README.md

deduplication

ML model to remove deduplication of records

Requirements:

• Python 2
• Jupyter Notebook
• numpy
• dedupe

Instructions:-

1. Make sure you have Jupyter Notebook installed. If not, do it by typing pip install jupyter in your console.

2. Install numpy and dedupe by typing pip install numpy and pip install dedupe respectively in console.

3. Navigate to the project folder.

4. Open the .ipynb file by typing jupyter notebook .\Deduplication.ipynb in your console.

The notebook will open on a new browser. The code along with output and explanation will be present in the notebook.