This 2-day instructor-led training course covers essential and more advanced classification algorithms that are commonly used both in socio-economic research and health industry. The attendees of the course will learn and practise implementations of logistic regression, Naive Bayes, k-Nearest Neighbours, Support Vector Machines, decision trees, adaptive boosting, extreme gradient boosting and random forests algorithms in Python programming language (and its libraries such as: Scikit-Learn, Statsmodels, SciPy, h2o, XGBoost etc.) using examples of datasets from social science, economics and healthcare. During the training course, the delegates will:
- Develop deep theoretical and practical understanding of binomial and multinomial classification algorithms such as logistic regression, Naive Bayes, k-NNs, SVMs, decision trees, adaptive and extreme gradient boosting methods, random forests and other ensembles,
- Learn to apply different evaluation metrics (e.g. confusion matrix, sensitivity, specificity, R squared, logarithmic loss, Gini coefficient, ROC AUC, Kappa, F1 score and many others) to compare the models between one another and to assess the quality of classifiers,
- Cross-validate the models using different re-sampling procedures,
- Implement hyperparameter tuning to optimise the models and improve their performance.
All methods presented during this course will be implemented in Python programming language either through custom-made code or with functions and methods available in NumPy, pandas, SciPy, Scikit-Learn, Scikit-Multilearn, Statsmodels, h2o and XGBoost libraries for Python.
This is a 2-day instructor-led online training course with a week-long follow up period. The course will run from 10:00 in the morning to ~16:30 each day and will include a 45-minute break for lunch between morning and afternoon sessions and one 15-minute afternoon coffee/tea break. Following the course, you will be able to submit your solutions to the homework exercises and you will receive feedback from the tutor.
This training course is tutor-led – all online tutorials are presented live by our expert instructor, you can ask questions, discuss the topic and interact with other learners. You can also email the tutor after the course if you have any questions related to the material presented during the course.
The course will be recorded – you will have access to the video recordings of the course webinars and additional resources such as datasets, Python code, academic papers related to the topic of the workshop, and supplementary exercises via Mind Project Learning Platform.
Course dates: Monday-Tuesday, 25th-26th of April 2022, 10:00-16:30 London (UK) time
Deadline for registrations: Friday, 22nd of April 2022 @ 17:00 London (UK) time
10:00 – 10:15 – Course welcome and logistics
10:15 – 10:45 – Introduction to classification models (theory and examples)
10:45 – 12:30 – Logistic regression in practice including evaluation metrics for binomial and multinomial classifiers – Python tutorial
12:30 – 13:15 – lunch break
13:15 – 14:00 – Naive Bayes as an example of probabilistic classifier
14:00 – 14:45 – K-Nearest Neighbours and Support Vector Machines in practice with evaluation metrics for multinomial classifiers – Python tutorial
14:45 – 15:00 – coffee/tea break
15:00 – 16:15 – K-Nearest Neighbours and Support Vector Machines in practice continued + exercise
16:15 – 16:30 – discussion and questions
10:00 – 10:45 – Tree-based classifiers and ensembles – theory and examples
10:45 – 12:30 – Decision trees in practice including hyperparameter tuning and re-sampling methods – Python tutorial
12:30 – 13:15 – lunch break
13:15 – 14:45 Ensembles in practice: Random Forests, Adaptive and Extreme Gradient Boosting – Python tutorial
14:45 – 15:00 – coffee/tea break
15:00 – 16:15 – Ensembles in practice continued + exercise
16:15 – 16:30 – discussion and course wrap-up
Course pre-requisites and further instructions
We recommend that all attendees have the most recent version of Anaconda Individual Edition of Python 3.9 installed on their PCs (any operating system). Anaconda’s Python is a free and fully-supported distribution and you can download it directly from https://www.anaconda.com/products/individual#Downloads. Please contact us should you have any questions or issues with the installation process. A list of Python libraries to pre-install before the course will be sent to the enrolled attendees in the Welcome Pack alongside other Joining Instructions.
We recommend that the attendees have practical experience in data processing or quantitative research – gathered from either professional work or university education/research. A good knowledge of statistics would be beneficial.
