"🔥Caltech Post Graduate Program In AI And Machine Learning - www.simplilearn.com/artificial-intelligence-masters-program-training-course?HKqjENq9OU&Comments&TH-cam 🔥IITK - Professional Certificate Course in Generative AI and Machine Learning (India Only) - www.simplilearn.com/iitk-professional-certificate-course-ai-machine-learning?HKqjENq9OU&Comments&TH-cam 🔥Purdue - Post Graduate Program in AI and Machine Learning - www.simplilearn.com/pgp-ai-machine-learning-certification-training-course?HKqjENq9OU&Comments&TH-cam 🔥IITG - Professional Certificate Program in Generative AI and Machine Learning (India Only) - www.simplilearn.com/iitg-generative-ai-machine-learning-program?HKqjENq9OU&Comments&TH-cam 🔥Caltech - AI & Machine Learning Bootcamp (US Only) - www.simplilearn.com/ai-machine-learning-bootcamp?HKqjENq9OU&Comments&TH-cam"
My professor took 1 hour to clear the basic concepts of KNN but I was unable to understand. Thanks for clearing my concepts in just under 15 minutes. Thanks a lot. Really appreciated. I am going to subscribe your channel. Thanks once again.
Thank you for the appreciation. You can check our videos related to various technologies and subscribe to our channel to stay updated with all the trending technologies.
Thank you for the appreciation. You can check our videos related to various technologies and subscribe to our channel to stay updated with all the trending technologies.
This is an amazing video! I am trying to help my niece and have never read anything about KNN in my life but the way this video explains it is simply awesome! So thankful to you for creating this video as it would help thousands of students and those family members that want to help them learn properly. Do not understand why some professors can't seem to explain it so simply as you have! God bless you man!
WooHoo! We are so happy you love our videos. Please do keep checking back in. We put up new videos every week on all your favorite topics. Whenever you have the time, you must also check out our blog page @simplilearn.com and tell us what you think. Have a good day!
you put it better than I did. I have been struggling to understand what KNN means. Had over 6 lecturers mentioning it in the class but it still sounded vague. But he just made my day with this video.
Thank you for choosing us as your learning partner. We are thrilled to hear that you enjoyed your experience with us! If you are looking to expand your knowledge further, we invite you to explore our other courses in the description box.
Thank you for sharing this video it was very clear in detailed manner with example. But I have a doubt in whether I to should take squareroot of n (n = Sum of Output of Distance Function) for calculating K. 5:11 (Choosing K) 8:55 (Choosing K=3)
I'm totally new to any machine learning or programming stuff, and tbh I was super scared about learning -'K-NN algorithm' because the word 'algorithm' already sounded scary enough. However, your analogy of "Cats or dogs" and "claws and ears" REALLY MADE A LOT OF SENSE! If I have to lecture my own class about machine learning someday for other beginners, I think your "cat and dog" analogy of explanation cannot be more simpler. Thanks for the great video!
20:32 Correction - standard scaler does not restrict the range of data between -1 to +1 . It converts the data to a mean of 0 and standard deviation of 1 . So if u take the mean of a standardised column ul find it equals 0. It basically skews the data to a smaller range and makes it comparable with other variables with different magnitudes which otherwise would not have been comparable. Min-max scaler (normalisation) restricts the data between 0 to +1.
We are glad you found our video helpful. Like and share our video with your peers and also do not forget to subscribe to our channel for not missing video updates. We will be coming up with more such videos. Cheers!
I guess im randomly asking but does any of you know of a trick to log back into an instagram account..? I somehow forgot the account password. I appreciate any help you can offer me
Thanks for a *fantastic* video!!! may I ask - when determining K, why do you do the sqrt of y_test, rather than y_train (or x_train, which is the same length). In the video, it looks like you intended to do that, then for some reason - changed it...
Thanks alot that's very helpful, but when trying to use StandardScaler an error occurs "ValueError: could not convert string to float" i can't solve it , ahat shall i do ? thanks in advance.
i know im late but anyways it occurs because string data cant be standaradized i.e. put into StandardScaler. comvert it to float value try doing this: df[column_name] = df[column_name].astype('float') (i didnt try it myself but it should hopefull solve the issue)
In the field of machine learning and specifically the problem of statistical classification, a confusion matrix, also known as an error matrix, is a specific table layout that allows visualization of the performance of an algorithm, typically a supervised learning one. Hope that helps!
I found this fascinating. Wish machine learning/data analysis was around when I was doing my CS masters degree. Lots of spare time to learn in retirement. Great video, and I loved the Python even more. I’ve always found the correct working code to be the true documentation.
