Your goal is to predict the total_cases label for each (city, year, weekofyear) in the test set. There are two cities, San Juan and Iquitos, with test data for each city spanning 5 and 3 years respectively. You will make one submission that contains predictions for both cities. The data for each city have been concatenated along with a city column indicating the source: sj for San Juan and iq for Iquitos. The test set is a pure future hold-out, meaning the test data are sequential and non-overlapping with any of the training data. Throughout, missing values have been filled as NaNs.

Pls follow full description of the project here https://www.drivendata.org/competitions/44/dengai-predicting-disease-spread/page/82/

Review it and assess if this is a good project, if it was the join!