Hands-On Automated Machine Learning

Profiling your Python script line by line

Go to your Terminal and run the following command:

$ pip install line_profiler

Once installation is finished, you can save the preceding snippet to a filename knn_prediction.py.

As you have noticed, nearest_neighbors_prediction is decorated as follows:

@profiledef nearest_neighbors_prediction(x, data, labels, k): …

It allows line_profiler to know which function to profile. Run the following command to save the profile results:

$ kernprof -l knn_prediction.py

The output will be as follows:

StartWrote profile results to knn_prediction.py.lprof

You can view the profiler results as follows:

$ python -m line_profiler knn_prediction.py.lprofTimer unit: 1e-06 sTotal time: 0.001079 sFile: knn_prediction.py ...