Before replacing the zero's by the mean in the columns you can first test is there is NanN in the data, if there is not you dont need the first line in the for loop I guess, data[column]=data[column].replace(0,NanN).
Hey Abhishek, thank you for appreciating our work. We are glad to have helped. Do check out our other tutorial videos and subscribe to us to stay connected. Cheers :)
Two Questions: 1. How do you embed a KNN model into a real application? 2. If you train a model on scaled data, how do you implement the resulting model to any platform for real use? Thanks,
"Hey, we hope you enjoyed this video! If you want to learn more, you can check out this linl: www.simplilearn.com/tutorials/machine-learning-tutorial/knn-in-python And don't forget to like, share and subscribe to our channel! :)"
Hey, thank you for appreciating our work. We are glad to have helped. Do check out our other tutorial videos and subscribe to us to stay connected. Cheers :)
We are glad you found our video helpful. Like and share our video with your peers and also do not forget to subscribe to our channel for not missing video updates. We will be coming up with more such videos. Cheers!
WooHoo! We are so happy you love our videos. Please do keep checking back in. We put up new videos every week on all your favorite topics. Whenever you have the time, you must also check out our blog page @simplilearn.com and tell us what you think. Have a good day!
Hey Aaron, thank you for appreciating our work. We are glad to have helped. We are happy to receive a new subscriber and we hope you are loving our community. We put up new videos on all important topics, so stay tuned. Cheers!
Hey, thank you for appreciating our work. We are glad to have helped. Do check out our other tutorial videos and subscribe to us to stay connected. Cheers :)
Hey Denis, thank you for appreciating our work. We are glad to have helped. Do check out our other tutorial videos and subscribe to us to stay connected. Cheers :)
Hey Aditya, thank you for appreciating our work. We are glad to have helped. Do check out our other tutorial videos and subscribe to us to stay connected. Cheers :)
Here the p is not that we are predicting person is diabteic or not .. it is used becuase of euclidean distance formula..if we use manhattan, then p will be equal to 1
Wow, your way of explaining and your didactic examples and materials are simply awesome!!. You got a new subscriber. Thank you, and please keep posting your amazing work.
I don't understand the confusion matrix. From what I understand, 94 - (actual) No diabetes 13 - (predicted) Has diabetes 32 - (actual) Has diabetes 15 - (predicted) No diabetes. Why is the matrix arranged like this? Wouldn't it be easier to compare actual vs predicted values for each outcome? Eg. 94 and 15 being in the same row so it translates to 94 people having no diabetes in actuality whereas the model predicted 15 people having no diabetes.
Hi Denise, Confusion matrix has 4 parameters - True positive, True negative, False positive and False negative. There are other metrics that can be derived from a confusion matrix. Watch the video below to learn how confusion matrix in detail: th-cam.com/video/prWyZhcktn4/w-d-xo.html Thank you for watching!
We are glad you found our video helpful, Scott. Like and share our video with your peers and also do not forget to subscribe to our channel for not missing video updates. We will be coming up with more such videos. Cheers!
Hello, thanks for viewing our tutorial. It would be helpful if you will provide your email ID to us so that we can send the requested dataset promptly. On the off chance that you need your email ID to be kept hidden from others, we can do that too. Hope that helps.
Hi, great video thanks for putting it up. I have a question - now we know the model is 80% accurate but how to apply this to the question if someone has diabetes or not? Thats what i want to know how to do. thanks.
Ninteen minutes from this vdieo and this is magnificent love your teaching style keep going with more videos if you are good in math please release linear algrebra or calculs thank you
Hey, thank you for appreciating our work. We are glad to have helped. Do check out our other tutorial videos and subscribe to us to stay connected. Cheers :)
Thank you very much for this informative lecture. May I ask about the Feature Selection? sc_X =StandardScaler() X_train = sc_X.fit_transform(X_train) X_test = sc_X.transform(X_test) When to use fit_transform and transform? Why is it different for the training and testing dataset? Will appreciate your answers. Thank you very much
"fit_transform" applies both a fit (fits the scaler to the dataset) and a transform (transforms the dataset, standardizing it) over the training data. Therefore, once you apply "fit_transform", you can just apply "transform" over the test data. You can check the functions associated with StandardScaler in the following link: scikit-learn.org/stable/modules/generated/sklearn.preprocessing.StandardScaler.html By checking that, I had another related doubt: why not fit the scaler using the whole data (with train and test together)? I mean, it's possible that X_train has values ranging from 1 to 10 while X_test has values ranging from 1 to 20. Wouldn't it mess with the standardization?
