def fit(self, X, y):
"""
Generates and optimizes all legitimate pipelines. The best pipeline can be retrieved from `self.best_estimator_`
:param X: Training data
:param y: Corresponding observations
:return: `self`
"""
_X, _y = X, y
if self.cat_cols is not None:
from category_encoders.one_hot import OneHotEncoder
enc = OneHotEncoder(
cols=self.cat_cols, return_df=False, handle_unknown="ignore"
)
enc.fit(X)
_X = enc.transform(X)
X_, y_ = _X, _y
self.num_features = len(X_[0])
for l in range(1, self.length + 1):
self._cast(l, X_, y_)
self.best_estimator_ = list(self.get_top(1).items())[0][1][0]
self.best_estimator_score = list(self.get_top(1).items())[0][1][1]
return self
def enc(X):
e = CEOneHotEncoder(use_cat_names=True, handle_unknown='ignore').fit(X)
return e.transform(X)
def eoa_fit(self, X, y, **kwargs):
"""
Applies evolutionary optimization methods to find an optimum pipeline
:param X: Training data
:param y: Corresponding observations
:param kwargs: `EOA` parameters
:return: `self`
"""
from .structsearch import BoxSample, CompactSample
from .eoa import EOA
_X, _y = X, y
if self.cat_cols is not None:
from category_encoders.one_hot import OneHotEncoder
enc = OneHotEncoder(cols=self.cat_cols, return_df=False, handle_unknown='ignore')
enc.fit(X)
_X = enc.transform(X)
X_, y_ = _X, _y
self.num_features = len(X_[0])
Pop = []
for l in range(1, self.length + 1):
candidates = self.words.Generate(l)
for cnddt in candidates:
if self._validate_sequence(cnddt):
Pop.append(cnddt)
def _eval(ppl):
if self.couldBfirst == []:
from sklearn.pipeline import Pipeline
else:
from imblearn.pipeline import Pipeline
from sklearn.model_selection import RandomizedSearchCV
if self.surrogates is None:
from numpy import logspace
from sklearn.gaussian_process import GaussianProcessRegressor
from sklearn.kernel_ridge import KernelRidge
from sklearn.gaussian_process.kernels import Matern, Sum, ExpSineSquared, WhiteKernel
param_grid_gpr = {"alpha": logspace(-8, 1, 20),
"kernel": [Sum(Matern(length_scale=l_, nu=p), WhiteKernel(noise_level=q))
for l_ in logspace(-3, 3, 20)
for p in [0.5, 1.5, 2.5]
for q in logspace(-3, 1.5, 20)]}
GPR = RandomizedSearchCV(GaussianProcessRegressor(), param_distributions=param_grid_gpr, n_iter=20,
cv=2)
param_grid_krr = {"alpha": logspace(-4, 0, 10),
"kernel": [Sum(Matern(), ExpSineSquared(l_, p))
for l_ in logspace(-2, 2, 20)
for p in logspace(0, 2, 20)]}
KRR = RandomizedSearchCV(KernelRidge(), param_distributions=param_grid_krr, n_iter=30, cv=2)
self.surrogates = [(KRR, 35, CompactSample, 'L-BFGS-B'), (GPR, 50, BoxSample, 'L-BFGS-B')]
self.min_random_evals = 10
from collections import OrderedDict
fitted = OrderedDict([])
for seq in ppl:
best_mdl, best_scr = self.optimize_pipeline(seq, X_, y_)
if seq not in self.models:
self.models[seq] = (best_mdl, best_scr)
if self.verbose > 0:
print("score:%f" % best_scr)
print(best_mdl)
fitted[seq] = -best_scr
return fitted
num_parents = kwargs.pop('num_parents', 30)
mutation_prob = kwargs.pop('mutation_prob', .1)
_eoa = EOA(population=Pop, fitness=_eval, num_parents=num_parents, mutation_prob=mutation_prob,
term_genes=self.couldBlast, init_genes=self.couldBfirst, **kwargs)
_eoa()
self.best_estimator_ = list(self.get_top(1).items())[0][1][0]
return self