-
- Deepens Python skills with real-world machine learning applications
- Enhances forecasting and data analysis using time series techniques
- Covers supervised, unsupervised, and NLP methods for business insights
- Applies Scikit-Learn tools to solve classification and prediction tasks
- Boosts corporate software performance through practical ML integration
This course aims to extend and solidify your Python experience by exploring Machine Learning techniques. Machine Learning and AI are introduced using Python libraries. The underlying principles and terminology of Machine Learning are introduced. Delegates can then use ML to gain insights from existing data stores.
The course has been specifically developed to follow on from the previous course delivered to Vodafone delegates. It covers Machine Learning features in more depth offering a deep dive into relevant areas. The skills learned can be applied to corporate software and data to provide significant improvements with an emphasis on best practise.
Duration
2 days
Prerequisites
- Approx. 6 months Python experience
What you’ll learn
- The principles of machine learning
- Making forecasts from training data
- Supervised and unsupervised learning techniques
- Using Natural Language Processing to work with text
Course details
Working with Time Series Data
- Introduction to Time Series Data
- Indexing and Plotting Time Series Data
- Testing Data for Stationarity
- Making Data Stationary
- Forecasting Time Series Data
- Scaling Back the ARIMA Results
Introduction to Machine Learning
- Machine Learning Concepts
- How Machine Learning Can Help Businesses
- Learning From Training Data
- Classification Of Data
- Clustering Data
Getting Started with Scikit-Learn
- Scikit-Learn Essentials
- A Closer Look at Datasets
Understanding the Scikit-Learn API
- Introduction
- Scikit-Learn API Essentials
- Performing Linear Regression
Going Further with Scikit-Learn
- Introduction
- Understanding Naïve Bayes Classification
- Naïve Bayes Example using Scikit-Learn
Machine Learning Case Study
- Overview
- Example application
- Loading the digits data from Scikit-Learn
- Drawing the digits
- Reducing dimensionality of the data
- Predicting future digits
- Identifying classification errors
Natural Language Processing
- Overview
- Tokenizing
- Filtering stop words
- Stemming
- Tagging
- Chunking
- Chinking
- Named entity recognition
- Additional techniques