This is the Data Mavericks team repository we used, to communicate our insights we gathered with each other during the datathon competition at the MN Data Derby 2023. We eventually ended up third in the Advanced competition. The task during this competition was to gather insights on food prices and inflation, including differences during the covid years and the start of the war in Ukraine. Besides gathering insides, we also got the task to forecast the food prices for the years 2023 and 2024, which we took even further up to 2030. The complete task can be found in the 2023 Data Derby Challenge Questions file.
This is a description of what each folders in this branch contains:
- In the [DATA] originals folder you can find the original XLSL files that we got from the Data Derby organization.
- In the [DATA] preprocessed csv's folder you can find the CSV files that have been preprocessed from the XLSL files.
- In the [DATA] extra folder you can find CSV files that were found online on publicly accessible websites. These data were used to further improve our insights and forecasting model.
- In the [Notebooks] data preprocessing folder you can find the Jupyter Notebooks that have been used within this Data Derby Project to preprocess the data from its original XSLS files to CSV files.
- In the [Notebooks] question insights folder you can find the Jupyter Notebooks that have been used to gather the insights to answer each question.
Finally, the final presentation we used to share our insights with the jury on April 8th, 2023 can be found in the file Data Derby Presentation - Data Mavericks.pptx.
Feel free to leave feedback as this would help us further improve ourselves!
Thank you, Team Data Mavericks