Data Processing and Exploratory Data Analysis

Learn how to employ some classic exploratory data analysis methods on a particular use case.

rate limit

Code not recognized.

About this course

Welcome to the course on data processing and exploratory data analysis
Imagine you are a maintenance engineer who is interested in figuring out what data you have available in Open Industrial Data. In other words, you are interested in getting to know your data better by employing some classic exploratory data analysis methods. You also know that the pressure transmitter for the suction gas outlet spikes occasionally during operation. Are we able to identify these periods statistically? You will learn how to retrieve TimeSeries data from CDF, find TimeSeries with incomplete information, update TimeSeries, determine the correlation between two sets of data, and use statistics to characterize anomalous periods.

You will learn how to:

  • Retrieve TimeSeries data from CDF
  • Find TimeSeries with incomplete information
  • Update TimeSeries
  • Determine the correlation between two sets of data
  • Use statistics to characterize anomalous periods

Who should take this course?
This course was created for anybody interested to learn more about data science in practice.
This course is independent, but also part of the learning path of Getting hands-on with data science. We recommend that first, you take all courses from the Data Science Fundamentals series.

Prerequisites
Access to Open Industrial Data and Jupyter notebook installed on your computer. You can find information on how to install Jupyter Notebooks here.

Instructors
This course was developed by Cognite Academy.



Omar Akabbal



Rebecca Seyfarth



Angela Atkinson

Curriculum

  • Preview
    What's the story?
  • Welcome
  • What you are going to achieve in this course?
  • Set up
  • Access to the CDF project
  • Open Industrial Data
  • Notebook set up
  • Identify missing components in time-series data
  • Intro
  • Notebook explained
  • Check your knowledge
  • Determine Correlation Between Two Sets of Data
  • Intro
  • Video walkthrough
  • Notebook explained
  • Calculate Deviation to Find Periods of Great Variance
  • Intro
  • Video walkthrough
  • Notebook explained
  • Overall Statistical Analysis
  • Intro
  • Video walkthrough
  • Notebook explained
  • Key takeaways
  • Feedback

About this course

Welcome to the course on data processing and exploratory data analysis
Imagine you are a maintenance engineer who is interested in figuring out what data you have available in Open Industrial Data. In other words, you are interested in getting to know your data better by employing some classic exploratory data analysis methods. You also know that the pressure transmitter for the suction gas outlet spikes occasionally during operation. Are we able to identify these periods statistically? You will learn how to retrieve TimeSeries data from CDF, find TimeSeries with incomplete information, update TimeSeries, determine the correlation between two sets of data, and use statistics to characterize anomalous periods.

You will learn how to:

  • Retrieve TimeSeries data from CDF
  • Find TimeSeries with incomplete information
  • Update TimeSeries
  • Determine the correlation between two sets of data
  • Use statistics to characterize anomalous periods

Who should take this course?
This course was created for anybody interested to learn more about data science in practice.
This course is independent, but also part of the learning path of Getting hands-on with data science. We recommend that first, you take all courses from the Data Science Fundamentals series.

Prerequisites
Access to Open Industrial Data and Jupyter notebook installed on your computer. You can find information on how to install Jupyter Notebooks here.

Instructors
This course was developed by Cognite Academy.



Omar Akabbal



Rebecca Seyfarth



Angela Atkinson

Curriculum

  • Preview
    What's the story?
  • Welcome
  • What you are going to achieve in this course?
  • Set up
  • Access to the CDF project
  • Open Industrial Data
  • Notebook set up
  • Identify missing components in time-series data
  • Intro
  • Notebook explained
  • Check your knowledge
  • Determine Correlation Between Two Sets of Data
  • Intro
  • Video walkthrough
  • Notebook explained
  • Calculate Deviation to Find Periods of Great Variance
  • Intro
  • Video walkthrough
  • Notebook explained
  • Overall Statistical Analysis
  • Intro
  • Video walkthrough
  • Notebook explained
  • Key takeaways
  • Feedback