Python Machine Learning Tutorial #12 - Implementing K-Means Clustering

This python machine learning tutorial covers k means clustering. How to implement K means clustering in python using sklearn.

**************************************************************

Use the Code "SAVE6144" For 50% Off!

**************************************************************

Please leave a LIKE and SUBSCRIBE for more content!

Tags:
- Tech With Tim
- Python Tutorials
- Python machine learning tutorial
- Machine learning tutorial python
- How does k-means work
- K means clustering python
- K means clustering tutorial

[WolverineAndSloth]

Some more infos on the scores we calculate here:

* homogeneity - checks if each cluster contains only members of a single class. ranges from 0-1 with 1 being the best score

* completeness - checks if all members of a given class are assigned to the same cluster (ranges from 0-1 again)

* v_measure - is the harmonic mean of homo. and compl. (ranges from 0-1 again)

* adjusted_rand_score - similarity of the actual values and their predicitions, ignoring permutations and with chance normalization (range from -1 to 1 with -1 being bad, 1 being perfect and 0 being random)

* adjusted_mutual_info - agreement of the actual values and predictions, ignoring permutations (from 0-1 with 0 being random agreement and 1 being perfect agreement)

* silhouette_score - This uses two values, the mean distance between a sample and all other points in the same class as well as the mean distance between a sample and all other points in the nearest cluster to calculate a score that ranges from -1 to 1, with the former being incorrect, and the latter standing for highly dense clustering. 0 indicates overlapping clusters.

[jimmyturner]

that "taregts" part😂😂oh my ribs😅. Anyways I've tried LOTS of tutorials on Machine Learning.Couldn't understand even one. This was THE BEST. Love how you thoughtfully explained, even the underlying concepts and crazy math behind the algorithms in an easy manner. Thanks to you I can finally start my AI journey. Off to your neural networks tutorial....🏃🏃🏃

[vitnovak]

O M G this whole course was SO GOOD! Hit the exact level of abstraction and knowledge I needed! Thank you so much!

[ChadHuffman]

This is great stuff, Tim. Your efforts are appreciated. I'm really looking forward to your neural networking series. Cheers

[StyleTrick]

Thank you for the great content Tim! Just finished the ML playlist and looking to learn from your other playlists. Keep up the amazing work Tim, truly appreciate it!

[louben]

Thank you Tim for bringing 12 episodes full of content about ML online! please keep on going the great work, best from Amsterdam cozy East-Side

[insected]

im just getting into python and machine learning and I come from a trading background. Going through this playlist has been perfect for me; not super advanced so that I miss important concepts, but in depth enough so that I can understand what is happening under the hood and have a degree of confidence in pursuing further knowledge. Really appreciate it.

[karolworkowski]

Thank you very much Tim, as total beginner with programming I was able to follow through entire tutorial (sometimes had to rewatch few parts but thats due to my lack of knowledge, not your explanation), i really enjoyed real life examples and explanations based on actual data/lines of codes. I tried get into programming several times already but always gave up do to complexity and amount of information that had to be already known, i followed through entire tutorial and cant wait to start your next one :D Great job

[tacpreppers]

Excellent series Tim! Watched them all, doing Neural Nets now!

[BananaDorian]

Thanks so muck for the tutorial, it was very interesting! (learned during quarantine.) I am now looking forward to the neural-networking series! Take care of your health too during these strange times Tim. (from a new subscriber and student from Japan)

[weixuancheng]

Such an easy tutorial to follow along! Was really helpful for a beginner. Thanks for the amazing series

[deedeezhou]

Thanks, Tim, Really looking forward for your neural network tutorial .

[duyvuoantran]

Appreciated! After watching a tan of ML tutorial videos, finally find your channel. step by step to get basic understanding, nice visualization explain and GREAT efforts! I'm looking forward for your future tuts :D
btw, could you make a video about collecting and pre-processing real data (how that would be like ?), for some kind of simple ML project

[stephenc]

Great tutorial, many thanks! I'll look forward to the neural networks one

[yongnujin]

Thank you Tim, these wonderful lectures really help me!

[iraklikoberidze]

If you copy the code ( The one witch was taken from sklearn website ) or even if you write it yourself it will give you an error because it is outdated. So try this one instead:


def bench_k_means(estimator, name, data):
estimator.fit(data)

.format(name, estimator.inertia_,
metrics.homogeneity_score(y, estimator.labels_),
metrics.completeness_score(y, estimator.labels_),
metrics.v_measure_score(y, estimator.labels_),
metrics.adjusted_rand_score(y, estimator.labels_),
metrics.adjusted_mutual_info_score(y, estimator.labels_),
metrics.silhouette_score(data, estimator.labels_,
metric='euclidean')))

[techiedawood]

This tutorial has taught me a lot.
Great tutorial,
Keep it up Tech with Tim

[muhammadtalhabaig]

Thanks Tim for this series! Time to check out the neural networks series now! 😃

[rajdeepsil]

So I followed the entire series in one go, without getting bored at all, and trust me IT WAS AMAZING and so simply explained. Keep on doing the GREAT WORK that you are doing, and I will soon start with the Neural Network Series
Love from India

[fahdkoraiche]

I have watched the whole -machine learning - deep learning - django and flask series and written everything down, it actually helped me alot with my studies, i hope you'll make more videos about advanced techniques like cross validation, confusion matrix, lift curve, Roc-Auc, F1 score, recall and more. I am sure it's going to make more sense coming from you! thanks alot (y)