Support parameter positive for QuantileLinearRegression

Author: sdpython

_unittests/ut_mlmodel/test_quantile_regression.py

@@ -32,6 +32,22 @@ def test_quantile_regression_no_intercept(self):
         self.assertEqual(clq.intercept_, 0)
         self.assertEqualArray(clr.intercept_, clq.intercept_)
 
+    def test_quantile_regression_no_intercept_positive(self):
+        X = numpy.array([[0.1, 0.2], [0.2, 0.3]])
+        Y = numpy.array([1., 1.1])
+        clr = LinearRegression(fit_intercept=False, positive=True)
+        clr.fit(X, Y)
+        clq = QuantileLinearRegression(fit_intercept=False, positive=True)
+        clq.fit(X, Y)
+        self.assertEqual(clr.intercept_, 0)
+        self.assertEqual(clq.intercept_, 0)
+        self.assertGreater(clr.coef_.min(), 0)
+        self.assertGreater(clq.coef_.min(), 0)
+        self.assertEqualArray(clr.intercept_, clq.intercept_)
+        self.assertEqualArray(clr.coef_[0], clq.coef_[0])
+        self.assertGreater(clr.coef_[1:].min(), 3)
+        self.assertGreater(clq.coef_[1:].min(), 3)
+
     def test_quantile_regression_intercept(self):
         X = numpy.array([[0.1, 0.2], [0.2, 0.3], [0.3, 0.3]])
         Y = numpy.array([1., 1.1, 1.2])
@@ -44,6 +60,21 @@ def test_quantile_regression_intercept(self):
         self.assertEqualArray(clr.intercept_, clq.intercept_)
         self.assertEqualArray(clr.coef_, clq.coef_)
 
+    def test_quantile_regression_intercept_positive(self):
+        X = numpy.array([[0.1, 0.2], [0.2, 0.3], [0.3, 0.3]])
+        Y = numpy.array([1., 1.1, 1.2])
+        clr = LinearRegression(fit_intercept=True, positive=True)
+        clr.fit(X, Y)
+        clq = QuantileLinearRegression(
+            verbose=False, fit_intercept=True, positive=True)
+        clq.fit(X, Y)
+        self.assertNotEqual(clr.intercept_, 0)
+        self.assertNotEqual(clq.intercept_, 0)
+        self.assertEqualArray(clr.intercept_, clq.intercept_)
+        self.assertEqualArray(clr.coef_, clq.coef_)
+        self.assertGreater(clr.coef_.min(), 0)
+        self.assertGreater(clq.coef_.min(), 0)
+
     def test_quantile_regression_intercept_weights(self):
         X = numpy.array([[0.1, 0.2], [0.2, 0.3], [0.3, 0.3]])
         Y = numpy.array([1., 1.1, 1.2])

mlinsights/mlmodel/quantile_regression.py

@@ -31,7 +31,7 @@ class QuantileLinearRegression(LinearRegression):
 
     def __init__(self, fit_intercept=True, normalize=False, copy_X=True,
                  n_jobs=1, delta=0.0001, max_iter=10, quantile=0.5,
-                 verbose=False):
+                 positive=False, verbose=False):
         """
         :param fit_intercept: boolean, optional, default True
             whether to calculate the intercept for this model. If set
@@ -59,11 +59,12 @@ def __init__(self, fit_intercept=True, normalize=False, copy_X=True,
         :param quantile: float, by default 0.5,
             determines which quantile to use
             to estimate the regression.
+        :param positive: when set to True, forces the coefficients to be positive.
         :param verbose: bool, optional, default False
             Prints error at each iteration of the optimisation.
         """
         LinearRegression.__init__(self, fit_intercept=fit_intercept, normalize=normalize,
-                                  copy_X=copy_X, n_jobs=n_jobs)
+                                  copy_X=copy_X, n_jobs=n_jobs, positive=positive)
         self.max_iter = max_iter
         self.verbose = verbose
         self.delta = delta
@@ -131,7 +132,8 @@ def compute_z(Xm, beta, Y, W, delta=0.0001):
             Xm = X
 
         clr = LinearRegression(fit_intercept=False, copy_X=self.copy_X,
-                               n_jobs=self.n_jobs, normalize=self.normalize)
+                               n_jobs=self.n_jobs, normalize=self.normalize,
+                               positive=self.positive)
 
         W = numpy.ones(X.shape[0]) if sample_weight is None else sample_weight
         self.n_iter_ = 0
@@ -197,5 +199,4 @@ def score(self, X, y, sample_weight=None):
             if mult is not None:
                 epsilon *= mult * 2
             return epsilon.sum() / X.shape[0]
-        else:
-            return mean_absolute_error(y, pred, sample_weight=sample_weight)
+        return mean_absolute_error(y, pred, sample_weight=sample_weight)