rail.interactive.estimation.algos.k_nearneigh module

rail.interactive.estimation.algos.k_nearneigh.k_near_neigh_estimator(**kwargs)

KNN-based estimator

—

The main interface method for the photo-z estimation

This will attach the input data (defined in inputs as “input”) to this Estimator (for introspection and provenance tracking). Then call the run(), validate(), and finalize() methods.

The run method will call _process_chunk(), which needs to be implemented in the subclass, to process input data in batches. See RandomGaussEstimator for a simple example.

Finally, this will return a QPHandle for access to that output data.

—

This function was generated from the function rail.estimation.algos.k_nearneigh.KNearNeighEstimator.estimate

Parameters:

  • input_data (TableLike, required) – A dictionary of all input data

  • model (numpy.ndarray, required)

  • chunk_size (int, optional) – Number of objects per chunk for parallel processing or to evalute per loop in single node processing Default: 10000

  • hdf5_groupname (str, optional) – name of hdf5 group for data, if None, then set to ‘’ Default: photometry

  • zmin (float, optional) – The minimum redshift of the z grid or sample Default: 0.0

  • zmax (float, optional) – The maximum redshift of the z grid or sample Default: 3.0

  • nzbins (int, optional) – The number of gridpoints in the z grid Default: 301

  • id_col (str, optional) – name of the object ID column Default: object_id

  • redshift_col (str, optional) – name of redshift column Default: redshift

  • calc_summary_stats (bool, optional) – Compute summary statistics Default: False

  • calculated_point_estimates (list, optional) – List of strings defining which point estimates to automatically calculate using qp.Ensemble.Options include, ‘mean’, ‘mode’, ‘median’. Default: []

  • recompute_point_estimates (bool, optional) – Force recomputation of point estimates Default: False

  • bands (list, optional) – Names of columns for magnitude by filter band Default: [‘mag_u_lsst’, ‘mag_g_lsst’, ‘mag_r_lsst’, ‘mag_i_lsst’,…]

  • ref_band (str, optional) – band to use in addition to colors Default: mag_i_lsst

  • nondetect_val (float, optional) – value to be replaced with magnitude limit for non detects Default: 99.0

  • mag_limits (dict, optional) – Limiting magnitudes by filter Default: {‘mag_u_lsst’: 27.79, ‘mag_g_lsst’: 29.04, ‘mag_r_lsst’: 29.06,…}

Returns:

Handle providing access to QP ensemble with output data

Return type:

qp.core.ensemble.Ensemble

rail.interactive.estimation.algos.k_nearneigh.k_near_neigh_informer(**kwargs)

Train a KNN-based estimator

—

The main interface method for Informers

This will attach the input_data to this Informer (for introspection and provenance tracking).

Then it will call the run(), validate() and finalize() methods, which need to be implemented by the sub-classes.

The run() method will need to register the model that it creates to this Estimator by using self.add_data(‘model’, model).

Finally, this will return a ModelHandle providing access to the trained model.

—

This function was generated from the function rail.estimation.algos.k_nearneigh.KNearNeighInformer.inform

Parameters:

  • training_data (TableLike, required) – dictionary of all input data, or a TableHandle providing access to it

  • hdf5_groupname (str, optional) – name of hdf5 group for data, if None, then set to ‘’ Default: photometry

  • zmin (float, optional) – The minimum redshift of the z grid or sample Default: 0.0

  • zmax (float, optional) – The maximum redshift of the z grid or sample Default: 3.0

  • nzbins (int, optional) – The number of gridpoints in the z grid Default: 301

  • nondetect_val (float, optional) – value to be replaced with magnitude limit for non detects Default: 99.0

  • mag_limits (dict, optional) – Limiting magnitudes by filter Default: {‘mag_u_lsst’: 27.79, ‘mag_g_lsst’: 29.04, ‘mag_r_lsst’: 29.06,…}

  • bands (list, optional) – Names of columns for magnitude by filter band Default: [‘mag_u_lsst’, ‘mag_g_lsst’, ‘mag_r_lsst’, ‘mag_i_lsst’,…]

  • ref_band (str, optional) – band to use in addition to colors Default: mag_i_lsst

  • redshift_col (str, optional) – name of redshift column Default: redshift

  • train_frac (float, optional) – fraction of training data used to make tree, rest used to set best sigma Default: 0.75

  • seed (int, optional) – Random number seed for NN training Default: 0

  • sigma_grid_min (float, optional) – minimum value of sigma for grid check Default: 0.01

  • sigma_grid_max (float, optional) – maximum value of sigma for grid check Default: 0.075

  • ngrid_sigma (int, optional) – number of grid points in sigma check Default: 10

  • leaf_size (int, optional) – min leaf size for KDTree Default: 15

  • nneigh_min (int, optional) – int, min number of near neighbors to use for PDF fit Default: 3

  • nneigh_max (int, optional) – int, max number of near neighbors to use ofr PDF fit Default: 7

  • only_colors (bool, optional) – if only_colors True, then do not use ref_band mag, only use colors Default: False

Returns:

Handle providing access to trained model

Return type:

numpy.ndarray