Automating Ml Pipelines For Song Recommendation System

Free Download Automating Ml Pipelines For Song Recommendation System
Published 10/2024
MP4 | Video: h264, 1920×1080 | Audio: AAC, 44.1 KHz
Language: English | Size: 1.74 GB | Duration: 4h 46m
Automate Song Recommendations with Docker, MLFlow, and CI/CD Practices for Machine Learning Algorithms.

What you’ll learn
Understand the Math Behind ML Algorithms: You will learn the mathematical concepts that underlie popular machine learning algorithms.
Implement Machine Learning Algorithms: You will gain hands-on experience in coding and applying various machine learning algorithms.
Design and Build MLFlow Tracking: You will learn how to use MLFlow for tracking and managing machine learning experiments effectively.
Implement Microservices with Docker: You will learn how to create and manage microservices for automating machine learning pipelines using Docker.
Automate Model Training and Evaluation: You will learn to use Airflow triggers to automate the process of training and evaluating machine learning models.
Set Up Git CI/CD for a Song Recommender App: You will learn how to implement CI/CD for a song recommendation web app.
Requirements
Basic Knowledge of Python programming, as it will be used for implementing machine learning algorithms and building ML pipeline microservices.
A desire to learn and experiment with machine learning and microservices is encouraged.
Description
Math Behind Machine Learning Algorithms:K-Nearest Neighbors (KNN): A method for finding similar songs based on user preferences.Random Forest (RF): An algorithm that combines many decision trees for better predictions.Principal Component Analysis (PCA): A technique for reducing the number of features while retaining important information.K-Means Clustering: A way to group similar songs together based on features.Collaborative Filtering: Making recommendations based on user interactions and preferences.Data Processing Techniques:Feature Engineering (Feature Importance using Random Forest): Feature importance analysis and creating new features from existing data to improve model accuracy.Data Pre-processing (Missing Data Imputation): Cleaning and preparing data for analysis.Evaluation and Tuning:Hyperparameter Tuning (Collaborative Filtering, KNN, Naive Bayes Classifier): Adjusting the settings of algorithms to improve performance.Evaluation Metrics (Precision, Recall, ROC, Accuracy, MSE): Methods to measure how well the model performs.Data Science Fundamentals:TF-IDF (Term Frequency and Inverse Document Frequency): A technique for analyzing the importance of words in song lyrics.Correlation Analysis: Understanding how different features relate to each other.T-Test: A statistical method for comparing groups of data.Automation Tools:Building Microservices using Docker: Use containers to run applications consistently across different environments.Airflow: Automate workflows and schedule tasks for running ML models.MLFlow: Manage and track machine learning experiments and models effectively.By the end of the course, you will know how to build and automate the training, evaluation, and deployment of an ML model for a song recommendation system using these tools, libraries and techniques.
Overview
Section 1: Introduction
Lecture 1 Course Introduction
Section 2: Machine Learning – Math Intuition
Lecture 2 Math Behind Collaborative Filtering
Lecture 3 Math Behind KNN (Euclidean Distance)
Lecture 4 Math Behind Naive Bayes (Bayes Theorem)
Lecture 5 Math Behind TF and IDF
Lecture 6 Math Behind Cosine Similarity
Lecture 7 Evaluation Metric – MSE
Lecture 8 Math Behind – K-Means Clustering (Unsupervised Learning)
Lecture 9 Math Behind Principal Component Analysis
Lecture 10 Math Behind Pearson Correlation
Lecture 11 Math Behind – T-Statistic Test
Lecture 12 Evaluation Metrics – Classification Models
Section 3: ML Experimentation – Supervised & Unsupervised Learning
Lecture 13 Module Artifacts
Lecture 14 Project Env Setup (Conda)
Lecture 15 Import required libraries
Lecture 16 Understanding the features in data
Lecture 17 Data Preprocessing
Lecture 18 Feature Engineering
Lecture 19 Pearson Correlation Analysis
Lecture 20 T-Test Statistics
Lecture 21 Collaborative Filtering – User Genre Matrix
Lecture 22 Creation of user similarity network visualization (Cosine Similarity)
Lecture 23 Songs Recommender Engine Model – Collaborative Filtering
Lecture 24 Fetch Songs Recommendation – Collaborative Filtering Model
Lecture 25 KNN and Naive Bayes Model Pipeline
Lecture 26 Model Hyperparameter Tuning
Lecture 27 Best Estimator Recommendation
Lecture 28 K-Means Clustering and PCA
Section 4: Airflow – Automate Collaborative Filtering model training and deployment
Lecture 29 Module Artifacts
Lecture 30 Code Environment Setup
Lecture 31 MLFlow Lifecycle and Commands
Lecture 32 Airflow Lifecycle and Commands
Lecture 33 DAG Setup – Data Splitting, User Genre Matrix Generation, Training & Evaluation
Lecture 34 train_and_deploy.py W/O Airflow
Lecture 35 Optional – DAG Assets Validation
Section 5: Building Microservices for MLFlow and Airflow using Docker
Lecture 36 docker-compose.yml Lifecycle (Theory)
Lecture 37 Dockerfile (Python and Airflow)
Lecture 38 Microservices – docker-compose.yml
Lecture 39 Building Docker Image for Python
Lecture 40 Building Docker Image for Airflow
Section 6: ML Pipeline Orchestration – Airflow Triggers and MLFlow Experiments
Lecture 41 Build and Compose up the Microservices
Lecture 42 Orchestrating the ML Job Triggers and Logs
Section 7: Song Recommender System Web App
Lecture 43 Import required modules
Lecture 44 Load Pkl Model
Lecture 45 Fallback condition for recommender system
Lecture 46 Load and Fetch cache Data
Lecture 47 Building UI for song recommender system
Lecture 48 Filter and Join recommendations
Lecture 49 Testing the recommender app in localhost environment
Lecture 50 Push the codebase to Github repository
Lecture 51 Deploy recommender app to Streamlit cloud with Github CI/CD
Section 8: Challenges / Takeaways / Homework
Lecture 52 Automating ML Pipeline Song Recommendation: Challenges / Takeaways / Homework
Lecture 53 Thank you!
Lecture 54 Codebase Artifacts
Students pursuing studies in data science, computer science, or related disciplines who want to enhance their practical skills in machine learning and automation.,Individuals looking to deepen their understanding of machine learning and its applications in real-world scenarios, particularly in recommendation systems.,Programmers interested in expanding their skill set to include machine learning concepts and automation practices using tools like Docker, MLFlow, and Airflow.,Professionals wanting to learn how to build and automate machine learning pipelines and improve their workflow efficiency.,Anyone with a foundational knowledge of machine learning who wants to gain practical experience in implementing algorithms and automating processes.,Individuals looking to enhance their qualifications and job prospects by adding machine learning and automation expertise to their portfolio.
Screenshot
Homepage

https://www.udemy.com/course/automating-ml-pipelines-for-song-recommendation-system/