Insights from the Instacart Online Grocery Shopping Dataset 2017
Summary
The transition to online grocery ordering is a growing trend. After using pyspark for data preparation and employing machine learning algorithms, I´ve managed to achieve a F1 score of 0.3804. In conclusion, the prediction problem hasn't yet achieved a performance to make a broader impact.
These are the files created in order:
- Data Wrangling (Python 3).ipynb
- Data Storytelling (Pyspark) - Data Wrangling.ipynb
- Data Storytelling (Python 3) - SNA.ipynb
- Inferential Statistics (Python 3).ipynb
- Collaborative Filtering (Pyspark) - Data Wrangling.ipynb
- Collaborative Filtering (Python 3) - Machine Learning.ipynb
- Capstone Project 1 - Milestone Report (Python 3).ipynb
- Capstone Project 1 - Final Submission (R).ipynb