Hello, thanks for viewing our tutorial. It would be helpful if you will provide your email ID to us so that we can send the requested dataset promptly. On the off chance that you need your email ID to be kept hidden from others, we can do that too. Hope that helps.
Hi Hari, thanks for watching our video. We have sent the requested dataset to your mail ID. Also, Subscribe to our channel by clicking on the bell icon for never missing another update. Cheers!
Hi Himanshu, thanks for checking out our tutorial. We have sent the requested dataset to your mail ID. Whenever you have the time, you must also check out our blog page @simplilearn.com and tell us what you think. Have a good day!
Hello Antonny, thanks for viewing our tutorial. It would be helpful if you will provide your email ID to us so that we could send the requested dataset promptly. On the off chance that you need your email ID to be kept hidden from others, we can do that also. Hope that helps.
Hello Aisha, thanks for viewing our tutorial and we hope it is helpful. It would be helpful if you will provide your email ID to us so that we could send the requested dataset promptly.
Hi Redamichael, There are multiple methods to improve the accuracy of any model. Some of them are feature engineering, feature selection, algorithm tuning, and ensemble methods.
Hey Vandan, thank you for appreciating our work. We are glad to have helped. Do check out our other tutorial videos and subscribe to us to stay connected. Cheers :)
If a give an input list for the KNN algorithm to predict the classes of each element, How can I print out the list of inputs only belonging to a particular class?
Hi The video is very nice about KNN. I have one question here: to find the optimum k value is it sqrt (y_test) or sqrt (y) sqrt (y_test)? Thanks in advance...
Is there a mistake at 7:54? It must be: (170-167)²-(57-54)². in your formular, the last number is 51... the x value of d1 in the coordinate system is wrong? Im right?
WooHoo! We are so happy you love our videos. Please do keep checking back in. We put up new videos every week on all your favorite topics. Whenever you have the time, you must also check out our blog page @simplilearn.com and tell us what you think. Have a good day!
Hello Jai, thanks for viewing our tutorial. It would be helpful if you will provide your email ID to us so that we could send the requested dataset promptly. On the off chance that you need your email ID to be kept hidden from others, we can do that also. Hope that helps.
Hi Jai, thanks for sharing your email ID. We have shared the requested dataset to your mail ID. Do check out our other tutorial videos and subscribe to us to stay connected. Cheers :)
hello, that's a great tutorial, thanks for the effort. I don't know if I missed it but I can't seem to find where you trained the model, or that step is not really important?!
For someone that is just hoping into Data science, this video is absolutely magnificent and loved how you go step by step on data preparation and KNN algorithm. Is there any way that I might get the dataset? Congrats for the video.
Hello Luis, thanks for viewing our tutorial. It would be helpful if you will provide your email ID to us so that we could send the requested dataset promptly. On the off chance that you need your email ID to be kept hidden from others, we can do that also. Hope that helps.
Hello Apoorva, thanks for viewing our tutorial and we hope it is helpful. It would be helpful if you will provide your email ID to us so that we could send the requested dataset promptly.
Hi, great video. After we have created the model, how do we use it to predict whether new patients would have diabetes or not? Is there some sort of execution code we need to run to load the new data and test it against the model you built?
Great that you liked the tutorial, Nealabh! If you agree that Machine Learning is a good career move, please refer to this, www.simplilearn.com/big-data-and-analytics/machine-learning-certification-training-course. Also, Subscribe to our channel by clicking on the bell icon for never missing another update. Cheers !
Hello kamlesh, thanks for the kind comment. It would be helpful if you will provide your email ID to us so that we could send the requested dataset promptly. On the off chance that you need your email ID to be kept hidden from others, we can do that also. Hope that helps.
Hi Kamlesh, thanks for watching our video. We have sent the requested dataset to your mail ID. Do subscribe, like and share to stay connected with us. Cheers :)
selecting the value for K is sqrt of number of data points but here in this exaple tutor has taken sqrt of number of data points in test sample, please explain...and also missed on different ways of selecting K values...
U used test data to calculate k value. But we r fitting the model using train data. So, is it correct to use test data instead of train data for k value calculation. Plssss suggest..thx in advance.
