Udemy
Turn what you know into an opportunity and reach millions around the world.
Learn More
Your cart is empty.
Keep shopping
KNIME for Data Science and Data Cleaning
Rating: 4.5 out of 5(47 ratings)
382 students

KNIME for Data Science and Data Cleaning

Data Science with KNIME , How to do data cleaning with KNIME, AI Machine learning with KNIME, ETL with KNIME, data prep
Created byDan We
Last updated 3/2025
English
English [Auto],

What you'll learn

  • How to use Tensorflow in KNIME
  • How to do DataScience in KNIME WITH AND WITHOUT CODING
  • How to solve data cleaning and data preparation challenges
  • How to replace Excel and start KNIME for ETL and data cleaning issues
  • Examples of data science machine learning workflows with KNIME
  • Hopefully a higher efficiency in data preparation and data science related work
  • Enhance your basic KNIME skills already acquired ( for example in my KNIME crash course on udemy)

Course content

2 sections • 24 lectures • 2h 51m total length

  • 1 Welcome to Knime Lets get started0:55

    Discover how KNIME accelerates data science and data cleaning by building a no-code natural language processing workflow and exploring transfer learning with Python, enabling faster, more efficient analytics.

  • Before you start0:23
  • Download all resources0:03

    Attached you can download the resources

  • 4 Copying or Moving files with KNIME7:35

    Learn to copy and move files in KNIME using the transfer files note, filter for sales Excel files, and copy them into a new destination folder.

  • 5 Reading multiple excel files - potential errors and solutions8:22

    Learn how to read multiple Excel files in KNIME with the Excel reader, configure folder inputs, filter by extensions, manage headers and data types, and troubleshoot structure mismatches.

  • 6 Reading multiple Excel files - benefits of loops10:26

    Learn to read multiple Excel files with a loop in KNIME, filtering by folder path and Excel extension, and handle varied column types with flexible loop settings.

  • 7 Excel files with different table structure in KNIME8:19

    Demonstrate reading Excel files with different table structures in KNIME by listing files, looping through them, and merging columns to align the schema for a single output data table.

  • 8 Useful Nodes - Column Aggregations13:07

    Learn to use the column aggregator node to concatenate and aggregate multiple columns, handle missing values, and apply numeric and text data methods to produce yearly totals.

  • 9 Countries - data cleaning challenge8:48

    Learn to clean a country data set in KNIME using the unbefitting note, the cell splitter note, and the pivoting note to transform, split, and re-pivot data while preserving country.

  • 10 Merge Table Challenge in KNIME7:06

    Merge Excel tables in Knime by mapping characters to series using a dynamic chunk loop. Extract table dimensions to set rows per chunk and append columns to build a dataset.

  • 11 A Json file challenge in KNIME13:36

    Learn to use KNIME for data science and data cleaning by building a dataprep workflow that reads json, extracts countries and cities, and assembles a final country-city table.

  • 12 Create the Neural Network h5 model file to be used in Knime8:48

    Develop a neural network with Keras on the Boston housing data, scale features, train with early stopping and model checkpoint, and save the h5 file for KNIME predictions.

  • 13 Mismatching addresses - Introduction to similarity search in KNIME8:12

    Learn to match mismatched and misspelled addresses in KNIME using fuzzy matching and the similarity search, leveraging Levenshtein distance and nearest neighbor results.

  • 14 Tensorflow Neural Network Regression Implementation in Knime10:15

    Load a pre-trained TensorFlow regression model in KNIME, read and scale Excel data, split features from the target, and produce a house-price prediction for comparison with the original value.

  • 15 Transferlearning in Knime using Python scripts11:42

    Explore transfer learning in Knime using Python scripts, loading TensorFlow models like ResNet50, preprocessing images, and exporting predictions to a dataframe via the Python source node.

  • 16 Introduction to NLP in KNIME8:59

    Learn how to perform sentiment analysis in KNIME using a Twitter dataset, convert sentiment to string, balance classes with stratified sampling, and convert tweets into documents for natural language processing.

  • 17 NLP in KNIME 2 Data preprocessing and cleaning9:09
  • 18 NLP in KNIME 3 bag of words and document vector8:56

    Knime creates a bag of words from preprocessed tweets, computes relative term frequency, builds a document vector with a sentiment label, shuffles data, and filters to prepare for modeling.

  • 19 NLP in KNIME Choose ML Algorithm and score our model7:30

    Explore NLP in KNIME by building a decision tree workflow, with options like random forest or SVM, then filter the class column, train, and score for accuracy on training data.

  • Congratulations, thanks a lot and one favor to ask0:21
  • You want to learn more? Lets do it together0:55

Requirements

  • for beginners with KNIME my KNIME crash course on udemy is highly recommended to take first
  • No extra costs - KNIME can be downloaded for free
  • Basic knowledge of machine learning is certainly helpful for the later lectures in this course
  • The course complements my other Data science course with KNIME on udemy (I try to keep the overlapp as little as possible to give you the best kind of experience)

Description

Data science and Data cleaning and Data preparation with KNIME

Hello everyone hope you are doing fine.

Let’s face it. Data preparation ,data cleaning, data preprocessing (whatever you want to call it) is most often the most tedious and time consuming work in the data science / data analysis area.

So many people ask: How can we speed up the process and be more efficient?

Well one option could be to use tools which allow us to speed up the process (and sometimes reduce the amount of code we need to write).

Meet KNIME



A great tool which comes to our rescue. KNIME allows us to do data preparation / data cleaning 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. WITH KNIME we can also do Data Science, so machine learning and AI with or without coding.

And the best: The Desktop version is completely free!


So, is it worth it to dive deeper into KNIME? ABSOLUTELY!


This course is the third KNIME class and expands the knowledge you have acquired in the other classes

"KNIME - a crash course for beginners"

"Data science and Data preparation with KNIME"


Please note: For some examples we use Python in combination with KNIME. So if you have no prior Python knowledge the section might be a bit harder for you. But if you follow along it is definitely worth it!


We do not cover the basics (e.g. the interface, basic data import and filter nodes,...) here. If you need  to refresh your knowlege or you have not had the chance to learn the basics I would highly recommend to check at least the crash course first (which covers all the basics in a great and funny case study!)

In this class we extend our skills by

  • learning to use additional helpful KNIME nodes not covered in the other two classes

  • solve data cleaning challenges together

  • use pretrained models in tensorflow in KNIME (involves Python coding)

  • learn the fundametals for NLP tasks (Natural language processing) in KNIME using only KNIME nodes (without any additional coding)

If that does not sound like fun, then what? So, if that is interesting to you then let’s get started!

Are you ready? 

Who this course is for:

  • (Aspiring) data scientists
  • (Aspiring) data analysts
  • Everyone interested in the data analysis , data analytics and data science area
  • data scientists / analysts who want to work smarter faster and more efficient
  • Excel users who want to learn better ways to prepare data. Excel is nice but KNIME is AWESOME!

Report abuse