We have an exciting video today where we’ll be training a YouTube comments spam detection model using Python and scikit-learn’s machine learning library!

Deploying the ML Model to Heroku using a Flask API: https://youtu.be/Q_Z5kzKpofk

Sections:
0:00 - Intro
0:25 - Reviewing the dataset
1:30 - Going over Google Colab
1:56 - Building the spam classifier
11:10 - Evaluating the performance of the model
12:47 - Exporting the model
14:10 - Discussing limitations of the model

Google Colab: https://research.google.com/colaboratory/
Scikit-learn’s Multinomial Naive Bayes: https://scikit-learn.org/stable/modules/generated/sklearn.naive_bayes.MultinomialNB.html
TF-IDF: https://en.wikipedia.org/wiki/Tf–idf
Dataset: https://archive.ics.uci.edu/ml/datasets/YouTube+Spam+Collection

Source Code: https://github.com/jacksonyuan-yt/youtube-comments-spam-classifier

Found this video helpful? Feel free to support this channel here: https://ko-fi.com/jacksonyuan

#python #scikit-learn #machine learning