def test_selects_all():
from sklearn.neighbors import KNeighborsClassifier
from mlxtend.data import wine_data
X, y = wine_data()
knn = KNeighborsClassifier(n_neighbors=4)
sbs = SBS(knn,
k_features=13,
scoring='accuracy',
cv=3,
print_progress=False)
sbs.fit(X, y)
assert (len(sbs.indices_) == 13)
def test_Iris():
from sklearn.neighbors import KNeighborsClassifier
from sklearn.datasets import load_iris
iris = load_iris()
X = iris.data
y = iris.target
knn = KNeighborsClassifier(n_neighbors=4)
sbs = SBS(knn,
k_features=2,
scoring='accuracy',
cv=5,
print_progress=False)
sbs.fit(X, y)
assert (sbs.indices_ == (0, 3))
assert (round(sbs.k_score_, 2) == 0.96)
import SequentialFeatureSelector as SBS
from sklearn.linear_model import LogisticRegression
import matplotlib.pyplot as plt
#%% load sample data
iris = load_iris()
x = pd.DataFrame(iris.data, \
columns=iris.feature_names)
#%% create a logistic regression object
lr = LogisticRegression()
#%% create an SBS object
sbs = SBS(estimator=lr,
k_features=(1, 3),
forward=False,
scoring='accuracy',
cv=5)
#%% fit the model
sbs = sbs.fit(x, iris.target)
#%% show the selected features
sbs.k_feature_names_
# console output:
# ('sepal length (cm)', 'petal length (cm)',
# 'petal width (cm)')
#%% show a full report on the feature selection
sbs_results = pd.DataFrame(sbs.get_metric_dict()).\
T. \
