bump v0.15.1

CHANGES.md

@@ -1,4 +1,4 @@
-# version 0.15.0
+# version 0.15.1
 
 - Can use pandas DataFrame in `LSBoostRegressor`, `LSBoostClassifier` and `AdaOpt`
 

mlsauce/__init__.py

@@ -23,7 +23,7 @@
 # Dev branch marker is: 'X.Y.dev' or 'X.Y.devN' where N is an integer.
 # 'X.Y.dev0' is the canonical version of 'X.Y.dev'
 #
-__version__ = "0.10.0"
+# __version__ = "0.10.0"
 
 
 # On OSX, we can get a runtime error due to multiple OpenMP libraries loaded

mlsauce/adaopt/_adaopt.py

@@ -9,13 +9,12 @@
 from tqdm import tqdm
 from ..utils import subsample
 from ..utils import cluster
+from ..utils import cythonize_file 
 
 try:
     from . import _adaoptc as adaoptc
 except ImportError:
-    import pyximport
-
-    pyximport.install()
+    cythonize_file("_adaoptc.pyx")
     import _adaoptc
 
 
@@ -203,8 +202,8 @@ def fit(self, X, y, **kwargs):
         n_classes = len(np.unique(y_))
 
         assert n == len(y_), "must have X.shape[0] == len(y)"
-        
-        try: 
+
+        try:
 
             res = adaoptc.fit_adaopt(
                 X=np.asarray(X_).astype(np.float64),
@@ -220,7 +219,7 @@ def fit(self, X, y, **kwargs):
                 gamma=self.gamma,
                 tolerance=self.tolerance,
             )
-        
+
         except ValueError:
 
             res = _adaoptc.fit_adaopt(
@@ -306,7 +305,7 @@ def predict_proba(self, X, **kwargs):
         n_test = X.shape[0]
 
         if self.n_jobs is None:
-            try: 
+            try:
                 return adaoptc.predict_proba_adaopt(
                     X_test=np.asarray(X, order="C").astype(np.float64),
                     scaled_X_train=np.asarray(
@@ -348,7 +347,7 @@ def predict_proba(self, X, **kwargs):
 
         scaled_X_test = X / norm(X, ord=2, axis=1)[:, None]
 
-        try: 
+        try:
 
             if self.type_dist == "euclidean":
 
@@ -538,7 +537,6 @@ def multiproc_func(i, *args):
                         probs=probs_test_i, weights=weights_test_i
                     )
 
-
         if self.verbose == 1:
             res = Parallel(n_jobs=self.n_jobs, prefer="threads")(
                 (multiproc_func)(m) for m in tqdm(range(n_test))

mlsauce/booster/_booster_classifier.py

@@ -1,19 +1,18 @@
-try:
-    from . import _boosterc as boosterc
-except ImportError:
-    import pyximport
-    pyximport.install()
-    import _boosterc
+
 import numpy as np
 import pandas as pd
 import platform
 import warnings
 from sklearn.preprocessing import PolynomialFeatures
 from sklearn.base import BaseEstimator
 from sklearn.base import ClassifierMixin
-
 from ..utils import cluster
-
+from ..utils import cythonize_file 
+try:
+    from . import _boosterc as boosterc
+except ModuleNotFoundError:
+    cythonize_file("_boosterc.pyx")
+    import _boosterc
 
 class LSBoostClassifier(BaseEstimator, ClassifierMixin):
     """LSBoost classifier.
@@ -192,7 +191,7 @@ def fit(self, X, y, **kwargs):
             )
             X = np.column_stack((X, clustered_X))
 
-        try: 
+        try:
             self.obj = boosterc.fit_booster_classifier(
                 np.asarray(X, order="C"),
                 np.asarray(y, order="C"),
@@ -291,7 +290,7 @@ def predict_proba(self, X, **kwargs):
                     ),
                 )
             )
-        try:     
+        try:
             return boosterc.predict_proba_booster_classifier(
                 self.obj, np.asarray(X, order="C")
             )

mlsauce/booster/_booster_regressor.py

@@ -1,10 +1,3 @@
-try:
-    from . import _boosterc as boosterc
-except ImportError:
-    import pyximport
-
-    pyximport.install()
-    import _boosterc
 import numpy as np
 import pandas as pd
 import platform
@@ -14,8 +7,12 @@
 from sklearn.preprocessing import PolynomialFeatures
 from . import _boosterc as boosterc
 from ..predictioninterval import PredictionInterval
-from ..utils import cluster
-
+from ..utils import cluster, cythonize_file
+try:
+    from . import _boosterc as boosterc
+except ModuleNotFoundError:
+    cythonize_file("_boosterc.pyx")
+    import _boosterc
 
 class LSBoostRegressor(BaseEstimator, RegressorMixin):
     """LSBoost regressor.
@@ -210,7 +207,7 @@ def fit(self, X, y, **kwargs):
             )
             X = np.column_stack((X, clustered_X))
 
