adding docstring to LinearSVC and test to make sure the coef_ and intercept_...

adding docstring to LinearSVC and test to make sure the coef_ and intercept_ returned by SVC and LinearSVC are the same.

git-svn-id: https://scikit-learn.svn.sourceforge.net/svnroot/scikit-learn/trunk@704 22fbfee3-77ab-4535-9bad-27d1bd3bc7d8

scikits/learn/svm.py

@@ -261,23 +261,47 @@ class LinearSVC(object):
     """
     Linear Support Vector Classification.
 
+    Similar to SVC with parameter kernel='linear', but uses internally
+    liblinear rather than libsvm, so it has more flexibility in the
+    choice of penalties and loss functions and should be faster for
+    huge datasets.
 
     Parameters
     ----------
+    X : array-like, shape = [nsamples, nfeatures]
+        Training vector, where nsamples in the number of samples and
+        nfeatures is the number of features.
+    Y : array, shape = [nsamples]
+        Target vector relative to X
 
-    Also accepts parameter penalty, that can have values 'l1' or 'l2'
+    loss : string, 'l1' or 'l2' (default 'l2')
+        Specifies the loss function. With 'l1' it is the standard SVM
+        loss (a.k.a. hinge Loss) while with 'l2' it is the squared loss.
+        (a.k.a. squared hinge Loss)
 
-    Similar to SVC with parameter kernel='linear', but uses internally
-    liblinear rather than libsvm, so it has more flexibility in the
-    choice of penalties and loss functions and should be faster for
-    huge datasets.
+    penalty : string, 'l1' or 'l2' (default 'l2')
+        Specifies the norm used in the penalization. The 'l2'
+        penalty is the standard used in SVC. The 'l1' leads to coef_
+        vectors that are sparse.
+
+    dual : bool, (default True)
+        Specifies the norm used in the penalization. The 'l2'
+        penalty is the standard used in SVC. The 'l1' leads to coef_
+        vectors that are sparse.
 
     TODO: wrap Cramer & Singer
+
+    References
+    ----------
+    LIBLINEAR -- A Library for Large Linear Classification
+    http://www.csie.ntu.edu.tw/~cjlin/liblinear/
+
     """
     _solver_type = {'l2l2_1': 1, 'l2l2_0' : 2, 'l2l1_1' : 3, 'l1l2_0' : 5}
 
-    def __init__(self, penalty='l2', loss='l2', dual=False, eps=1e-4, C=1.0):
+    def __init__(self, penalty='l2', loss='l2', dual=True, eps=1e-4, C=1.0):
         s = penalty + loss + '_' + str(int(dual))
+        print s
         try: self.solver_type = self._solver_type[s]
         except KeyError:
             raise ValueError('Not supported set of arguments')

scikits/learn/tests/test_svm.py

@@ -124,7 +124,7 @@ def test_LinearSVC():
     assert_array_equal(clf.predict(T), true_result)
 
     # the same with l1 penalty
-    clf = svm.LinearSVC(penalty='l1')
+    clf = svm.LinearSVC(penalty='l1', dual=False)
     clf.fit(X, Y)
     assert_array_equal(clf.predict(T), true_result)
 
@@ -138,14 +138,17 @@ def test_LinearSVC():
     clf.fit(X, Y)
     assert_array_equal(clf.predict(T), true_result)
 
-def test_coef_SVC_vs_LinearSVC():
+def test_coef_and_intercept_SVC_vs_LinearSVC():
+    """
+    Test that SVC and LinearSVC return the same coef_ and intercept_
+    """
     svc = svm.SVC(kernel='linear', C=1)
     svc.fit(X, Y)
-    print svc.coef_
-    linsvc = svm.LinearSVC(C=1)
+    linsvc = svm.LinearSVC(C=1, penalty='l2', loss='l1', dual=True)
     linsvc.fit(X, Y)
-    print linsvc.coef_
 
     assert_array_equal(linsvc.coef_.shape, svc.coef_.shape)
+    assert_array_almost_equal(linsvc.coef_, svc.coef_, 5)
+    assert_array_almost_equal(linsvc.intercept_, svc.intercept_, 6)
 
     
\ No newline at end of file