1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
|
"""
==================
Pipeline Anova SVM
==================
Simple usage of Pipeline that runs successively a univariate
feature selection with anova and then a C-SVM of the selected features.
"""
from sklearn import svm
from sklearn.datasets import samples_generator
from sklearn.feature_selection import SelectKBest, f_regression
from sklearn.pipeline import make_pipeline
from sklearn.model_selection import train_test_split
from sklearn.metrics import classification_report
print(__doc__)
# import some data to play with
X, y = samples_generator.make_classification(
n_features=20, n_informative=3, n_redundant=0, n_classes=4,
n_clusters_per_class=2)
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=42)
# ANOVA SVM-C
# 1) anova filter, take 3 best ranked features
anova_filter = SelectKBest(f_regression, k=3)
# 2) svm
clf = svm.SVC(kernel='linear')
anova_svm = make_pipeline(anova_filter, clf)
anova_svm.fit(X_train, y_train)
y_pred = anova_svm.predict(X_test)
print(classification_report(y_test, y_pred))
|