-        try: 
+        try:
             self.obj = boosterc.fit_booster_regressor(
                 X=np.asarray(X, order="C"),
                 y=np.asarray(y, order="C"),
@@ -320,7 +317,7 @@ def predict(self, X, level=95, method=None, **kwargs):
             preds = self.pi.predict(X, return_pi=True)
             return preds
 
-        try: 
+        try:
             return boosterc.predict_booster_regressor(
                 self.obj, np.asarray(X, order="C")
             )

mlsauce/lasso/__init__.py

@@ -1,6 +1,6 @@
 try:
     from ._lasso import LassoRegressor
-except ImportError:
+except ModuleNotFoundError:
     pass
 
 __all__ = ["LassoRegressor"]

mlsauce/lasso/_lasso.py

@@ -5,21 +5,19 @@
 from sklearn.base import BaseEstimator
 from sklearn.base import RegressorMixin
 from numpy.linalg import inv
-
-try:
-    from . import _lassoc as mo
-except ImportError:
-    import pyximport
-
-    pyximport.install()
-    import _lassoc
-from ..utils import get_beta
+from ..utils import get_beta, cythonize_file
 
 if platform.system() in ("Linux", "Darwin"):
     import jax.numpy as jnp
     from jax import device_put
     from jax.numpy.linalg import inv as jinv
 
+try:
+    from . import _lassoc as mo
+except ModuleNotFoundError:
+    cythonize_file("_lassoc.pyx")
+    import _lassoc
+
 
 class LassoRegressor(BaseEstimator, RegressorMixin):
     """Lasso.
@@ -79,7 +77,7 @@ def fit(self, X, y, **kwargs):
             self: object.
 
         """
-        try: 
+        try:
 
             self.ym, centered_y = mo.center_response(y)
             self.xm = X.mean(axis=0)
@@ -141,7 +139,7 @@ def fit(self, X, y, **kwargs):
             )
             self.beta = res[0]
             return self
-        
+
         except ValueError:
 
             self.ym, centered_y = _lassoc.center_response(y)
@@ -205,8 +203,6 @@ def fit(self, X, y, **kwargs):
             self.beta = res[0]
             return self
 
-
-
     def predict(self, X, **kwargs):
         """Predict test data X.
 

mlsauce/ridge/__init__.py

@@ -1,6 +1,6 @@
 try:
     from ._ridge import RidgeRegressor
-except ImportError:
+except ModuleNotFoundError:
     pass
 
 __all__ = ["RidgeRegressor"]

mlsauce/ridge/_ridge.py

@@ -5,20 +5,19 @@
 from sklearn.base import RegressorMixin
 from numpy.linalg import inv
 
-try:
-    from . import _ridgec as mo
-except ImportError:
-    import pyximport
-
-    pyximport.install()
-    import _ridgec
-from ..utils import get_beta
+from ..utils import get_beta, cythonize_file
 
 if platform.system() in ("Linux", "Darwin"):
     import jax.numpy as jnp
     from jax import device_put
     from jax.numpy.linalg import inv as jinv
 
+try:
+    from . import _ridgec as mo
+except ModuleNotFoundError:
+    cythonize_file("_ridgec.pyx")
+    import _ridgec
+
 
 class RidgeRegressor(BaseEstimator, RegressorMixin):
     """Ridge.
@@ -70,7 +69,7 @@ def fit(self, X, y, **kwargs):
             self: object.
 
