def run(self):
# generate all candidates
self.generate()
#starting_feature_matrix = self.create_starting_features()
self.generate_target()
self.global_starting_time = time.time()
for k in range(1, len(self.raw_features)+1):
all_f = CandidateFeature(IdentityTransformation(len(self.raw_features)), self.raw_features)
t = CandidateFeature(SelectKBestTransformer(len(self.raw_features),k), [all_f])
t.pipeline.fit(self.dataset.splitted_values['train'], self.current_target)
X = t.transform(self.dataset.splitted_values['train'])
X_test = t.transform(self.dataset.splitted_values['test'])
print("time: " + str(time.time() - self.global_starting_time))
clf = GridSearchCV(self.classifier(), self.grid_search_parameters, cv=self.preprocessed_folds, scoring=self.score, iid=False,
error_score='raise')
clf.fit(X, self.current_target)
print('test score: ' + str(clf.score(X_test, self.test_target)))
print("\n\n")
def run(self):
self.global_starting_time = time.time()
# generate all candidates
self.generate()
#starting_feature_matrix = self.create_starting_features()
self.generate_target()
all_f = CandidateFeature(
IdentityTransformation(len(self.raw_features)), self.raw_features)
feature_names = [str(r) for r in self.raw_features]
t = CandidateFeature(
SissoTransformer(len(self.raw_features), feature_names,
["^2", "^3", "1/"]), [all_f])
t.pipeline.fit(self.dataset.splitted_values['train'],
self.train_y_all_target)
X = t.transform(self.dataset.splitted_values['train'])
X_test = t.transform(self.dataset.splitted_values['test'])
print("time: " + str(time.time() - self.global_starting_time))
clf = GridSearchCV(self.classifier(),
self.grid_search_parameters,
cv=self.preprocessed_folds,
scoring=self.score,
iid=False,
error_score='raise')
clf.fit(X, self.train_y_all_target)
print(X_test)
print('test score: ' + str(clf.score(X_test, self.test_target)))
print("\n\n")
import numpy as np
from fastsklearnfeature.reader.Reader import Reader
from fastsklearnfeature.splitting.Splitter import Splitter
from fastsklearnfeature.configuration.Config import Config
from fastsklearnfeature.transformations.GroupByThenTransformation import GroupByThenTransformation
from fastsklearnfeature.candidates.CandidateFeature import CandidateFeature
from fastsklearnfeature.candidates.RawFeature import RawFeature
f0 = RawFeature('col0', 0, {})
f1 = RawFeature('col1', 1, {})
training = np.array([[6, 1], [5, 1], [4, 2], [3, 2]])
print(training[0, 1])
print(training.shape)
c = CandidateFeature(GroupByThenTransformation(np.sum, 2), [f0, f1])
c.fit(training)
print(c.transform(training))
'''
raw_features[1].fit(training)
print(raw_features[1].transform(training))
raw_features[0].fit(training)
print(raw_features[0].transform(training))
'''