Returning to our case study, let's develop a univariate linear regression model in Apache Spark using its machine learning library, MLlib, in order to predict the total daily bike renters using our bike sharing dataset:
The following sub-sections describe each of the pertinent cells in the corresponding Jupyter Notebook for this use case, entitled chp04-01-univariate-linear-regression.ipynb, and which may be found in the GitHub repository accompanying this book.
- First, we import the required Python dependencies, including pandas (Python data analysis library), matplotlib (Python plotting library), and pyspark (Apache Spark Python API). By using the %matplotlib magic function, any plots that we ...