         """
-        try: 
+        try:
             self.ym, centered_y = mo.center_response(y)
         except ValueError:
             self.ym, centered_y = _ridgec.center_response(y)
@@ -99,21 +98,25 @@ def fit(self, X, y, **kwargs):
                     # self.beta, _, _, _ = np.linalg.lstsq(X_, y_, rcond=None)
                     self.beta = get_beta(X_, y_)
                 except Exception:
-                    try: 
+                    try:
                         x = inv(
-                            mo.crossprod(X_) + self.reg_lambda * np.eye(X_.shape[1])
+                            mo.crossprod(X_)
+                            + self.reg_lambda * np.eye(X_.shape[1])
                         )
                         hat_matrix = mo.tcrossprod(x, X_)
                         self.beta = mo.safe_sparse_dot(hat_matrix, centered_y)
                     except ValueError:
                         x = inv(
-                            _ridgec.crossprod(X_) + self.reg_lambda * np.eye(X_.shape[1])
+                            _ridgec.crossprod(X_)
+                            + self.reg_lambda * np.eye(X_.shape[1])
                         )
                         hat_matrix = _ridgec.tcrossprod(x, X_)
-                        self.beta = _ridgec.safe_sparse_dot(hat_matrix, centered_y)
+                        self.beta = _ridgec.safe_sparse_dot(
+                            hat_matrix, centered_y
+                        )
             return self
 
-        try: 
+        try:
             x = jinv(
                 mo.crossprod(X_, backend=self.backend)
                 + self.reg_lambda * jnp.eye(X_.shape[1])
@@ -151,7 +154,7 @@ def predict(self, X, **kwargs):
         """
         X_ = (X - self.xm[None, :]) / self.xsd[None, :]
 
-        try: 
+        try:
             if self.backend == "cpu":
                 if isinstance(self.ym, float):
                     return self.ym + mo.safe_sparse_dot(X_, self.beta)
@@ -170,11 +173,12 @@ def predict(self, X, **kwargs):
                 if isinstance(self.ym, float):
                     return self.ym + _ridgec.safe_sparse_dot(X_, self.beta)
                 return self.ym[None, :] + _ridgec.safe_sparse_dot(X_, self.beta)
-            
+
             # if self.backend in ("gpu", "tpu"):
             if isinstance(self.ym, float):
-                return self.ym + _ridgec.safe_sparse_dot(X_, self.beta, backend=self.backend)
-            return self.ym[None, :] + _ridgec.safe_sparse_dot(X_, self.beta, backend=self.backend)
-
-
-
+                return self.ym + _ridgec.safe_sparse_dot(
+                    X_, self.beta, backend=self.backend
+                )
+            return self.ym[None, :] + _ridgec.safe_sparse_dot(
+                X_, self.beta, backend=self.backend
+            )

mlsauce/stump/__init__.py

@@ -1,6 +1,6 @@
 try:
     from ._stump_classifier import StumpClassifier
-except ImportError:
+except ModuleNotFoundError:
     pass
 
 __all__ = ["StumpClassifier"]

mlsauce/stump/_stump_classifier.py

@@ -1,13 +1,12 @@
 import numpy as np
 from sklearn.base import BaseEstimator
 from sklearn.base import ClassifierMixin
+from ..utils import cythonize_file 
 
 try:
     from . import _stumpc as stumpc
-except ImportError:
-    import pyximport
-
-    pyximport.install()
+except ModuleNotFoundError:
+    cythonize_file("_stumpc.pyx")
     import _stumpc
 
 
@@ -45,7 +44,7 @@ def fit(self, X, y, sample_weight=None, **kwargs):
         """
 
         if sample_weight is None:
-            try: 
+            try:
                 self.obj = stumpc.fit_stump_classifier(
                     X=np.asarray(X, order="C"),
                     y=np.asarray(y, order="C"),
@@ -60,7 +59,7 @@ def fit(self, X, y, sample_weight=None, **kwargs):
 
             return self
 
-        try: 
+        try:
             self.obj = stumpc.fit_stump_classifier(
                 X=np.asarray(X, order="C"),
                 y=np.asarray(y, order="C"),
@@ -112,7 +111,7 @@ def predict_proba(self, X, **kwargs):
 
             probability estimates for test data: {array-like}
         """
-        try: 
+        try:
             return stumpc.predict_proba_stump_classifier(
                 self.obj, np.asarray(X, order="C")
             )

mlsauce/utils/__init__.py

@@ -1,10 +1,11 @@
 from .sampling.rowsubsampling import subsample
-from .misc.misc import cluster, merge_two_dicts, flatten, is_float, is_factor
+from .misc.misc import cluster, cythonize_file, merge_two_dicts, flatten, is_float, is_factor
 from .progress_bar import Progbar
 from .get_beta import get_beta
 
 __all__ = [
     "cluster",
+    "cythonize_file",
     "subsample",
     "merge_two_dicts",
     "flatten",