def algo_diagnostics(dataset_config, yatsm_config, X, y,
row, col, algo, n_fold, make_plots=True):
""" Display algorithm diagnostics for a given X and y
Args:
dataset_config (dict): dict of dataset configuration options
yatsm_config (dict): dict of YATSM algorithm options
X (np.ndarray): X feature input used in classification
y (np.ndarray): y labeled examples
row (np.ndarray): row pixel locations of `y`
col (np.ndarray): column pixel locations of `y`
algo (sklearn classifier): classifier used from scikit-learn
n_fold (int): number of folds for crossvalidation
make_plots (bool, optional): show diagnostic plots (default: True)
"""
# Print algorithm diagnostics without crossvalidation
logger.info('<----- DIAGNOSTICS ----->')
if hasattr(algo, 'oob_score_'):
logger.info('Out of Bag score: {p}'.format(p=algo.oob_score_))
kfold_summary = np.zeros((0, 2))
logger.info('<----------------------->')
logger.info('KFold crossvalidation scores:')
kf = KFold(y.size, n_folds=n_fold)
kfold_summary = np.vstack((kfold_summary,
diagnostics.kfold_scores(X, y, algo, kf)
))
logger.info('<----------------------->')
logger.info('Stratified KFold crossvalidation scores:')
kf = StratifiedKFold(y, n_folds=n_fold)
kfold_summary = np.vstack((kfold_summary,
diagnostics.kfold_scores(X, y, algo, kf)
))
logger.info('<----------------------->')
logger.info('Spatialized shuffled KFold crossvalidation scores:')
kf = diagnostics.SpatialKFold(y, row, col, n_folds=n_fold, shuffle=True)
kfold_summary = np.vstack((kfold_summary,
diagnostics.kfold_scores(X, y, algo, kf)
))
if make_plots:
test_names = ['KFold',
'Stratified KFold',
'Spatial KFold (shuffle)'
]
plots.plot_crossvalidation_scores(kfold_summary, test_names)
logger.info('<----------------------->')
if hasattr(algo, 'feature_importances_'):
logger.info('Feature importance:')
logger.info(algo.feature_importances_)
if make_plots:
plots.plot_feature_importance(algo, dataset_config, yatsm_config)
def algo_diagnostics(cfg, X, y, row, col, algo, n_fold, make_plots=True):
""" Display algorithm diagnostics for a given X and y
Args:
cfg (dict): YATSM configuration dictionary
X (np.ndarray): X feature input used in classification
y (np.ndarray): y labeled examples
row (np.ndarray): row pixel locations of `y`
col (np.ndarray): column pixel locations of `y`
algo (sklearn classifier): classifier used from scikit-learn
n_fold (int): number of folds for crossvalidation
make_plots (bool, optional): show diagnostic plots (default: True)
"""
# Print algorithm diagnostics without crossvalidation
logger.info("<----- DIAGNOSTICS ----->")
if hasattr(algo, "oob_score_"):
logger.info("Out of Bag score: %f" % algo.oob_score_)
kfold_summary = np.zeros((0, 2))
test_names = ["KFold", "Stratified KFold", "Spatial KFold (shuffle)"]
def report(kf):
logger.info("<----------------------->")
logger.info("%s crossvalidation scores:" % kf.__class__.__name__)
try:
scores = diagnostics.kfold_scores(X, y, algo, kf)
except Exception as e:
logger.warning("Could not perform %s cross-validation: %s" % (kf.__class__.__name__, e.message))
else:
return scores
kf = KFold(y.size, n_folds=n_fold)
kfold_summary = np.vstack((kfold_summary, report(kf)))
kf = StratifiedKFold(y, n_folds=n_fold)
kfold_summary = np.vstack((kfold_summary, report(kf)))
kf = diagnostics.SpatialKFold(y, row, col, n_folds=n_fold, shuffle=True)
kfold_summary = np.vstack((kfold_summary, report(kf)))
if make_plots:
plots.plot_crossvalidation_scores(kfold_summary, test_names)
logger.info("<----------------------->")
if hasattr(algo, "feature_importances_"):
logger.info("Feature importance:")
logger.info(algo.feature_importances_)
if make_plots:
plots.plot_feature_importance(algo, cfg)
def algo_diagnostics(X, y, row, col, algo):
""" Display algorithm diagnostics for a given X and y
Args:
X (np.ndarray): X feature input used in classification
y (np.ndarray): y labeled examples
row (np.ndarray): row pixel locations of `y`
col (np.ndarray): column pixel locations of `y`
algo (sklearn classifier): classifier used from scikit-learn
"""
# Print algorithm diagnostics without crossvalidation
logger.info('<----- DIAGNOSTICS ----->')
if hasattr(algo, 'oob_score_'):
logger.info('Out of Bag score: {p}'.format(p=algo.oob_score_))
kfold_summary = np.zeros((0, 2))
logger.info('<----------------------->')
logger.info('KFold crossvalidation scores:')
kf = KFold(y.size, n_folds=n_fold)
kfold_summary = np.vstack(
(kfold_summary, diagnostics.kfold_scores(X, y, algo, kf)))
logger.info('<----------------------->')
logger.info('Stratified KFold crossvalidation scores:')
kf = StratifiedKFold(y, n_folds=n_fold)
kfold_summary = np.vstack(
(kfold_summary, diagnostics.kfold_scores(X, y, algo, kf)))
logger.info('<----------------------->')
logger.info('Spatialized shuffled KFold crossvalidation scores:')
kf = diagnostics.SpatialKFold(y, row, col, n_folds=n_fold, shuffle=True)
kfold_summary = np.vstack(
(kfold_summary, diagnostics.kfold_scores(X, y, algo, kf)))
if make_plots:
test_names = ['KFold', 'Stratified KFold', 'Spatial KFold (shuffle)']
plots.plot_crossvalidation_scores(kfold_summary, test_names)
logger.info('<----------------------->')
if hasattr(algo, 'feature_importances_'):
logger.info('Feature importance:')
logger.info(algo.feature_importances_)
if make_plots:
plots.plot_feature_importance(algo, dataset_config, yatsm_config)