Your PC needs to be connected to a stable WiFi/Internet network (either home or office-based) and have Zoom video-conferencing application installed.
You will need at least one commonly used web browser installed on your PC (e.g. Chrome, Safari, Firefox, Edge etc.) to access our Mind Project Learning Platform.
The primary spoken and written language of the course is English.
By enrolling on one of our online training courses you agree to the Training Terms and Conditions. Please read the Training Terms and Conditions before purchasing this course.
Your course instructor
Your instructor for this course will be Simon Walkowiak. Simon is a director at Mind Project Limited and a Ph.D. researcher in Artificial Intelligence at the Bartlett Centre for Advanced Spatial Analysis (University College London) and the Alan Turing Institute in London. Simon holds BSc (First Class Honours) in Psychology with Neuroscience and MSc (Distinction) in Big Data Science. He conducts and manages research projects on implementation and computational optimisation of novel AI approaches applicable to large-scale datasets to predict human behaviour and spatial cognition. Simon is the author of “Big Data Analytics with R” (2016) – a widely used textbook on high-performance computing with R language and its compatibility with ecosystem of Big Data tools e.g. SQL/NoSQL databases, Spark, Hadoop etc. Apart from research and data management consultancy, during the past several years, Simon has taught at more than 150 in-house or open-to-public statistical training courses (in R, Python, SQL and Scala for Spark languages) in the UK, Europe, Asia and USA. His major clients include organisations from finance and banking (HSBC, RBS, GE Capital, European Central Bank, Credit Suisse, ING etc.), research and academia (GSMA, CERN, University of Cambridge, UK Data Archive, Agri-Food Biosciences Institute, Newcastle University etc.), health (NHS), insurance (Liberty IT), transport (Steer Group) and government (Home Office, Ministry of Justice, Government Actuary’s Department etc.).
Discounts and multiple bookings
We offer 2 types of enrolment options:
- Regular Fee – full-priced enrolment for learners representing commercial organisations or self-funded individuals who do not meet our eligibility criteria for discounted rates (please see below),
- Discounted Fee – applicable to undergraduate and postgraduate students as well as representatives of registered charitable organisations and non-governmental organisations (NGOs) – this category also includes employees of the National Health Service (NHS).
Students and individuals eligible for the Discounted Fee should submit a copy of their student or organisation ID card (with their name and card expiry date visible) when making the purchase of their place on the course for the discount eligibility verification purposes. Alternatively, the discount eligibility can be verified by submitting either i.) a copy of a letter from the university registrar or student’s department confirming your status, or ii.) a copy of a letter from your employer (on a company letter-headed paper with a charity/NGO registration number) which confirms your current position within the organisation.
Apart from the discounted fees for students or employees of charitable organisations and NGOs, we are able to offer further discounts on the overall cost of your training if you wish to attend multiple related courses or enrol several delegates on this specific course. Please note that this offer is only available through our website.
- If you book 3 or 4 tickets on any of our tutor-led open-to-public online training courses, you will receive 5% discount on the total price of your booking.
- If you book 5 or more tickets on any of our tutor-led open-to-public online training courses, you will receive 10% discount on the total price of your booking.
All discounts are calculated automatically when tickets are added to the Cart. For bookings of 6 and more delegates on one course, we recommend that you contact us directly – we may be able to arrange a separate course just for your delegates at a discounted rate.
Arrange this course at your organisation
If your delegates cannot attend this public course, or you are interested in arranging this training course explicitly for your delegates (or at your premises) or simply you need a bespoke, made-to-measure training solution, please request a quote for the in-house version of this course based on your specific needs and desired outcomes of the training.
You may email us directly at info(at)mindproject.io and include the following information in your enquiry:
contact details to a person who should receive the quote,
number of delegates you would like to train,
approximate number of online sessions (or half-days / full days for on-site in-house course) you would like to arrange the course for (including additional support/project guidance if needed),
location of the training venue if not online,
any details on course customisation or specific topics you would like the course to address – most importantly, please indicate desired outcomes of the course if different then presented above,
any other questions you may have.
If you don’t know the answers to questions above or you are at early stages of course planning, we would be happy to arrange an informal chat and help you choose the most suitable and budget-efficient option.