This project uses a Linear Regression model to predict ice cream sales based on temperature data. It was my first hands-on experience with scikit-learn and Azure Machine Learning, where I trained, tested, and deployed a regression model through a local notebook.
The goal was to estimate the number of ice cream sales given certain temperature values. After training the model, it was able to make predictions such as 1444 and 908 sales for different temperature inputs.
The notebook includes:
- Data preprocessing and visualization
- Model training with scikit-learn
- Model evaluation
- Connection to Azure ML for deployment and testing
This project taught me several important concepts, including:
- How to build and train a regression model using scikit-learn
- How to prepare and register datasets for testing in Azure ML
- How to deploy a trained model to Azure Machine Learning
- How to communicate with the deployed model via endpoints
- Basic use of the Azure CLI to manage resources and workflows
- Python
- scikit-learn
- Azure Machine Learning
- Azure CLI
- Jupyter Notebook
The model produced rounded sales predictions close to 1444 and 908, showing that even a simple regression approach can provide valuable insights.
This project represents my first steps into machine learning model deployment and cloud integration using Azure ML.