Hey Abubakar, thank you for appreciating our work. We are glad to have helped. Do check out our other tutorial videos and subscribe to us to stay connected. Cheers :)
Hey Tejas, thank you for appreciating our work. We are glad to have helped. Do check out our other tutorial videos and subscribe to us to stay connected. Cheers :)
"🔥Caltech Post Graduate Program In AI And Machine Learning - www.simplilearn.com/artificial-intelligence-masters-program-training-course?HKqjENq9OU&Comments&TH-cam
🔥IITK - Professional Certificate Course in Generative AI and Machine Learning (India Only) - www.simplilearn.com/iitk-professional-certificate-course-ai-machine-learning?HKqjENq9OU&Comments&TH-cam
🔥Purdue - Post Graduate Program in AI and Machine Learning - www.simplilearn.com/pgp-ai-machine-learning-certification-training-course?HKqjENq9OU&Comments&TH-cam
🔥IITG - Professional Certificate Program in Generative AI and Machine Learning (India Only) - www.simplilearn.com/iitg-generative-ai-machine-learning-program?HKqjENq9OU&Comments&TH-cam
🔥Caltech - AI & Machine Learning Bootcamp (US Only) - www.simplilearn.com/ai-machine-learning-bootcamp?HKqjENq9OU&Comments&TH-cam"
My professor took 1 hour to clear the basic concepts of KNN but I was unable to understand. Thanks for clearing my concepts in just under 15 minutes. Thanks a lot. Really appreciated. I am going to subscribe your channel. Thanks once again.
Thank you for the appreciation. You can check our videos related to various technologies and subscribe to our channel to stay updated with all the trending technologies.
I've been trying to understand this for weeks and you've summed it up in the first 2 minutes. Light bulb moment!
Glad you found it useful! Thank you for watching!
Incredible video. I used it when I first heard of KNN to better understand it, and just used it to create my first model. You all are the best!
Thank you for the appreciation. You can check our videos related to various technologies and subscribe to our channel to stay updated with all the trending technologies.
This is an amazing video! I am trying to help my niece and have never read anything about KNN in my life but the way this video explains it is simply awesome! So thankful to you for creating this video as it would help thousands of students and those family members that want to help them learn properly. Do not understand why some professors can't seem to explain it so simply as you have! God bless you man!
WooHoo! We are so happy you love our videos. Please do keep checking back in. We put up new videos every week on all your favorite topics. Whenever you have the time, you must also check out our blog page @simplilearn.com and tell us what you think. Have a good day!
you put it better than I did. I have been struggling to understand what KNN means. Had over 6 lecturers mentioning it in the class but it still sounded vague. But he just made my day with this video.
These tutorials are easy to understand and informative compared to other videos😌Thanks:)
You're welcome 😊
My uni teacher made knn sucha scary thing to me... thanks God i found this vid...i m in love with knn now
Happy to help
Great video, up until the point where you skipped the part where you show how to train the algorithm. One could argue thats the most important part...
Keep learning with us .Stay connected with our channel and team :) . Do subscribe the channel for more updates : )
I really really love how you broke down the topic and able to pass across all valuable information in a short while. Thank you
Thank you for choosing us as your learning partner. We are thrilled to hear that you enjoyed your experience with us! If you are looking to expand your knowledge further, we invite you to explore our other courses in the description box.
Thank you for sharing this video it was very clear in detailed manner with example.
But I have a doubt in whether I to should take squareroot of n (n = Sum of Output of Distance Function) for calculating K.
5:11 (Choosing K)
8:55 (Choosing K=3)
I'm totally new to any machine learning or programming stuff, and tbh I was super scared about learning -'K-NN algorithm' because the word 'algorithm' already sounded scary enough. However, your analogy of "Cats or dogs" and "claws and ears" REALLY MADE A LOT OF SENSE! If I have to lecture my own class about machine learning someday for other beginners, I think your "cat and dog" analogy of explanation cannot be more simpler. Thanks for the great video!
Glad you enjoyed our video! We have a ton more videos like this on our channel. We hope you will join our community!
20:32 Correction - standard scaler does not restrict the range of data between -1 to +1 . It converts the data to a mean of 0 and standard deviation of 1 . So if u take the mean of a standardised column ul find it equals 0. It basically skews the data to a smaller range and makes it comparable with other variables with different magnitudes which otherwise would not have been comparable. Min-max scaler (normalisation) restricts the data between 0 to +1.
true, the formula is normalisedX= (X-mean)/deviation
Best data science video ever. so detailed and explanatory. very good for beginners. Please keep making detailed videos like this
We are glad you found our video helpful. Like and share our video with your peers and also do not forget to subscribe to our channel for not missing video updates. We will be coming up with more such videos. Cheers!
We hope you enjoyed watching our video. The link for the dataset used in the video is provided in the description. Thanks!
