def __init__(self, clf, scoring="roc_auc", verbose=0):
"""
Initializes the class.
Args:
clf (binary classifier):
Model fitted on X_train.
scoring (string or probatus.utils.Scorer, optional):
Metric for which the model performance is calculated. It can be either a metric name aligned with
predefined classification scorers names in sklearn
([link](https://scikit-learn.org/stable/modules/model_evaluation.html)).
Another option is using probatus.utils.Scorer to define a custom metric.
verbose (int, optional):
Controls verbosity of the output:
- 0 - nether prints nor warnings are shown
- 1 - 50 - only most important warnings
- 51 - 100 - shows other warnings and prints
- above 100 - presents all prints and all warnings (including SHAP warnings).
"""
self.clf = clf
self.scorer = get_single_scorer(scoring)
self.verbose = verbose
def __init__(
self,
clf,
scoring="roc_auc",
test_prc=0.25,
n_jobs=1,
verbose=0,
random_state=None,
):
"""
Initializes the class.
Args:
clf (model object):
Binary classification model or pipeline.
scoring (string or probatus.utils.Scorer, optional):
Metric for which the model performance is calculated. It can be either a metric name aligned with
predefined
[classification scorers names in sklearn](https://scikit-learn.org/stable/modules/model_evaluation.html).
Another option is using probatus.utils.Scorer to define a custom metric. The recommended option for this
class is 'roc_auc'.
test_prc (float, optional):
Percentage of data used to test the model. By default 0.25 is set.
n_jobs (int, optional):
Number of parallel executions. If -1 use all available cores. By default 1.
verbose (int, optional):
Controls verbosity of the output:
- 0 - neither prints nor warnings are shown
- 1 - 50 - only most important warnings
- 51 - 100 - shows other warnings and prints
- above 100 - presents all prints and all warnings (including SHAP warnings).
random_state (int, optional):
Random state set at each round of feature elimination. If it is None, the results will not be
reproducible and in random search at each iteration a different hyperparameters might be tested. For
reproducible results set it to an integer.
""" # noqa
self.clf = clf
self.test_prc = test_prc
self.n_jobs = n_jobs
self.random_state = random_state
self.verbose = verbose
self.scorer = get_single_scorer(scoring)
def __init__(
self,
clf,
step=1,
min_features_to_select=1,
cv=None,
scoring="roc_auc",
n_jobs=-1,
verbose=0,
random_state=None,
):
"""
This method initializes the class.
Args:
clf (binary classifier, sklearn compatible search CV e.g. GridSearchCV, RandomizedSearchCV or BayesSearchCV):
A model that will be optimized and trained at each round of feature elimination. The recommended model
is [LGBMClassifier](https://lightgbm.readthedocs.io/en/latest/pythonapi/lightgbm.LGBMClassifier.html),
because it by default handles the missing values and categorical variables. This parameter also supports
any hyperparameter search schema that is consistent with the sklearn API e.g.
[GridSearchCV](https://scikit-learn.org/stable/modules/generated/sklearn.model_selection.GridSearchCV.html),
[RandomizedSearchCV](https://scikit-learn.org/stable/modules/generated/sklearn.model_selection.RandomizedSearchCV.html)
or [BayesSearchCV](https://scikit-optimize.github.io/stable/modules/generated/skopt.BayesSearchCV.html#skopt.BayesSearchCV).
step (int or float, optional):
Number of lowest importance features removed each round. If it is an int, then each round such a number of
features are discarded. If float, such a percentage of remaining features (rounded down) is removed each
iteration. It is recommended to use float, since it is faster for a large number of features, and slows
down and becomes more precise with fewer features. Note: the last round may remove fewer features in
order to reach min_features_to_select.
If columns_to_keep parameter is specified in the fit method, step is the number of features to remove after
keeping those columns.
min_features_to_select (int, optional):
Minimum number of features to be kept. This is a stopping criterion of the feature elimination. By
default the process stops when one feature is left. If columns_to_keep is specified in the fit method,
it may overide this parameter to the maximum between length of columns_to_keep the two.
cv (int, cross-validation generator or an iterable, optional):
Determines the cross-validation splitting strategy. Compatible with sklearn
[cv parameter](https://scikit-learn.org/stable/modules/generated/sklearn.feature_selection.RFECV.html).
