Add check for sample_weights

Author: MechCoder

sklearn/linear_model/tests/test_logistic.py

@@ -586,7 +586,8 @@ def test_logistic_regression_sample_weights():
  clf_sw_none.fit(X, y)
  clf_sw_ones = LR(solver=solver, fit_intercept=False)
  clf_sw_ones.fit(X, y, sample_weight=np.ones(y.shape[0]))
- assert_array_almost_equal(clf_sw_none.coef_, clf_sw_ones.coef_, decimal=4)
+ assert_array_almost_equal(
+ clf_sw_none.coef_, clf_sw_ones.coef_, decimal=4)
 
  # Test that sample weights work the same with the lbfgs,
  # newton-cg, and 'sag' solvers
@@ -597,8 +598,15 @@ def test_logistic_regression_sample_weights():
  clf_sw_sag = LR(solver='sag', fit_intercept=False,
  max_iter=2000, tol=1e-7)
  clf_sw_sag.fit(X, y, sample_weight=y + 1)
- assert_array_almost_equal(clf_sw_lbfgs.coef_, clf_sw_n.coef_, decimal=4)
- assert_array_almost_equal(clf_sw_lbfgs.coef_, clf_sw_sag.coef_, decimal=4)
+ clf_sw_liblinear = LR(solver='liblinear', fit_intercept=False,
+ max_iter=50, tol=1e-7)
+ clf_sw_liblinear.fit(X, y, sample_weight=y + 1)
+ assert_array_almost_equal(
+ clf_sw_lbfgs.coef_, clf_sw_n.coef_, decimal=4)
+ assert_array_almost_equal(
+ clf_sw_lbfgs.coef_, clf_sw_sag.coef_, decimal=4)
+ assert_array_almost_equal(
+ clf_sw_lbfgs.coef_, clf_sw_liblinear.coef_, decimal=4)
 
  # Test that passing class_weight as [1,2] is the same as
  # passing class weight = [1,1] but adjusting sample weights
@@ -609,12 +617,13 @@ def test_logistic_regression_sample_weights():
  clf_cw_12.fit(X, y)
  clf_sw_12 = LR(solver=solver, fit_intercept=False)
  clf_sw_12.fit(X, y, sample_weight=sample_weight)
- assert_array_almost_equal(clf_cw_12.coef_, clf_sw_12.coef_, decimal=4)
+ assert_array_almost_equal(
+ clf_cw_12.coef_, clf_sw_12.coef_, decimal=4)
 
  # Test the above for l1 penalty and l2 penalty with dual=True.
  # since the patched liblinear code is different.
  clf_cw = LogisticRegression(
- solver="liblinear", fit_intercept=False, class_weight={0:1, 1:2},
+ solver="liblinear", fit_intercept=False, class_weight={0: 1, 1: 2},
  penalty="l1")
  clf_cw.fit(X, y)
  clf_sw = LogisticRegression(
@@ -623,7 +632,7 @@ def test_logistic_regression_sample_weights():
  assert_array_almost_equal(clf_cw.coef_, clf_sw.coef_, decimal=4)
 
  clf_cw = LogisticRegression(
- solver="liblinear", fit_intercept=False, class_weight={0:1, 1:2},
+ solver="liblinear", fit_intercept=False, class_weight={0: 1, 1: 2},
  penalty="l2", dual=True)
  clf_cw.fit(X, y)
  clf_sw = LogisticRegression(

sklearn/svm/base.py

@@ -10,7 +10,8 @@
 from ..base import BaseEstimator, ClassifierMixin
 from ..preprocessing import LabelEncoder
 from ..multiclass import _ovr_decision_function
-from ..utils import check_array, check_random_state, column_or_1d, check_X_y
+from ..utils import check_array, check_consistent_length, check_random_state
+from ..utils import column_or_1d, check_X_y
 from ..utils import compute_class_weight, deprecated
 from ..utils.extmath import safe_sparse_dot
 from ..utils.validation import check_is_fitted
@@ -891,6 +892,10 @@ def _fit_liblinear(X, y, C, fit_intercept, intercept_scaling, class_weight,
  y_ind = np.asarray(y_ind, dtype=np.float64).ravel()
  if sample_weight is None:
  sample_weight = np.ones(X.shape[0])
+ else:
+ sample_weight = np.array(sample_weight, dtype=np.float64, order='C')
+ check_consistent_length(sample_weight, X)
+
  solver_type = _get_liblinear_solver_type(multi_class, penalty, loss, dual)
  raw_coef_, n_iter_ = liblinear.train_wrap(
  X, y_ind, sp.isspmatrix(X), solver_type, tol, bias, C,