Removes normalize attributes (deprecated) (#113)

* Removes normalize attributes (deprecated)

* Update appveyor.yml

* Update appveyor.yml

Author: xadupre

_unittests/ut_mlmodel/test_quantile_regression.py

@@ -61,7 +61,7 @@ def test_quantile_regression_intercept(self):
         self.assertNotEqual(clr.intercept_, 0)
         self.assertNotEqual(clq.intercept_, 0)
         self.assertEqualArray(clr.intercept_, clq.intercept_)
-        self.assertEqualArray(clr.coef_, clq.coef_)
+        self.assertEqualArray(clr.coef_, clq.coef_, atol=1e-10)
 
     @unittest.skipIf(
         compare_module_version(sklver, "0.24") == -1,
@@ -77,7 +77,7 @@ def test_quantile_regression_intercept_positive(self):
         self.assertNotEqual(clr.intercept_, 0)
         self.assertNotEqual(clq.intercept_, 0)
         self.assertEqualArray(clr.intercept_, clq.intercept_)
-        self.assertEqualArray(clr.coef_, clq.coef_)
+        self.assertEqualArray(clr.coef_, clq.coef_, atol=1e-10)
         self.assertGreater(clr.coef_.min(), 0)
         self.assertGreater(clq.coef_.min(), 0)
 
@@ -92,7 +92,7 @@ def test_quantile_regression_intercept_weights(self):
         self.assertNotEqual(clr.intercept_, 0)
         self.assertNotEqual(clq.intercept_, 0)
         self.assertEqualArray(clr.intercept_, clq.intercept_)
-        self.assertEqualArray(clr.coef_, clq.coef_)
+        self.assertEqualArray(clr.coef_, clq.coef_, atol=1e-10)
 
     def test_quantile_regression_diff(self):
         X = numpy.array([[0.1], [0.2], [0.3], [0.4], [0.5]])

appveyor.yml

@@ -12,7 +12,7 @@ init:
 install:
   - "%PYTHON%\\python -m pip install --upgrade pip"
   # for many packages
-  - pip install llvmlite numba
+  - "%PYTHON%\\Scripts\\pip install llvmlite numba"
   - "%PYTHON%\\Scripts\\pip install -r requirements-win.txt"
   # install precompiled versions not available on pypi
   - "%PYTHON%\\Scripts\\pip install torch torchvision torchaudio"

mlinsights/mlmodel/quantile_regression.py

@@ -29,21 +29,14 @@ class QuantileLinearRegression(LinearRegression):
     value.
     """
 
-    def __init__(self, fit_intercept=True, normalize=False, copy_X=True,
+    def __init__(self, fit_intercept=True, copy_X=True,
                  n_jobs=1, delta=0.0001, max_iter=10, quantile=0.5,
                  positive=False, verbose=False):
         """
         :param fit_intercept: boolean, optional, default True
             whether to calculate the intercept for this model. If set
             to False, no intercept will be used in calculations
             (e.g. data is expected to be already centered).
-        :param normalize: boolean, optional, default False
-            This parameter is ignored when ``fit_intercept`` is set to False.
-            If True, the regressors X will be normalized before regression by
-            subtracting the mean and dividing by the l2-norm.
-            If you wish to standardize, please use
-            :class:`sklearn.preprocessing.StandardScaler` before calling ``fit`` on
-            an estimator with ``normalize=False``.
         :param copy_X: boolean, optional, default True
             If True, X will be copied; else, it may be overwritten.
         :param n_jobs: int, optional, default 1
@@ -65,12 +58,12 @@ def __init__(self, fit_intercept=True, normalize=False, copy_X=True,
         """
         try:
             LinearRegression.__init__(
-                self, fit_intercept=fit_intercept, normalize=normalize,
+                self, fit_intercept=fit_intercept,
                 copy_X=copy_X, n_jobs=n_jobs, positive=positive)
         except TypeError:
             # scikit-learn<0.24
             LinearRegression.__init__(
-                self, fit_intercept=fit_intercept, normalize=normalize,
+                self, fit_intercept=fit_intercept,
                 copy_X=copy_X, n_jobs=n_jobs)
         self.max_iter = max_iter
         self.verbose = verbose
@@ -140,12 +133,12 @@ def compute_z(Xm, beta, Y, W, delta=0.0001):
 
         try:
             clr = LinearRegression(fit_intercept=False, copy_X=self.copy_X,
-                                   n_jobs=self.n_jobs, normalize=self.normalize,
+                                   n_jobs=self.n_jobs,
                                    positive=self.positive)
         except AttributeError:
             # scikit-learn<0.24
             clr = LinearRegression(fit_intercept=False, copy_X=self.copy_X,
-                                   n_jobs=self.n_jobs, normalize=self.normalize)
+                                   n_jobs=self.n_jobs)
 
         W = numpy.ones(X.shape[0]) if sample_weight is None else sample_weight
         self.n_iter_ = 0