I guess im randomly asking but does any of you know of a trick to log back into an instagram account..?
I somehow forgot the account password. I appreciate any help you can offer me
What a gem!!! Very clear and logic. I just have a question of k (k=11). Why using the sqrt(len(X_test))-1, not the sqrt(len(X_train))-1. Thanks!!!!
Keep learning with us .Stay connected with our channel and team :) . Do subscribe the channel for more updates : )
Thanks for a *fantastic* video!!! may I ask - when determining K, why do you do the sqrt of y_test, rather than y_train (or x_train, which is the same length). In the video, it looks like you intended to do that, then for some reason - changed it...
Many thanks team, this leaa than 30mins clip saved me a couple of days to learn similar thing from some books and articles. Fantastic job :)
Glad it was helpful!
Thanks alot that's very helpful, but when trying to use StandardScaler an error occurs
"ValueError: could not convert string to float"
i can't solve it , ahat shall i do ?
thanks in advance.
i know im late but anyways it occurs because string data cant be standaradized i.e. put into StandardScaler. comvert it to float value
try doing this:
df[column_name] = df[column_name].astype('float')
(i didnt try it myself but it should hopefull solve the issue)
Finally ! easiest video i found😅.Thanks simplilearn!!!
Hello, thank you for watching our video. We are glad that you liked our video. Do subscribe and stay connected with us. Cheers :)
whats a confusion matrix?
In the field of machine learning and specifically the problem of statistical classification, a confusion matrix, also known as an error matrix, is a specific table layout that allows visualization of the performance of an algorithm, typically a supervised learning one. Hope that helps!
If you're confused about confusion matrix, you should check out zero r and one r classifier.
This is really simple as the name of the channel suggests, thanks
Glad you think so! Thank you for watching!
I found this fascinating. Wish machine learning/data analysis was around when I was doing my CS masters degree. Lots of spare time to learn in retirement. Great video, and I loved the Python even more. I’ve always found the correct working code to be the true documentation.
Glad it was helpful!
Thank you very much for this tutorial, it has been very clear, it has helped me a lot for my first Machine Learning model. Awesome!!
Glad it helped!
This is the best explanation I have seen so far. Thank you.
You're very welcome!
best tutorial of KNN i've ever watched. It helps me a lot
Glad you enjoyed our video! We have a ton more videos like this on our channel. We hope you will join our community!
One of the best explanations I have come across, thank you so much!
Glad it was helpful!
Before replacing the zero's by the mean in the columns you can first test is there is NanN in the data, if there is not you dont need the first line in the for loop I guess,
data[column]=data[column].replace(0,NanN).
A simple command is: dataset.isnull().sum()
Everything is great the only issue was the mic , please use some other it actually comes with a lot of intensity
Thanks for watching our video and sharing your thoughts. Do subscribe to our channel and stay tuned for more. Cheers!
nice video but could you guys show us how we can insert the new data into the model and the model itself will classify it.
Hey ,we'll go into these implementations in detail in another video. Stay tuned!
Wonderful explaination of the code which many of the other channels lack in their videos. THank you so much for explaining each step...
Hey Abhishek, thank you for appreciating our work. We are glad to have helped. Do check out our other tutorial videos and subscribe to us to stay connected. Cheers :)
Two Questions:
1. How do you embed a KNN model into a real application?
2. If you train a model on scaled data, how do you implement the resulting model to any platform for real use?
Thanks,
"Hey, we hope you enjoyed this video! If you want to learn more, you can check out this linl: www.simplilearn.com/tutorials/machine-learning-tutorial/knn-in-python
And don't forget to like, share and subscribe to our channel! :)"
Very nice explanation .....awesome visualization.
Hello, thank you for watching our video. We are glad that you liked our video. Do subscribe and stay connected with us. Cheers :)
Great tutorial. Thank you!
Amazing video. I'm learning data science and this helps a lot!
Glad it was helpful!
Thank you so much for such wonderful tutorial ! Can't express how grateful I am for this. Everything is very nicely explained.
Hey, thank you for appreciating our work. We are glad to have helped. Do check out our other tutorial videos and subscribe to us to stay connected. Cheers :)
UBER helpful - well set up and well explained - THANK U
Glad it was helpful!
Very good video easy way to understand.
Glad it was helpful!
Thank you for such great explanation !!!
You are welcome!
amazing video It clicked for me around 8:30. I am trying to make a 20Q voice bot
We are glad you found our video helpful. Like and share our video with your peers and also do not forget to subscribe to our channel for not missing video updates. We will be coming up with more such videos. Cheers!
