label="cluster 3")
this code is showing an error sir. can you fix it?
this is the error:
TypeError Traceback (most recent call last)
~\anaconda3\lib\site-packages\pandas\core\indexes\base.py in get_loc(self, key, method, tolerance)
3628 try:
-> 3629 return self._engine.get_loc(casted_key)
3630 except KeyError as err:
~\anaconda3\lib\site-packages\pandas\_libs\index.pyx in pandas._libs.index.IndexEngine.get_loc()
~\anaconda3\lib\site-packages\pandas\_libs\index.pyx in pandas._libs.index.IndexEngine.get_loc()
TypeError: '(array([False, False, False, ..., False, True, False]), 0)' is an invalid key
During handling of the above exception, another exception occurred:
InvalidIndexError Traceback (most recent call last)
~\AppData\Local\Temp\ipykernel_17080\3756939222.py in
1 ## plotting all the clusters and their centriods:
2 plt.figure(figsize=(12,6))
----> 3 plt.scatter(X[y==0,0],X[y==0,1],s=50, c='green',label="cluster 1")
4 plt.scatter(X[y==1,0],X[y==1,1],s=50, c='red',label="cluster 2")
5 plt.scatter(X[y==2,0],X[y==2,1],s=50, c='blue',label="cluster 3")
~\anaconda3\lib\site-packages\pandas\core\frame.py in __getitem__(self, key)
3503 if self.columns.nlevels > 1:
3504 return self._getitem_multilevel(key)
-> 3505 indexer = self.columns.get_loc(key)
3506 if is_integer(indexer):
3507 indexer = [indexer]
~\anaconda3\lib\site-packages\pandas\core\indexes\base.py in get_loc(self, key, method, tolerance)
3634 # InvalidIndexError. Otherwise we fall through and re-raise
3635 # the TypeError.
-> 3636 self._check_indexing_error(key)
3637 raise
3638
~\anaconda3\lib\site-packages\pandas\core\indexes\base.py in _check_indexing_error(self, key)
5649 # if key is not a scalar, directly raise an error (the code below
5650 # would convert to numpy arrays and raise later any way) - GH29926
-> 5651 raise InvalidIndexError(key)
5652
5653 @cache_readonly
InvalidIndexError: (array([False, False, False, ..., False, True, False]), 0)
Can you do a live session explaining ML projects?
hi! I haven't thought about it. I'll definitely consider that.
May I know your github account?
kindly upload subtitle also
I'll include auto subtitles
finished coding
Hindi subtitles 😅😅😅
Thank you very much