def fit(self, external_cols=None):
self.predictors = {}
self.predictions_cv = pd.DataFrame()
for i_model, model in enumerate(self.models):
model_name = stringify2(model, i_model)
if self.verbose:
logd(model_name)
t0 = u.t()
i_predictor = self.base_predictor(self.X, self.y, model, scoring=self.scoring,
n_folds=self.n_folds, random_state=self.random_state,
shuffle=self.shuffle, n_jobs=self.predictors_n_jobs,
preprocessor=self.preprocessor, verbose=self.verbose)
col = model_name
i_predictor.fit()
i_prediction_cv = i_predictor.predict()
if not len(self.predictions_cv):
self.predictions_cv = i_prediction_cv.rename(columns={i_predictor.cv_col: col}) # [i_predictor.cv_col]
else:
df = i_prediction_cv[[i_predictor.cv_col]].rename(columns={i_predictor.cv_col: col})
# TODO assert index is not duplicate
self.predictions_cv = self.predictions_cv.merge(df, left_index=True, right_index=True)
i_predictor.fit_test()
self.predictors[model_name] = i_predictor
if self.verbose:
logd("Fit %s in %2.2f seconds" % (model_name, u.td(t0)))
self.fit_ensemble(external_cols=external_cols)
def __init__(self, x, y, models, ensemble_model, scoring=None, n_folds=3, random_state=SEED,
shuffle=False, n_jobs=-1, stratified=False, preprocessor=None, verbose=0,
ensemble_grid_params=None, score_greater_is_better=False):
assert isinstance(models, (list, tuple, set)), type(models)
assert isinstance(ensemble_model, sklearn.base.BaseEstimator), \
"%s != %s" % (type(ensemble_model), type(sklearn.base.BaseEstimator))
self.X = x
self.y = y
self.ensemble_model = ensemble_model
self.n_folds = n_folds
self.shuffle = shuffle
self.models = models
self.stratified = stratified
self.random_state = random_state
self.predictors_n_jobs = n_jobs
self.scoring = scoring
self.preprocessor = preprocessor
self.verbose = verbose
self.ensemble_scaler = None
self.score_greater_is_better = score_greater_is_better
self.base_predictor = KStratifiedPred if self.stratified else KFoldPred
# TODO n_jobs split ensemble and CV
self.true_col = "TRUE"
self.cols = map(lambda i: "%s" % stringify2(i[1], i[0]), enumerate(models))
self.predictions_cv = None
self.predictions = None
self.ensemble_grid_params = ensemble_grid_params
self.predictors = {}