Thank you for this illustrative and informative video. Excellent job explaining KNN and a practical real life Python application example.
WooHoo! We are so happy you love our videos. Please do keep checking back in. We put up new videos every week on all your favorite topics. Whenever you have the time, you must also check out our blog page @simplilearn.com and tell us what you think. Have a good day!
This video really helped my overall understanding of KNN and refreshed my understanding of the euclidean distance formula. Subscribed!
Hey Aaron, thank you for appreciating our work. We are glad to have helped. We are happy to receive a new subscriber and we hope you are loving our community. We put up new videos on all important topics, so stay tuned. Cheers!
Hi. You are doing an amazing work and it is so helpful. Is it possible to have the slides for our better understanding? Thank you
Thanks for the video! simple yet detail explanation!
Hey, thank you for appreciating our work. We are glad to have helped. Do check out our other tutorial videos and subscribe to us to stay connected. Cheers :)
Brief and very clear! Thanks!
Hey Denis, thank you for appreciating our work. We are glad to have helped. Do check out our other tutorial videos and subscribe to us to stay connected. Cheers :)
Very nice explanation!!
Glad it helped!
thanks for such an impressive video.It covered all the important topics and code as well. Thankyou so so much
We are so grateful for your kind words. Also, subscribe to our channel and stay tuned for more videos. Cheers!
Good video. Clearly explained all the concept and Diabetes example is neat! Thanks!
Hey Aditya, thank you for appreciating our work. We are glad to have helped. Do check out our other tutorial videos and subscribe to us to stay connected. Cheers :)
what an amazing video , thank you!
You're so welcome!
Replace directly 0 with mean … callus you please let me know the reason to replace 0 with nan values ?
Here the p is not that we are predicting person is diabteic or not .. it is used becuase of euclidean distance formula..if we use manhattan, then p will be equal to 1
Thanks for sharing the information. Do subscribe to our channel and stay tuned for more. Cheers!
This was really good compared to others, thanks i'll keep looking for more. Cheers!
Awesome, thank you!
Wow, your way of explaining and your didactic examples and materials are simply awesome!!. You got a new subscriber. Thank you, and please keep posting your amazing work.
We appreciate your kind comment. Welcome aboard!
great video. Can you please explain what should be the F score. Should we aim for higher F score similar to accuracy?
Hi Hemachandran, the F1 score is the average of precision and recall. Thank you for watching!
superb explanation
Thank you so much 🙂
I don't understand the confusion matrix. From what I understand,
94 - (actual) No diabetes
13 - (predicted) Has diabetes
32 - (actual) Has diabetes
15 - (predicted) No diabetes.
Why is the matrix arranged like this? Wouldn't it be easier to compare actual vs predicted values for each outcome? Eg. 94 and 15 being in the same row so it translates to 94 people having no diabetes in actuality whereas the model predicted 15 people having no diabetes.
Hi Denise,
Confusion matrix has 4 parameters - True positive, True negative, False positive and False negative.
There are other metrics that can be derived from a confusion matrix. Watch the video below to learn how confusion matrix in detail:
th-cam.com/video/prWyZhcktn4/w-d-xo.html
Thank you for watching!
Simple and efficient, thumbs up
Glad you like it!
Thanks! A simple but very good turorial!
Hey Madhvapathi, thank you for appreciating our work. We are glad that you liked our video. Do subscribe and stay connected with us. Cheers :)
Thanks a lot for explaining very clearly.
Glad it was helpful!
This is so amazing, thank you 😊
You're so welcome!
This is such a great tutorial! Thank you so much!
We are glad you found our video helpful, Scott. Like and share our video with your peers and also do not forget to subscribe to our channel for not missing video updates. We will be coming up with more such videos. Cheers!
Amazing video, everything I expected was there, thank you.
Glad you enjoyed it! Thank you for watching!
Great Video! Can I get that diabetes data set , so I can practice with it ? . Thanks.
Hello, thanks for viewing our tutorial. It would be helpful if you will provide your email ID to us so that we can send the requested dataset promptly. On the off chance that you need your email ID to be kept hidden from others, we can do that too. Hope that helps.
@@SimplilearnOfficial vedasiva4u@gmail.com , yes please make it hidden. Thank you very much for doing this.
Hi, great video thanks for putting it up. I have a question - now we know the model is 80% accurate but how to apply this to the question if someone has diabetes or not? Thats what i want to know how to do. thanks.
Thanks for watching our video and sharing your thoughts. Do subscribe to our channel and stay tuned for more. Cheers!
