Practical Data Science with Python Training in South Africa

• GCSE level mathematics or above. Alternatively, familiar and comfortable with logical and mathematical thinking
• Familiar with basic knowledge of programming: variables, scope, functions

At the end of the course attendees will know:

• Fundamental concepts of Data Science
• Methodologies used in Machine Learning
• Summary statistics and how to use statistical inference to analyse data
• Hands on Python programming language for numerical analysis
• Most used simple machine learning algorithms

At the end of the course attendees will be able to:

• Speak the language of data scientists
• Write Python programs to analyse data
• Understand a Python program in the context of data analytics
• Explore and visualise data using Python
• Build working machine learning models

01 Introduction to Data Science

• Understanding Big Data challenges for storage and analytics
• Identifying potential Big Data projects
• Designing successful Data Science projects

02 Introduction to Machine Learning

• Identify types of machine learning:
  • Supervised
  • Unsupervised
  • Reinforcement Learning
• Identify use cases

03 Jupyter Notebook

• Identify Anaconda and Jupyter
• Work with Jupyter Notebooks
• Practical Lab Activity

04 Python Fundamentals Review

• Review of Python techniques:
  • Data Types and Assignment
  • Lists, Tuples, Strings, Sets and Dictionaries – and how to address from them
  • Selection and Iteration structures
  • Subroutine definitions
• Practical Lab Activity

05 Introduction to Pandas and Numpy

• Dataframes and how to address from them
• Read from a CSV and exploration of documentation for reading from other sources
• Dataframe methods and using the documentation
• Practical Lab Activity

06 Exploratory Data Analysis

• In the context of identifying appropriate Machine Learning methods:
  • Interpreting descriptive statistics using Pandas
  • Interpreting correlations and associations
• Practical Lab Activity

07 Data Visualisation

• In the context of identifying appropriate Machine Learning methods:
  • Interpreting visualisations using Pandas, Seaborn, and Matplotlib
  • Interpreting correlations and associations
  • Interpreting visualisations for EDA
• Practical Lab Activity

08 Data Preparation

• Data Preparation techniques in the context of selected Machine Learning methods:
  • Checking the quality of the data and understanding it's source
  • Identifying when to remove, replace, or retain missing data
  • Handling Imbalanced Data
  • Scaling and Normalisation requirements
• Practical Lab Activity

09 Linear Regression

• Identify appropriate situations for using Linear Regression
• Use the Supervised Machine Learning workflow to create, evaluate, tune, and visualise a linear regression model
• Practical Lab Activity

10 Logistic Regression

• Identify appropriate situations for using Logistic Regression
• Use the Supervised Machine Learning workflow to create, evaluate, and tune a logistic regression model
• Practical Lab Activity

11 Decision Trees and Random Forests

• Identify appropriate situations for using Decision Trees
• Use the Supervised Machine Learning workflow to create, evaluate, tune, and visualise a Decision Tree model
• Identify alternative classification models such as Random Forests and how to compare them
• Practical Lab Activity

12 Clustering with K-means

• Understanding and implementing the k-means clustering algorithm
• Evaluate the model performance and select k
• Practical Lab Activity