Course Outline for Analytics and Data Manipulation with KNIME - Beginners

Course Outline for Analytics and Data Manipulation with KNIME - Beginners

This introductory course is designed for absolute beginners without any prior technical knowledge. The best part about this course is that it gives the learner the power to perform advanced data manipulation and analytics without coding!

KNIME allows us to do data preparation / data cleaning and perform analytics tasks in a very appealing drag and drop interface. (No coding experience is required yet it still allows us if we want to use languages like R, Python or Java. So, we can code if we want but don’t have to!). The flexibility of KNIME makes that happen.

The Goal of this course is to be able to use KNIME for Data Science and Analytics Projects. This is a hand on course. By the end of those course, the learner should be able to:

Learning Outcome

• Comprehend the types of problems and business processes in real life and use KNIME to analyse it.
• Process data with KNIME:
  • Filter Data,
  • Integrate Data
  • Concatenate Data
  • Join Data
• Manipulate Date with KNIME:
  • Discretize Data
  • Normalize Data
  • Pivot Data
• Use Machine Learning for analytics
  • Understand how ML actually works
  • Use pre built ML techniques
  • Understand and manipulate control features for different ML techniques
• Get introduced to some advanced KNIME features
  • Acquire data from external live sources
  • Integrate data from live sources with local data for advanced analytics

The prerequisite for this course are:

• Familiarity with using a personal computer.
• Good command of English language.
• Comfortable using the internet.
• Basic understanding of FIle systems.

This is a Three day course which includes:

Modules

• Introduction to Data Science and Analytics

Use KNIME for scientific methods, processes, algorithms and systems to extract knowledge and insights from structured and unstructured data (primary form excel and csv sources), and apply knowledge and actionable insights from the acquired data.

• Problem Comprehension

Learn the process of understanding the goals and the underlying ‘why’ behind the data in question. The learners will understand how to work with data to clearly define the problem before they can start thinking of solutions.

• Problem Translation

Learn how to break the problem into a process flow that always includes an understanding of the business problem, an understanding of the data that is required, and the types of AI / ML and data science techniques that can solve the problem.

• Data Acquisition

This will demonstrate the various methods of extracting data from common and uncommon sources including API’s.

• Data Cleaning

This will expose the learner to the importance of data cleaning as well as various methods and techniques to identify cleaning requirements as well cleaning techniques.

• Other Data Pre-processing

Conversion, JSON, XML, Pivot, Transformation and other pre processing that are required for successful analytics.

• Machine Learning

Learn KNIME’s drag and drop Machine Learning techniques, as well as how to control nodes and improve efficiency. The primary exposures will be made to XGBoost, Linear Regression, KNN and other common techniques.

• Models

Understand what models of ML are used for analytics for which scenarios without delving too deep into the mathematics of it but rather its practical implementation.

• Classifications

Understand how to use KNIME to undergo the process of predicting the class of given data points. The learner will get hands-on training to classify targets and labels or categories as well as learn techniques to determine which of the features are contributing to the predictive analysis.

• Predictions

Use KNIME to understand various techniques of predicting information from existing data using KNIME’s built-in ML and AI nodes.

• Time Series Analysis

Time series analysis covers various tasks from aggregating and inspecting seasonality in time series to building an AutoRegressive Integrated Moving Average (ARIMA) model and checking the model residuals.