If None, then cv of 5 is used.
scoring (string or probatus.utils.Scorer, optional):
Metric for which the model performance is calculated. It can be either a metric name aligned with predefined
[classification scorers names in sklearn](https://scikit-learn.org/stable/modules/model_evaluation.html).
Another option is using probatus.utils.Scorer to define a custom metric.
n_jobs (int, optional):
Number of cores to run in parallel while fitting across folds. None means 1 unless in a
`joblib.parallel_backend` context. -1 means using all processors.
verbose (int, optional):
Controls verbosity of the output:
- 0 - neither prints nor warnings are shown
- 1 - 50 - only most important warnings
- 51 - 100 - shows other warnings and prints
- above 100 - presents all prints and all warnings (including SHAP warnings).
random_state (int, optional):
Random state set at each round of feature elimination. If it is None, the results will not be
reproducible and in random search at each iteration a different hyperparameters might be tested. For
reproducible results set it to an integer.
""" # noqa
self.clf = clf
if isinstance(self.clf, BaseSearchCV):
self.search_clf = True
else:
self.search_clf = False
if (isinstance(step, int) or isinstance(step, float)) and step > 0:
self.step = step
else:
raise (ValueError(
f"The current value of step = {step} is not allowed. "
f"It needs to be a positive integer or positive float."))
if isinstance(min_features_to_select,
int) and min_features_to_select > 0:
self.min_features_to_select = min_features_to_select
else:
raise (ValueError(
f"The current value of min_features_to_select = {min_features_to_select} is not allowed. "
f"It needs to be a greater than or equal to 0."))
self.cv = cv
self.scorer = get_single_scorer(scoring)
self.random_state = random_state
self.n_jobs = n_jobs
self.report_df = pd.DataFrame([])
self.verbose = verbose
def __init__(
self,
clf,
strategies,
scoring="roc_auc",
cv=5,
model_na_support=False,
n_jobs=-1,
verbose=0,
random_state=None,
):
"""
Initialise the class.
Args :
clf (binary classifier,sklearn.Pipeline):
A binary classification model, that will used to evaluate various imputation strategies.
strategies (dictionary of sklearn.impute objects or any other scikit learn compatible imputer.):
Dictionary containing the sklearn.impute objects.
e.g.
strategies = {'KNN' : KNNImputer(n_neighbors=3),
'Simple Median Imputer' : SimpleImputer(strategy='median',add_indicator=True),
'Iterative Imputer' : IterativeImputer(add_indicator=True,n_nearest_features=5,
sample_posterior=True)}
This allows you to have fine grained control over the imputation method.
scoring (string, list of strings, probatus.utils.Scorer or list of probatus.utils.Scorers, optional):
Metrics for which the score is calculated. It can be either a name or list of names metric names and
needs to be aligned with predefined [classification scorers names in sklearn](https://scikit-learn.org/stable/modules/model_evaluation.html).
Another option is using probatus.utils.Scorer to define a custom metric.
model_na_support(boolean): default False
If the classifier supports missing values by default e.g. LightGBM,XGBoost etc.
If True an default comparison `No Imputation` result will be added indicating the model performance without any explict imputation.
If False only the provided strategies will be used.
n_jobs (int, optional):
Number of cores to run in parallel while fitting across folds. None means 1 unless in a
`joblib.parallel_backend` context. -1 means using all processors.
verbose (int, optional):
Controls verbosity of the output:
- 0 - nether prints nor warnings are shown
- 1 - 50 - only most important warnings regarding data properties are shown (excluding SHAP warnings)
- 51 - 100 - shows most important warnings, prints of the feature removal process
- above 100 - presents all prints and all warnings (including SHAP warnings).
random_state (int, optional):
Random state set at each round of feature elimination. If it is None, the results will not be
reproducible and in random search at each iteration a different hyperparameters might be tested. For
reproducible results set it to integer.
""" # noqa
self.clf = clf
self.model_na_support = model_na_support
self.cv = cv
self.scorer = get_single_scorer(scoring)
self.strategies = strategies
self.verbose = verbose
self.n_jobs = n_jobs
self.random_state = random_state
self.fitted = False
self.report_df = pd.DataFrame([])