Install
Download the Bot and follow the instructions to install it in your AAE Control Room.
Impact Analysis Using Correlation Model
This bot performs a statistical parametric correlation operation among multiple numerical variables and provides the impact and degree of relationship.
Top Benefits
- Improve Decision Making: Better decision making for real world applications.
- Increase Productivity: Save 30% of time in the feature selection process and automation workflow creation.
- Zero Maintenance: Model is provided as SaaS using the serverless function architecture of Azure.
- Runs in Cloud: Model runs in Azure and provides output without needing an infrastructure to run.
- Ease of use: Model is easy to setup, highly scalable, and fault tolerant (Each request is independent of another request).
Tasks
- The correlation bot performs parametric 'Pearson correlation'.
- The bot provides correlation coefficients (r) among variables.
- The bot helps in understanding the extent of a relationship among numerical variables to make data-driven business decisions.
This bot performs a statistical parametric correlation operation among multiple numerical variables and provides the impact and degree of relationship.
Inputs:
- Path: Path of the CSV file. For example: C:~Housing.csv
- Column Count: Count of columns available in CSV file being provided with input data.
- Input Column Names: Name of columns being provided in CSV file. For example 'SNo','Price','Lotsize','Bedrooms'......
- Input Column Data Type: Data Type of columns being provided in CSV file in the same order as column names. For example: 'Numeric','Numeric','Numeric'......
- Missing Number Value Replacement: A value that can be used by Model in case CSV file has blank field/s or missing numerical value/s.
- Ignore Columns: Column name that the model should ignore while calculating correlation. For example: 'SNo','Driveway','Recroom'......
- The bot takes a CSV file as an input, performs a parametric correlation operation on numerical variables and provides output in Excel to exhibit the extent of a relationship (not causality).
- Output: The result in Excel.
- Column field1 and field2 has the column names on which correlation has been processed.
- Column correlation has the extent of relationship for each combination.