Given training data (train.csv) on Uber/Lyft trip OD locations, starting time and durations, we would like to estimate travel times between two specified locations at a given departure time using machine learning models (SVR, random forest, neural networks, …). 

The training dataset (train.csv) contains a csv file with ride start and end locations (specified as WGS84 coordinates), trip start time (local time), and trip duration in seconds. Each line is a trip and has the following format:

```row_id, start_lng, start_lat, end_lng, end_lat, datetime, duration```

The test dataset (test.csv) contains a csv file with ride start and end locations (specified as WGS84 coordinates), and trip start time (local time). You need to build model based on the training set and estimate the travel times for all trips in the test set. 
Each line in the test set has the following format:

```row_id, start_lng, start_lat, end_lng, end_lat, datetime```

Your output file, titled submission.csv, should have two columns: row id (row_id) and estimated duration (duration) in seconds for each line in the test file, where the row_id column refers to the corresponding row in the test file for which you are making the prediction. It should also have the following header specified as the first line of the file:

```row_id, duration```