Ninteen minutes from this vdieo and this is magnificent love your teaching style keep going with more videos if you are good in math please release linear algrebra or calculs thank you
Hey, thank you for appreciating our work. We are glad to have helped. Do check out our other tutorial videos and subscribe to us to stay connected. Cheers :)
Thank you very much for this informative lecture. May I ask about the Feature Selection?
sc_X =StandardScaler()
X_train = sc_X.fit_transform(X_train)
X_test = sc_X.transform(X_test)
When to use fit_transform and transform? Why is it different for the training and testing dataset?
Will appreciate your answers. Thank you very much
"fit_transform" applies both a fit (fits the scaler to the dataset) and a transform (transforms the dataset, standardizing it) over the training data. Therefore, once you apply "fit_transform", you can just apply "transform" over the test data. You can check the functions associated with StandardScaler in the following link: scikit-learn.org/stable/modules/generated/sklearn.preprocessing.StandardScaler.html
By checking that, I had another related doubt: why not fit the scaler using the whole data (with train and test together)? I mean, it's possible that X_train has values ranging from 1 to 10 while X_test has values ranging from 1 to 20. Wouldn't it mess with the standardization?
@@filipechesco I actually noted that if you apply fit_transform on both test and train data, the accuracy and f1 score slightly changes
Great tutorial. Where can I get the dataset from?
Hello, thanks for viewing our tutorial. It would be helpful if you will provide your email ID to us so that we can send the requested dataset promptly. On the off chance that you need your email ID to be kept hidden from others, we can do that too. Hope that helps.
Thank you alot for your work
Our pleasure!
A clear explanation for the KNN Algorithm with use case. Could you please share the data set for the practice purpose.
hari.sompalli0205@gmail.com this is my mail id. Thanks in Advance.
Hi Hari, thanks for watching our video. We have sent the requested dataset to your mail ID. Also, Subscribe to our channel by clicking on the bell icon for never missing another update. Cheers!
Can you please email the dataset to himanshu.sheth@gmail.com Thanks in advance for the same
Hi Himanshu, thanks for checking out our tutorial. We have sent the requested dataset to your mail ID. Whenever you have the time, you must also check out our blog page @simplilearn.com and tell us what you think. Have a good day!
The video is very awesome , how would I get the diabetes data set for practice?
Hello Antonny, thanks for viewing our tutorial. It would be helpful if you will provide your email ID to us so that we could send the requested dataset promptly. On the off chance that you need your email ID to be kept hidden from others, we can do that also. Hope that helps.
Thank you Simplilearn team for the clear explanation. Can you please provide the dataset and the python notebook used in the video?
Hello Aisha, thanks for viewing our tutorial and we hope it is helpful. It would be helpful if you will provide your email ID to us so that we could send the requested dataset promptly.
Thank You ! Best explanation with a simplistic example. Can I ask how could we improve the efficiency of the model ??
Hi Redamichael,
There are multiple methods to improve the accuracy of any model. Some of them are feature engineering, feature selection, algorithm tuning, and ensemble methods.
what fit() function do, as we know that we didn't train the Knn so why we are doing fit()
"Hi Sughanshu,
The fit() method is used to train the model by passing the training parameters."
Great video!!! just one question: i didnt understand what part of the video was the 'k' you chose?
Replacing zeros using pandas
zero_not_accepted = ['Glucose','BloodPressure','SkinThickness','BMI','Insulin']
print(diabetes_data[zero_not_accepted].mean())#to know values of mean
diabetes_data[zero_not_accepted] = diabetes_data[zero_not_accepted].replace(0, diabetes_data[zero_not_accepted].mean())
Hey this is really an amazing video! I was looking for this type of video and to my luck i found this!!
Hey Vandan, thank you for appreciating our work. We are glad to have helped. Do check out our other tutorial videos and subscribe to us to stay connected. Cheers :)
amazing video. I learned a lot and it was very clear and informative
Glad it was helpful!
If a give an input list for the KNN algorithm to predict the classes of each element, How can I print out the list of inputs only belonging to a particular class?
Nice tutorial. How you have selected the list item for zero_not_accepted? Why the "Age" column is not taken for the list item?
Thank you for this great course. Very well explained. I subscribe :)
Awesome, thank you for subscribing to our channel.
Hi The video is very nice about KNN.
I have one question here:
to find the optimum k value
is it sqrt (y_test) or sqrt (y) sqrt (y_test)?
Thanks in advance...
also in some part of video you mentioned k = sqrt (n) , where n is total number of data points ?
Yes, "n" represents the number of data points and not the features.
