%%viewer [https://player.vimeo.com/video/670141220?h=3e15012ff4] %%

__%%( color: #003399; font-size: 30px;)Data Analytics:__

In the current developments towards a smart industry (4.0), more and more data is collected concerning your operation processes. Insights in the data could contribute to improving these processes. After getting the data from your systems, and validating it with help of the Data Validation tool, the Process Data Analytics tools provides insights consisting of reports, visualizations and other analysis methods that describe the state of your processes and/or machinery. The process analytics tool consists of several data analytics modules that describe and analyse the underlying process data. In this tool, we strive to perform data science techniques such as classification, clustering and pattern mining accompanied by visualizations. Within the tool, we focus on the analyzing Time Series data.


\\__%%( color: #003399; font-size: 16px;)Type of tool:__ desktop application to install \\
\\__%%( color: #003399; font-size: 16px;)Short description of the tool: __
The tool is meant to guide users into starting with using Data Analytics at their organization.\\
\\__%%( color: #003399; font-size: 16px;)Required skills: __

- Process/material: e.g. knowledge of material properties\\
- Digitalization: Installation of programming tools\\

\\__%%( color: #003399; font-size: 16px;)Required programs %%( color: #003000; font-size: 14px;)(step-by-step guide and links provided in user guideline blow): __
\\- Python 
\\- Java
\\- Anaconda
\\- Tool files from the GitHub (link below)


\\__%%( color: #003399; font-size: 24px;)This tool supports you to:__ 

- Visualize process data

- Compare two production runs (one with virgin material and one with recyclate) 

- Explore patterns inside a dataset 



\\__%%( color: #003399; font-size: 18x;)Example use case:__ 

After validating your data with help of e.g., the data validation tool, we can begin analyzing to get further insights.
The Data Analytics tool is an interactive dashboard that helps with interpreting the variables in your dataset with help of visuals.
By providing your own data in the 'data' folder, several analytical options are at your disposal.
For example, a correlation plot that gives insights into which variables are behaving similarly, or a PCA analysis that will help determining the most influential variables in your dataset.

\\__%%( color: #003399; font-size: 24px;)Tool guideline and access: __
\\ - ⚠️ We recommend to open and save the user guideline before proceeding: [Data Analytics/Di-Plast_Data Analytics_Installation Guideline.docx]
\\- Get the code/installation files from [https://github.com/cslab-hub/DataAnalytics_Diplast]

\\__%%( color: #003399; font-size: 16px;)Contact person of the tool: __
Jurgen van den Hoogen [mailto:j.o.d.hoogen@jads.nl] & Stefan Bloemheuvel [mailto:s.d.bloemheuvel@jads.nl] form the Jheronimus Academy of Data Science (JADS).

__%%( color: #003399; font-size: 16px;)Screenshots:__
%%carousel 
  [Data Analytics/data_analytics_home.png]
  [Data Analytics/data_analytics_feature_selection.png]
  [Data Analytics/data_analytics_comparison.png]
  [Data Analytics/data_analytics_final_data_report.png]
/%

\\
\\
__%%( color: #003399; font-size: 24px;)Related tools:__

__%%( color: #003399; font-size: 16px;) Before applying this tool:__
\\We recommend also taking a look at the following Di-Plast tools below. They can help you to gather necessary information and data, help to better prepare your data and continue working with it afterwards:
\\--> Improve internal information and material flow -> [VSM]
\\--> Get guidance to set up a working data infrastructure -> [Data Infrastructure Wiki]
\\--> Find the right sensor to survey your process -> [Sensor Tool]
\\--> Validate your process data -> [Data Validation]
\\
\\__%%( color: #003399; font-size: 16px;)After applying this tool:__
\\-->Get important insights in enhancing your data understanding
 -> [Exploratory Pattern Analytics]
\\-->Match material requirements with material properties -> [Matrix]