Data Science - Assessment
Data Science - Assessment
You are provided a dataset of a cyclone preheater which is part of an industrial process. In the duration
of operation there are instances of abnormal operations.
Objective:
Using python and any algorithm of your choice, highlight time periods where this abnormality can be
observed.
There are 6 variables and 370k records. Data is recorded once every 5 minutes over a duration of 3
years.
Expected output:
Prepare a zip/rar folder with the following files and share with the ExactSpace team, as indicated. Name
of the folder must be candidate’s “FirstName_LastName_DataScience”
1. Your resume
2. Provide the source code file/s of your work
3. A ppt with 3-5 slides detailing the following:
● Data preparation – What kind of treatment or processing did you apply on the raw data
possible. What was the reasoning behind your specific decisions?
● Analysis strategy – Detail the methodology you followed to analyze the data.
● Insights – What did you find out from the data provided. Where are the abnormal periods
and how did you identify them?