Machine Learning for Data Scientists

 

Data Scientists
 

• Attendants should have knowledge:
  • Python
  • Spark fundamentals
  • Pyspark fundamentals

Part I. Data Science Fundamentals

• Unit 1. Data Science Overview

Business Analytics, Data Analytics, Data Science. Data Scientist and Data Engineering roles. Traditional Analytics with the Data Warehouse. The Data Lake, its advantages and limitations. Data formats in the Data lake. The lakehouse and several ways to implement it. The Data Fabric. Data Science Methodology.

• Unit 2. Introduction to Artificial Intelligence and Machine Learning

Concise theoretical introduction to Artificial Intelligence, Machine Learning. Feature Engineering. Types of Learning (Structured, Semi-Structured and Unstructured Learning). Deep Learning. Introduction to Machine Learning Algorithms. Machine Learning Packages. Part II. Data Processing

• Unit 3. Pyspark SparkML

Introduction to Spark ML with Structured Data. Introduction to pyspark.ml packages for (Extracting, Transforming and selecting features, Classification and Regression, Clustering, Collaborative Filtering, Model Evaluation). Feature processing, Splitting data in Train, Test and Validation sets. Introduction to Algorithm analytics. Lab included

• Unit 4. Feature Engineering

Introduction to Feature Processing. Types of features. Feature Scaling, Feature Bucketing. Feature Cleansing.

• Unit 5. Advanced Feature Engineering

Feature Whitening. Feature Reduction. Part III. Machine learning

• Unit 6. Machine learning steps and functions

Machine Learning algorithms. Machine Learning statistics. Machine Learning processing steps. Splitting Datasets.

• Unit 7. Supervised Learning – Regression

Regression algorithms.Regression Trees, Linear Regression, Logistic Regression Lab included

• Unit 8. Supervised Learning – Classification

Classification Algorithms Lab included

• Unit 9. Unsupervised Learning – Clustering

Euclidean distance, Hierarchical Clustering. Clustering Data. K-means Clustering Algorithm. Lab Included

• Unit 10. Deep Learning

Artificial Neural Networks, Multi-Layer Perceptrons and Convolutional Neural Networks Lab included

• Unit 11. Data Pipelines in Spark

Anatomy of a data pipeline. Details on data pipeline operations. Data pipelines design considerations. feature selection and build Machine learning pipelines. Data engineering best practices for your data pipelines. Lab included

• Unit 12. Machine Learning model management

Hyperparameters and hyperparameter tuning. Model management considerations. Part IV. GraphFrames

• Unit 13. Introduction to GraphFrames and Graph Processing

Spark and Graphs. Graph Operators, Graph Builders, Graph Algorithms, GraphFrames Labs Included

• Unit 14. Machine Learning and GraphFrames

Recommendation Algorithms. Clusterting. Labs Included