MicroLIA.extract_features
Created on Thu Jan 12 14:30:12 2017
@author: danielgodinez
Module Contents
Functions
|
This function will compute the statistics used to train the RF. |
- MicroLIA.extract_features.extract_all(time: numpy.typing.ArrayLike, mag: numpy.typing.ArrayLike, magerr: numpy.typing.ArrayLike, apply_weights: bool = True, feats_to_use: Optional[List[int]] = None, convert: bool = True, zp: float = 24, return_names: bool = False) Union[numpy.ndarray, Tuple[numpy.ndarray, List[str]]][source]
This function will compute the statistics used to train the RF. Amplitude dependent features are computed first, after which the mag/flux is normalized by the maximum value to compute the remanining features. By default a conversion from mag to flux is performed. If input is in flux or you wish to work in mag, set convert to False.
Parameters:
- timearray
Time of observations
- magarray
Magnitude array.
- magerrarray
Corresponing photometric errors.
- apply_weightsbool, optional
Whether to apply weights based on the magnitude errors. Defaults to True.
- feats_to_usearray
Array containing indices of features to use. This will be used to index the columns in the data array. Defaults to None, in which case all columns in the data array are used.
- convertboolean, optional
If False the features are computed with the input magnitudes, defaults to True to convert and compute in flux.
- zpfloat
Zeropoint of the instrument, only used if convert=True. Defaults to 24.
- return_namesbool
If True the first output will be the stats array, and the second will be the list of corresponding feature names. Defaults to False, in which case only the stats array is returned.
Returns:
- array
All features to use for classification.