Rating is available when the video has been rented.
This feature is not available right now. Please try again later.
Published on Feb 19, 2018
Today I am going to discuss the different steps you will take though a data science project. Just a quick note, not all data science projects will go through all these steps. Some will focus one or two points others you will go through all of them.
1. Data exploration: Before you can do anything with the data you have to know what it is. This will involve topics such as plotting the data to see what it looks like, understanding the kind of data that you have, e.g. numerical, text, categorical.
2. Data cleaning: Once you know what data you have you will have to clean your data. This involves, assessing missing values, looking for incorrect data etc. Its important to note that stage is very likely to be repeated as the subsequent steps could show further peculiarities in your data.
3. Data analysis: Once you have cleaned your data you can begin the nitty gritty analysis of your data. For example, building models to fit your data, using machine learning etc.
4. Data Visualisation: Now that you have some analysis you will want to visualise it. Making sure that each visualisation is clear and sends the message is a key skill to being a good data scientist.
5. Presenting results: All projects will have someone who posed the question or questions. As such, you will need to present the results to that stakeholder(s). First thing to understand is who is in the audience, i.e. technical or non-technical. This will play a big part in the structure and language of your report.
Thanks so much for tuning in to this episode for Deeps’ Data Science Minute! To learn more about these different aspects of data science, head over to www.pivigo.com and in just a few clicks you can access all of our amazing resources to help you at all stages of your data science journey. Best of all registration is free!