actsnclass.run_time_domain

actsnclass.run_time_domain(user_choice)

Command line interface to the Time Domain Active Learning scenario.

Parameters:

• -d (sequence) – List of 2 elements. First and last day of observations since the beginning of the survey.
• -m (str) – Full path to output file to store metrics of each loop.
• -q (str) – Full path to output file to store the queried sample.
• -f (str) – Complete path to directory holding features files for all days.
• -s (str) – Query strategy. Options are ‘UncSampling’ and ‘RandomSampling’.
• -b (int (optional)) – Size of batch to be queried in each loop. Default is 1.
• -c (str (optional)) – Machine Learning algorithm. Currently only ‘RandomForest’ is implemented.
• -fm (str (optional)) – Feature extraction method. Currently only ‘Bazin’ is implemented.
• -sc (bool (optional)) – If True, display comment with size of samples on screen.
• -t (str or int) – Choice of initial training sample. If ‘original’: begin from the train sample flagged in the file If int: choose the required number of samples at random, ensuring that at least half are SN Ia Default is ‘original’.

Returns:

• metric file (file) – File with metrics calculated in each iteration.
• queried file (file) – All objects queried during the search, in sequence.

Examples

Use directly from the command line.

>>> run_time_domain.py -d <first day of survey> <last day of survey>
>>>        -m <output metrics file> -q <output queried file> -f <features directory>
>>>        -s <learning strategy> -fm <path to full light curve features >

Be aware to check the default options as well!