You can use sqrt(y_test) to find the most appropriate value for k or try using the elbow method.
Is there a mistake at 7:54? It must be: (170-167)²-(57-54)². in your formular, the last number is 51... the x value of d1 in the coordinate system
is wrong? Im right?
Amazing video, on a real life project, what would be the impact of an accuracy score of let's say 90% over an accuracy score of above 90%?
WooHoo! We are so happy you love our videos. Please do keep checking back in. We put up new videos every week on all your favorite topics. Whenever you have the time, you must also check out our blog page @simplilearn.com and tell us what you think. Have a good day!
Nice one. But it would be helpful, if once you can post the link to download the sample dataset.
Hello Jai, thanks for viewing our tutorial. It would be helpful if you will provide your email ID to us so that we could send the requested dataset promptly. On the off chance that you need your email ID to be kept hidden from others, we can do that also. Hope that helps.
@@SimplilearnOfficial dev.jeyakumar@gmail.com, Thanks.
Hi Jai, thanks for sharing your email ID. We have shared the requested dataset to your mail ID. Do check out our other tutorial videos and subscribe to us to stay connected. Cheers :)
omg thank you for explaining the code
You are welcome! Do subscribe to our channel and stay tuned.
hey there is an error when i try to run this command
Y_pred=knn.predict(X_test)
Y_pred
this is the error, Notfittederror
hello, that's a great tutorial, thanks for the effort. I don't know if I missed it but I can't seem to find where you trained the model, or that step is not really important?!
It is our pleasure! Check out :www.simplilearn.com/tutorials/machine-learning-tutorial/knn-in-python for more in-depth tutorials! Happy learning!
For someone that is just hoping into Data science, this video is absolutely magnificent and loved how you go step by step on data preparation and KNN algorithm. Is there any way that I might get the dataset? Congrats for the video.
Hello Luis, thanks for viewing our tutorial. It would be helpful if you will provide your email ID to us so that we could send the requested dataset promptly. On the off chance that you need your email ID to be kept hidden from others, we can do that also. Hope that helps.
Hi
This video was really helpful
Could you please share the dataset
Hello Apoorva, thanks for viewing our tutorial and we hope it is helpful. It would be helpful if you will provide your email ID to us so that we could send the requested dataset promptly.
Video is awesome and cat's are better than dogs xD
Glad you enjoyed our video! We have a ton more videos like this on our channel. We hope you will join our community!
Kudos mate Wonderful Video!
Glad you enjoyed it
Can i use k-nn if i have like 48 features? Or was it too much? If so, what type of ML method would you recommend for it?
You'd rather use random forest for this.
Hi, great video. After we have created the model, how do we use it to predict whether new patients would have diabetes or not? Is there some sort of execution code we need to run to load the new data and test it against the model you built?
did you found the answer?
SIr, Extremely useful
Glad to hear that! Thank you for watching!
Really helpful video, simple examples and explanation
Great that you liked the tutorial, Nealabh! If you agree that Machine Learning is a good career move, please refer to this, www.simplilearn.com/big-data-and-analytics/machine-learning-certification-training-course. Also, Subscribe to our channel by clicking on the bell icon for never missing another update. Cheers !
one of the best tutorial ever,sir can you pls share the dataset...Thank you.
Hello kamlesh, thanks for the kind comment. It would be helpful if you will provide your email ID to us so that we could send the requested dataset promptly. On the off chance that you need your email ID to be kept hidden from others, we can do that also. Hope that helps.
@@SimplilearnOfficial sure kamlesh9707@gmail.com...thank you so much..
Hi Kamlesh, thanks for watching our video. We have sent the requested dataset to your mail ID. Do subscribe, like and share to stay connected with us. Cheers :)
cool tutorial. keep it up!
Thanks, you too!
selecting the value for K is sqrt of number of data points but here in this exaple tutor has taken sqrt of number of data points in test sample, please explain...and also missed on different ways of selecting K values...
U used test data to calculate k value. But we r fitting the model using train data. So, is it correct to use test data instead of train data for k value calculation. Plssss suggest..thx in advance.
Thanks a lot that's video is very useful my concept
Hey Abubakar, thank you for appreciating our work. We are glad to have helped. Do check out our other tutorial videos and subscribe to us to stay connected. Cheers :)
Thank you for sharing this in very A nice and clear explanation for the KNN Algorithm with use case.
Appreciated !!
Hey Tejas, thank you for appreciating our work. We are glad to have helped. Do check out our other tutorial videos and subscribe to us to stay connected. Cheers :)