def select_k_best_features_using_univariate_selection(class_name,
k_best_features,
training_set):
class_names = map(lambda x: x["classes"][class_name], training_set)
numerical_characteristics_training_set = map(
lambda x: x,
map(lambda x: select_numerical_characteristics(x), training_set))
X_new = SelectKBest(f_classif, k=k_best_features).fit_transform(
numerical_characteristics_training_set, class_names)
best_features_indexes = map(
lambda x: numerical_characteristics_training_set[0].index(x), X_new[0])
return map(lambda i: numerical_characteristics[i], best_features_indexes)
def adjust_optimal_features_using_recursive_feature_elimination(class_name, training_set):
class_names = map(lambda x: x["classes"][class_name], training_set)
numerical_characteristics_training_set = map(lambda x: x, map(lambda x: select_numerical_characteristics(x), training_set))
# Create the RFE object and compute a cross-validated score.
svc = SVC(kernel="linear")
# The "accuracy" scoring is proportional to the number of correct classifications
rfecv = RFECV(estimator=svc, step=1, cv=StratifiedKFold(class_names, 2), scoring='accuracy')
# ToDo: check if class has more than one representant always
rfecv.fit(numerical_characteristics_training_set, class_names)
optimal_features_indexes = [i for i, x in enumerate(rfecv.ranking_) if x == 1]
print("Optimal number of features : %d" % rfecv.n_features_)
return map(lambda i: numerical_characteristics[i], optimal_features_indexes)
# X_new.shape
def adjust_optimal_features_using_recursive_feature_elimination(
class_name, training_set):
class_names = map(lambda x: x["classes"][class_name], training_set)
numerical_characteristics_training_set = map(
lambda x: x,
map(lambda x: select_numerical_characteristics(x), training_set))
# Create the RFE object and compute a cross-validated score.
svc = SVC(kernel="linear")
# The "accuracy" scoring is proportional to the number of correct classifications
rfecv = RFECV(estimator=svc,
step=1,
cv=StratifiedKFold(class_names, 2),
scoring='accuracy')
# ToDo: check if class has more than one representant always
rfecv.fit(numerical_characteristics_training_set, class_names)
optimal_features_indexes = [
i for i, x in enumerate(rfecv.ranking_) if x == 1
]
print("Optimal number of features : %d" % rfecv.n_features_)
return map(lambda i: numerical_characteristics[i],
optimal_features_indexes)
# X_new.shape
def select_k_best_features_using_univariate_selection(class_name, k_best_features, training_set): class_names = map(lambda x: x["classes"][class_name], training_set) numerical_characteristics_training_set = map(lambda x: x, map(lambda x: select_numerical_characteristics(x), training_set)) X_new = SelectKBest(f_classif, k=k_best_features).fit_transform(numerical_characteristics_training_set, class_names) best_features_indexes = map(lambda x: numerical_characteristics_training_set[0].index(x), X_new[0]) return map(lambda i: numerical_characteristics[i], best_features_indexes)