Assignment#3

Using Apache spark written in scala NOT java.

1. Read the user_artist_data.txt from the data set available at https://bit.ly/1KiJdOR in spark and print out first 5 entries.

2. Transform the data read in the above step into a data frame with columns user and artist.

3. Generate the good id for the artist from the bad id and than display artist name associated with that id.

4. Build the recommender system using the dataset and evaluate the performance of the system. What metric did you use to evaluate the performance?

5. Select the hyperparameters for your model and evaluate the impact of the performance metric.

Copy and paste the code used to achieve each of the above tasks and the screenshots of your outputs in your report.